The University of Essex team has devised a new approach to training neural networks called Target Space, which stabilizes the learning process by tweaking neuron firing strengths. This method enables deeper neural networks with fewer training examples and computing resources, accelerating AI breakthroughs.
SourceUniversity of Essex·JournalJournal of Machine Learning Research·TypeComputational simulation/modeling·DateFeb 22, 2022
Apple iPhone 17 Pro
Apple iPhone 17 Pro delivers top performance and advanced cameras for field documentation, data collection, and secure research communications.
A new study at McGill University found that an AI tutoring system improved surgical skills and learning outcomes among medical students compared to human instructors. The AI-powered Virtual Operative Assistant taught safe techniques and provided personalized feedback, leading to a 36% better performance rate.
SourceMcGill University·JournalJAMA Network Open·TypeExperimental study·DateFeb 22, 2022
Researchers at the University of Copenhagen have developed an AI method to recognize and detect insect species based on their wingbeats, enabling easier monitoring of biodiversity. The method uses infrared sensors to measure wingbeats and group insects into different species without human input.
SourceUniversity of Copenhagen - Faculty of Science·JournalEcological Informatics·DateFeb 21, 2022
Researchers studied how diverse neural network training datasets impact generalization. They found that data diversity is key to overcoming bias, but also degrade performance when neural networks are trained for multiple tasks simultaneously. The study highlights the importance of designing diverse and controlled datasets in machine le...
SourceMassachusetts Institute of Technology·JournalNature Machine Intelligence·DateFeb 21, 2022
Anker Laptop Power Bank 25,000mAh (Triple 100W USB-C)
Anker Laptop Power Bank 25,000mAh (Triple 100W USB-C) keeps Macs, tablets, and meters powered during extended observing runs and remote surveys.
Researchers at Tokyo Institute of Technology have developed a new AI processor called Hiddenite, which achieves state-of-the-art accuracy in sparse neural networks with lower computational burdens. The chip drastically reduces external memory access for enhanced computational efficiency.
SourceTokyo Institute of Technology·TypeExperimental study·DateFeb 18, 2022
A new imaging method, combining optimal imaging and machine learning, can determine cell viability without chemical staining. The approach achieved a 95% accuracy rate and has the potential to be applied in hospitals and research labs.
SourceBeckman Institute for Advanced Science and Technology·JournalNature Communications·TypeExperimental study·DateFeb 17, 2022
Recent advances in AI for drug design have shown promising results, but further improvement is needed to translate early successes into effective drugs. Active learning and explainable AI hold the key to harnessing data value and designing correct molecules.
SourceHealth Data Science·JournalHealth Data Science·DateFeb 17, 2022
SAMSUNG T9 Portable SSD 2TB
SAMSUNG T9 Portable SSD 2TB transfers large imagery and model outputs quickly between field laptops, lab workstations, and secure archives.
A UCI team uncovered key brain mechanisms by which the hippocampus organizes memories into sequences, enabling decision-making. The finding may help understand memory failures in Alzheimer's disease and other forms of dementia.
SourceUniversity of California - Irvine·JournalNature Communications·TypeObservational study·DateFeb 15, 2022
A machine-learning algorithm named MAD3 can predict mechanical properties of metals without performing physical tests, cutting testing time by 1,000 times. The algorithm replaces traditional simulation software, enabling faster research and development with minimal resources.
SourceDOE/Sandia National Laboratories·JournalMaterials Science and Engineering·DateFeb 15, 2022
Jonathan Niles-Weed, an assistant professor at NYU's Courant Institute of Mathematical Sciences, has been awarded a prestigious Sloan Research Fellowship for his groundbreaking work in statistical theory and optimal transport. The fellowship recognizes his creativity, innovation, and research accomplishments in the field of data science.
A research team developed an algorithm that instantly assesses and adjusts brain stimulation placement using electroencephalography (EEG) feedback. The method can find the optimal stimulation parameters in just 1-2 minutes, potentially improving the efficacy of TMS treatment for brain disorders like chronic pain and depression.
SourceAalto University·JournalBrain Stimulation·DateFeb 15, 2022
Celestron NexStar 8SE Computerized Telescope
Celestron NexStar 8SE Computerized Telescope combines portable Schmidt-Cassegrain optics with GoTo pointing for outreach nights and field campaigns.
Researchers at Mayo Clinic Cancer Center developed a machine learning algorithm that integrates genetic data from over 5,000 patients to predict patient benefit from chemotherapy and immunotherapy. A 32-gene molecular signature was identified, providing prognostic information and predicting patient response to immunotherapy.
SourceMayo Clinic·JournalNature Communications·DateFeb 14, 2022
Researchers found AI-synthesized faces to be nearly indistinguishable from real faces and rated as more trustworthy. The study's results have significant implications for the spread of manipulated images, including potential use in revenge porn and propaganda.
SourceLancaster University·JournalProceedings of the National Academy of Sciences·TypeExperimental study·DateFeb 14, 2022
Researchers at Universidad Carlos III de Madrid developed a computer vision system to analyze cells in microscopy videos, allowing for automatic characterization of cell behavior. The system enables faster analysis of thousands of cells compared to traditional methods, which typically involve manual segmentation and tracking.
SourceUniversidad Carlos III de Madrid·JournalMedical Image Analysis·TypeImaging analysis·DateFeb 11, 2022
Anastasios Kyrillidis has won a National Science Foundation CAREER Award to explore the theory and design of non-convex optimization algorithms. His research aims to devise algorithmic foundations and theory that will accelerate problem-solving in machine learning, information processing, and optimization.
Garmin GPSMAP 67i with inReach
Garmin GPSMAP 67i with inReach provides rugged GNSS navigation, satellite messaging, and SOS for backcountry geology and climate field teams.
Researchers developed a new reagent-free detection technique for SARS-CoV-2 using Raman spectroscopy and machine learning. The method shows an accuracy of 80% in detecting COVID-19 infections from saliva samples, overcoming limitations of RT-PCR testing.
SourceSPIE--International Society for Optics and Photonics·JournalJournal of Biomedical Optics·DateFeb 9, 2022
Researchers at Medical University of Vienna discovered that certain microbiome profiles following lung transplantation can provide prognostic information for future changes in lung function. Machine Learning analyzed multiomics data, including the microbiome, lipidome, and metabolome, to predict lung function deterioration.
SourceMedical University of Vienna·JournalEuropean Respiratory Journal·DateFeb 7, 2022
Researchers developed a hybrid machine-learning approach combining CNN and LSTM to recognize complex hand gestures in prosthetic hands. The technique achieved far superior performance than traditional machine learning efforts, with an accuracy of over 80%, but struggled with certain pinching gestures.
SourceBeijing Institute of Technology Press Co., Ltd·JournalCyborg and Bionic Systems·TypeExperimental study·DateFeb 7, 2022
Researchers developed a method called 6mASCOPE that measures DNA tagging system accuracy and distinguishes bacterial from human DNA. The study found high levels of methylation in plant, fly, mouse, and human cells, but mostly attributed to contamination.
SourceThe Mount Sinai Hospital / Mount Sinai School of Medicine·JournalScience·TypeExperimental study·DateFeb 3, 2022
Rigol DP832 Triple-Output Bench Power Supply
Rigol DP832 Triple-Output Bench Power Supply powers sensors, microcontrollers, and test circuits with programmable rails and stable outputs.
Researchers developed a neural network algorithm to predict art auction prices, relying on visual and non-visual characteristics of artworks. While human experts were more accurate, the algorithm showed promise in identifying market inefficiencies, such as auctioneer biases.
SourceUniversity of Luxembourg·JournalThe Journal of Finance·DateFeb 2, 2022
Researchers developed a machine learning algorithm to automate propofol dosing for unconscious patients, matching human performance in sophisticated simulations. The 'dose penalty' model improved upon traditional software, but limitations remain, highlighting challenges in AI system accuracy and real-world application.
SourcePicower Institute at MIT·JournalArtificial Intelligence in Medicine·TypeComputational simulation/modeling·DateFeb 2, 2022
A new technique uses compression to reduce data transmission size, allowing for efficient federated learning on wireless devices. The approach has been shown to condense data packets by up to 99%, making it suitable for areas with limited bandwidth.
SourceNorth Carolina State University·JournalIEEE Journal of Selected Topics in Signal Processing·TypeExperimental study·DateFeb 1, 2022
Creality K1 Max 3D Printer
Creality K1 Max 3D Printer rapidly prototypes brackets, adapters, and fixtures for instruments and classroom demonstrations at large build volume.
Researchers developed a novel scheme that reduces energy consumption while improving traffic prediction accuracy by up to 40% compared to benchmark schemes. The scheme uses software defined network and edge computing to control the operation of base stations, ensuring both sustainability and performance.
SourceShibaura Institute of Technology·TypeComputational simulation/modeling·DateJan 31, 2022
Rice University scientists employ machine-learning techniques to streamline the process of synthesizing graphene from waste through flash Joule heating. The lab used its custom optimization model to improve graphene crystallization from four starting materials over 173 trials.
SourceRice University·TypeExperimental study·DateJan 31, 2022
Researchers developed MonoCon, a new AI technique that enables accurate identification of 3D objects in 2D images. By incorporating auxiliary context, the method improves object detection and estimation accuracy, paving the way for safer and more robust autonomous vehicles.
SourceNorth Carolina State University·TypeComputational simulation/modeling·DateJan 26, 2022
Researchers developed AI models trained on clinical data from a statewide health information exchange to predict healthcare resource utilization for individuals with COVID-19. The models demonstrated accurate public health predictions and provided valuable insights into patient-level need for healthcare resources.
SourceRegenstrief Institute·JournalJournal of Medical Internet Research·DateJan 26, 2022
Fluke 87V Industrial Digital Multimeter
Fluke 87V Industrial Digital Multimeter is a trusted meter for precise measurements during instrument integration, repairs, and field diagnostics.
A team of scientists developed an AI-based model to predict personal thermal comfort based on spatial parameters, achieving exceptional accuracy. The study highlights the importance of incorporating architectural features in models to reduce energy consumption.
SourceXi'an Jiaotong-Liverpool University·JournalJournal of Building Engineering·TypeComputational simulation/modeling·DateJan 25, 2022
Researchers at the University of Oklahoma have developed a molecular framework that solves the challenge of predicting peptide structures. The framework bridges experimental and computer sciences, enabling the use of machine learning and artificial intelligence to model peptide structures for materials engineering.
SourceUniversity of Oklahoma·JournalScience Advances·DateJan 25, 2022
Researchers developed an AI system that can analyze retinal scans to identify patients at high risk of a heart attack over the next year. The system uses deep learning techniques and achieves an accuracy of 70-80%, revolutionizing the way patients are screened for signs of heart disease.
SourceUniversity of Leeds·JournalNature Machine Intelligence·TypeComputational simulation/modeling·DateJan 25, 2022
Scientists at Vienna University of Technology have developed a new type of neural network that can accurately simulate the quark-gluon plasma, a state of matter present in the early universe. The networks use gauge invariant convolutional neural networks to recognize patterns and predict properties of the plasma.
SourceVienna University of Technology·JournalPhysical Review Letters·TypeComputational simulation/modeling·DateJan 25, 2022
Physicists have detected X particles in quark-gluon plasma produced in the Large Hadron Collider, a phenomenon that could reveal the particles' unknown structure. The discovery uses machine-learning techniques to sift through massive datasets and identify decay patterns characteristic of X particles.
SourceMassachusetts Institute of Technology·JournalPhysical Review Letters·DateJan 24, 2022
Aranet4 Home CO2 Monitor
Aranet4 Home CO2 Monitor tracks ventilation quality in labs, classrooms, and conference rooms with long battery life and clear e-ink readouts.
A team at the University of Washington has created an optical computing system that not only reduces noise but also utilizes it to improve creative output. The system uses a Generative Adversarial Network and demonstrates the viability of this technology at a large scale.
SourceUniversity of Washington·JournalScience Advances·DateJan 21, 2022
Researchers used electronic health record data from over 700 hospitals to train and evaluate three machine learning algorithms, finding that XGBoost provided the highest accuracy in predicting CDI among hospitalized patients. The study suggests that MLAs can help reduce the clinical and economic impact of healthcare-associated infections.
SourceAssociation for Professionals in Infection Control·JournalAmerican Journal of Infection Control·TypeComputational simulation/modeling·DateJan 20, 2022
A new approach uses reinforcement learning algorithm to help robotic knee mimic intact human knee in walking, achieving 100% success rate on even ground. The technology also adapts to uneven terrain and changes in walking pace, promising a more comfortable experience for prosthetic users.
SourceChinese Association of Automation·JournalIEEE/CAA Journal of Automatica Sinica·DateJan 20, 2022
Researchers developed a machine learning approach enabling robots to separate, recognize, and grasp individual objects with high accuracy. The method achieved 97% success rate in real-world experiments, paving the way for industrial parts sorting and residential waste sorting applications.
SourceChinese Association of Automation·JournalIEEE/CAA Journal of Automatica Sinica·DateJan 20, 2022
A new federally funded study will use machine learning to create a first-of-its-kind algorithm predicting individual responses to food and dietary routines. The National Institutes of Health's All of Us Research Program will recruit 10,000 participants nationwide.
SourcePennington Biomedical Research Center·DateJan 20, 2022
GoPro HERO13 Black
GoPro HERO13 Black records stabilized 5.3K video for instrument deployments, field notes, and outreach, even in harsh weather and underwater conditions.
MIT researchers develop teaching phase that guides humans in understanding AI strengths and weaknesses, enabling more accurate decisions and faster conclusions. The technique helps humans build a mental model of the AI agent, reducing reliance on biased assumptions.
SourceMassachusetts Institute of Technology·DateJan 20, 2022
MIT researchers develop a method to test feature-attribution methods for machine-learning models. They find that even the most popular methods often miss important features in an image and some perform as poorly as a random baseline. This has major implications for high-stakes situations like medical diagnoses.
SourceMassachusetts Institute of Technology·DateJan 19, 2022
Research finds a strong association between retinal age and real age, with large gaps associated with increased mortality risk. The 'retinal age gap' could be used as a screening tool to predict mortality risk, particularly for non-cardiovascular causes.
SourceBMJ Group·JournalBritish Journal of Ophthalmology·TypeObservational study·DateJan 18, 2022
A new project aims to improve the performance of Graph Neural Networks (GNNs) by leveraging weak supervision and additional information. The research has potential applications in fraud detection, agriculture, and cancer diagnosis.
SourceUniversity of Illinois School of Information Sciences·DateJan 18, 2022
A new algorithm, FusionM4Net, has been developed to classify skin lesions with improved diagnostic accuracy. The algorithm uses a multi-stage data fusion process and outperforms previous state-of-the-art algorithms.
SourceTechnical University of Munich (TUM)·JournalMedical Image Analysis·TypeData/statistical analysis·DateJan 14, 2022
AmScope B120C-5M Compound Microscope
AmScope B120C-5M Compound Microscope supports teaching labs and QA checks with LED illumination, mechanical stage, and included 5MP camera.
Researchers found animal-dispersed plant species' ability to adapt to climate change reduced by 60% due to bird and mammal losses. Global seed dispersal mapping revealed severe declines in temperate regions, with tropical areas at high risk if endangered species go extinct.
SourceRice University·JournalScience·TypeData/statistical analysis·DateJan 13, 2022
A new platform uses machine learning to design and build transformable, inflatable systems with potential applications in medicine, architecture, robotics, space travel, and more. The researchers used finite element simulations and neural networks to learn how to control the deformation of membranes when pressurized.
SourceHarvard John A. Paulson School of Engineering and Applied Sciences·JournalAdvanced Functional Materials·DateJan 12, 2022
A new PET/CT artificial intelligence model has been developed to predict the risk of future heart attacks with improved accuracy. By combining information from PET and CT angiography, the model provides a more robust prediction of heart attack risk than clinical data alone.
SourceSociety of Nuclear Medicine and Molecular Imaging·JournalJournal of Nuclear Medicine·DateJan 11, 2022
Researchers at Beckman Institute have defined a mathematical framework for identifying hallucinations in biomedical images. This framework will enable researchers and radiologists to quantitatively assess their image reconstruction methods and prevent patient misdiagnosis.
SourceBeckman Institute for Advanced Science and Technology·JournalIEEE Transactions on Medical Imaging·TypeImaging analysis·DateJan 10, 2022
A team of researchers at Washington University in St. Louis used machine learning to understand how locusts can consistently recognize smells despite environmental factors, finding that combining the activity of ON and OFF neurons provides a simple yet effective solution.
SourceWashington University in St. Louis·JournalProceedings of the National Academy of Sciences·TypeExperimental study·DateJan 10, 2022
Nikon Monarch 5 8x42 Binoculars
Nikon Monarch 5 8x42 Binoculars deliver bright, sharp views for wildlife surveys, eclipse chases, and quick star-field scans at dark sites.
Researchers found that two commonly used atomic fingerprints, ACSF and SOAP, are insensitive to certain movements, leading to the failure of machine learning in resolving four-body interactions. This limitation affects the accuracy of reproducing these interactions with limited success.
SourceNational Centre of Competence in Research (NCCR) MARVEL·TypeComputational simulation/modeling·DateJan 10, 2022
The European Research Council has awarded €1.5 million in grants to three Saarbrücken-based researchers. Their projects focus on artificial intelligence and cybersecurity, with aims to develop fairer machine learning algorithms and secure computing methods.
Researchers at NIMS successfully fabricated high-performance neodymium magnets using machine learning, optimizing processing conditions with limited experimental data. By leveraging active learning and Bayesian optimization, they were able to achieve better magnetic properties than conventional sintered magnets.
SourceNational Institute for Materials Science, Japan·TypeExperimental study·DateJan 7, 2022
DJI Air 3 (RC-N2)
DJI Air 3 (RC-N2) captures 4K mapping passes and environmental surveys with dual cameras, long flight time, and omnidirectional obstacle sensing.
Researchers used AI tools to analyze tissue samples from 439 patients with head and neck cancers, identifying those who could benefit from reduced radiation therapy. The study aims to improve treatment decisions for patients, reducing side effects and improving quality of life.
SourceCase Western Reserve University·JournalJNCI Journal of the National Cancer Institute·TypeImaging analysis·DateJan 6, 2022
A recent study found that conventional metrics for detecting audio adversarial examples are unreliable and fail to accurately represent human perception. Researchers proposed a more robust evaluation method, but acknowledge the complexity of modeling auditory perception with mathematical metrics.
SourceUniversity of the Basque Country·JournalComputers & Security·DateJan 6, 2022
New experiments challenge conventional wisdom on neuronal refractory periods, discovering durations exceeding 20 milliseconds and sensitivity to input signal origin. These findings may hold the key to understanding degenerative diseases and advancing artificial intelligence-based applications.
SourceBar-Ilan University·JournalPhysical Review E·DateJan 5, 2022
A pilot study suggests that machine learning algorithms combining EKG and electronic health record data can more effectively screen for pulmonary embolisms than current tests. The fusion model was found to be 15-30% more effective at accurately identifying cases, especially severe ones.
SourceThe Mount Sinai Hospital / Mount Sinai School of Medicine·JournalEuropean Heart Journal - Digital Health·TypeExperimental study·DateDec 21, 2021
Meta Quest 3 512GB
Meta Quest 3 512GB enables immersive mission planning, terrain rehearsal, and interactive STEM demos with high-resolution mixed-reality experiences.
Researchers develop system to image millions of brain cell connections in real-time, revealing key locations for learning and memory encoding. The new tool allows scientists to study synapse activity on a massive scale, with potential applications in understanding diseases such as Alzheimer's and autism.
Researchers analyzed hundreds of thousands of secure email messages between doctors and patients to find that most doctors use language too complex for their patients' low health literacy. Effective communication can improve patient outcomes by tailoring electronic messages to match the complexity of the patient's language.
SourceUniversity of California - San Francisco·JournalScience Advances·DateDec 17, 2021
An analysis of data from 16 US states found that wine and spirit sales increased during the early months of the pandemic, while beer sales declined. Visits to liquor stores increased, but those to bars and pubs decreased.
SourceUniversity at Buffalo·JournalPLOS ONE·DateDec 17, 2021
Researchers developed an AI model that can diagnose COVID-19 with high accuracy, using federated learning to preserve patient data privacy. The model was trained on over 9,000 CT scans from 23 hospitals in the UK and China, and validated against a panel of radiologists.
SourceUniversity of Cambridge·JournalNature Machine Intelligence·TypeComputational simulation/modeling·DateDec 16, 2021
A team of UBC Okanagan researchers has developed a system to enhance interactions between humans and robots in industrial settings. The system uses artificial intelligence and machine learning to capture and analyze the environment, allowing robots to respond in a timely manner to ensure human safety.
SourceUniversity of British Columbia Okanagan campus·JournalRobotics and Computer-Integrated Manufacturing·TypeMeta-analysis·DateDec 14, 2021
Apple iPad Pro 11-inch (M4)
Apple iPad Pro 11-inch (M4) runs demanding GIS, imaging, and annotation workflows on the go for surveys, briefings, and lab notebooks.
Researchers simulated an attack that falsified mammogram images, fooling both AI breast cancer diagnosis models and human radiologist experts. The study highlights the need to develop ways to make AI models more robust to adversarial attacks, which could lead to incorrect cancer diagnoses.
SourceUniversity of Pittsburgh·JournalNature Communications·TypeComputational simulation/modeling·DateDec 14, 2021
Researchers developed an algorithm to differentiate life-threatening gunshot events from non-life-threatening plastic bag explosion events. The study found that 75% of plastic bag pop sounds were misclassified as gunshot sounds, highlighting the need for a diverse dataset of similar sounds.
SourceFlorida Atlantic University·JournalSensors·TypeExperimental study·DateDec 13, 2021