Category Archives: Machine Learning
Crushing It: Autonomous AI Robot Creates a Shock-Absorbing Shape No Human Ever Could – SciTechDaily
Boston Universitys robot MAMA BEAR autonomously creates and tests energy-absorbing structures, recently achieving a record 75% efficiency, with applications ranging from shipping materials to military gear. Credit: Devin Hahn, Boston University Productions
An autonomous robot created a shock-absorbing shape no human ever could. Learn what it means for designing safer helmets, packaging, car bumpers, and more.
Within the confines of a lab in Boston Universitys College of Engineering, a robot arm drops small, plastic objects into a box precisely placed on the floor to catch them as they fall. One by one, these tiny objectfeather-light, cylindrical pieces, no bigger than an inch tallfill the box. Some are blue, others red, purple, green, or black.
Each of these structures is the result of an experiment in robot autonomy. Operating independently and adapting through ongoing learning, the robot is on a quest to create the most efficient energy-absorbing shape to ever exist.
To do this, the robot creates a small plastic structure with a 3D printer, records its shape and size, moves it to a flat metal surfaceand then crushes it with a pressure equivalent to an adult Arabian horse standing on a quarter. The robot then measures how much energy the structure absorbed, how its shape changed after being squashed, and records every detail in a vast database.
Then, it drops the crushed object into the box and wipes the metal plate clean, ready to print and test the next piece. It will be ever-so-slightly different from its predecessor, its design and dimensions tweaked by the robots computer algorithm based on all past experimentsthe basis of whats called Bayesian optimization. Experiment after experiment, the 3D structures get better at absorbing the impact of getting crushed.
Inside a lab in Boston Universitys College of Engineering, a robot arm drops small, plastic objects into a box placed perfectly on the floor to catch them as they fall. One by one, these tiny structuresfeather-light, cylindrical pieces, no bigger than an inch tallfill the box. Some are red, others blue, purple, green, or black. Each object is the result of an experiment in robot autonomy. On its own, learning as it goes, the robot is searching for, and trying to make, an object with the most efficient energy-absorbing shape to ever exist. Credit: Devin Hahn, Boston University Productions
These relentless iterations are possible because of the work of Keith Brown, an ENG associate professor of mechanical engineering, and his team in the KABlab. The robot, named MAMA BEARshort for its lengthy full title, Mechanics of Additively Manufactured Architectures Bayesian Experimental Autonomous Researcherhas evolved since it was first conceptualized by Brown and his lab in 2018. By 2021, the lab had set the machine on its quest to make a shape that absorbs the most energy, a property known as its mechanical energy absorption efficiency. This current iteration has run continuously for over three years, filling dozens of boxes with more than 25,000 3D-printed structures.
Why so many shapes? There are countless uses for something that can efficiently absorb energysay, cushioning for delicate electronics being shipped across the world or for knee pads and wrist guards for athletes. You could draw from this library of data to make better bumpers in a car, or packaging equipment, for example, Brown says.
To work ideally, the structures have to strike the perfect balance: they cant be so strong that they cause damage to whatever theyre supposed to protect, but should be strong enough to absorb impact. Before MAMA BEAR, the best structure anyone ever observed was about 71 percent efficient at absorbing energy, says Brown. But on a chilly January afternoon in 2023, Browns lab watched their robot hit 75 percent efficiency, breaking the known record. The results were just published today (May 21) in the journal Nature Communications.
When we started out, we didnt know if there was going to be this record-breaking shape, says Kelsey Snapp (ENG25), a PhD student in Browns lab who oversees MAMA BEAR. Slowly but surely we kept inching up, and broke through.
The record-breaking structure looks like nothing the researchers would have expected: it has four points, shaped like thin flower petals, and is taller and narrower than the early designs.
Were excited that theres so much mechanical data here, that were using this to learn lessons about design more generally, Brown says.
Their extensive data is already getting its first real-life application, helping to inform the design of new helmet padding for US Army soldiers. Brown, Snapp, and project collaborator Emily Whiting, a BU College of Arts & Sciences associate professor of computer science, worked with the US Army and went through field testing to ensure helmets using their patent-pending padding are comfortable and provide sufficient protection from impact. The 3D structure used for the padding is different from the record-breaking piecewith a softer center and shorter stature to help with comfort.
MAMA BEAR is not Browns only autonomous research robot. His lab has other BEAR robots performing different taskslike the nano BEAR, which studies the way materials behave at the molecular scale using a technology called atomic force microscopy. Brown has also been working with Jrg Werner, an ENG assistant professor of mechanical engineering, to develop another system, known as the PANDAshort for Polymer Analysis and Discovery ArrayBEAR to test thousands of thin polymer materials to find one that works best in a battery.
Theyre all robots that do research, Brown says. The philosophy is that theyre using machine learning together with automation to help us do research much faster.
Not just faster, adds Snapp. You can do things you couldnt normally do. We can reach a structure or goal that we wouldnt have been able to achieve otherwise, because it would have been too expensive and time-consuming. He has worked closely with MAMA BEAR since the experiments began in 2021, and gave the robot its ability to seeknown as machine visionand clean its own test plate.
The KABlab is hoping to further demonstrate the importance of autonomous research. Brown wants to keep collaborating with scientists in various fields who need to test incredibly large numbers of structures and solutions. Even though they already broke a record, we have no ability to know if weve reached the maximum efficiency, Brown says, meaning they could possibly break it again. So, MAMA BEAR will keep on running, pushing boundaries further, while Brown and his team see what other applications the database can be useful for. Theyre also exploring how the more than 25,000 crushed pieces can be unwound and reloaded into the 3D printers so the material can be recycled for more experiments.
Were going to keep studying this system, because mechanical efficiency, like so many other material properties, is only accurately measured by experiment, Brown says, and using self-driving labs helps us pick the best experiments and perform them as fast as possible.
Reference: Superlative mechanical energy absorbing efficiency discovered through self-driving lab-human partnership 21 May 2024, Nature Communications. DOI: 10.1038/s41467-024-48534-4
Go here to see the original:
Crushing It: Autonomous AI Robot Creates a Shock-Absorbing Shape No Human Ever Could - SciTechDaily
What is Overfitting in Machine Learning? – TechTarget
What is overfitting in machine learning?
Overfitting in machine learning occurs when a model excessively fits the training data, capturing both relevant patterns and inconsequential noise, resulting in inaccurate predictions of new data. Simpler models are less susceptible to capturing noise or irrelevant patterns, which increases the likelihood of generalizing effectively to unseen data.
For example, imagine a company using machine learning to select a few candidates to interview from a large set of resumes based solely on the resume content. The model can consider relevant factors, such as education, experience and skills. However, it overly fixates on font choices, rejecting highly qualified applicants for using Helvetica rather than Times New Roman.
Most factors contributing to overfitting can be found in the model, data or training methods. If a machine learning model is too complex, it memorizes training data closely rather than learning the relevant underlying pattern.
If the training data contains too much noise or if the training data set is too small, the model does not have enough good data to distinguish between signal and noise. If a model trains for too long -- even with optimized data and model -- it starts learning noises, reducing performance the longer it trains. Another potential pitfall is repeatedly testing a model on the same validation data, leading to implicit overfitting to a stale data set.
Underfitting is the opposite of overfitting in that the machine learning model doesn't fit the training data closely enough, thus failing to learn the pattern in the data. Underfitting can be caused by using a too-simple model for a complex problem.
In the above example where a company evaluates resumes with machine learning, an underfit model is too simplistic and fails to capture the relationship between resume contents and job requirements. For example, the underfit model may select all resumes containing specific keywords, such as Java and JavaScript, even if only JavaScript skills are required for the position. The learning model focuses too much on just the word Java, and skills are completely different for JavaScript. It then fails to detect suitable candidates in the training and new data.
One sign of an overfit model is when it performs well on the training data but poorly on new data. However, there are other methods to test the model's performance more effectively.
K-fold cross-validation is an essential tool in assessing the performance of a model. The training data is randomly split into K subsets of equal size, referred to as folds. One fold is reserved for final validation, and the model is trained on the remaining folds. The model then validates the remaining fold and calculates the performance metrics. This process is performed K times, using a different fold as the validation fold during each iteration. The performance metrics are then averaged to get a single overall performance measure for the model.
Technically, two learning curves are generated for one analysis. One learning curve is generated on the training data set to evaluate how the model is learning, and the other curve is generated on the validation set, which evaluates how well the model is generalizing to new data. Then, the learning curves plot performance metrics, such as error or accuracy, against the number of training data points.
As the data set increases, patterns in the performance metrics begin to emerge. When the training error and the validation error plateau, that indicates that adding more data does not meaningfully change the fit. A learning curve for an underfitting model trends close and high. A learning curve for an overfitting model contains lower error values, but there is a gap between the validation and training results, indicating the model is underperforming on the validation data.
Organizations must improve the model and data to prevent overfitting in machine learning.
Here are some ways to refine and optimize models to decrease the risk of overfitting in machine learning.
Understanding the problem and selecting the appropriate machine learning algorithm are crucial at the beginning of a project. While cost evaluation and performance optimization are important, beginners should start with the simplest algorithm to avoid complications and improve generalization. Simple algorithms, such as k-means clustering or k-nearest neighbors, offer more straightforward interpretation and debugging.
In machine learning, features are the individual measurable properties or characteristics of the data used as inputs for training a model. Feature selection identifies which features are the most useful for the model to learn, which reduces the model's dimensionality.
The risk of overfitting increases with the complexity of the model. Regularization is putting constraints on that model during training to avoid complications.
During the training process, the weights of the machine learning model -- or coefficients -- are adjusted to minimize the loss function, which represents the difference between the predicted outputs of a model and the actual target values. The loss function can be represented by the following:
minL()
Regularization adds a new term || || to the loss function and then solves for the set of weights that minimizes the output.
minL() + || ||
There are different ways to do this, depending on the model type.
Ridge regression is a linear regression technique that adds the sum of the squares of the weights to the loss function during training, aiming to prevent overfitting by keeping the coefficients as small as possible without reducing them to zero.
Least absolute shrinkage and selection operator (LASSO) regression adds the sum of the absolute values of the model's weights to the loss function. This automatically performs feature selection by eliminating the weights of the least important features.
Elastic net regression adds a regularization term that is the sum of ridge and LASSO regression, introducing the hyperparameter , which controls the balance between ridge regression ( = 1) and LASSO regression ( = 0) and determines how much automatic feature selection is done on the model.
This method works for iterative learning algorithms, such as gradient descent. A model learns with more data. As the model learns and more data is provided, the prediction error on both the training and validation sets goes down. When too much data is added, overfitting begins to occur, and the error rate on the validation set starts to increase. Early stopping is a form of regularization that stops model training once the validation data's error rate reaches its minimum or when a plateau is detected.
Dropout is a regularization technique used in deep neural networks. Each neuron has a probability -- known as the dropout rate -- that it is ignored or "dropped out" at each data point in the training process. During training, each neuron is forced to adapt to the occasional absence of its neighbors and rely more on its inputs. This leads to a stronger, more resilient network with reduced susceptibility to minor input variations, which minimizes the risk of the network mistaking noise for meaningful data. Adjusting the dropout rate can address overfitting by increasing it or underfitting by decreasing it.
Ensemble methods aggregate predictions from multiple models toward the end of a machine learning project, which reduces both bias and variance, leading to more comprehensive predictions. An example of an ensemble method is random forests, which build multiple decision trees during training. Each tree is trained on a random subset of the data and features. During prediction, the random forest aggregates the predictions of individual trees to produce a final prediction, often achieving high accuracy and robustness against overfitting.
The data is just as vital as the model, so organizations can do the following to improve data.
A large training data set provides a more comprehensive representation of the underlying problem, enabling the model to learn the true patterns and dependencies rather than memorizing specific instances.
Data augmentation helps reduce overfitting by copying one training data instance and then altering it slightly so it is learnable to the model but not detectable by a human. The model has more opportunities to learn the desired pattern, while increasing its tolerance for different environments. Data augmentation is especially helpful in balancing a data set because it includes more underrepresented data, helping to improve the model's ability to generalize across diverse scenarios and avoid biases in the training data.
Original post:
What is Overfitting in Machine Learning? - TechTarget
Predicting Chaos With AI: The New Frontier in Autonomous Control – SciTechDaily
Advanced machine learning algorithms have shown potential in efficiently controlling complex systems, promising significant improvements in autonomous technology and digital infrastructure.
Recent research highlights the development of advanced machine learning algorithms capable of controlling complex systems efficiently. These new algorithms, tested on digital twins of chaotic electronic circuits, not only predict and control these systems effectively but also offer significant improvements in power consumption and computational demands.
According to a new research study, systems controlled by next-generation computing algorithms could give rise to better and more efficient machine learning products.
Researchers used machine learning techniques to construct a digital twina virtual replicaof an electronic circuit known for its chaotic behavior. They found that they were successful at predicting how it would behave and using that information to control it.
Many everyday devices, like thermostats and cruise control, utilize linear controllers which use simple rules to direct a system to a desired value. Thermostats, for example, employ such rules to determine how much to heat or cool a space based on the difference between the current and desired temperatures.
Yet because of how straightforward these algorithms are, they struggle to control systems that display complex behavior, like chaos.
As a result, advanced devices like self-driving cars and aircraft often rely on machine learning-based controllers, which use intricate networks to learn the optimal control algorithm needed to best operate. However, these algorithms have significant drawbacks, the most demanding of which is that they can be extremely challenging and computationally expensive to implement.
Now, having access to an efficient digital twin is likely to have a sweeping impact on how scientists develop future autonomous technologies, said Robert Kent, lead author of the study and a graduate student in physics at The Ohio State University.
The problem with most machine learning-based controllers is that they use a lot of energy or power and they take a long time to evaluate, said Kent. Developing traditional controllers for them has also been difficult because chaotic systems are extremely sensitive to small changes.
These issues, he said, are critical in situations where milliseconds can make a difference between life and death, such as when self-driving vehicles must decide to brake to prevent an accident.
The study was published recently in Nature Communications.
Compact enough to fit on an inexpensive computer chip capable of balancing on your fingertip and able to run without an internet connection, the teams digital twin was built to optimize a controllers efficiency and performance, which researchers found resulted in a reduction of power consumption. It achieves this quite easily, mainly because it was trained using a type of machine learning approach called reservoir computing.
The great thing about the machine learning architecture we used is that its very good at learning the behavior of systems that evolve in time, Kent said. Its inspired by how connections spark in the human brain.
Although similarly sized computer chips have been used in devices like smart fridges, according to the study, this novel computing ability makes the new model especially well-equipped to handle dynamic systems such as self-driving vehicles as well as heart monitors, which must be able to quickly adapt to a patients heartbeat.
Big machine learning models have to consume lots of power to crunch data and come out with the right parameters, whereas our model and training is so extremely simple that you could have systems learning on the fly, he said.
To test this theory, researchers directed their model to complete complex control tasks and compared its results to those from previous control techniques. The study revealed that their approach achieved a higher accuracy at the tasks than its linear counterpart and is significantly less computationally complex than a previous machine learning-based controller.
The increase in accuracy was pretty significant in some cases, said Kent. Though the outcome showed that their algorithm does require more energy than a linear controller to operate, this tradeoff means that when it is powered up, the teams model lasts longer and is considerably more efficient than current machine learning-based controllers on the market.
People will find good use out of it just based on how efficient it is, Kent said. You can implement it on pretty much any platform and its very simple to understand. The algorithm was recently made available to scientists.
Outside of inspiring potential advances in engineering, theres also an equally important economic and environmental incentive for creating more power-friendly algorithms, said Kent.
As society becomes more dependent on computers and AI for nearly all aspects of daily life, demand for data centers is soaring, leading many experts to worry over digital systems enormous power appetite and what future industries will need to do to keep up with it.
And because building these data centers as well as large-scale computing experiments can generate a large carbon footprint, scientists are looking for ways to curb carbon emissions from this technology.
To advance their results, future work will likely be steered toward training the model to explore other applications like quantum information processing, Kent said. In the meantime, he expects that these new elements will reach far into the scientific community.
Not enough people know about these types of algorithms in the industry and engineering, and one of the big goals of this project is to get more people to learn about them, said Kent. This work is a great first step toward reaching that potential.
Reference: Controlling chaos using edge computing hardware by Robert M. Kent, Wendson A. S. Barbosa and Daniel J. Gauthier, 8 May 2024, Nature Communications. DOI: 10.1038/s41467-024-48133-3
This study was supported by the U.S. Air Forces Office of Scientific Research. Other Ohio State co-authors include Wendson A.S. Barbosa and Daniel J. Gauthier.
Read this article:
Predicting Chaos With AI: The New Frontier in Autonomous Control - SciTechDaily
Patient classification and attribute assessment based on machine learning techniques in the qualification process for … – Nature.com
Aim
An adrenal incidentaloma (AI) is an asymptomatic adrenal mass that is recognized incidentally during imaging examinations and is not associated with suspected adrenal pathology1,2. Incidental discovery of adrenal masses has increased recently due to wider application and technical improvement of abdominal imaging procedures, with a prevalence of approximately 0.26.9% in radiological studies1,3,4,5. A comprehensive hormonal evaluation of newly diagnosed adrenal masses at their initial presentation was recommended by the European Society of Endocrinology in 20166.
Patients should be referred for adrenalectomy with clinically significant hormone excess, radiological findings suspicious for malignancy, signs of local invasion, and when the tumour is greater than 5cm6. Underlying comorbidities, advanced age, and Hispanic ethnicity were associated with more frequent postoperative complications. Therefore, the coexistence of heart failure or respiratory failure should always be considered before qualifying for surgical treatment of adrenal tumours7.
The primary objective of this study was to compare several machine learning (ML) techniques in a qualification for adrenalectomy and choose the most accurate algorithm as a valuable adjunct tool for doctors to simplify making therapeutic decisions by using the most innovative and modern methods. To the best of our knowledge, this study is the firstattempt to apply ML techniques to qualify for the surgical treatment of AI using both the results of diagnostic tests and computed tomography (CT) image features. Preliminary results of this study were presented in a poster session at the European Congress of Endocrinology8.
In the literature, most studies apply computer vision techniques to recognize the type of tumour based on CT images9,10,11,12,13,14,15,16. In one study, the authors evaluated ML-based texture analysis of unenhanced CT images in differentiating pheochromocytoma from lipid-poor adenoma in adrenal incidentaloma10. The textural features were computed using the MaZda software package, and two classification methods were used: multivariable logistic regression (accuracy of 94%) and number of positive features by comparison to cut-off values (accuracy of 85%). The results were encouraging; however, decision classes were unbalanced and the accuracy values were computed on the test set. Therefore, they were biased estimators. In another study, the authors applied a multivariable logistic regression model with 11 selected textural features computed using MaZda software11. The cut-off point obtained using the eceiver operating characteristic (ROC) curve applied to the expression obtained from logistic regression resulted in a sensitivity of 93% and 100% specificity. Again, these results were obtained using the same set used to train the model. In another study performed by Li et al., ML models were used to differentiate pheochromocytoma from lipid-poor adenoma based on the radiologists description of unenhanced and enhanced CT images9. The authors used three classifiers: multivariate logistic regression, SVM and random forest. As a result, two separate models based on multivariable logistic regression were proposed, each using three CT features: M1 with preenhanced CT value, shape, and necrosis/cystic changes (accuracy of 86%) and M2 using only preenhanced CT features: CT value, shape, and homogeneity (accuracy of 83%). Elmohr et al. used the ML algorithm to differentiate large adrenal adenomas from carcinomas on contrast-enhanced computed tomography, and its diagnostic accuracy for carcinomas was higher than that of radiologists13. Other studies have evaluated the accuracy of ML-based texture analysis of unenhanced CT images in differentiating lipid-poor adenoma from pheochromocytoma, with performance accuracy ranging from 85 to 89%10,14.
The literature also includes papers applying ML techniques to magnetic resonance imaging (MRI) data. An example of such work is a study where the authors utilized logistic regression with the least absolute shrinkage and selection operator (LASSO) to select MRI image features and distinguish between non-functional AI and adrenal Cushings syndrome17.
In studies involving a large number of features (e.g.: software packages such as MaZdA can calculate several hundred texture parameters for images), dimensionality reduction is required. Techniques commonly used (or combinations of them) are: LASSO with regression18,19,20,21, elimination of correlated features9,21 or those with low intraclass correlation (ICC)18, training of classifiers for subsets of features and selection of subsets with the highest classifier accuracy9, elimination of features with p-values above the accepted error rate for coefficients in regression models, use of feature discrimination power calculated using the ROC curve for each feature separately10.
Artificial neural networks (ANN) are flexible and powerful ML techniques that have evolved from the idea of simulating the human brain, however their successful application usually requires datasets much larger that other classification methods17,18,19.
To improve the quality of patient care, recent studies have been conducted in several different sectors using modern techniques. There are two types of ML-based models: current-condition identification and forward prediction20. In Table 1, we have summarized studies concerning the utilization of ML techniques in AI management.
Read more from the original source:
Patient classification and attribute assessment based on machine learning techniques in the qualification process for ... - Nature.com
Grid Dynamics Achieves the Amazon Web Services Machine Learning Competency – Chronicle-Tribune
State Alabama Alaska Arizona Arkansas California Colorado Connecticut Delaware Florida Georgia Hawaii Idaho Illinois Indiana Iowa Kansas Kentucky Louisiana Maine Maryland Massachusetts Michigan Minnesota Mississippi Missouri Montana Nebraska Nevada New Hampshire New Jersey New Mexico New York North Carolina North Dakota Ohio Oklahoma Oregon Pennsylvania Rhode Island South Carolina South Dakota Tennessee Texas Utah Vermont Virginia Washington Washington D.C. West Virginia Wisconsin Wyoming Puerto Rico US Virgin Islands Armed Forces Americas Armed Forces Pacific Armed Forces Europe Northern Mariana Islands Marshall Islands American Samoa Federated States of Micronesia Guam Palau Alberta, Canada British Columbia, Canada Manitoba, Canada New Brunswick, Canada Newfoundland, Canada Nova Scotia, Canada Northwest Territories, Canada Nunavut, Canada Ontario, Canada Prince Edward Island, Canada Quebec, Canada Saskatchewan, Canada Yukon Territory, Canada
Zip Code
Country United States of America US Virgin Islands United States Minor Outlying Islands Canada Mexico, United Mexican States Bahamas, Commonwealth of the Cuba, Republic of Dominican Republic Haiti, Republic of Jamaica Afghanistan Albania, People's Socialist Republic of Algeria, People's Democratic Republic of American Samoa Andorra, Principality of Angola, Republic of Anguilla Antarctica (the territory South of 60 deg S) Antigua and Barbuda Argentina, Argentine Republic Armenia Aruba Australia, Commonwealth of Austria, Republic of Azerbaijan, Republic of Bahrain, Kingdom of Bangladesh, People's Republic of Barbados Belarus Belgium, Kingdom of Belize Benin, People's Republic of Bermuda Bhutan, Kingdom of Bolivia, Republic of Bosnia and Herzegovina Botswana, Republic of Bouvet Island (Bouvetoya) Brazil, Federative Republic of British Indian Ocean Territory (Chagos Archipelago) British Virgin Islands Brunei Darussalam Bulgaria, People's Republic of Burkina Faso Burundi, Republic of Cambodia, Kingdom of Cameroon, United Republic of Cape Verde, Republic of Cayman Islands Central African Republic Chad, Republic of Chile, Republic of China, People's Republic of Christmas Island Cocos (Keeling) Islands Colombia, Republic of Comoros, Union of the Congo, Democratic Republic of Congo, People's Republic of Cook Islands Costa Rica, Republic of Cote D'Ivoire, Ivory Coast, Republic of the Cyprus, Republic of Czech Republic Denmark, Kingdom of Djibouti, Republic of Dominica, Commonwealth of Ecuador, Republic of Egypt, Arab Republic of El Salvador, Republic of Equatorial Guinea, Republic of Eritrea Estonia Ethiopia Faeroe Islands Falkland Islands (Malvinas) Fiji, Republic of the Fiji Islands Finland, Republic of France, French Republic French Guiana French Polynesia French Southern Territories Gabon, Gabonese Republic Gambia, Republic of the Georgia Germany Ghana, Republic of Gibraltar Greece, Hellenic Republic Greenland Grenada Guadaloupe Guam Guatemala, Republic of Guinea, Revolutionary People's Rep'c of Guinea-Bissau, Republic of Guyana, Republic of Heard and McDonald Islands Holy See (Vatican City State) Honduras, Republic of Hong Kong, Special Administrative Region of China Hrvatska (Croatia) Hungary, Hungarian People's Republic Iceland, Republic of India, Republic of Indonesia, Republic of Iran, Islamic Republic of Iraq, Republic of Ireland Israel, State of Italy, Italian Republic Japan Jordan, Hashemite Kingdom of Kazakhstan, Republic of Kenya, Republic of Kiribati, Republic of Korea, Democratic People's Republic of Korea, Republic of Kuwait, State of Kyrgyz Republic Lao People's Democratic Republic Latvia Lebanon, Lebanese Republic Lesotho, Kingdom of Liberia, Republic of Libyan Arab Jamahiriya Liechtenstein, Principality of Lithuania Luxembourg, Grand Duchy of Macao, Special Administrative Region of China Macedonia, the former Yugoslav Republic of Madagascar, Republic of Malawi, Republic of Malaysia Maldives, Republic of Mali, Republic of Malta, Republic of Marshall Islands Martinique Mauritania, Islamic Republic of Mauritius Mayotte Micronesia, Federated States of Moldova, Republic of Monaco, Principality of Mongolia, Mongolian People's Republic Montserrat Morocco, Kingdom of Mozambique, People's Republic of Myanmar Namibia Nauru, Republic of Nepal, Kingdom of Netherlands Antilles Netherlands, Kingdom of the New Caledonia New Zealand Nicaragua, Republic of Niger, Republic of the Nigeria, Federal Republic of Niue, Republic of Norfolk Island Northern Mariana Islands Norway, Kingdom of Oman, Sultanate of Pakistan, Islamic Republic of Palau Palestinian Territory, Occupied Panama, Republic of Papua New Guinea Paraguay, Republic of Peru, Republic of Philippines, Republic of the Pitcairn Island Poland, Polish People's Republic Portugal, Portuguese Republic Puerto Rico Qatar, State of Reunion Romania, Socialist Republic of Russian Federation Rwanda, Rwandese Republic Samoa, Independent State of San Marino, Republic of Sao Tome and Principe, Democratic Republic of Saudi Arabia, Kingdom of Senegal, Republic of Serbia and Montenegro Seychelles, Republic of Sierra Leone, Republic of Singapore, Republic of Slovakia (Slovak Republic) Slovenia Solomon Islands Somalia, Somali Republic South Africa, Republic of South Georgia and the South Sandwich Islands Spain, Spanish State Sri Lanka, Democratic Socialist Republic of St. Helena St. Kitts and Nevis St. Lucia St. Pierre and Miquelon St. Vincent and the Grenadines Sudan, Democratic Republic of the Suriname, Republic of Svalbard & Jan Mayen Islands Swaziland, Kingdom of Sweden, Kingdom of Switzerland, Swiss Confederation Syrian Arab Republic Taiwan, Province of China Tajikistan Tanzania, United Republic of Thailand, Kingdom of Timor-Leste, Democratic Republic of Togo, Togolese Republic Tokelau (Tokelau Islands) Tonga, Kingdom of Trinidad and Tobago, Republic of Tunisia, Republic of Turkey, Republic of Turkmenistan Turks and Caicos Islands Tuvalu Uganda, Republic of Ukraine United Arab Emirates United Kingdom of Great Britain & N. Ireland Uruguay, Eastern Republic of Uzbekistan Vanuatu Venezuela, Bolivarian Republic of Viet Nam, Socialist Republic of Wallis and Futuna Islands Western Sahara Yemen Zambia, Republic of Zimbabwe
Go here to read the rest:
Grid Dynamics Achieves the Amazon Web Services Machine Learning Competency - Chronicle-Tribune
Machine Learning Revolutionizes Cybersecurity; Detecting, Preventing Threats – TechiExpert.com
Cybersecurity is highly critical and it is assumed the threats to continue evolving and growing. Organizations are turning to advanced technologies like artificial intelligence (AI) and machine learning (ML) to combat the threats. The technologies are revolutionizing how we detect as well as prevent cyber attacks. The technologies are offering innovative solutions and these can enhance our cybersecurity defenses.
AI and ML are powerful tools. These have the capabilities to fight against cyber threats due to their analyzing capabilities of vast amounts of data quickly as well as accurately. The two technologies can detect patterns and anomalies that might indicate a cyber attack. Behavioral analysis is one of the ways to serve the purpose. The tools learn the normal behavior patterns of users and devices within a network, the so-called User and Entity Behavior Analytics (UEBA).
One another way is through network traffic analysis. AI and ML monitor network traffic for unusual patterns like unexpected data transfers or communication. The method helps in identifying potential threats before significant damage takes place. Moreover, deception technology can trick attackers into revealing themselves.
AI and ML also automate defensive responses to detected threats. ML algorithms are trained on large datasets of malware and hence can identify as well as neutralize malware variants with high accuracy. AI systems can analyze emails and websites to detect phishing attempts. It can block the malware variants. Modern intrusion detection systems (IDS) use AI to analyze network traffic.
Security Orchestration, Automation and Response (SOAR) platforms integrate AI and ML to automate incident response workflows. These can automatically isolate infected systems, block malicious traffic and initiate other counter-measures. Hence, the response time is quick and reduces the burden on human analysts.
Automated patch management analyzes vulnerability data and prioritize patching efforts based on risk levels. AI ensures that critical vulnerabilities are addressed promptly and simultaneously reduces the opportunity for attackers.
Read the original post:
Machine Learning Revolutionizes Cybersecurity; Detecting, Preventing Threats - TechiExpert.com
Deep learning for high-resolution seismic imaging | Scientific Reports – Nature.com
Review of seismic imaging
The goal of seismic imaging is to infer subsurface structures based on observed seismic data. This can be achieved by solving inverse problems. Reverse Time Migration (RTM) is an imaging technique based on the wave equation25, which utilizes the cross-correlation of the underground forward and backward wavefields, demonstrating excellent adaptability, especially in areas with complex structures and high velocity variations. The formula for the cross-correlation imaging condition is expressed as:
$$I(x,z)={int }_{0}^{T}{u}_{text{f }}(x,z,t)*{u}_{text{b }}(x,z,t)dt$$
(1)
Here, (I(x,z)) represents the RTM result, ({u}_{text{f }}(x,z,t)) denotes the forward wavefield, and ({u}_{text{b }}(x,z,t)) is the backward wavefield.
However, RTM suffers from low-frequency noise and inaccurate amplitudes, limiting its application in seismic imaging. To address the shortcomings of RTM, Least Squares Reverse Time Migration (LSRTM) associates the migration imaging result with seismic data26, constructing the least squares objective function:
$$E({varvec{m}})=frac{1}{2}{parallel {varvec{L}}{varvec{m}}-{{varvec{d}}}_{{text{obs}}}parallel }^{2}$$
(2)
Here, ({{varvec{d}}}_{{text{obs}}}) represents the observed data, ({varvec{L}}) is the forward operator, and ({varvec{m}}) is the subsurface structural parameter.
LSRTM involves key steps such as forward simulation, backpropagation, gradient computation, and optimization algorithms. Through iterative optimization to minimize the error between observed and simulated data, LSRTM enhances the quality of seismic imaging.
In this study, we introduce a hybrid architecture (Fig.1) that integrates Transformer and CNN to address seismic imaging tasks. Within the Transformer framework, the need for a one-dimensional sequence as input necessitates an initial transformation of the input image. The Image Patching phase involves partitioning the input image into a series of equally sized image patches, each with a size of ({P}^{2}). This transforms the original (Htimes W) image into an (Ntimes Ptimes P) sequence, where (N) represents the sequence length, encompassing (frac{Htimes W}{{P}^{2}}) image patches. Consequently, the input image is reshaped into a one-dimensional sequence, with each image patch corresponding to a vector. The adoption of a smaller patch size enables enhanced capture of intricate details within the image, thus elevating the model's accuracy, albeit at the expense of increased computational overhead27. In view of balancing between model efficacy and computational efficiency, we establish (P=16). In the Input Embedding stage, a linear transformation is applied to each segmented image patch, mapping it to a continuous vector representation. As the Transformer model abstains from utilizing recurrent or convolutional layers for sequence processing, positional encoding is incorporated into the input embedding vector to discern the positional information of each image patch.
Network architecture diagram.
$${mathbf{Z}}_{0}=[{{varvec{X}}}_{p}^{1}mathbf{E};{mathbf{X}}_{p}^{2}mathbf{E};dots ;{mathbf{X}}_{p}^{N}mathbf{E}]+{mathbf{E}}_{text{pos}}$$
(3)
The proposed model employs a Transformer Encoder comprising ({text{L}}=12) layers to process the image sequence, with each encoder layer composed of Multi-Head Self-Attention (MSA) and Multi-Layer Perceptron (MLP).
$${mathbf{Z}}_{l}^{mathrm{^{prime}}}={text{MSA}}({text{LN}}({mathbf{Z}}_{l-1}))+{mathbf{Z}}_{l-1},l=1dots L$$
(4)
$${mathbf{Z}}_{l}={text{MLP}}({text{LN}}({mathbf{Z}}_{l}^{mathrm{^{prime}}}))+{mathbf{Z}}_{l}^{mathrm{^{prime}}},l=1dots L$$
(5)
Here, ({text{LN}}(cdot )) denotes layer normalization, (l) is the identifier for intermediate blocks, and L is the number of Transformer layers.
These stacked Transformer layers facilitate capturing the complexity of the data from a multiscale perspective. To prevent the loss of primary features by solely relying on the last layer output, we employ a multi-level feature extraction strategy. In addition to the final layer (12th layer), features are extracted from the 6th and 9th layers, representing deep, intermediate, and shallow features, providing a rich and multiscale feature space. These three layers of features are adjusted to different resolutions of feature maps and fused through ASFF, resulting in adaptive aggregation at each scale.
ASFF constitutes an attention-based spatial feature integration strategy devised to amalgamate feature maps originating from diverse spatial resolutions within deep neural networks28. Its principal objective is to augment the model's perceptual acuity concerning targets across varying scales. ASFF dynamically weights and fuses features from distinct spatial resolutions by learning task-specific attention weights.
We represent features at resolution level ({ell}) (where ({ell}in left{mathrm{1,2},3right})) as ({x}^{l}). For level ({ell}), we resize features from other levels (n) ((nne {ell})) to the same shape as ({x}^{l}). Let ({x}_{ij}^{nto {ell}}) denote the feature vector at position ((i,j)) on the feature map, adjusted from level (n) to level ({ell}). We perform the following fusion of corresponding level ({ell}) features:
$${y}_{ij}^{{ell}}={alpha }_{ij}^{{ell}}cdot {x}_{ij}^{1to {ell}}+{beta }_{ij}^{{ell}}cdot {x}_{ij}^{2to {ell}}+{gamma }_{ij}^{{ell}}cdot {x}_{ij}^{3to {ell}}$$
(6)
Here, ({y}_{ij}^{{ell}}) signifies the vector at position ((i,j)) in the output feature map ({y}^{{ell}}) across channels. The spatial importance weights ({alpha }_{ij}^{{ell}}), ({beta }_{ij}^{{ell}}), and ({gamma }_{ij}^{{ell}}) for features from three different levels to level ({ell}) are adaptively learned by the network. To ensure the effectiveness of weights, constraints ({alpha }_{ij}^{{ell}}+{beta }_{ij}^{{ell}}+{gamma }_{ij}^{{ell}}=1) and ({alpha }_{ij}^{{ell}}, {beta }_{ij}^{{ell}}, {gamma }_{ij}^{{ell}}in [mathrm{0,1}]) are enforced. These constraints ensure the validity and range of the weights. The weights are computed using softmax functions with control parameters as follows:
$${alpha }_{ij}^{{ell}}=frac{{e}^{{lambda }_{{alpha }_{ij}}^{{ell}}}}{{e}^{{lambda }_{{alpha }_{ij}}^{{ell}}}+{e}^{{lambda }_{{beta }_{ij}}^{{ell}}}+{e}^{{lambda }_{{gamma }_{ij}}^{{ell}}}}$$
(7)
$${beta }_{ij}^{{ell}}=frac{{e}^{{lambda }_{{beta }_{ij}}^{{ell}}}}{{e}^{{lambda }_{{alpha }_{ij}}^{{ell}}}+{e}^{{lambda }_{{beta }_{ij}}^{{ell}}}+{e}^{{lambda }_{{gamma }_{ij}}^{{ell}}}}$$
(8)
$${gamma }_{ij}^{{ell}}=frac{{e}^{{lambda }_{{gamma }_{ij}}^{{ell}}}}{{e}^{{lambda }_{{alpha }_{ij}}^{{ell}}}+{e}^{{lambda }_{{beta }_{ij}}^{{ell}}}+{e}^{{lambda }_{{gamma }_{ij}}^{{ell}}}}$$
(9)
The calculation of control parameters ({lambda }_{{alpha }_{ij}}^{{ell}}),({lambda }_{{beta }_{ij}}^{{ell}}), and ({lambda }_{{gamma }_{ij}}^{{ell}}) is performed through (1{text{x}}1) convolution layers from ({x}_{ij}^{1to {ell}}),({x}_{ij}^{2to {ell}}), and ({x}_{ij}^{3to {ell}}), respectively. These parameters are learned through standard backpropagation during network training.
Overall, this approach furnishes the model with a rich and multiscale feature space, thereby contributing to its performance in complex seismic imaging tasks.
Visit link:
Deep learning for high-resolution seismic imaging | Scientific Reports - Nature.com
Hong Kong big data utilised for building predictive AI and more AI briefs – Healthcare IT News
CU Medicine develops severe hypoglycemia predictive AI
Researchers from the Faculty of Medicine at the Chinese University of Hong Kong (CU Medicine) have utilised anonymised big data from the Hospital Authority Data Collaboration Laboratory to develop a new machine learning model that can predict the risk of severe hypoglycemia among older diabetic adults.
They analysed about 1.5 million records of more than 360,000 senior individuals with diabetes from 2013-2018. Based on the XGBoost machine learning algorithm, the risk prediction model uses 258 predictors, including demographics, admissions, and diagnoses, to predict severe hypoglycemia events requiring hospitalisation in the next 12 months.
Besides prolonged hospitalisation, severe hypoglycemia isalso associated with an increased risk of falls, cardiovascular disease, dementia, and all-cause mortality, CU Medicine noted.
Achieving an 85% positive predictive value in a study, the model can bepotentially integrated into EHR decision support systems for pre-emptive interventions, such as correcting the timing and dosage of insulin injections orchanging to diabetes medications with lower hypoglycemic potential.
Indian military looks to develop diagnosis support AI
India's Armed Forces Medical Services has partnered with the Indian Institute of Technology in Kanpur, Uttar Pradesh for the joint research and development of technology solutions addressing the health problems of soldiers deployed in difficult terrains.
Under their memorandum of understanding, IIT Kanpur will also help the Armed Forces Medical College's Armed Forces Centre for Computational Medicine in creating diagnostic AI models.
Alodokter joins Indonesia's digital health mission
Digital health company Alodokter is cooperating with the Indonesian government in expanding access to health services across the country through telemedicine.
It signed a memorandum of understanding with the Ministry of Health to collaborate in such areas as raising healthcare workers' capacity by providing professional credit units; health communications and education; conducting health development surveys; and providing telemedicine services.
Mahidol Univesity to trial Japanese endoscopic AI
Mahidol University in Thailand is collaborating with Japanese startup AI Medical Service (AIM) to assess the applicability of the latter's endoscopic AI in the Thai setting.
This comes as AIM looks to expand its market presence globally after receiving regulatory approvals in Japan and Singapore over the past four months.
Indonesian university to test Korean medical AI for lung disease, stroke diagnosis
The Universitas Gadjah Mada Academic Hospital in Indonesia will also conduct a clinical trial of three diagnosis support AI from South Korean medical AI company, Deepnoid.
Under their memorandum of understanding, the hospital will be testing Deepnoid's diagnosis aid software for multiple lung diseases, lung nodules, and brain aneurysms for 18 months. This comes as the hospital, which saw a two-fold rise in X-ray, MRI, and CT readings over the past three years, is bracing forgrowingdemand for imaging while only having 22 readers to date.
The results of this clinical trial will inform Deepnoid's application for a regulatory licence in Indonesia, the company shared.
Read more:
Hong Kong big data utilised for building predictive AI and more AI briefs - Healthcare IT News
Science has an AI problem. This group says they can fix it. – University of California San Diego
One of the main takeaways is transparency. The checklist calls on researchers to provide detailed descriptions of each machine learning model, including the code, the data used to train and test the model, the hardware specifications used to produce the results, the experimental design, the projects goals and any limitations of the studys findings. The standards are flexible enough to accommodate a wide range of nuance, including private datasets and complex hardware configurations, according to the authors.
While the increased rigor of these new standards might slow the publication of any given study, the authors believe wide adoption of these standards would increase the overall rate of discovery and innovation, potentially by a significant amount.
What we ultimately care about is the pace of scientific progress, said sociologist Emily Cantrell, one of the lead authors, who is pursuing her Ph.D. at Princeton. By making sure the papers that get published are of high quality and that theyre a solid base for future papers to build on, that potentially then speeds up the pace of scientific progress. Focusing on scientific progress itself and not just getting papers out the door is really where our emphasis should be.
Kapoor concurred. The errors hurt. At the collective level, its just a major time sink, he said. That time costs money. And that money, once wasted, could have catastrophic downstream effects, limiting the kinds of science that attract funding and investment, tanking ventures that are inadvertently built on faulty science and discouraging countless numbers of young researchers.
In working toward a consensus about what should be included in the guidelines, the authors said they aimed to strike a balance: simple enough to be widely adopted, comprehensive enough to catch as many common mistakes as possible.
They say researchers could adopt the standards to improve their own work; peer reviewers could use the checklist to assess papers; and journals could adopt the standards as a requirement for publication.
The scientific literature, especially in applied machine learning research, is full of avoidable errors, Narayanan said. And we want to help people. We want to keep honest people honest.
The paper, Consensus-based recommendations formachine-learning-based science, published on May 1 in Science Advances, included the following authors: Sayash Kapoor, Princeton University; Emily Cantrell, Princeton University; Kenny Peng, Cornell University; Thanh Hien (Hien) Pham, Princeton University; Christopher A. Bail, Duke University; Odd Erik Gundersen, Norwegian University of Science and Technology; Jake M. Hofman, Microsoft Research; Jessica Hullman, Northwestern University; Michael A. Lones, Heriot-Watt University; Momin M. Malik, Center for Digital Health, Mayo Clinic; Priyanka Nanayakkara, Northwestern; Russell A. Poldrack, Stanford University; Inioluwa Deborah Raji, University of California-Berkeley; Michael Roberts, University of Cambridge; Matthew J. Salganik, Princeton University; Marta Serra-Garcia, University of California-San Diego; Brandon M. Stewart, Princeton University; Gilles Vandewiele, Ghent University; and Arvind Narayanan, Princeton University.
Adapted from a Princeton University release
Learn more about research and education at UC San Diego in: Artificial Intelligence
Follow this link:
Science has an AI problem. This group says they can fix it. - University of California San Diego
Research on a machine learning-based adaptive and efficient screening model for psychological symptoms of … – Nature.com
Data collection Data collection
The research group collected 17-dimensional basic trait data (Supplementary Information1. andSupplementary Information 2.) of 25480 samples of community correction prisoners in Zhejiang Province, China, and the corresponding Symptom Checklist-90 (SCL-90) and Health Survey Short Form (SF-12) data. These data were collected through the standardized community correction digital management platform of the Zhejiang Provincial Department of Justice, covering the period from January 2020 to December 2020. The 17-dimensional characteristics mainly include age, sex, treatment level (general control, strict control), whether adult, education level, dmicile (urban or rural), whether there are infectious diseases, whether belongs to the following three categories (unemployed individuals, those without relatives to rely on, individuals without a place to live), whether there is a criminal record, crime type, supervision time, whether there is recidivism, whether there is anti-government tendency, whether there are five kinds of involvement (terrorism, cults, drugs, gangs, and gun trafficking), whether there are four histories (drug use history, escape history, suicide history, police assault history), correction status (in correction, released from the status of correction), occupation before arrest. The SCL-90 traditional scale obtained 9 kinds of psychological measurement indicators: somatization, obsessive-compulsive symptoms, interpersonal sensitivity, depression, anxiety, hostility, terror, paranoia, and psychosis. Due to the incomplete basic information registered in some judicial offices, the samples with missing values in the basic information were removed and matched, resulting in a total of 25,214 sample data.
Due to the privacy and compliance issue of patients, it is difficult to collect a large number of medical data, especially the data of specific groups. The research group has invested a lot of manpower, material and financial resources in the construction of this data set (Supplementary Information 3.).
The research design has been approved by the Ethics Research Committee of the Zhejiang Community Correction Management Bureau. This study was carried out in accordance with the Declaration of Helsinki, and all procedures were carried out in accordance with relevant guidelines and regulations. The Committee waived the requirement of informed consent for this study because the researchers only access the database for analysis purposes, and all personnel, including patient data, are desensitized, and there is no conflict of interest among personnel of each unit.
The pretreatment of tabulated data described in the paper includes missing value imputation, outlier detection and removal and data standardization, as follows:
Missing values refer to situations where the values of certain features or variables in a table are missing or not recorded. In machine learning modeling, handling missing values is crucial36. Choosing appropriate filling methods can improve the predictive performance of the model, making the data more complete and reliable37. In this study, there were some missing values in the raw data we used, and most of the missing values were filled in by manually tracing the raw materials. For a small amount of other missing values such as age and other quantitative data, we use mean interpolation to fill in, as the mean can represent the central trend of the data and help maintain its distribution.For qualitative data such as crime types, we use the median to fill in, which is a better choice because it can reduce the impact of extreme values while maintaining the order and level of the data38.
Outliers refer to data points that are significantly different from other data points or deviate from the normal range. Outliers may have adverse effects on data analysis and modeling, so they need to be eliminated or handled. To ensure the accuracy and reliability of the data, we carried out outlier detection and elimination. We use the Rajda criterion to deal with outliers. The process takes the given confidence probability of 99.7% as the standard, and is based on the standard deviation of 3 times of the data column. The abnormal data row greater than the value is deleted, and when the residual error vb of the measured value xb is greater than 3 times , outliers should be eliminated.
$$left| {vb} right| = left| {xb - x} right| > 3sigma .$$
Data standardization is to transform the data of different scales and ranges into a unified standard scale to eliminate the influence of dimensions and make different features comparable. In the stage of data preprocessing, we normalize the numerical features from minimum to maximum. By linearly mapping the values of each feature to the range of 0 to 1, we eliminate the differences of different feature scales and make them comparable.
Based on symptom checklist-90(SCL-90), this study constructed an adaptive scale (between question groups) simplification screening evaluation model based on multi-label classification algorithm, and used Health Survey Short Form(SF-12), a primary screening tool commonly used by community correction management institutions, as a simplified baseline method for comparative analysis.
We used the multi-label classification model for scale (between question groups) simplification to analyze the risk degree of individuals in nine categories of psychological measurement indicators, and simplified the scale structure based on the risk distribution. The goal of scale simplification is to simplify the questions, make the scale more readable and easy to understand, and help readers get core information and insight more quickly. During the process of scale simplification, it is necessary to make trade-offs and decisions according to the data and the needs of the audience to ensure that enough information is retained while maintaining simplicity and clarity.
The basic principle of the multi-label classification algorithm (as shown in Fig. 1 and Table 1) is to recognize the association between features and labels by learning historical data, so as to predict new labels. It can integrate the results of multiple tags, find the association between multiple tags, and solve the multiple conflicts that may exist in the multi-tag classification problem, so as to effectively improve the accuracy of classification. It can also help us quickly identify features, thus reducing the time of classification.
Binary relevance (first-order, y tags are independent of each other). It is a problem transformation method. The core idea is to decompose the multi-label classification problem. BR is simple and easy to understand. When there is no dependent relationship between Y values, the effect of the model is good.
Classifier chains (high-order, y tags are interdependent). Its principle is similar to the BR conversion method. In this case, the first classifier is trained only on the input data, and then each classifier is trained on all previous classifiers in the input space and chain. A certain number of binary classifiers can be combined into a single multi-label model to explore the correlation between multiple targets.
Rakle (random k-labelsets, high-order, y tags are interdependent). It can divide the original large tag set into a certain number of small tag sets, then use RF to train the corresponding classifier, and finally integrate the prediction results. RakeID is a high-order strategy algorithm, which can mine the correlation of multiple tags according to the size of the tag subset.
Multi label classification algorithm.
For the latter two algorithms, if there is a clear dependency between tags, the generalization ability of the final model is better than that of the model constructed by binary relevance. The problem is that it is difficult to find a more suitable tag dependency.
The core principle of oversampling method is to increase some samples in the category with fewer samples to achieve category balance. SMOTE is the representative algorithm of the oversampling method. In the process of modeling, SMOTE (Synthetic Minority Over-sampling Technique) is used to solve the problem of category imbalance. SMOTE increases the number of minority samples by synthesizing new minority samples, to balance the unbalanced data set.
Because the total number of samples collected is sufficient, the training data adopts 5-fold cross-validation to prevent the model from overfitting and increase the robustness of the model. The extracted feature data is randomly divided into five parts, four of which are used for training, and one part is retained as test data. The above process is repeated five times, using different test data each time. Then the results of these five times are summarized, and the average value is taken as the estimation of the algorithm performance index. Five cross-validation is a popular algorithm choice at present.
In this paper, SF-12 was used as a comparison tool. SF-12 is a commonly used health questionnaire survey tool, which is used to assess the health status and quality of life of individuals. SF-12 is a simplified version derived from the SF-36 questionnaire, which retains the core concepts and dimensions of SF-36. However, it reduces the number of questions and improves the efficiency of questionnaire implementation. The simplicity and efficiency of the SF-12 questionnaire make it a common tool in large-scale epidemiological research and clinical practice. It can be used to evaluate the health status of different groups and the effect of health intervention, and compare the health differences between different groups.
If all SCL-90 subscales of the actual sample are diagnosed as risk-free, the sample is defined as a negative sample. If any subscale test is risky, the sample is defined as a positive sample. Similarly, if all the sub-tags predicted by the multi-label model are 0, the sample is negative. If there is any positive sub-tag, the sample is positive:
If the actual 9 labels are all negative, the mental state is healthy and marked as a negative sample.
If one of the actual 9 labels is positive, the mental state is unhealthy and marked as a positive sample.
Similarly, if all of the predicted 9 tags are negative, the mental state is healthy and the tag is negative.
If one of the predicted 9 tags is positive, the mental state is unhealthy and marked as a positive sample.
According to the actual mental state and the predicted value, the confusion matrix (as shown in Table 2) is drawn, which is composed of the following four important definitions: true positive (TP), false positive (FP), false negative (FN) and true negative (TN).
The overall effect of the model is evaluated by the following indicators, including accuracy, sensitivity, specificity and F1. The relevant measurement standards are as follows:
$${text{Accuracy }} = left( {{text{TP }} + {text{ TN}}} right)/left( {{text{TP }} + {text{ TN }} + {text{ FP }} + {text{ FN}}} right),$$
$${text{Sensitivity }} = {text{ TP}}/left( {{text{TP }} + {text{ FN}}} right),$$
$${text{Precision }} = {text{ TP}}/left( {{text{TP }} + {text{ FP}}} right),$$
$${text{F1}} = {2} times {text{Sensitivity}} times {text{Precision}}/left( {{text{Precision}} + {text{Sensitivity}}} right).$$
In the multi label classification problem, accuracy_Score, Hamming loss and 0-1 loss related evaluation indicators can be based on the prediction results of a single tag or the overall prediction results.
Accuracy_Score is the correctly predicted score (default) or count. In multi-label classification, the function returns the subset precision. If the whole set of predicted tags of the sample matches the real tag combination, the subset accuracy is 1. Otherwise, it is 0.
Hamming loss: Hamming loss measures the prediction accuracy of the model for each label, that is, the ratio of the number of labels with average prediction errors to the total number of labels. It calculates the prediction result of each tag and returns a value between 0 and 1. The smaller the value, the more accurate the prediction is.
0-1 loss is a common classification loss function, which is used to measure the prediction error of the classification model. It takes 1 when the prediction is wrong and 0 when the prediction is correct, so it is named 0-1 loss.
Simplification rate refers to the proportion of the simplified scale to the original scale, which can be used to evaluate the degree of simplification of the scale. Scale simplification refers to simplifying the structure of the original scale by reducing the number of items, deleting redundant or unnecessary items, or merging multiple items. The simplification rate of the scale can be calculated in the following way: simplification rate (number of simplified items/original number of items) 100%. In other words, the simplification rate based on the multi-label model is calculated as follows: simplification rate (the number of sub-labels predicted to be negative)/(the total number of samples).
The Ethics Committee of the Zhejiang Community Correction Management Bureau has waived the informed consent requirement for this study, as researchers accessing the database is only for analytical purposes, including patient data, which is desensitized, and there are no conflicts of interest between personnel in each unit. The research design has been approved by the Ethics Research Committee of the Zhejiang Community Correction Management Bureau. This study was conducted in accordance with the Helsinki Declaration, and all procedures were conducted in accordance with relevant guidelines and regulations.
Continued here:
Research on a machine learning-based adaptive and efficient screening model for psychological symptoms of ... - Nature.com