Page 324«..1020..323324325326..330340..»

Preparing for a Digital Battlefield: National Security and Cryptocurrency – The Cipher Brief

SPONSORED CONTENT The modern battlefield has seen a transformation in the visibility of military and intelligence operations. To be seen or not seen is often the differentiator between success and failure, driving operations into the shadows. Increasingly, the same is true for transnational crime, illicit payments, sanctions-busting and criminal activity.

From Russian ransomware gangs to North Korean hackers, threat actors have looked to cryptocurrencies for revenue generation, money laundering, sanctions evasion and other illicit activity. Many of these actors perceive blockchain-based transactions to be protected from the prying eyes of regulators or law enforcement; especially for cross-border transactions. However, the reality is quite the opposite. Public blockchain technology is designed to be a trusted method for transactions explicitly because every transaction is published and available to everyone on the blockchain. Law enforcement, counter-terrorism, counter threat-finance and national security agencies worldwide are able to harness the power of blockchain technology to track and trace the flow of funds in ways impossible in the traditional world.

As we move further into a world where conflict and competition are fought at least in part on blockchains, it is critical to understand how cybercriminals, sanction-violators and nation state actors use blockchains to move crypto-currencies and other digital assets.

The native properties of public blockchains data that is transparent, traceable and permanent enables government agencies to leverage blockchain intelligence to identify risks more readily and more effectively in order to take action against illicit actors. Not unlike conventional battlefield intelligence, the tools of blockchain intelligence capture threat activity, threat intent and threat vulnerabilities. Through this advantage, regulators, special operators, sanction-enforcers and law enforcers can disrupt threat actors on the digital battlefield.

This is sponsored content. Consider publishing your national security-related, thought leadership content in The Cipher Brief, with a monthly audience reach of more than 500K national security influencers from the public and private sectors. Drop us a note at [emailprotected].

What is Blockchain Intelligence?

Also known as blockchain analytics, blockchain intelligence analyzes raw blockchain data in order to surface insights and risk indicators. It allows law enforcement and national security agencies unprecedented visibility into real-time financial flows. The nature of blockchain technology the open and distributed ledger upon which tokens can be sent means that each transaction is verified and logged in a shared, immutable record, along with the timestamp of the transaction and the addresses involved. This data can be used to understand connections between on-chain addresses, and can also be paired with off-chain intelligence to identify links to real-world entities. Illumination of financial flows through Blockchain Intelligence not only includes blockchain records, but sets the stage for expanded identification of threat actors who are hiding in plain sight.

State Actors, National Security Threats, and Cryptocurrencies; Deadly Combinations

The viability and value of blockchain intelligence can be readily seen in terrorist activity, sanctions-violations and law enforcement activities; but the blockchain ecosystem also harbors bigger prey. Increasingly, state actors have made use of blockchain technology for sanctions evasion, weapons proliferation, cybercrimes and other destabilizing activity. No nation state has attempted to exploit vulnerabilities within the crypto ecosystem as effectively as North Korea.

North Korea Continues to Attack the Crypto Ecosystem

Hackers tied to North Korea stole approximately USD 700 million in cryptocurrency in 2023, according to TRM Labs. North Korea was responsible for almost a third of all funds stolen in crypto attacks last year, despite a 20% reduction from the USD 850 million haul in 2022. Hacks perpetrated by North Korea were on average ten times as damaging as those perpetrated by other actors. Nearly USD 3 billion worth of crypto has been lost to North Korean threat actors since 2017.

OFAC has used sanctions to target cryptocurrency mixers and other services that North Korea has used to launder hacked funds. Cryptocurrency mixers are services that obfuscate transactional information, allowing users to obscure their connection to certain cryptocurrencies. While mixers are used for lawful purposes, North Korea has used them at scale to launder funds. However actions against mixers such as Tornado Cash and Sinbad demonstrate the ability of national security agencies to target the services used by North Korea to launder hacked and stolen funds.

For example, in March 2022, Lazarus Group struck the Ronin bridge, a service that allows users to move funds from one blockchain to another, stealing over $600 million in cryptocurrency that could potentially be used by North Korea for weapons proliferation and other destabilizing activity. What followed was OFAC using blockchain intelligence to trace the stolen funds sanctioning both the blockchain addresses to which the funds moved, and the mixing services that North Korea utilized to launder the proceeds including centralized bitcoin mixer blender.io and decentralized Ethereum mixer Tornado Cash. These rapid sanctions designations were only possible because of the transparent nature of public blockchains.

OFACs sanctioning of Tornado Cash succeeded in radically reducing usage of the service. According to TRM, the overall volume passing through Tornado Cash decreased by close to 85% post OFAC sanctions. Perhaps most importantly, North Korean hackers appear to have largely abandoned the service in favor of more traditional Bitcoin mixers. With nearly USD 1.5 billion stolen in the past two years alone, North Koreas hacking prowess demands continuous vigilance and innovation from business and governments.

Looking for a way to get ahead of the week in cyber and tech?Sign up for theCyber Initiatives GroupSunday newsletter to quickly get up to speed on the biggest cyber and tech headlines and be ready for the week ahead. Sign up today.

Terrorist groups have looked to crypto as one piece of financing puzzle

Particularly following the Hamas attacks on Israel in October 2023, the use of cryptocurrency by international terrorist groups has taken on renewed urgency among governments, policymakers and researchers. And while cash, hawala and even traditional money services remain the default tools for terrorism financing, TRM research found a growing interest in and use of crypto by terrorist groups and their supporters. Nevertheless, to date cryptocurrency use (especially as it relates to fundraising campaigns) appears to be primarily confined to small-scale transactions of under USD 100. Three-quarters of donations to terrorist fundraising campaigns were under USD 500, with around 40% at USD 100 or less.

While the overall volume remains relatively low, in recent years, terrorist groups and their supporters have used cryptocurrency more recently using the stablecoin Tether (USDT) on the TRON (TRX) blockchain to solicit donations and conduct cross-border payments. This includes ISIS and its affiliates in multiple countries around the world, as well as Iranian-backed groups like Hamas and Palestinian Islamic Jihad (PIJ), which have received hundreds of thousands of dollars in cryptocurrency over the past few years.

However, in 2023 Hamas and or sympathetic fundraising campaigns received only modest amounts of crypto, possibly due to the successful targeting of these accounts by Israeli authorities and private sector agencies. Indeed, Hamas announced last year that it would no longer accept cryptocurrency donations.

This could be related to the successful targeting by US and Israeli authorities. Over the last few years, Israels National Bureau for Counter Terror Financing (NBCTF) has repeatedly targeted Hamas use of cryptocurrency, seizing dozens of cryptocurrency addresses with tens of millions of dollars in volume, controlled by entities affiliated with Hamas. For example, on October 10, 2023, the cyber branch of the Israel Polices Lahav 433 announced the seizure of cryptocurrency accounts belonging to Hamas and in July 2021, the NBCTF released a copy of an administrative seizure for Bitcoin, Dogecoin, TRON, and other cryptocurrency addresses controlled by agents of Hamas.

In December 2022, TRMs blockchain intelligence platform identified an address controlled by Shamil Hukumatov. Turkish authorities alleged that the Tajikistan national worked to recruit Tajiks to join the ISIS affiliate in Afghanistan, known as the Islamic State in Khurasan (ISKP or ISIS-K) and launch attacks against the Tajik government. TRM Labs notified Binance, the exchange used by the group to cash out some of their funds. Using know-your-customer (KYC) controls, Binances compliance and financial crime teams identified the person operating the account and alerted the local authorities. The information led to the arrest of two individuals in Tajikistan in April 2023. Turkish authorities arrested Hukumatov two months later.

Its not just for the President anymore.Are you getting your daily national security briefing?Subscriber+Members have exclusive access to theOpen Source Collection Daily Brief, keeping you up to date on global events impacting national security.It pays to be a Subscriber+Member.

Darknet markets and non-compliant exchanges fuel Russias money laundering state

Russia has long been a haven for money launderers, ransomware gangs, and darknet markets. This activity has been facilitated by non-compliant cryptocurrency exchanges, OTC brokers, and networks of facilitators who move funds using cryptocurrencies and other methods for Russian elites in order to evade ever-expanding sanctions. However, law enforcement and national security agencies are targeting Russia-linked ransomware networks. For example, on February 20, 2024, the UKs National Crime Agency, the US Department of Justice, the FBI, and Europol announced the disruption of LockBit and the takedown of its associated website infrastructure. In addition, the US Treasury Departments Office of Foreign Assets Control (OFAC) designated two Russian nationals for their involvement as LockBit affiliates.

Through on-chain analysis, TRM estimates that addresses controlled by LockBit administrators and affiliates have received over GBP 160 million (USD 200 million) in bitcoin since 2022, of which over GBP 50 million (USD 63 million) are still unspent in multiple addresses on-chain.

Additionally, last year the U.S. Department of Justice and the U.S. Treasury Department announced a coordinated action against non-compliant Hong Kong-registered cryptocurrency exchange Bitzlato, for facilitating Russian illicit finance particularly, ransomware and darknet markets allowing Treasurys Financial Crimes Enforcement Network (FinCEN) to issue for the first time an order pursuant to section 9714(a) of the Combating Russian Money Laundering Act.

Treasurys strategy began to take shape in 2021 when it sanctioned Russia-based exchanges Suex, Chatex, followed by an action in 2022 against exchange Garantex for facilitating payments to Russian language darknet market Hydra.

Iran has turned to crypto to move funds in international trade

Even as both Iran and Russia have banned their residents from using cryptocurrencies for payments, these two governments have been working to establish crypto payments for foreign trade. Iran already announced its first official import order worth $10 million back in August 2022. Statements from Russias finance ministrys financial policy department had already confirmed that Russia is exploring how to use crypto for international payments.

Most recently, in the wake of the October 7 attacks on Israel there has been a focus on the way that Iran funds terrorism. In January 2024, U.S. Department of the Treasurys Office of Foreign Assets Control (OFAC) imposed sanctions on financial facilitators that have played key roles in funds transfers, including cryptocurrency transfers, from Irans Islamic Revolutionary Guard Corps-Qods Force (IRGC-QF) to Hamas and Palestinian Islamic Jihad (PIJ) in Gaza.

In addition, in February 2024, OFAC targeted individuals and entities involved in the government of Irans program to develop a Central Bank Digital Currency (CBDC).

What national security news are you missing today? Get full access to your own national security daily brief by upgrading to Subscriber+Member status.

Treasury has effectively targeted crypto-denominated fentanyl sales

Following a multi-year boom, crypto-denominated fentanyl dropped by over 150% in 2023 according to TRM Labs.

Despite the slowdown in growth, total volumes still grew by over 80% over 2023 from USD 16 million to USD 29 million. Moreover, such crypto-denominated sales likely represent a fraction of the total market for fentanyl and fentanyl precursors, most of which continue to be traded using traditional currency.

The decrease in the growth rates appears to correlate with significant sanctions and enforcement events: the US Treasurys Office of Foreign Assets Control (OFAC) sanctioned 135 individuals and entities linked to fentanyl production and distribution across 12 designation events. That followed a steady increase in designation activity since 2018, with five individuals and entities designated in 2019, seven in 2020, 15 in 2021 and 17 in 2022 (see Sanctions section below).

It is impossible to ascribe any one cause to the decreased crypto-related fentanyl sales in 2023: other events, such as indictments by the US Department of Justice (DOJ), may have also contributed to the trend. However, OFACs actions are likely to have disrupted supplies by increasing the risks of engaging with targeted precursor manufacturers. As illicit actors continue to use cryptocurrencies for the illicit trade of fentanyl, law enforcement and national security agencies can use blockchain intelligence for sanctions, arrests and other disruptions.

Conclusion

National security, sanctions enforcement, counter-criminal and counter-terrorism success increasingly requires the tools and techniques to operate in new and evolving domains. As more and more transactions occur on blockchains, we will continue to see criminal and state actors look to take advantage of the promise of cryptocurrencies. The ability to investigate, seize, and disrupt those transactions is critical.

As illicit actors and nation states take advantage of emerging technologies, leveraging blockchain intelligence allows us to see threat actors even on the digital battlefield.

This is sponsored content. Consider publishing your national security-related, sponsored content in The Cipher Brief, with a monthly audience reach of more than 500K national security influencers from the public and private sectors. Drop us a note at[emailprotected].

Read the original:
Preparing for a Digital Battlefield: National Security and Cryptocurrency - The Cipher Brief

Read More..

KuCoin, Execs Charged With Bank Secrecy Act and Unlicensed Money Transmission Offenses – Investopedia

Key Takeaways

Global cryptocurrency exchange KuCoin and two of its founders have been indicted on criminal charges of operating without a license for transmitting money and failing to establish an anti-money laundering (AML) program in accordance with the Bank Secrecy Act (BSA).

KuCoin is accused by the U.S. Attorney's Office for the Southern District of New York of neglecting to verify the identities of its customers adequately or to report any suspicious activities. The BSA mandates that financial platforms implement stringent measures for identifying their customers and reporting any transactions that could suggest criminal activities.

Other international crypto exchanges, such as Binance and BitMEX, have faced similar charges in the past.

KuCoin's founders, Chun Gan and Ke Tang, are alleged to have concealed their platform's significant engagement with U.S. traders. According to U.S. authorities Tuesday, this strategy allowed KuCoin to amass more than 30 million customers and billions of dollars in daily trades because it didn't follow the legal obligations in place for financial institutions operating within or targeting the U.S. market.

Overall, KuCoin is accused of facilitating the laundering of more than $5 billion in suspicious funds via deposits and $4 billion via withdrawals.

As [Tuesday's] Indictment alleges, KuCoin and its founders deliberately sought to conceal the fact that substantial numbers of U.S. users were trading on KuCoins platform," U.S. Attorney Damian Williams said in a statement. "Indeed, KuCoin allegedly took advantage of its sizeable U.S. customer base to become one of the worlds largest cryptocurrency derivatives and spot exchanges, with billions of dollars of daily trades and trillions of dollars of annual trade volume."

The charges also underscore an allegedly deliberate attempt by KuCoin and its founders to operate outside of the global financial regulatory structure. By actively disguising the presence of its U.S. clientele and misleading investors about the geographic distribution of its customer base, KuCoin sought exemption from the stringent AML and Know Your Customer (KYC) requirements, the charges allege.

This evasion of legal duties was alleged to have continued until the company was confronted with a federal criminal investigation, after which it implemented a KYC process in July 2023albeit one that applied only to new customers, leaving a vast number of existing users, including those in the U.S., unverified, according to the indictment.

Last December, KuCoin reached a $22 million settlement over charges of operating an unregistered exchange from New York Attorney General Letitia James. Notably, that case referred to ether as a security, which has recently been disclosed as a new area of focus for the Securities and Exchange Commission (SEC).

Continue reading here:
KuCoin, Execs Charged With Bank Secrecy Act and Unlicensed Money Transmission Offenses - Investopedia

Read More..

Brainedge: Revolutionizing Global Education with AI-Powered Language Translation and Cryptocurrency Rewards – CryptoPotato

[PRESS RELEASE Grand Cayman, Cayman Island, March 27th, 2024]

In an unprecedented leap towards democratising global education, Brainedge proudly announces the launch of its revolutionary e-learning platform, set to transform how non-English speaking learners access world-class education. By seamlessly blending advanced AI-powered language translation technology with an innovative cryptocurrency rewards system, Brainedge is poised to break down the barriers of language and financial constraints, making high-quality education accessible to billions of learners worldwide.

Revolutionizing Learning Across Languages

At its core, Brainedge is designed to serve young learners aged 15 to 35, who, until now, have been marginalised due to the lack of access to education in their native languages. With Brainedges state-of-the-art Text-to-Video AI features and hyper-realistic AI avatars, courses from top university professors and subject matter experts are instantly translated into over 100 local languages. This groundbreaking approach ensures that high-quality education is not a privilege of the few but a right for all, irrespective of language proficiency.

Incentivising Education with Cryptocurrency Rewards

Brainedge is not just transforming access to education; it is redefining the motivation behind learning. For the first time in the e-learning space, Brainedge introduces a rewards system where learners earn $LEARN tokens, Brainedges native cryptocurrency for completing lessons modules and courses. This innovative model encourages continuous learning and course completion, offering both knowledge acquisition and financial benefits.

Empowering Learners Worldwide

Our mission at Brainedge is to empower learners by providing access to world-class education and rewarding their achievements, said Dr. Md Moniruzzaman, Co-Founder of Brainedge. We believe that by removing language barriers and incentivising learning, we can unlock the untapped potential of millions of learners around the globe. Education should have no boundaries, and with Brainedge, were making that a reality.

Brainedge is a pioneering e-learning platform that offers courses in over 100 languages, made accessible through AI-driven translation and taught by the worlds leading educators. With its unique cryptocurrency rewards system, Brainedge is committed to enhancing global education, making learning accessible and rewarding for everyone, everywhere.

Brainedge invites users to embark on this exciting journey to reshape the future of education. Users can discover more about how Brainedge is setting new standards in the e-learning industry at http://www.brainedge.ai

Twitter | Discord | Telegram

Continued here:
Brainedge: Revolutionizing Global Education with AI-Powered Language Translation and Cryptocurrency Rewards - CryptoPotato

Read More..

Why Spot Ether ETFs Could Face a Difficult Path to Approval – Investopedia

Key Takeaways

The Securities and Exchange Commission (SEC) is considering applications for spot exchange-traded funds (ETFs) for ether (ETHUSD), the native token of the Ethereum blockchain and the second largest cryptocurrency by market capitalization. But experts are increasingly skeptical that approval will come any time soon.

The agency's approval of spot-bitcoin (BTCUSD) ETFs earlier this year turbocharged the demand for the cryptocurrency, propelling its price to multiple records, but an encore with ether appears less likely due to a number of factors.

The SEC has already delayed decisions on approvals for ether ETFs by Fidelity, BlackRock (BLK) and Grayscale, questioning whether the proposals are supported by the same arguments that led to the approval of the bitcoin funds, and over security concerns.

"My cautiously optimistic attitude for ETH ETFs has changed from recent months. We now believe these will ultimately be denied May 23rd for this round. The SEC hasn't engaged with issuers on Ethereum specifics. Exact opposite of #BitcoinETFs this fall," Bloomberg Intelligence's James Seyffart wrote in an X post last week.

Industry watchers are skeptical that approvals will come in May, as scheduled, for a variety of reasons. Primary among them is the fact that ether is stakeda process in which cryptocurrency holders lock up their funds as collateral to support the operations of a blockchain network in exchange for rewards in the form of additional cryptocurrency.

On March 18, Fidelity added an amendment to its proposal to allow traders to stake some of the assets held, and a day later Grayscale amended its application to add staking as well.

Last year, the SEC cracked down on staking, fining cryptocurrency exchange Kraken $30 million and forcing the company to shut down its staking-as-a-service business for not following securities law. It also sued Coinbase (COIN) for its staking offering. That litigation is still in process.

When investors provide tokens to staking-as-a-service providers, they lose control of those tokens and take on risks associated with those platforms, with very little protection, the SEC said at the time of the Kraken fine.

That could be interesting in the context of an Ether ETF, where investors do not actually hold the tokens. Instead, they get shares in a fund that has pooled their resources to invest in a portfolio comprising the underlying token.

In a note dated March 12, crypto researcher Noelle Acheson pointed out the uniqueness of staking ether could lead to denial because there's "regulatory fog" surrounding the activity.

Spot bitcoin ETFs were approved by the SEC in January after several failed attempts. The regulator had previously denied filings until last year when a U.S. Court of Appeals for the District of Columbia said the SEC failed to adequately explain its reasoning for the rejections, specifically in the case of the conversion of the Grayscale Bitcoin Trust (GBTC) into an ETF. That court ruling led the commission to approve the listing and trading of the spot bitcoin ETF shares.

Jake Chervinsky, chief legal officer at Variant, an early-stage crypto fund, wrote in post on X March 11 that the commission could come up with new grounds for denial that werent tested by Grayscale in court, which would likely also be subject to a court challenge. The SEC is more than willing to take litigation risk and lose in court based on a preference for being viewed as fighters in a war against crypto rather than being accused of rolling over, Chervinsky wrote.

Earlier this month, SEC Chair Gary Gensler declined to say in an interview with Yahoo Finance whether he would approve the Ether ETF applications. He continued to criticize cryptocurrency saying it "has challenges" and is "rife with abuses and fraud," Yahoo Finance reported.

Acheson said that there's a conceptual problem for Ether that didn't apply to bitcoin. "This statement may irritate many, but ETH was created to be used, not held," Acheson said.

ETH can be a store of value among other functions, but thats not where its main advantage lies, she said.

"It is the field for the largest distributed computing platform in the world, and powers a range of decentralized applications," Acheson said, while bitcoin in her opinion is a product to be held. "Basically, for BTC a spot ETF makes sense. For ETH, less so," she said.

Another point of difference could arise out of the classification of ether as a security, as opposed to bitcoin, which is considered a commodity. Bloomberg reported on Mar. 20 that the SEC is investigating Ethereum Foundation, in what could lead to classification of ether as a security.

If the SEC is able to classify ether as a security, it would have far reaching consequences not just for the token, but the cryptocurrency markets as a whole. Ether would have to abide by securities laws and the SEC would have more power to regulate the cryptocurrency and how its traded. It could also open doors for other crypto tokens to be classified as securities, leading to greater regulatory scrutiny.

Coinbase's chief legal officer Paul Grewal said in a post on X last week that some regulators in the past have clarified ether's status as commodity while the SEC itself has doubted whether the token could be identified as a security.

"The SEC has no good reason to deny the ETH ETP applications. And we hope they wont try to invent one by questioning the long established regulatory status of ETH, which the SEC has repeatedly endorsed," Grewal wrote.

On Monday, Graycale's chief legal officer Craig Salm sounded an optimistic tone in posts on X, saying that the issues that were resolved in the run-up to the approval of the spot bitcoin ETFs were the same as those the SEC must weigh now.

"The only difference is rather than the ETF holding bitcoin, it holds ether," Salm said. "So in many ways, the SEC already has engaged and issuers simply have less to engage on this time."

"Perhaps I will feel differently as we get closer to final approve/deny dates in late May 2024, but at this point, I don't think perceived lack of engagement from regulators should be indicative of one outcome or another," Salm said.

Go here to read the rest:
Why Spot Ether ETFs Could Face a Difficult Path to Approval - Investopedia

Read More..

30 Essential Questions and Answers on Machine Learning and AI – Electronics Weekly

Its called 30 Essential Questions and Answers on Machine Learning and AI, and looks to answer concisely some of the key questions around these areas.

The publishers write:

If youre ready to venture beyond introductory concepts and dig deeper into ML, deep learning, and AI, the question-and-answer format of Machine Learning Q and AI will make things fast and easy for you, without a lot of mucking about.

Born out of questions often fielded by author Sebastian Raschka, the direct, no-nonsense approach of this book makes advanced topics more accessible and genuinely engaging. Each brief, self-contained chapter journeys through a fundamental question in AI, unraveling it with clear explanations, diagrams, and hands-on exercises.

For a taster, you can download and read Chapter 17 on Encoder- And Decoder-Style Transformers.

The books author is Sebastian Raschka, PhD, who is an ML and AI researcher.

He is currently Lead AI Educator at Lightning AI and was previously Assistant Professor of Statistics at the University of Wisconsin-Madison, where he specialised in researching deep learning and ML. You can find out more about his research.

Title: 30 Essential Questions and Answers on Machine Learning and AI Author: Sebastian Raschka Publisher: No Starch Press Format: Print / e-book (PDF, Mobi, and ePub) Price: $49.99, $39.99 Pages: 264 Date: March 2024 ISBN-13: 9781718503762

See also: Gadget Book library extends its virtual shelves

Go here to read the rest:
30 Essential Questions and Answers on Machine Learning and AI - Electronics Weekly

Read More..

What is AI? Everything to know about artificial intelligence – ZDNet

Overall, the most notable advancements in AI are the development and release of GPT 3.5 and GPT 4. But there have been many other revolutionary achievements in artificial intelligence -- too many to include here.

Here are some of the most notable:

ChatGPT is an AI chatbot capable of generating and translating natural language and answering questions. Though it's arguably the most popular AI tool, thanks to its widespread accessibility, OpenAI made significant waves in artificial intelligence by creating GPTs 1, 2, and 3 before releasing ChatGPT.

Also:5 ways to use chatbots to make your life easier

GPT stands for Generative Pre-trained Transformer, and GPT-3 was the largest language model at its 2020 launch, with 175 billion parameters. Then came GPT-3.5, which powers the free tier of ChatGPT. The largest version, GPT-4, accessible through ChatGPT Plus or Microsoft Copilot, has one trillion parameters.

Though the safety of self-driving cars is a top concern of potential users, the technology continues to advance and improve with breakthroughs in AI. These vehicles use machine-learning algorithms to combine data from sensors and cameras to perceive their surroundings and determine the best course of action.

Also: An autonomous car that wakes up and greets you could be in your future

Tesla's autopilot feature in its electric vehicles is probably what most people think of when considering self-driving cars. Still, Waymo, from Google's parent company, Alphabet, makes autonomous rides, like a taxi without a taxi driver, in San Francisco, CA, and Phoenix, AZ.

Cruise is another robotaxi service, and auto companies like Audi, GM, and Ford are also presumably working on self-driving vehicle technology.

The achievements of Boston Dynamics stand out in the area of AI and robotics. Though we're still a long way away from creating AI at the level of technology seen in the movie Terminator, watching Boston Dyanmics' robots use AI to navigate and respond to different terrains is impressive.

Google's sister companyDeepMindis an AI pioneer making strides toward the ultimate goal of artificial general intelligence (AGI). Though not there yet, the company initially made headlines in 2016 with AlphaGo, a system that beat a human professional Go player.

Since then, DeepMind has created a protein-folding prediction system that can predict the complex 3D shapes of proteins. It has also developed programs to diagnose eye diseases as effectively as the top doctors worldwide.

Read the rest here:
What is AI? Everything to know about artificial intelligence - ZDNet

Read More..

Deepfake detection: Inauthentic content lacks telltale signs of life – Earth.com

Deepfake detection involves identifying videos and images that have been manipulated using artificial intelligence and machine learning techniques to make it appear as though individuals are saying or doing things they never actually did.

As deepfakes become more sophisticated, detecting them becomes increasingly challenging, but it is crucial for maintaining trust in digital media.

The primary approach to deepfake detection is to use machine learning models trained to differentiate between genuine and manipulated content. These models analyze various aspects of the media, such as inconsistencies in facial expressions, unnatural blinking patterns, and discrepancies in lighting or background noise.

Since deepfakes are created by algorithms that can have specific weaknesses, these models often look for signs that those algorithms have been used.

Now, deepfake detection has entered a new era with an innovative breakthrough by scientists at Klick Labs. The team has developed an unprecedented approach for combating the increasingly sophisticated world of audio deepfakes.

Utilizing artificial intelligence, this method captures the subtle nuances that distinguish genuine human speech from artificial imitations. It presents a promising solution to challenges highlighted by recent incidents, such as the fake Joe Biden robocall and the counterfeit Taylor Swift cookware advertisement on Meta.

Consequently, this advancement arrives at a critical moment, with increasingly indistinguishable artificial voices becoming more common.

The inspiration for this novel detection method has a dual origin. Initially, it stems from Klick Labs prior research on employing vocal biomarkers to improve health outcomes. Moreover, it is fueled by a fascination with the portrayal of artificial intelligence in science fiction movies, like Blade Runner.

Subsequently, researchers honed in on the signs of life in human speech, such as breathing patterns and micro-pauses. They crafted a technique that leverages these vocal biomarkers for accurate deepfake detection.

Yan Fossat, Senior Vice President of Klick Labs and the studys principal investigator, emphasized the effectiveness of this approach.

Our findings highlight the potential to use vocal biomarkers as a novel approach to flagging deepfakes because they lack the telltale signs of life inherent in authentic content, explained Fossat. These signs are usually undetectable to the human ear but are now discernible thanks to machine learning and vocal biomarkers.

The open-access journal JMIR Biomedical Engineering recently published the study titled Investigation of Deepfake Voice Detection using Speech Pause Patterns: Algorithm Development and Validation. The study demonstrates how vocal biomarkers, combined with machine learning, can distinguish between deepfakes and authentic audio with reliable precision.

The research involved 49 participants with diverse backgrounds and accents. Deepfake models were trained on their voice samples to create corresponding artificial audio samples. Through analyzing speech pause metrics, the team was able to differentiate real from fake voices with approximately 80 percent accuracy.

This development is especially pertinent in light of recent voice cloning scams and the Federal Communications Commissions decision to outlaw deepfake voices in robocalls. Furthermore, with Metas initiative to label AI-generated content and the looming threat of deepfakes influencing the upcoming U.S. presidential election, the need for effective detection methods is more pressing than ever.

Fossat acknowledged the constant evolution of deepfake technology and the ongoing challenge it presents. While our study offers a promising solution to this growing problem, we recognize the need to continuously advance our detection technology to keep pace with the increasing realism of deepfakes, he said.

Klick Labs pioneering work highlights the potential of AI and vocal biomarkers in safeguarding digital communication authenticity. It also underscores the necessity of innovation amidst evolving digital threats. As deepfakes become more realistic, advancing detection methods is crucial to maintain our digital integrity.

Ultimately, deepfake detection is a multifaceted challenge. Its a critical field of research as the implications of undetected deepfakes can be significant, affecting everything from personal reputations to the integrity of democratic processes.

The full study was published in the journal JMIR Biomedical Engineering.

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates.

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

View original post here:
Deepfake detection: Inauthentic content lacks telltale signs of life - Earth.com

Read More..

Digital Twinning: New Machine Learning Research Tracks Heart Failure Development for Targeted Treatment – Carle Illinois College of Medicine

They say everybody has a double, and that could be very good news for some heart patients. A Carle Illinois College of Medicine researcher and his team are developing tools to create digital twins for heart failure patients to help pinpoint the cause and track the development of heart disease. The teams work may eventually identify the best treatments for an individual patients disease profile and offer new hope for patients whose disease doesnt respond to existing treatments.

CI MED MD/PhD candidate Pranav Dorbala is leveraging his background in computer science and the latest medical research to create individualized digital twins or virtual representations of a patients heart. Through this digital twin approach, we can leverage the prior knowledge of science and the data-fitting abilities of machine learning to create a much more powerful model of the human heart, Dorbala explained.

Working with a multidisciplinary team from the Coordinated Science Labs DEPEND group (under the leadership of Electrical and Computer Engineering Professor Ravishankar Iyer), Dorbala is using data on genetics, proteins, and other factors known to play a part in heart failure to create a personalized digital replica. If we model a heart in the computer, we can tailor the digital model to fit the patients physical heart, he said. And unlike a physical model, digital twins are flexible under changing conditions and over time. Through this digital model, we can leverage machine learning, deep learning, and reinforcement learning (ML) to simulate the effects of various individual patient-related factors, heart structure and function, and treatments to identify the risk of developing heart failure and novel treatment options.

Heart failure is largely driven by changes in the heart that occur to compensate for a loss of heart function (either due to specific insult like a heart attack or due to the aging process including the effects of high blood pressure, diabetes, and other factors), Dorbala explained. When the heart over-corrects for this loss of function, heart failure occurs. This process of heart remodeling is one of the main pathways in the development of heart failure, making the digital doubles ability to change even more valuable in identifying causes and potential treatments.

Dorbalas digital twin research builds on his earlier work focused on understanding the various mechanistic pathways the heart uses to remodel itself. The work looked at protein systems and pathways in the development of a broadly defined type of heart disease known as Heart Failure with Preserved Ejection Fraction (HFpEF) which has no standard effective treatment. If we identify these pathways, we can group patients with similar pathway-based changes to better predict who is at risk for heart failure and who may benefit from specific drug therapies, Dorbala said.

The teams model will be tested on large groups of clinical data from real patients, tracking which patients develop heart failure over time. Our next steps are to identify methods to output translational clinical measures from our digital twin to maximize the benefit of this innovation in the clinical setting, Dorbala said. We want to integrate the proteomic pathway data such that we understand how enrichment of specific biological pathways results in specific remodeling patterns in the heart.

Dorbala says the ultimate step in the digital twin research project will integrate clinical trial data to identify therapies, including drug treatments, that result in the greatest benefit and best outcomes in patients with heart failure that hasnt responded to existing therapies.

Dorbalas mentors on the digital twin project include project lead, Electrical and Computer Engineering and CI MED Professor Ravishankar Iyer, and collaborator Dr.Amil Shah of the University of Texas Southwestern Medical Center. The team also works closely with collaborators at the Brigham and Womens Hospital (Harvard Medical School) in Boston.

Continue reading here:
Digital Twinning: New Machine Learning Research Tracks Heart Failure Development for Targeted Treatment - Carle Illinois College of Medicine

Read More..

Webinar: Land Your Dream Job with Gen AI Tools – Simplilearn

In today's fast-paced job market, standing out to potential employers is more challenging than ever. But what if you could harness the power of Generative AI to catch their eye and secure your dream job?

Join us for an exclusive webinar on 14 April24 (11:00 AM IST) that will change how you approach your job search. Discover cutting-edge Gen AI tools that can simplify your job search, enhance your resume, optimize your social media profile, and prepare you for interviews like never before.

Who Can Attend This Webinar?

This session is designed for:

What Tools Will Be Covered?

Dive deep into the functionalities and benefits of the following Gen AI tools, among others:

..and more!

What Else Will You Get?

Apart from an in-depth walkthrough of these revolutionary tools, attendees will gain access to:

What are you waiting for? In an era where technology drives opportunities, join this webinar and learn how to make it work in your favor.

See original here:
Webinar: Land Your Dream Job with Gen AI Tools - Simplilearn

Read More..

Application of machine learning for identification of heterotic groups in sunflower through combined approach of … – Nature.com

Experiment 1

For accurate identification of heterotic grouping pattern, a multi-prong strategy was adopted, wherein morphological, bio-chemical, and molecular datasets of sunflower genotypes were analyzed by using three clustering algorithms, i.e., hierarchical, K-means and hierarchical+K-means hybrid classification algorithm. Efficacy of these three machine learning algorithms were tested on the sunflower genotypes and the algorithm that best explains and accurately classified the genotypes were used for final parental selection for further hybrid development.

Figure2 represents the dendrogram obtained by using hierarchical classification algorithm. For hierarchical clustering, Ward.D2 method was applied on combined dataset of morphological+bio-chemical+molecular characterization. Cluster diagram (Fig.2) showed two distinct classes of genotypes, wherein cluster 1 contains all the restorer lines, while cluster 2 has CMS+B-line and self-pollinated lines. Number of genotypes grouped in cluster 1 includes 31 sunflower genotypes, while the rest 78 sunflower genotypes grouped in cluster 2. Further, at genetic distance of 18, these clusters can be sub-divided into 6 smaller groups. Sub-group 1-A has six genotypes, while there are 3, 8, 6, 2 and 6 genotypes in subgroup 1-B, 1-C, 1-D, 1-E and 1-F respectively. Likewise, Cluster-2 can be divided into six sub-groups at the genetic distance 18. The number of genotypes recorded in sub-group 2-A was 8, while sub-group 2-B had 11 genotypes. Similarly, the number of genotypes recorded in sub-groups 2-C, 2-D, 2-E, and 2-F were 7, 20, 20 and 12 respectively.

Hierarchical clustering of 109 sunflower genotypes through Ward.D2 method.

K-means cluster algorithm is an unsupervised machine learning based approach that tends to group the similar data points in one cluster, which is away from the dis-matching data points. More precisely, this algorithm aims to minimize the sum of square values within a cluster and consequently maximize the sum of squares between clusters. In the present study, K-means clustering applied on the 109 sunflower genotypes, precisely grouped the sunflower genotypes into 2 major clusters (Fig.3). The size of cluster 1 is 31, while cluster 2 classified 78 sunflower genotypes. Cluster 1 predominantly contains restorer lines, while cluster 2 contains self-pollinated (SFP) lines i.e. A-lines and B-lines of sunflower genetic pool under study. Although K-means application precisely grouped the sunflower genotypes into two major clusters, selecting genotypes with more precision to smaller groups was not possible using this algorithm. As many SFP lines lie closer to the A-line or B-lines, making it harder to distinguish between them.

K-means clustering of 109 sunflower genotypes.

Finally, a hybrid algorithm by using hierarchical+K-means clustering algorithms was applied on the sunflower genotypes to examine if the accuracy of harvesting more precise heterotic groups can be improved further or not? Setting the number of k(s) to 12, two major clusters were observed, that were further grouped into 12 smaller clusters (Fig.4). Cluster 1 contains 12 genotypes in which there were 2 B-lines and 10 restorer lines, cluster 2 contains 8 genotypes (4 CMS+4 B-lines). Cluster 3 had 4 genotypes (1 B-line+3 SFP lines), and 12 genotypes (6 CMS-lines, 5 B-lines and 1 SFP line) were grouped into cluster 4. Cluster 5 gathered 15 genotypes which were all Restorer lines, 11 genotypes were grouped in cluster 6 (5 CMS lines, 4 SFP lines, 1 Restorer line and 1 B-line). Likewise, cluster 7 had 6 sunflower genotypes (5 SFP lines+1 CMS lines), cluster 8 had 11 genotypes (6 SFP lines, 4 restorer lines and 1 CMS line). 6 sunflower genotypes (3 CMS lines, 2 SFP lines and 1 restorer lines) were grouped in cluster 9, while cluster 10 showed a grouping of 8 genotypes (3 CMS lines, 3 Restorer lines and 2 B-lines). Cluster 11 had 8 sunflower genotypes (3 SFP lines, 2 CMS lines, 2 B-lines and 1 Restorer line) and 8 sunflower genotypes tend to group in cluster 12 (3 Restorer, 2 CMS-lines, 2 B-lines and 1 SFP line).

Clustering of 109 sunflower genotypes through hybrid (hierarchical+K-means) machine learning.

Grouping of sunflower genotypes observed by the application of hybrid algorithm (hierarchical+K-means) was found to be useful to some extent as it can be used to group closer genotypes, however, grouping of genotypes with distinct characteristics like restorer lines and CMS lines closely is somewhat confusing, hence this algorithm is also found to be not a good fit for the current study. As the grouping of genotypes using hierarchical clustering algorithm is clearer and more definitive, hence selection of potential parents for the development of sunflower hybrids were based on the grouping observed through hierarchical clustering approach.

As 12 clusters were observed through hierarchical clustering method, 1 genotype from each of the 12 clusters was selected for further utilization in sunflower hybrid breeding program. Genotypes exhibiting the highest seed yield potential from each of the 12 clusters (recorded at the height of 18) were selected. Moreover, all the restorer lines tend to cluster separately from CMS lines, hence Line Tester mating design was followed for sunflower hybrid F1 development.

To assess the practical efficiency of the identified heterotic groups, selected parental lines were crossed in Line Tester mating design and 36 F1 hybrids of sunflower were generated. Heterosis (mid-parent heterosis, better parent heterosis) and combining ability analysis (General combining ability and Specific combining ability) were conducted to evaluate the potential of methodology used for identification/mining of heterotic grouping pattern and thereof selection of potential parental lines for commercial hybrid development.

Table 1 presents the mean performance of 12 sunflower lines that were planted at NARC, Islamabad. The study focused on nine agro-morphological traits. Among the lines, CMS-HAP-112 exhibited the shortest duration to initiate flowering, taking only 46.5days, while RHP-41 had the longest duration of 56.5days. CMS-HAP-111 completed 100% flowering the earliest, within 55days, followed by CMS-HAP-112 at 55.5days. On the other hand, RHP-41 took the maximum number of days to complete flowering, with a duration of 67.5days. Regarding plant height, the 12 parental sunflower lines displayed a range from 200.14cm (CMS-HAP-54) to 134.6cm (CMS-HAP-111). In terms of leaf area, CMS-HAP-56 had the highest recorded value of 257.48 cm2, while RHP-38 had the lowest average leaf area of 141.5 cm2. The largest head diameter of 19.3cm was observed in CMS-HAP-99, whereas the smallest head diameter of 10.45cm was found in RHP-38. In the context of stem curvature, the lowest value recorded was 6.95cm for RHP-71, while CMS-HAP-111 and CMS-HAP-12 exhibited the highest stem curvatures of 48cm and 45.7cm, respectively. The number of leaves varied among the parental lines, with CMS-HAP-111 having the fewest leaves (23.35), and CMS-HAP-112 having the highest number of leaves (33.1), followed by CMS-HAP-99 (33). The 100 seed weight of the parental lines ranged from 3.48g (RHP-69) to 6.61g (CMS-HAP-99). CMS-HAP-112 displayed the highest mean seed yield per plant at 68.19g, while the lowest seed yield per plant was observed in RHP-68 (27.28g) and RHP-41 (27.9g) (Table 1).

Table 2 shows the average of 36 sunflower hybrids grown in NARC, Islamabad. The research focused on nine agromorphological traits. Hybrids RHP-68CMS-HAP-112 and RHP-38CMS-HAP-112 had the shortest flowering times, only 44days. On the other hand, the hybrid RHP-71CMS-HAP-56 had the longest time to flower initiation at 56.5days. RHP-68CMS-HAP-112 and RHP-38CMS-HAP-54 showed the minimum number of days (50) required for hybrids to complete 100% flowering, whereas RHP-71CMS- HAP-111 was 66 5days. The number of days until the flowering rate reaches 100%. Regarding the mean leaf area approaching physiological maturity, RHP-71CMS-HAP-56 showed the highest value of 176.53 cm2, while RHP-69CMS-HAP had the lowest mean leaf area. The largest head diameter he recorded with the RHP-71CMS-HAP-99 was 23.95cm, followed by he with the RHP-53CMS-HAP-111 with a diameter of 22.77cm. Conversely, RHP-68CMS-HAP-112 had the smallest head diameter of 17.11cm, followed by RHP-68CMS-HAP-54 with 17.53cm, and the tallest hybrid in terms of plant height was RHP-71CMS. -HAP-112 had an average height of 175.17cm. while the smaller hybrids were RHP-53CMS-HAP-111 (131cm) and RHP-41CMS-HAP-56 (132cm).

Regarding stem curvature, the lowest recorded value was 42.77cm for RHP-68CMS-HAP-54, followed by RHP-53CMS-HAP-54 with a stem curvature of 48.83cm. HAP-99 and RHP-38CMS-HAP-112 exhibited maximum stem curvatures of 77.5cm and 74.83cm, respectively. RHP-53CMS-HAP-111 has the lowest number of seats (26), RHP-71CMS-HAP-56 has the highest number of seats (36.67), followed by RHP-71CMS-HAP-99 continued. (36.17). Test weights of hybrids ranged from 4.41g (RHP-71CMS-HAP-111) to 7.34g (RHP-38CMS-HAP-12). The minimum seed yield per plant for hybrid RHP-53CMS-HAP-111 was 49.3g, whereas RHP-71CMS-HAP-54 showed the highest average seed yield of 103.36g per plant, compared to RHP-41 followed by RHP-41CMS-HAP-111 of 99.45g.

Results of heterosis and heterobeltiosis for nine morphological characteristics of sunflower plants are presented in Table 3 and 4. Range of heterosis for days to flower initiation reported in present study was from 10.14**% (CMS-HAP-111RHP-71) to 13.04% (CMS-HAP-56RHP-68). The heterotic effects of six hybrids were found to be in positive direction, while non-significant heterosis effects were found of six cross combinations. Remaining all cross combinations showed a highly significant heterosis for days to flower initiation. Heterobeltiotic effects recorded for 36 sunflower hybrids were found to be in the range of 20.35% (CMS-HAP-112RHP-41) to 3.65*% (CMS-HAP-111RHP-71). Most of heterobeltiotic effects are in negative direction.

CMS-HAP-54RHP-38 showed the maximum heterotic effect in negative direction for days taken to 100% flowering ( 18.37**%) followed by CMS-HAP-56RHP-41 ( 17.0**%) and CMS-HAP-56 xRHP-38 ( 16.73**%). Whereas hybrid CMS-HAP-111RHP-71 depicted the highest positive heterotic effect for this trait (13.68**%) followed by CMS-HAP-12RHP-71 (8.94**%). The heterotic effect was significant for all hybrids except for CMS-HAP-111RHP-53. Range of heterobeltiosis was recorded from -23.7**% (CMS-HAP-112RHP-41) to 7.26**% (CMS-HAP-111RHP-71). Heterobeltiotic effect of all the hybrid combinations found to be statistically highly significant for days to complete flowering except four hybrids viz., CMS-HAP-112RHP-71, CMS-HAP-12RHP-71, CMS-HAP-54RHP-71 and CMS-HAP-99RHP-71.

Results obtained of heterosis and heterobeltiosis effects for leaf area in hybrid combination under study depicted that heterosis over mid parent ranged from 3.63ns% to 44.26**%. Highest magnitude of positive heterosis effect was noted for CMS-HAP-12RHP-38 (3.63ns%) while negative heterotic effect in negative direction was recorded for F1 hybrid CMS-HAP-56RHP-41 ( 44.26**%). Highest effect for heterobeltiosis observed in negative direction was ( 48.28**%) for CMS-HAP-56RHP-41, followed by CMS-HAP-56RHP-68 ( 46.11**%). Heterobeltiotic effects of 29 hybrids was found to be statistically significant.

Maximum heterosis for head diameter was observed for CMS-HAP-12RHP-38 (59.49**%), whereas lowest magnitude of mid parent heterosis was depicted by CMS-HAP-112RHP-68(4.65ns%) (Table 3). All hybrids exhibited positive mid parent heterosis. Maximum heterobeltiosis was observed for CMS-HAP-12RHP-71 (31.71**%), while minimum heterobeltiosis was recorded for CMS-HAP-99RHP-69 ( 6.68ns%). Only six sunflower hybrids showed a negative heterobeltiotic effect for head diameter. Maximum mid parent heterosis for plant height recorded was 31.4**% (CMS-HAP-54RHP-53), while minimum mid parent heterosis of 13.92*% was observed for CMS-HAP-111RHP-38. As many as thirty hybrids exhibited a negative magnitude of mid parent heterosis for head diameter in the present study. Range of heterobeltiosis observed was from 35.34% (CMS-HAP-54RHP-68) to 5.17*% (CMS-HAP-111RHP-71). Results for heterobeltiosis of 34 hybrids were found to be negative with respect to better parent heterosis.

Range of heterotic effects for the 36 sunflower hybrids under study recorded was from 65.87**% (CMS-HAP-111RHP-69) to 317.24**% (CMS-HAP-54RHP-71). All sunflower F1 hybrid combinations under study expressed highly significant positive heterotic effects for stem curvature. Heterobeltiosis was statistically significant for 24 hybrids and all 36 F1 hybrids showed positive heterotic effects over the best parent. Maximum heterobeltiosis observed was for CMS-HAP-99RHP-68 (194.68**%), while minimum heterobeltiosis was recorded for CMS-HAP-111RHP-69 (10.06ns%). Results for number of leaves per plant obtained depicted that maximum positive heterosis was recorded for CMS-HAP-111RHP-71 (45.58**%) followed by CMS-HAP-56RHP-71 (31.89**%). Maximum magnitude of negative heterotic effect was noted for CMS-HAP-112RHP-53 ( 9.25ns%), followed by CMS-HAP-99RHP-69 ( 8.66ns%). Of all the 36 hybrid combinations under study, 22 expressed positive heterosis for the average number of leaves per plant. Highest magnitude of heterobeltiotic effect in negative direction was recorded for CMS-HAP-111RHP-53 ( 20.37**%) while maximum better parent positive heterosis was noted for CMS-HAP-111RHP-71 (36.02**%) followed by CMS-HAP-56RHP-71 (24.29**%).

Among all the hybrids tested the results of 25 hybrids for 100 seed weight was found to be statistically significant (Table 4). Maximum heterotic effect noted for this character was 57.72**% (CMS-HAP-56RHP-69) while minimum mid-parent heterosis observed was 3.45ns% (CMS-HAP-111RHP-71). Only two hybrid combinations expressed heterosis for 100 seed weight in negative direction. Heterosis over better parent for 100 seed weight ranges from 15.49*% (CMS-HAP-111RHP-38) to 37.18**% (CMS-HAP-56RHP-53). Results of 10 hybrid combinations were found to be statistically significant. Heterobeltiotic effect of 24 hybrids were on positive side (Table 4). Among all the 36 hybrids tested, 35 sunflower hybrids expressed a positive mid parent heterosis for seed yield per plant. The maximum heterotic effect noted for this character was 134.69**% (CMS-HAP-111RHP-41) followed by 125.18**% (CMS-HAP-12RHP-71) and minimum mid-parent heterosis observed was 1.79ns (CMS-HAP-112RHP-53). Maximum heterobeltiosis recorded was 74.93**% (CMS-HAP-11RHP-41) while minimum heterobeltiosis noted was 27.58ns% (CMS-HAP-112RHP-53). Heterobeltiotic effect of only nine hybrids were negative while rest of 27 hybrids expressed a positive gain over their better parent for seed yield per plant (Table 4).

Line Tester mating design had the ability to evaluate a greater number of hybrids than the diallel and partial diallel mating designs. This technique of hybrid evaluation is quite successful in cases where hybrids must be developed from Restorer and complete male sterile lines. Results pertaining to General Combining Ability of 12 parental lines are presented in Table 5.

Pursual of GCA estimates of all 12 hybrids for DFI showed that only two parents, one CMS, i.e., CMS-HAP-12 (7.65**) and one R-line i.e., RHP-68 (1.07**) had positive and significant GCA effects. Similarly, the same two parents had the highest, positive and significant GCA effect for DFC, depicting that these hybrids are late maturing. For leaf area GCA estimates, CMS-HAP-12 (14.73**) were found to be highly significant and positive among all the 12 parental lines under examination, while CMS-HAP-99 showed the lowest GCA magnitude of 13.99**. GCA effects for average leaf area for all the six male lines were found to be non-significant. Range of GCA estimates for head diameter recorded was from 2.57** (CMS-HAP-12) to 1.17** (CMS-HAP-54), while among male lines RHP-68 was found to be a good general combiner for head diameter with GCA effect of 1.02*. The best general combining ability recorded for plant height was from CMS-HAP-12 (13.22**), while lowest GCA estimate of 10.3** was shown by CMS-HAP-111. Stem curvature GCA estimates of all the 12 parents under study were found to be statistically non-significant. GCA of number of leaves per plant were highly significant for two CMS lines viz., CMS-HAP-111 ( 1.94**) and CMS-HAP-12 (4.53**). RHP-71 (0.64ns) showed the maximum GCA among tester lines. For 100 seed weight only 2 parental lines i.e., CMS-HAP-112 (0.45*) and RHP-69 (0.41*) showed good general combining ability for this yield related important plant characteristic. CMS-HAP-12 exhibited highest GCA effect of 20.43** for seed yield per plant among female lines, while for testers no male line exhibited a significant positive GCA effect for seed yield.

Result of combination specific combining ability of thirty-six sunflower hybrids developed from 12 parental line following L T mating design for nine agro-morphological traits are presented in Table 6. SCA effect of CMS-HAP-12RHP-68 (3.18**) was the highest for DFI, while SCA estimate of 2.9** showed by CMS-HAP-112RHP-41 was the lowest in magnitude. Combination specific combining ability estimates for days taken to flower completion was found to be highest for CMS-HAP-12RHP-68 (3.60**), while CMS-HAP-112RHP-68 cross combination recorded maximum negative SCA effect for DFC, showing that this cross combination is the earliest in flowering than rest of hybrids study. Significant SCA estimates were recorded for all the 36 hybrids for leaf area with maximum SCA effect of 20.87** was observed for CMS-HAP-54RHP-38. Only three hybrids showed a positive and significant SCA magnitude for head diameter, with maximum value of 2.46* (CMS-HAP-12RHP-38). For head diameter, 21 hybrid combination depicted a negative SCA estimates showing that head diameter of hybrids was less than that of their respective parents. The highest magnitude of SCA for plant height was shown by CMS-HAP-112RHP-71 (15.6*). Combination specific combining ability estimates for stem curvature were positive for 34 cross combinations. Range of SCA effects for number of leaves per plant was from 3.47* (CMS-HAP-99RHP-41) to 3.53* (CMS-HAP-11RHP-53). Only one cross combination was found to be significant for head diameter SCA effect and in negative direction, i.e., CMS-HAP-111RHP-38 ( 1.30**). Positive SCA effects of 17 hybrids for 100 seed weight was observed. For seed yield per plant magnitude of SCA recorded was positive for 19 cross combinations, while maximum positive SCA magnitude was depicted by CMS-HAP-111RHP-53 (3.60**) followed by CMS-HAP-112RHP-53 (2.93**).

Original post:
Application of machine learning for identification of heterotic groups in sunflower through combined approach of ... - Nature.com

Read More..