Everything here was posted deliberately — imported by The Combine and approved, submitted by someone, or added from a search. Nothing appears in this library just because it exists in an academic index.
Looking for something that isn't here yet? Search the whole literature from the homepage — anything you add there lands in this library.
John Preskill · Quantum · 2018 · 8,680 citations
Quantum computers with 50-100 noisy qubits will soon beat classical machines at some tasks, but they won't transform computing until gates get far more accurate.
T. Prusti, J. H. J. de Bruijne, A. G. A. Brown, A. Vallenari, C. Babusiaux + 95 more · Astronomy and Astrophysics · 2016 · 7,100 citations
ESA's Gaia satellite, launched in 2013 and orbiting 1.5 million km from Earth, is mapping the positions, motions and properties of over a billion stars.
Dolf Gielen, Francisco Boshell, Değer Saygin, Morgan Bazilian, Nicholas Wagner + 1 more · Energy Strategy Reviews · 2019 · 4,936 citations
Renewables plus energy efficiency could meet two-thirds of global energy demand by 2050 and deliver most of the emissions cuts needed to stay under 2 °C.
Fei Jiang, Yong Jiang, Hui Zhi, Yi Dong, Hao Li + 7 more · Stroke and Vascular Neurology · 2017 · 4,846 citations
A survey of how AI is already used in medicine — mostly cancer, neurology and cardiology — and what still blocks its use in real clinics.
Κωνσταντίνος Λιάκος, Patrizia Busato, Dimitrios Moshou, Simon Pearson, Dionysis Bochtis · Sensors · 2018 · 3,287 citations
A survey of machine learning in farming finds it already predicts yields, spots diseases and weeds, and monitors livestock, soil and water from sensor data.
Riccardo Miotto, Fei Wang, Shuang Wang, Xiaoqian Jiang, Joel T. Dudley · Briefings in Bioinformatics · 2017 · 3,122 citations
Deep learning can turn messy biomedical data into better health predictions, but its "black box" nature must be fixed before clinicians will trust it.
Shuroug A. Alowais, Sahar S. Alghamdi, Nada Alsuhebany, Tariq Alqahtani, Abdulrahman Alshaya + 8 more · BMC Medical Education · 2023 · 3,077 citations
A review argues AI can outperform clinicians in tasks like diagnosis and dosing, but ethical, legal and expertise gaps still block safe adoption.
Nicola Rieke, Jonny Hancox, Wenqi Li, Fausto Milletarì, Holger R. Roth + 12 more · npj Digital Medicine · 2020 · 2,942 citations
Hospitals can train shared medical AI without sharing patient data — federated learning moves the model to the data, not the data to the model.
Ernesto Panadero · Frontiers in Psychology · 2017 · 2,753 citations
Six major self-regulated learning theories largely agree and fit together, but which one works best depends on students' age and education level.
Pierre Friedlingstein, Michael O’Sullivan, Matthew W. Jones, Robbie M. Andrew, Judith Hauck + 81 more · Earth system science data · 2020 · 2,595 citations
Humans emitted about 11.2 billion tonnes of carbon a year in the 2010s; roughly half was absorbed by land and oceans, the rest stayed in the air.
Ansam Khraisat, Iqbal Gondal, Peter Vamplew, Joarder Kamruzzaman · Cybersecurity · 2019 · 1,957 citations
A review of intrusion detection systems argues signature-based tools miss novel attacks while anomaly-based ones trigger false alarms, and evaluation datasets are outdated.
R. Vinayakumar, Mamoun Alazab, K. P. Soman, Prabaharan Poornachandran, Ameer Al-Nemrat + 1 more · IEEE Access · 2019 · 1,896 citations
A deep neural network beats classical machine learning at spotting network and host intrusions across six benchmark attack datasets, and the authors propose a scalable real-time monitoring framework.
Charles D. Dziuban, Charles R. Graham, Patsy Moskal, Anders Norberg, Nicole Sicilia · International Journal of Educational Technology in Higher Education · 2018 · 1,253 citations
Blended courses match or beat face-to-face and online options on student success and dropout rates, and students judge course quality by consistent rules regardless of format.
Yang Xin, Lingshuang Kong, Zhi Liu, Yuling Chen, Yanmiao Li + 4 more · IEEE Access · 2018 · 1,224 citations
A survey mapping how machine learning and deep learning are used to detect network intrusions, plus the datasets, limits, and open problems in the field.
Li Ding, Yanying Wei, Libo Li, Tao Zhang, Haihui Wang + 5 more · Nature Communications · 2018 · 1,125 citations
Stacked MXene nanosheets form uniform sub-nanometer channels that let hydrogen through 160 times faster than CO2, beating the best existing gas-separation membranes.
Abhinav Sharma, Arpit Jain, Prateek Gupta, Vinay Chowdary · IEEE Access · 2020 · 1,090 citations
Machine learning now underpins smart farming — predicting soil properties, crop yields, diseases, weeds, livestock health and automating irrigation and harvesting.
Hyunwoo Yuk, Shaoting Lin, Chu Ma, Mahdi Takaffoli, Nicholas X. Fang + 1 more · Nature Communications · 2017 · 993 citations
Water-pumped hydrogel muscles make transparent soft robots that swim fast, kick balls, and catch a live fish while staying nearly invisible to eyes and sonar.
Ilie Gligorea, Marius Cioca, Romana Oancea, Andra-Teodora Gorski, Hortensia Gorski + 1 more · Education Sciences · 2023 · 913 citations
A review of 63 studies finds AI-driven adaptive e-learning personalizes learning paths and boosts engagement and test scores, though privacy and complexity remain obstacles.
E. M. B. M. Karunathilake, Anh Tuan Le, Seong Heo, Yong Suk Chung, Sheikh Mansoor · Agriculture · 2023 · 756 citations
Drones, sensors, IoT and machine learning can raise crop yields while cutting waste, but cost, data management and slow farmer adoption still hold precision agriculture back.
Tumaini Kabudi, Ilias O. Pappas, Dag Håkon Olsen · Computers and Education Artificial Intelligence · 2021 · 712 citations
A review of 147 studies finds AI adaptive learning systems are mostly small-scale prototypes that rarely tackle students' real, specific learning problems.
Mohd Javaid, Abid Haleem, Ravi Pratap Singh, Rajiv Suman, Shanay Rab · International Journal of Intelligent Networks · 2022 · 647 citations
A review arguing machine learning can ease overburdened health systems by speeding diagnosis, personalising treatment, cutting costs and spotting outbreaks early.
Geert M. Rutten, Hans H. C. M. Savelberg, Stuart Biddle, Stef Kremers · International Journal of Behavioral Nutrition and Physical Activity · 2013 · 500 citations
The authors coin "STUFF" (Stand Up For Fitness) — standing at least five minutes every half hour — as a catchy brand to make breaking up sitting spread.
Joseph Futoma, Morgan G. Simons, Trishan Panch, Finale Doshi‐Velez, Leo Anthony Celi · The Lancet Digital Health · 2020 · 454 citations
Chasing models that work everywhere can block machine learning that would actually help patients in a specific hospital — usefulness at the bedside should come first.
Jennifer Hay, Katie Drager · Linguistics · 2010 · 367 citations
Seeing stuffed kangaroos and koalas versus kiwis changed how New Zealanders heard vowels, showing that irrelevant regional cues shift speech perception.
Alexandre Vallée · Frontiers in Digital Health · 2023 · 336 citations
Virtual patient "digital twins" fed by real-time data could personalize treatment, flag health risks early, streamline hospital operations, and let clinicians rehearse procedures safely.
Srinu Nagireddi, Jatin R. Agarwal, Damodaran Vedapuri · ACS Engineering Au · 2023 · 297 citations
Capturing CO2 and turning it into fuels, chemicals, or underground storage is technically viable today, but cost, regulation, and public acceptance still block large-scale deployment.
Greeshma Gadikota · Communications Chemistry · 2021 · 238 citations
Turning CO2 into solid carbonate rock is energetically favorable and could both store carbon permanently and make useful materials — if the chemistry can be tuned.
Mohammed Badawy, Nagy Ramadan, Hesham Ahmed Hefny · Journal of Electrical Systems and Information Technology · 2023 · 232 citations
A survey of how machine learning and deep learning are used to predict disease, and the data, accuracy and trust problems still blocking real clinical use.
David Nesvorn, J. L. Alvarellos, L. Dones, Harold F. Levison · The Astronomical Journal · 2003 · 230 citations
Solar gravity clears out highly tilted and distant prograde moons of the giant planets, explaining why surviving irregular satellites cluster where they do.
Manal Al-Shafi, Osama Massarweh, Ahmad S. A. Abushaikha, Yusuf Biçer · Energy Reports · 2023 · 199 citations
Underground rock formations can store natural gas, hydrogen and buried CO2, but hydrogen's light molecules make it leak and mix more, complicating storage.
Paolo Giudici · Frontiers in Artificial Intelligence · 2018 · 195 citations
Fintech's new lending, advisory and crypto platforms create risks traditional banking models can't measure, so AI and statistical learning must be built into financial risk management.
Tianze Sun, Xiwang He, Xueguan Song, Liming Shu, Zhonghai Li · Frontiers in Medicine · 2022 · 194 citations
Digital twins — live virtual replicas of individual patients — could enable precise diagnosis and personalized treatment, but data collection and simulation hurdles remain.
Hossein Hassani, Xu Huang, Steve MacFeely · Big Data and Cognitive Computing · 2022 · 193 citations
Digital twins — live virtual copies of patients, devices and hospitals — could reshape healthcare, and this review proposes a framework for delivering them as a service.
Colin D. Hills, Nimisha Tripathi, Paula J. Carey · Frontiers in Energy Research · 2020 · 175 citations
Turning industrial wastes like slags and ashes into carbonate-cemented construction aggregates could lock away meaningful amounts of CO2 while making a saleable product.
Kang Zhang, Hong-Yu Zhou, Daniel Tomas Baptista‐Hon, Yuanxu Gao, Xiaohong Liu + 11 more · Patterns · 2024 · 148 citations
Digital twins — live virtual replicas of patients — could transform diagnosis and treatment, but biological variability, data gaps, and ethics still block real clinical use.
Lorenzo Diana, Pierpaolo Dini, Davide Paolini · Computers · 2025 · 144 citations
A broad review of intrusion detection systems, mapping how they work today across cloud, IoT and industrial networks, and where AI and blockchain could take them next.
Omid Moztarzadeh, Mohammad Behdad Jamshidi, Saleh Sargolzaei, Alireza Jamshidi, Nasimeh Baghalipour + 2 more · Bioengineering · 2023 · 130 citations
Simple, fast classical machine-learning models can power real-time digital twins of breast cancer for monitoring, diagnosis and prediction inside the metaverse.
Branka Stojanović, Josip Božić, Katharina Hofer-Schmitz, Kai Nahrgang, Andreas Weber⋆ + 4 more · Sensors · 2021 · 99 citations
Machine learning can spot fraudulent financial transactions, but detection rates vary widely by method and by which data features are used.
Md Morshed Alam, Md. Habibur Rahman, Md. Faisal Ahmed, Mostafa Zaman Chowdhury, Yeong Min Jang · Scientific Reports · 2022 · 98 citations
Pairing a Bi-LSTM forecaster with a scheduling optimizer lets a solar-plus-battery smart home cut its daily electricity bill under time-of-use pricing.
Luquan Ren, Bingqian Li, Guowu Wei, Kunyang Wang, Zhengyi Song + 3 more · iScience · 2021 · 94 citations
Soft robots still lag far behind living organisms in autonomy, self-repair and efficiency; copying biology's integrated sensing-actuation loops is the way to close the gap.
Ahmad Alzahrani, Mujeeb ur Rahman, Ghulam Hafeez, Gul Rukh, Sajjad H. Ali + 5 more · IEEE Access · 2023 · 85 citations
A genetic-algorithm scheduler for grids with wind, solar and batteries cut operating cost 59%, emissions 7%, and expected unserved load 2.67%.
Chengbo Fu, Lei Lü, Mansoor Pirabi · Digital Economy and Sustainable Development · 2024 · 74 citations
Green finance is a central tool for cutting emissions, but it remains underexplored in mainstream economics and finance journals, this review argues.
Zachary Johnson, Manob Jyoti Saikia · Bioengineering · 2024 · 70 citations
Wearable sensors can feed live biometric data into "human digital twins" — virtual patient copies used to predict disease, simulate trials, and monitor treatment remotely.
Tran Khanh Dang, Thanh Cong Tran, Luc Minh Tuan, Mai Viet Tiep · Applied Sciences · 2021 · 69 citations
Resampling credit card fraud data before the train/test split inflates accuracy above 99%, a leak that collapses to 1.81% precision when done correctly; deep reinforcement learning fared worse at 34.8% accuracy.
Selahattin Garip, Şaban Özdemir · Applied Sciences · 2022 · 65 citations
Pairing a new energy-management rulebook with particle swarm optimization finds the cheapest combination of solar panels and battery storage for a grid-connected microgrid.
Robert A. Jacobson · The Astronomical Journal · 2004 · 60 citations
Combining 37 years of telescope data with Pioneer 11, Voyager and Cassini tracking yields updated orbits for Saturn's major moons and a revised Saturn gravity field.
Anikó Nyéki, Miklós Neményi · Agronomy · 2022 · 54 citations
Combining farm sensor data with big-data and AI methods can make crop yield forecasts far more useful than traditional statistical models alone.
Yafei Zhao, Ken-ichi Itakura · Energies · 2023 · 44 citations
Review of CO2 storage options argues mineral carbonation with industrial waste and microbubble injection offer the cheapest, leak-free routes, and proposes injecting both into underground cavities.
Rebeca Soler Costa, Qing Tan, Frédérique C. Pivot, Xiaokun Zhang, Harris Wang · Texto Livre Linguagem e Tecnologia · 2021 · 44 citations
Personalized and adaptive learning tech can harm students if applied blindly; educators must balance data-driven tailoring with real human diversity and support needs.
R. Manivannan, Senthilkumar Selvaraj · International Journal of Computational Intelligence Systems · 2025 · 33 citations
A recurrent neural network whose settings are tuned by a nature-inspired "fox" search algorithm detects network intrusions 4-15% more accurately than four competing deep learning models.
Ritu Bala, Manpreet Kaur, Himani Thakur, Piyush Kashyap, Arun Karnwal + 1 more · International Journal of Chemical Engineering · 2025 · 32 citations
Carbon capture technology for heavy industry is technically feasible but stalled by high energy costs, weak incentives, thin regulation, and public distrust — not just engineering limits.
Vinayak Tanksale · Cybersecurity · 2024 · 31 citations
A lightweight LSTM-based system can spot attacks on a car's internal CAN network in near real time without the overhead of encryption.
Nazerke Baisholan, J. Eric Dietz, Sergiy Gnatyuk, Mussa Turdalyuly, Eric T. Matson + 1 more · Computers · 2025 · 29 citations
Reviewing only fraud-detection studies that keep real-world class imbalance, researchers find overused benchmark datasets, tree-based models dominating, misleading metrics, and almost no usable explainability.
Ahmed K. Jameil, Hamed Saffa Al-Raweshidy · IET Wireless Sensor Systems · 2024 · 27 citations
A cloud-based digital twin for patient monitoring cut telemetry latency 32% and predicted health status with 98% accuracy in 17 milliseconds.
Daniel Stronger, Peter Stone · Connection Science · 2006 · 27 citations
A robot can learn how its own movements and sensors behave using only its raw sensor data and action commands, with no external calibration or ground truth.
Michèle Roccotelli, Agostino Marcello Mangini, Maria Pia Fanti · IEEE Access · 2022 · 27 citations
A central district controller schedules shared solar, batteries and electric-vehicle storage across cooperative microgrids, cutting costly last-minute electricity purchases even when demand and generation are uncertain.
Mario Casillo, L. Cecere, Francesco Colace, Angelo Lorusso, D. Santaniello · De Computis · 2024 · 21 citations
Smartwatches and machine learning can track spa patients' vital signs in real time, letting thermal-water therapies be personalized and measurably therapeutic rather than merely relaxing.
Abhishek Kumar Gupta, Akshoy Ranjan Paul, Suvash C. Saha · Atmosphere · 2023 · 21 citations
India can cut emissions with carbon capture, but only if costs fall, technology scales up, and clear safety and storage regulations are written first.
Junjun Li, Yanyan Ma, Jiahui Bai, Cong Chen, Ting-Ting Xu + 1 more · Italian National Conference on Sensors · 2025 · 17 citations
A federated learning intrusion detector spots attacks on car networks with over 99% F1 score using just 1.11 MB of memory.
Reza Gheisari, Mariela Vazquez, Vasilis Tsigkis, Ali Erdemir, Karen L. Wooley + 1 more · Friction · 2023 · 15 citations
Tiny paraffin-filled capsules mixed into a polymer coating gave near-zero wear and a very low friction coefficient of 0.05, beating PTFE-filled coatings.
Md. Mamunur Rashid, Zarin Mosarat, A.K.M. Ahasan Habib, Arnob Ghosh, Kazi Sajedur Rahman + 5 more · Results in Engineering · 2025 · 13 citations
Connecting solar, wind and batteries to digital grids opens serious hacking routes, and current defenses lack real-time detection, cross-domain data protection and harmonized policy.
Qing Yang, Abdullah Al Mamun, Mengling Wu, Farzana Naznen · DIGITAL HEALTH · 2024 · 8 citations
Older Chinese adults adopt smart wearable health devices mainly when personal and social moral norms — rooted in health values and awareness of consequences — push them to.
Nilmini Wickramasinghe, Nalika Ulapane · Electronics · 2025 · 7 citations
Hospitals can share trained AI models instead of patient data, letting them build digital twins for clinical decisions without exposing anyone's records.
Oritsetimeyin V Arueyingho, Anmar Al-Taie, Claire McCallum · DIGITAL HEALTH · 2024 · 7 citations
A review of a decade of studies finds only six rigorous papers on machine learning for healthcare system management, mostly covering records, chatbots and disease prediction.
Jun Lin, Tiantian Sun, Rihui Song, Di Zhu, Lang-Zhou Liu + 3 more · Actuators · 2025 · 6 citations
Simulated stress-testing of a needle-insertion surgical robot, paired with a digital twin, uncovered real software flaws and measurable gaps between virtual and physical behavior.
Ubair Abdus Samad, M. A. Alam, El-Sayed M. Sherif, O. Alothman, A. Seikh + 1 more · International Journal of Electrochemical Science · 2015 · 6 citations
Adding the conductive polymer polyaniline to epoxy "2Pack" paint is tested as a way to make steel coatings better at resisting corrosion.
A. H. Shnain, G. Mohammed, Yalla Jeevan, Nagendra Kumar · SHS Web of Conferences · 2025 · 5 citations
A network of field sensors feeding live soil and weather data into predictive algorithms helped farmers raise crop yields and cut wasted water and fertiliser.
Nagendra Harish Jamithireddy · Research Briefs on Information and Communication Technology Evolution · 2023 · 3 citations
Machine learning ensembles and neural networks beat traditional rule-based credit scoring and fraud detection on precision, recall and AUC, while staying explainable.
Nagendra Harish Jamithireddy · Research Briefs on Information and Communication Technology Evolution · 2023 · 3 citations
Machine-learning ensembles and neural networks beat traditional rule-based credit and fraud models on precision, recall and AUC, while staying explainable enough for real use.
A. Barac, M. Holik, Kristijan Ćurić, M. Stojkov · Energies · 2026 · 3 citations
Solar panels paired with batteries, hydrogen storage and blockchain trading cut household grid electricity use by 45–50% and CO2 by up to 70% in simulations.
Houda Ben Mekhlouf, Abdellatif Moussaid, Fadoua Ghanimi · FinTech · 2026 · 2 citations
A learning-as-it-goes reinforcement learning agent starts out worse than statistical anomaly detection at catching card fraud but keeps improving as fraud tactics change.
Alshaimaa Abo-Alian, Alaa Prince AbdelHalim, Nagwa Badr · Cybersecurity · 2026 · 1 citations
Turning just five consecutive network packets into an RGB image lets a lightweight intrusion detector spot attacks early with 99% accuracy.
ARANANDA PUTRI, Nugroho Adi Sasongko, Donny Yoesgiantoro · PENDIPA Journal of Science Education · 2024 · 0 citations
Indonesia can only hit net-zero by 2060 while still using fossil fuels if it builds carbon capture infrastructure, especially CO2-based oil and gas recovery.
Minhee Jun, Hanseok Ko · Frontiers in The Internet of Things · 2026 · 0 citations
Processing health sensor data on the device and sending only meaningful events, not raw streams, cuts energy and bandwidth by orders of magnitude in simulated patient monitoring.
Aljohani A · PloS one · 2026
A hybrid transformer-plus-graph-network intrusion detector for cyber-physical systems hits about 98% average accuracy while also flagging how confident each prediction is.
Tiwari A, Navaneethan C · Frontiers in artificial intelligence · 2026
Deep learning detects cloud DDoS attacks near-perfectly in lab tests, but under 6% of 120 studies tackle adapting to new, unseen attacks in the real world.
George D, Hernandez Rivero JD, Mehmet M, Miranda Espino R, Guo X + 3 more · Optics express · 2026
A shoebox-scale three-axis laser accelerometer hits 60 pico-g/√Hz sensitivity and tracks real ground tremors as well as a commercial seismometer.
Mir SA, Momin U, E SK, Mir IA, Khan AR + 1 more · Frontiers in plant science · 2026
An attention-based deep learning model predicted apple yields in Himalayan orchards four weeks ahead with R² of 0.89, beating a CNN-LSTM baseline by 15.6%.
Fenoglio E, Nieroda M, Carvalho G, Smietanka M, Kalogeropoulos D + 1 more · JMIR medical informatics · 2026
A governance layer that issues cryptographically bound permissions and logs signed ALLOW/DENY decisions let new hospitals and AI agents join a federated health study without renegotiating the setup.
Cornelisse E, Kousa D, Menz BD, Murphy-Reuter B, Shahnam A + 35 more · Journal of medical Internet research · 2026
Researchers built OMNI, a free standardized scoring rubric that lets clinicians judge generative AI outputs, and piloted it on 250 health care examples.
Manivannan AG, Jayasankar N, Kashid VA, Patel RJ, G Prajapati B · Pharmaceutics · 2026
Microneedle patches deliver drugs painlessly through the skin, and this review argues they are nearly ready to move from lab prototypes to everyday clinical use.
Bashah A, Huixin Q, Zaawari H, Al-Waqeerah A, Ghaleb E + 3 more · JMIR medical informatics · 2026
Five popular AI chatbots were stress-tested with 27,300 answers on dental medical emergencies across three languages to see if unregulated consumer AI is safe at the chairside.
Lorn S, Chhon Y, San T, Sorn V · Public health challenges · 2026
AI could ease Cambodia's doctor shortages and rural care gaps, but only with phased rollout backed by infrastructure, local validation, training and governance.
Alhomoud A, Alharbi AR, Altorkmani NA · Sensors (Basel, Switzerland) · 2026
A two-engine intrusion detector built into sensor-cluster heads catches 96.4% of unseen flooding attacks that supervised models miss almost entirely, while extending battery life.
Bahramian A, Alavinia S · Membranes · 2026
Pushing harder through an oil-filtering membrane gets more oil through but lets more water slip past — faster cross-flow raises flux too, while keeping fouling easier to wash off.
Wang K, Lu X, Liu T, Fang J, Li X + 5 more · Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026
Smart factories need intelligence built into robots and materials themselves, not just software — the authors propose a combined AI, embodied, and physical intelligence framework.
Ahmed W, Rahaman MA, Roy P, Alam P · Frontiers in artificial intelligence · 2026
Label-free monitoring dashboards can look flawless while intrusion detectors silently fail, and none of 16 test-time adaptation methods beat the unadapted model under real year-to-year traffic shift.
Shin SJ, Roh SB, Kim HT, Lee KY, Kim SM + 2 more · Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026
Hydrogen atoms pushed through a palladium membrane can recombine into H2 and re-split, and tuning the membrane's surface coating controls which pathway drives hydrogenation.
Kumar SS, Jerlin MA · Frontiers in artificial intelligence · 2026
Traditional intrusion detection is too heavy for IoT devices, so this survey maps the shift toward federated, tiny on-device AI with explainable alerts.
Elhomsy P, Reliquet B, Sudria F · Pain research & management · 2026
AI already helps measure, predict and treat chronic pain across four clinical domains, but adoption stays fragmented due to data governance and untrained clinicians.
V A, V P · Frontiers in artificial intelligence · 2026
A hybrid CNN-BiGRU intrusion detector with game-theoretic adaptive thresholds spots rare DDoS and fraud attacks, but better rare-class detection can cost adversarial robustness.
Alshammari A · PloS one · 2026
A lightweight intrusion-detection AI that throttles itself when the power grid is dirty cut energy use 43% and emissions 58.7% while keeping 98.7% detection accuracy.
Davies JM, Gray L, Jayasinghe S, Vale S, Perrett KP · BMJ health & care informatics · 2026
Australia's allergy data is locked behind 77 national rules from 24 agencies, and the authors propose a "GATEway" framework to untangle it for research.
Sessa C, Lomeo E, Morale W, Gianni T, Bonerba B + 2 more · Sensors (Basel, Switzerland) · 2026
AI and wearable sensors can spot dialysis vascular access problems in retrospective data, but accuracy drops sharply in real-world prediction and no system has yet improved patient outcomes.
Huang T, Wang Y, Qin Y · Sensors (Basel, Switzerland) · 2026
Running two neural networks side by side and fusing their outputs with a gated cross-attention layer detects network attacks with ~99.8% accuracy on benchmark traffic data.
Hassan SR, Din S, Mohmand MI · Sensors (Basel, Switzerland) · 2026
Connected cars are increasingly hackable, and this survey maps how AI intrusion detection works, where its datasets and deployments fall short, and what research must fix next.
Alhafi D, Alanazi F · Sensors (Basel, Switzerland) · 2026
A 10.2-million-parameter transformer tailored to network traffic — custom tokenizer and data collator — detects IoT attacks with 96% binary F1 while running on-device.
Krumsvik RJ, Slettvoll V · Frontiers in medicine · 2026
Clickers and quiz apps help big lectures only when used as teaching infrastructure for feedback and discussion — and AI could make them adaptive next.
Basnawi A · Frontiers in medicine · 2026
Mass-gathering medical planning is hampered by inconsistent reporting: patient rates and hospital impacts vary wildly between studies, making direct comparison nearly impossible.
Hossain MM, Islam T, Chaion MH, Rabbani M, Islam MA + 4 more · Nanomaterials (Basel, Switzerland) · 2026
Soft, water-rich nanocomposite hydrogels are becoming stretchy skin-worn sensors that track vital signs, glucose and wound healing, but durability, comfort and regulation still block adoption.
Balciunaite A, Michelis MY, Filippi M, Paniagua P, Yasa O + 1 more · Nature communications · 2026
Computer-optimized muscle-and-scaffold designs made lab-grown muscle robots move up to eleven times further, enabling jumping, swimming, walking and gripping.
Elesawy HA, Ahmed AI, AboZaid YA, Said LA, Samy I + 1 more · HardwareX · 2026
A free, open-source circuit board combines industrial 24 V water-quality sensors with motor control for marine robots, hitting 99.97% data reliability over 240 hours of testing.
Ganesh LS, Kumar PM · Frontiers in artificial intelligence · 2026
A hybrid CNN + Bi-LSTM + attention model with transfer learning detects IoT cyberattacks across different networks with 96-98% accuracy, beating existing detectors.
Yoganand J, V RB, L S D, P N J · Frontiers in artificial intelligence · 2026
Adding federated trust learning, quantum-resistant encryption, and reusable trust tokens to a vehicle authentication framework cut cross-domain authentication delay by 45%.
Gong Z, Xiong N, Zhao C, Chen J, Ammar O + 4 more · Frontiers in public health · 2026
A federated CNN-Transformer model detects attacks on connected medical devices with ~99% accuracy across three datasets without pooling hospitals' raw data centrally.
Xue Z, Xu X, Tian L, Jian K, Zhang S + 5 more · Scientific reports · 2026
Deep coal seams in China's southern Qinshui Basin could store 575.5 million tonnes of CO2, best at 800–1100 m depth where CO2 turns supercritical.
Malik A, Bashir I · Acta psychologica · 2026
AI education research is split across disconnected fields, so this review of 32 studies proposes a 'Hybrid Intelligence' framework uniting learners, teachers and machines.
Zhou T, Li D · Molecules (Basel, Switzerland) · 2026
Saltier brine halves CO2's diffusion speed while heating it to 353 K nearly triples it, with pressure barely mattering below 30 MPa.
Adibi S, Rajabifard A, Shojaei D, Wickramasinghe N · Sensors (Basel, Switzerland) · 2024
Sensor-fed "digital twins" of patients — live virtual models built from wearables, IoT devices and AI — could reshape care in smart homes and hospitals, but remain largely unproven.
Ennassiri Y, de-Simón-Martín M, Bracco S, Robba M · Sensors (Basel, Switzerland) · 2024
A microgrid controller that factors in battery wear, wasted solar power and indoor comfort cuts renewable curtailment while holding batteries to about one cycle per day.
Sarker MT, Ramasamy G, Al Qwaid M, Hossen MS, Sadeque MG · Scientific reports · 2025
An AI-managed smart grid simulated for a 1,500-bed Malaysian hospital cut HVAC use 11.6%, lifted energy efficiency 25%, and met 86% of demand with rooftop solar.
Frimpong I, Hlormenu BA · Frontiers in digital health · 2026
Hundreds of AI models exist to spot alcohol, opioid, and cannabis use disorders, but almost none have made it into routine clinical care.
Ašić A, Devaux Y, Sopić M, Jusić A, Spahić L + 7 more · Journal of molecular and cellular cardiology plus · 2026
A new Europe-wide research network aims to make genetic testing routine for prescribing heart drugs, using AI, shared guidelines and policy reform.
Mendes A · Journal of education and health promotion · 2026
Brain-sensing and eye-tracking tools can track students' mental effort live, and this review argues universities should use them to redesign STEM teaching around cognitive load.
Varol M, Karakaya A · Sensors (Basel, Switzerland) · 2026
A review of explainable-AI intrusion detection for IoT finds the field now chases lightweight, transparent, privacy-preserving designs — but rarely validates its explanations or reproduces results.
Kordi F, Fortier P, Miled A · Sensors (Basel, Switzerland) · 2026
Software-only security testing misses how car cyberattacks physically behave; hardware- and vehicle-in-the-loop rigs plus AI detection are needed to realistically test and defend connected vehicles.
Feng T, Cao Y, Yu W, Zeng J, Li X + 2 more · Science advances · 2026
Entanglement that builds up naturally during quantum evolution shields many-body dynamics from local noise, offering free error protection with no extra qubits or control.
Yang X, Zhang Z, Li Q, Jing Z, Lu X + 2 more · Sensors (Basel, Switzerland) · 2026
A new method lets federated IoT intrusion detectors erase a device's data influence almost as well as full retraining, but far faster.
Alshdadi AA · Sensors (Basel, Switzerland) · 2026
A drone-assisted graph learning system spots coordinated DDoS attacks across EV charging networks with 97.7% accuracy, beating localized traffic-only detectors.
Sasikumar K, Nagarajan S · Frontiers in artificial intelligence · 2026
A hybrid Transformer-CNN trained with federated learning identifies users from mouse movements with 99.51% accuracy while keeping raw behavioral data on their own devices.
Campos PVS, Ramos AV, Habert AC, Esteves PM · ACS omega · 2026
Adding tiny amounts of a CO2-attracting porous powder to polyurethane films more than doubled CO2 flow and boosted CO2-over-nitrogen selectivity by up to 454%.
Kim JM, Lee JM, Kim HO, Kim YJ, Kim SS + 3 more · Frontiers in public health · 2026
Across all eight WHO global health emergencies, only COVID-19 strained every part of health systems, while staffing shortfalls and testing bottlenecks appeared in every single one.
Chan ML, Capatos AA, Lodahl P, Sørensen AS, Paesani S · NPJ quantum information · 2026
A full hardware blueprint for a fault-tolerant photonic quantum computer built from quantum-dot photon sources, with error-correction cycles running in microseconds.
El-Saboni Y, Awwal S, Mishra R, Sharma N, Gaur A + 1 more · JMIR medical informatics · 2026
Smart-home health monitoring works but is concentrated in wealthy European and Asian regions, with most systems still far from truly intelligent, adaptive care.
Chandroth J, Stoian G, Hemanth DJ · PloS one · 2026
Combining ant-colony feature selection with a CNN-BiLSTM attention network detects cyberattacks on smart consumer-electronics networks more accurately than existing intrusion detection methods.
Wattanasirichaigoon S · JMIR medical education · 2026
Doctors should earn continuing-education credit for demonstrated clinical reasoning in AI chat sessions, not for hours sat in lectures, under a proposed scoring framework.
Sree KCS, Shankar V · ACS omega · 2026
A simple 6-feature ridge regression trained on VQE-minus-Hartree-Fock energy gaps cuts quantum chemistry simulation errors by 3x to 640x, with no extra quantum computation.
Wang R, Zhang W, Quan X, Du R, Bing Z + 4 more · Science advances · 2026
A robot dog with a flexible, torque-amplifying spine timed to its legs runs faster and more efficiently than rigid-spine and rival flexible-spine designs.
Zeng X, Zhang Y, Wu C, Duan Q, Fan M + 3 more · Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026
Macrophages loaded with magnetic iron-platinum microrollers can be steered into solid tumors, where they trigger iron-driven cancer cell death and rally the immune system.
Park K, Park EKC, Park WH, Jeon EY · Bioengineering (Basel, Switzerland) · 2026
Wearables plus AI can flag disease early, but reported 85%+ accuracies come from small, controlled studies that rarely prove real-world clinical value.
Talay L, Xu C, Hom J, Swinckels L, Tan M + 2 more · Medicina (Kaunas, Lithuania) · 2026
Patients in a tirzepatide weight-loss app who actively engaged — via coaching, chatbot, or self-tracking — lost about 4.6% more body weight at 6 months than disengaged users.
Meena VD, Dotaniya ML, Meena MD, Jat RS, Meena MK + 5 more · PloS one · 2026
Using a handheld GreenSeeker sensor to time and size nitrogen doses in mustard raised seed yield 22.75% while using 18.7% less fertilizer than standard practice.
Guo X, Sun Y, Chen Y, Liu H, Liu X + 1 more · Biosensors · 2026
AI for diagnosing Alzheimer's has moved from hand-engineered machine learning to deep learning and now large language models that read speech and clinical notes.
Kaya I, Meylani R · Frontiers in psychology · 2026
A new 33-item survey reliably measures six distinct dimensions of trainee teachers' digital teaching competence, validated across nearly 1,500 Turkish students.
Singhal S, Kumar KA · Frontiers in big data · 2026
AI intrusion detection for industrial IoT scores well on benchmarks but still fails on generalization, explainability, adversarial attacks, and real-world edge deployment.
Siudak M, Combrzyński M, Oniszczuk T, Soja J, Oniszczuk A · Molecules (Basel, Switzerland) · 2026
Slow-release fertilizer coatings can cut nutrient waste and boost yields, but plastic coatings shed microplastics and release timing still fails under real field conditions.
Wang F, Wang FM, Guo AY, Wang L, Shang J · Frontiers in chemistry · 2026
Metal rods used to fix broken thigh bones often fit older patients poorly, and new electricity-generating and bioactive coatings could make them fit better and heal bone faster.
Tushar ZH, Mostafa MS · Poultry science · 2026
AI can inspect poultry carcasses and predict quality well in lab studies, but weak validation and plant-to-plant variation keep it from reliable commercial use.
Mohammed I, Mahgoub I · Sensors (Basel, Switzerland) · 2026
Pre-training intrusion detectors on big computer-network attack datasets, then fine-tuning on small IoT ones, beats training from scratch and compresses to run on edge devices.
Qaisarani SN, Badri SK, Khattak A, Alghazzawi DM, Alghamdi MY + 4 more · Scientific reports · 2026
A unified deep learning system, X-THREAT, spots rare and never-before-seen cyberattacks with 93-96% accuracy across three benchmarks while explaining its decisions.
Goel S, Govindaraj L, Kathirvel Murugan T · Frontiers in big data · 2026
HyperIDS combines hypergraph neural networks, quantum-inspired feature selection and a transformer ensemble to detect IoT cyberattacks with about 98.9% accuracy.
Shetty P, Shetty S, Varghese C · International journal of dentistry · 2026
AI and remote monitoring can cut orthodontic appointments and sharpen diagnosis, but almost all 23 studies reviewed came from urban clinics, not underserved areas.
Stankić A, Vujošević D, Radosavljević N, Jeremić A · Health informatics journal · 2026
A simple rules-based triage chatbot beat AI-powered versions on accuracy (71.8% vs 30.8-41.0%), yet testers preferred the smoother-talking but less accurate AI ones.
Mishra S, Alshenaifi R, Alfahidah RA · PloS one · 2026
Combining supervised and unsupervised detectors in a weighted ensemble, plus a hash-chained audit log, flags network intrusions with 98.85% accuracy and tamper-evident records.
McDonald VJF, Parsa S, Mastrodicasa D, Rodriguez F, Langlotz C + 4 more · BMJ digital health & AI · 2026
AI can automatically measure coronary calcium on ordinary chest CT scans, and those scores reliably predict heart attacks and death.
Abdi BM, Ali SM, Ali SA, Hussein MA, Adow AI + 1 more · Frontiers in public health · 2026
AI can help spot risky pregnancies and newborn illness earlier in poor countries, but only alongside real investment in data, infrastructure and regulation.
Hamdan M, Badr Z, Uribe SE, Reymus M, Kalenderian E + 1 more · International dental journal · 2026
Clinicians can now build medical and dental imaging AI without coding, and 138 studies show it works reasonably well — but external validation is often missing.
Mohanty S, Dash SP, Tanpure RS, Chakraborty S, Jeon BH + 1 more · Frontiers in bioengineering and biotechnology · 2026
Better-engineered reactor hardware — flow cells, gas-diffusion cathodes, packed-bed electrodes, built-in separation — is the main lever for making microbial electrosynthesis of fuels from CO2 practical.
Ahmad N, Cao Y, Liu W · Sensors (Basel, Switzerland) · 2026
A combined deep-learning and blockchain system detects attacks in cloud-connected sensor networks and logs them tamper-evidently, beating LSTM and CNN-RNN baselines on two datasets.
Gou J, Kang D, Lee H, Jang S, Song I · Scientific reports · 2026
Fusing near-daily 3 m satellite images with sparse 0.05 m drone photos produced daily 0.5 m crop maps, with the ESTARFM algorithm plus CACAO smoothing performing best.
Zhao S, Lin H, Jiang Y, Liu J · Frontiers in plant science · 2026
No single sensor or algorithm can estimate orchard yield alone — ground cameras count fruit best, while drones and spectral sensors map yield across regions.
Zhao P, Li W, Wang C, Wang B, Yang T + 4 more · Frontiers in plant science · 2026
Drone-based crop yield prediction works, but its accuracy is limited less by fancy models than by mismatched, poor-quality ground-truth yield data and untested transfer across years and regions.
Joseph L, M S, M V · Frontiers in big data · 2026
Combining boosted decision trees and bagged random forests detects IoT botnet traffic more sensitively, and SHAP explains which network features drove each decision.
Abdelhady G, Hussein KW, Gad IAA · Scientific reports · 2026
FedShield-IDS trains a CNN-LSTM intrusion detector across smart-home devices without sharing raw traffic, and uses SHAP to explain every alert.
Junar N, Arockiasamy K · Frontiers in artificial intelligence · 2026
Combining self-supervised learning, prototypical few-shot networks and continual learning detects new botnet attacks from very few samples, hitting 98.50% accuracy on CIC-IoT-2023.
Dillon MR, Mastroianni MA, Frappa N, Manzi J, Fuller SI + 5 more · Orthopaedic journal of sports medicine · 2026
Major league pitchers with lower, sidearm arm angles lost fewer days to shoulder and elbow injuries and performed at least as well as overhand pitchers.
Groisman L, Burla E, Kushnir D, Assaly S, Gat R + 3 more · Israel journal of health policy research · 2026
Water lines in 94% of surveyed Israeli dental clinics failed at least one quality test, with Legionella above threshold in 74% of samples.
Zhang B, Wen M · PloS one · 2025
A new controller that models a spacecraft's flexible panels as a continuous wave equation damps their vibrations faster and with less overshoot than standard PD control.
Raducan SD, Madeira G, Agrusa HF, Merrill CC, Marschall R + 5 more · Nature communications · 2025
Selam, the odd contact-binary moon of asteroid Dinkinesh, likely formed when several similar-sized moonlets gently collided and merged in orbit.
Xie X, Chen W, Xia C, Xing J, Chang L · Sensors (Basel, Switzerland) · 2025
A neural-network controller keeps a spacecraft towing a flexible truss inside preset safety bounds, tracking trajectories to about 5 mm in hardware tests.
Yan J, Cheng K, Wang W, Guo Z, Li Q + 4 more · Plants (Basel, Switzerland) · 2026
Drone LiDAR tracking of maize height over time predicts tasseling within about 2.6 days, replacing subjective manual field scouting.
Verbytskyi I, Lukianov M, Bartłomiejczyk M, Denysiuk S, Strzelecki R · Scientific reports · 2026
Upgrading tram and trolleybus DC substations in stages to host EV chargers, batteries and solar can pay back 10-20% annually while improving power quality.
Ahene E, Agyei RO, Gyening ROM, Obirikorang KA, Takyi K + 3 more · PloS one · 2026
A solar-powered fish farm monitor uses cameras and deep learning to track fish behaviour, health, water quality and feeding without grid electricity.
Ezzat A, Abdel-Khalik AS, Hamdy RA, Hamad MS · Scientific reports · 2026
A machine-learning charging controller for home solar EV setups raised on-site solar use by about 22% while keeping batteries out of aging-prone hot, high-charge conditions.
Innocent DC, Innocent RC, Innocent IP · Frontiers in digital health · 2026
AI can spot neglected tropical diseases in images, but black-box models block clinical trust — this review proposes a framework making such systems explainable for low-resource clinics.
Patil A, Mahajan S, Menpara J, Wagle S, Pareek P + 1 more · MethodsX · 2024
Storing bank transactions in a graph database and feeding those relationship features to machine learning models improves detection of fraudulent transactions.
Raj SAJ, Madiajagan M · Frontiers in artificial intelligence · 2026
A new intrusion detection system combines three machine learning models with an attention layer, SHAP explanations, and tamper-proof hashed logs to make attack alerts auditable.
GBD 2023 Road Injuries Collaborators · The Lancet. Public health · 2026
A global study estimates deaths and disability from road injuries in every country from 1990 to 2023, giving comparable numbers to guide road safety policy.
Baradziej S, Kochanska A · Discover artificial intelligence · 2026
AI tutors can boost grades while quietly eroding students' ability to judge and manage their own learning, so universities need a design framework that trains metacognition, minimises data collection and keeps students in control.
Manjengwa P, Yah C, Musekiwa A · African journal of primary health care & family medicine · 2026
South African men want HIV services that are close by, affordable, private and non-judgemental — 10 priorities identified from interviews in Gauteng.
Tang J, Wang MJ · Entropy (Basel, Switzerland) · 2026
Filtering noise from several qubit copies before error-correcting nearly doubles the surface code's error threshold and cuts logical errors 46-fold.
Kim C, Kang J, Kwon Y · Entropy (Basel, Switzerland) · 2026
Coupling four fixed-frequency transmons to one shared coupler yields CNOT gates above 98% fidelity in all six directions and maps directly onto surface-code plaquettes.
Motaharifard O, Daneshjou K, Bakhtiari M · Scientific reports · 2026
Solar panels entering a spacecraft's partial shadow can heat unevenly enough to trigger self-sustaining flutter vibrations, which this nonlinear model predicts and maps for the Hubble Telescope.
Chen X, Lei T, Zhao W, Ma S, Lai C + 1 more · Science advances · 2026
China's 3119 petrochemical plants emitted about 814 million tonnes of CO2 in 2021, with a few processes and chain stages driving most of it.
Xie Z, Fernandes R, Andresen GB · iScience · 2026
Europe's 2050 hydrogen use could range from near zero to 3,200 TWh/year, driven mostly by electrolyzer costs and carbon budget strictness, not transport demand.
Bilal M, Mohammad A, Imdadullah, Hameed S, Ahmad F + 1 more · Scientific reports · 2026
Scheduling a solar-wind-battery-fuel-cell microgrid with the NSGA-III algorithm cut operating costs to 131.73 cents while flattening demand peaks better than four rival methods.
El Hamid AMA, Elzohri HH, Sayed K · Scientific reports · 2026
Combining a grey-wolf optimizer for siting solar/wind units with a neural-network load forecaster cut power losses 61.7% and saved $1,741 a day on a test grid.
Li Z, Ren Z, Lin Y, Xia X, Li T + 4 more · Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026
Swallowable capsule robots can now steer magnetically, sample tissue, and deliver drugs inside the gut, but weak actuation, power, and navigation still block clinical use.
Zhang J, Wu T, Huang T, Zhang Y, Hou K + 2 more · Gels (Basel, Switzerland) · 2026
Thin, asymmetric hydrogel fibers respond to stimuli faster than bulk gels, and their internal architecture is what turns swelling into useful directional motion for soft robots.