The rapid growth of IoT networks necessitates efficient Intrusion Detection Systems(IDS)capable of addressing dynamic security threats under constrained resource environments.This paper proposes a hybrid IDS for IoT n...The rapid growth of IoT networks necessitates efficient Intrusion Detection Systems(IDS)capable of addressing dynamic security threats under constrained resource environments.This paper proposes a hybrid IDS for IoT networks,integrating Support Vector Machine(SVM)and Genetic Algorithm(GA)for feature selection and parameter optimization.The GA reduces the feature set from 41 to 7,achieving a 30%reduction in overhead while maintaining an attack detection rate of 98.79%.Evaluated on the NSL-KDD dataset,the system demonstrates an accuracy of 97.36%,a recall of 98.42%,and an F1-score of 96.67%,with a low false positive rate of 1.5%.Additionally,it effectively detects critical User-to-Root(U2R)attacks at a rate of 96.2%and Remote-to-Local(R2L)attacks at 95.8%.Performance tests validate the system’s scalability for networks with up to 2000 nodes,with detection latencies of 120 ms at 65%CPU utilization in small-scale deployments and 250 ms at 85%CPU utilization in large-scale scenarios.Parameter sensitivity analysis enhances model robustness,while false positive examination aids in reducing administrative overhead for practical deployment.This IDS offers an effective,scalable,and resource-efficient solution for real-world IoT system security,outperforming traditional approaches.展开更多
We present a novel method for scale-invariant 3D face recognition by integrating computer-generated holography with the Mellin transform.This approach leverages the scale-invariance property of the Mellin transform to...We present a novel method for scale-invariant 3D face recognition by integrating computer-generated holography with the Mellin transform.This approach leverages the scale-invariance property of the Mellin transform to address challenges related to variations in 3D facial sizes during recognition.By applying the Mellin transform to computer-generated holograms and performing correlation between them,which,to the best of our knowledge,is being done for the first time,we have developed a robust recognition framework capable of managing significant scale variations without compromising recognition accuracy.Digital holograms of 3D faces are generated from a face database,and the Mellin transform is employed to enable robust recognition across scale factors ranging from 0.4 to 2.0.Within this range,the method achieves 100%recognition accuracy,as confirmed by both simulation-based and hybrid optical/digital experimental validations.Numerical calculations demonstrate that our method significantly enhances the accuracy and reliability of 3D face recognition,as evidenced by the sharp correlation peaks and higher peak-to-noise ratio(PNR)values than that of using conventional holograms without the Mellin transform.Additionally,the hybrid optical/digital joint transform correlation hardware further validates the method's effectiveness,demonstrating its capability to accurately identify and distinguish 3D faces at various scales.This work provides a promising solution for advanced biometric systems,especially for those which require 3D scale-invariant recognition.展开更多
Scalable fabrication of homogeneous perovskite films remains crucial for bridging the efficiency gap between lab-scale solar cells and commercial solar modules.To tackle this issue,we introduce NCyano-4-methyl-N-pheny...Scalable fabrication of homogeneous perovskite films remains crucial for bridging the efficiency gap between lab-scale solar cells and commercial solar modules.To tackle this issue,we introduce NCyano-4-methyl-N-phenylbenzenesulfonamide(CMPS) additives into perovskite precursors,enabling slot-die coating of large-area modules under ambient conditions.CMPS suppresses colloidal aggregation and delays crystallization,yielding high-quality uniform films.Small-area devices(0.07 cm^(2) aperture area) incorporating CMPS exhibited a significant efficiency increase from 22.07 % to 24.58 %.Corresponding encapsulated devices maintained 85 % of their initial power conversion efficiency(PCE,average 23.56 %) after 1500 h of continuous maximum power point(MPP) tracking under one-sun illumination at 50-55℃.Furthermore,we demonstrate impressive efficiency of perovskite solar modules,achieving 20.57 %(52 cm^(2) aperture area) for 10 cm × 10 cm mini-modules and 17.02 %(260 cm^(2) aperture area) for 21 cm × 21 cm sub-modules,representing the state-of-the-art performance for solutionprocessed devices at these scales.展开更多
Optimizing routing and resource allocation in decentralized unmanned aerial vehicle(UAV)networks remains challenging due to interference and rapidly changing topologies.The authors introduce a novel framework combinin...Optimizing routing and resource allocation in decentralized unmanned aerial vehicle(UAV)networks remains challenging due to interference and rapidly changing topologies.The authors introduce a novel framework combining double deep Q-networks(DDQNs)and graph neural networks(GNNs)for joint routing and resource allocation.The framework uses GNNs to model the network topology and DDQNs to adaptively control routing and resource allocation,addressing interference and improving network performance.Simulation results show that the proposed approach outperforms traditional methods such as Closest-to-Destination(c2Dst),Max-SINR(mSINR),and Multi-Layer Perceptron(MLP)-based models,achieving approximately 23.5% improvement in throughput,50% increase in connection probability,and 17.6% reduction in number of hops,demonstrating its effectiveness in dynamic UAV networks.展开更多
Federated Learning(FL)has become a leading decentralized solution that enables multiple clients to train a model in a collaborative environment without directly sharing raw data,making it suitable for privacy-sensitiv...Federated Learning(FL)has become a leading decentralized solution that enables multiple clients to train a model in a collaborative environment without directly sharing raw data,making it suitable for privacy-sensitive applications such as healthcare,finance,and smart systems.As the field continues to evolve,the research field has become more complex and scattered,covering different system designs,training methods,and privacy techniques.This survey is organized around the three core challenges:how the data is distributed,how models are synchronized,and how to defend against attacks.It provides a structured and up-to-date review of FL research from 2023 to 2025,offering a unified taxonomy that categorizes works by data distribution(Horizontal FL,Vertical FL,Federated Transfer Learning,and Personalized FL),training synchronization(synchronous and asynchronous FL),optimization strategies,and threat models(data leakage and poisoning attacks).In particular,we summarize the latest contributions in Vertical FL frameworks for secure multi-party learning,communication-efficient Horizontal FL,and domain-adaptive Federated Transfer Learning.Furthermore,we examine synchronization techniques addressing system heterogeneity,including straggler mitigation in synchronous FL and staleness management in asynchronous FL.The survey covers security threats in FL,such as gradient inversion,membership inference,and poisoning attacks,as well as their defense strategies that include privacy-preserving aggregation and anomaly detection.The paper concludes by outlining unresolved issues and highlighting challenges in handling personalized models,scalability,and real-world adoption.展开更多
This review provides an insightful and comprehensive exploration of the emerging 2D material borophene,both pristine and modified,emphasizing its unique attributes and potential for sustainable applications.Borophene...This review provides an insightful and comprehensive exploration of the emerging 2D material borophene,both pristine and modified,emphasizing its unique attributes and potential for sustainable applications.Borophene’s distinctive properties include its anisotropic crystal structures that contribute to its exceptional mechanical and electronic properties.The material exhibits superior electrical and thermal conductivity,surpassing many other 2D materials.Borophene’s unique atomic spin arrangements further diversify its potential application for magnetism.Surface and interface engineering,through doping,functionalization,and synthesis of hybridized and nanocomposite borophene-based systems,is crucial for tailoring borophene’s properties to specific applications.This review aims to address this knowledge gap through a comprehensive and critical analysis of different synthetic and functionalisation methods,to enhance surface reactivity by increasing active sites through doping and surface modifications.These approaches optimize diffusion pathways improving accessibility for catalytic reactions,and tailor the electronic density to tune the optical and electronic behavior.Key applications explored include energy systems(batteries,supercapacitors,and hydrogen storage),catalysis for hydrogen and oxygen evolution reactions,sensors,and optoelectronics for advanced photonic devices.The key to all these applications relies on strategies to introduce heteroatoms for tuning electronic and catalytic properties,employ chemical modifications to enhance stability and leverage borophene’s conductivity and reactivity for advanced photonics.Finally,the review addresses challenges and proposes solutions such as encapsulation,functionalization,and integration with composites to mitigate oxidation sensitivity and overcome scalability barriers,enabling sustainable,commercial-scale applications.展开更多
Accurate blood pressure(BP)monitoring is essential for preventing and managing cardiovascular disease.Advancements in materials science,medicine,flexible electronic,and artificial intelligence(AI)have enabled cuffless...Accurate blood pressure(BP)monitoring is essential for preventing and managing cardiovascular disease.Advancements in materials science,medicine,flexible electronic,and artificial intelligence(AI)have enabled cuffless,unobtrusive BP monitoring systems,offering an alternative to traditional sphygmomanometers.However,extending these advances to real-world cardiovascular care particularly in resource-limited settings remains challenging due to constraints in computational resources,power efficiency,and deployment scalability.This review presents a comprehensive synthesis of AI-enhanced wearable BP monitoring,emphasizing its potential for personalized,scalable,and accessible healthcare.We systematically analyze the end-to-end system architecture,from mechano-electric sensing principles and AI-based estimation models to edge-aware deployment strategies tailored for low-resource environments.We further discuss clinical validation metrics and implementation barriers and prospective strategies.To bridge lab-to-field translation,we propose an innovative"sensor-model-deployment-assessment"co-design framework.This roadmap highlights how AI-enhanced BP technologies can support proactive hypertension control and promote cardiovascular health equity on a global scale.展开更多
Colorectal cancer is the third most diagnosed cancer worldwide,and immune checkpoint inhibitors have shown promising therapeutic outcomes in selected patient groups.This study performed a comprehensive analysis of mul...Colorectal cancer is the third most diagnosed cancer worldwide,and immune checkpoint inhibitors have shown promising therapeutic outcomes in selected patient groups.This study performed a comprehensive analysis of multi-omics data from The Cancer Genome Atlas colorectal adenocarcinoma cohort(TCGA-COADREAD),accessed through cBioPortal,to develop machine learning models for predicting progression-free survival(PFS)following immunotherapy.The dataset included clinical variables,genomic alterations in Kirsten Rat Sarcoma Viral Oncogene Homolog(KRAS),B-Raf Proto-Oncogene(BRAF),and Neuroblastoma RAS Viral Oncogene Homolog(NRAS),microsatellite instability(MSI)status,tumor mutation burden(TMB),and expression of immune checkpoint genes.Kaplan–Meier analysis showed that KRAS mutations were significantly associated with reduced PFS,while BRAF and NRAS mutations had no significant impact.MSI-high tumors exhibited elevated TMB and increased immune checkpoint expression,reflecting their immunologically active phenotype.We developed both survival and classification models,with the Extra Trees classifier achieving the best performance(accuracy=0.86,precision=0.67,recall=0.70,F1-score=0.68,AUC=0.84).These findings highlight the potential of combining genomic and immune biomarkers with machine learning to improve patient stratification and guide personalized immunotherapy decisions.An interactive web application was also developed to enable clinicians to input patient-specific molecular and clinical data and visualize individualized PFS predictions,supporting timely,data-driven treatment planning.展开更多
Over the past years,many efforts have been accomplished to achieve fast and accurate meta-heuristic algorithms to optimize a variety of real-world problems.This study presents a new optimization method based on an unu...Over the past years,many efforts have been accomplished to achieve fast and accurate meta-heuristic algorithms to optimize a variety of real-world problems.This study presents a new optimization method based on an unusual geological phenomenon in nature,named Geyser inspired Algorithm(GEA).The mathematical modeling of this geological phenomenon is carried out to have a better understanding of the optimization process.The efficiency and accuracy of GEA are verified using statistical examination and convergence rate comparison on numerous CEC 2005,CEC 2014,CEC 2017,and real-parameter benchmark functions.Moreover,GEA has been applied to several real-parameter engineering optimization problems to evaluate its effectiveness.In addition,to demonstrate the applicability and robustness of GEA,a comprehensive investigation is performed for a fair comparison with other standard optimization methods.The results demonstrate that GEA is noticeably prosperous in reaching the optimal solutions with a high convergence rate in comparison with other well-known nature-inspired algorithms,including ABC,BBO,PSO,and RCGA.Note that the source code of the GEA is publicly available at https://www.optim-app.com/projects/gea.展开更多
Electrochemical carbon dioxide reduction reaction(CO_(2)RR)provides a promising way to convert CO_(2)to chemicals.The multicarbon(C_(2+))products,especially ethylene,are of great interest due to their versatile indust...Electrochemical carbon dioxide reduction reaction(CO_(2)RR)provides a promising way to convert CO_(2)to chemicals.The multicarbon(C_(2+))products,especially ethylene,are of great interest due to their versatile industrial applications.However,selectively reducing CO_(2)to ethylene is still challenging as the additional energy required for the C–C coupling step results in large overpotential and many competing products.Nonetheless,mechanistic understanding of the key steps and preferred reaction pathways/conditions,as well as rational design of novel catalysts for ethylene production have been regarded as promising approaches to achieving the highly efficient and selective CO_(2)RR.In this review,we first illustrate the key steps for CO_(2)RR to ethylene(e.g.,CO_(2)adsorption/activation,formation of~*CO intermediate,C–C coupling step),offering mechanistic understanding of CO_(2)RR conversion to ethylene.Then the alternative reaction pathways and conditions for the formation of ethylene and competitive products(C_1 and other C_(2+)products)are investigated,guiding the further design and development of preferred conditions for ethylene generation.Engineering strategies of Cu-based catalysts for CO_(2)RR-ethylene are further summarized,and the correlations of reaction mechanism/pathways,engineering strategies and selectivity are elaborated.Finally,major challenges and perspectives in the research area of CO_(2)RR are proposed for future development and practical applications.展开更多
DURING our discussion at workshops for writing“What Does ChatGPT Say:The DAO from Algorithmic Intelligence to Linguistic Intelligence”[1],we had expected the next milestone for Artificial Intelligence(AI)would be in...DURING our discussion at workshops for writing“What Does ChatGPT Say:The DAO from Algorithmic Intelligence to Linguistic Intelligence”[1],we had expected the next milestone for Artificial Intelligence(AI)would be in the direction of Imaginative Intelligence(II),i.e.,something similar to automatic wordsto-videos generation or intelligent digital movies/theater technology that could be used for conducting new“Artificiofactual Experiments”[2]to replace conventional“Counterfactual Experiments”in scientific research and technical development for both natural and social studies[2]-[6].Now we have OpenAI’s Sora,so soon,but this is not the final,actually far away,and it is just the beginning.展开更多
The coronavirus(COVID-19)is a lethal virus causing a rapidly infec-tious disease throughout the globe.Spreading awareness,taking preventive mea-sures,imposing strict restrictions on public gatherings,wearing facial ma...The coronavirus(COVID-19)is a lethal virus causing a rapidly infec-tious disease throughout the globe.Spreading awareness,taking preventive mea-sures,imposing strict restrictions on public gatherings,wearing facial masks,and maintaining safe social distancing have become crucial factors in keeping the virus at bay.Even though the world has spent a whole year preventing and curing the disease caused by the COVID-19 virus,the statistics show that the virus can cause an outbreak at any time on a large scale if thorough preventive measures are not maintained accordingly.Tofight the spread of this virus,technologically developed systems have become very useful.However,the implementation of an automatic,robust,continuous,and lightweight monitoring system that can be efficiently deployed on an embedded device still has not become prevalent in the mass community.This paper aims to develop an automatic system to simul-taneously detect social distance and face mask violation in real-time that has been deployed in an embedded system.A modified version of a convolutional neural network,the ResNet50 model,has been utilized to identify masked faces in peo-ple.You Only Look Once(YOLOv3)approach is applied for object detection and the DeepSORT technique is used to measure the social distance.The efficiency of the proposed model is tested on real-time video sequences taken from a video streaming source from an embedded system,Jetson Nano edge computing device,and smartphones,Android and iOS applications.Empirical results show that the implemented model can efficiently detect facial masks and social distance viola-tions with acceptable accuracy and precision scores.展开更多
In this paper,we design a total infrared(IR)absorber based on a dispersive band structure of two-dimensional(2D)multiwall carbon nanotube(MWCNTs)square array working from near IR(NIR)to mid IR(MIR)regime.The absorptio...In this paper,we design a total infrared(IR)absorber based on a dispersive band structure of two-dimensional(2D)multiwall carbon nanotube(MWCNTs)square array working from near IR(NIR)to mid IR(MIR)regime.The absorption characteristics have been investigated by the 2D finite-difference time domain(FDTD)method in square lattice photonic crystal(PC)of the multipole Drude-Lorentz model inserted to the dispersive dielectric function of MWCNTs.Dispersive photonic band structure and scattering parameters for the wide range of lattice constants from 15 nm to 3500 nm with various filling ratios have been calculated.The results show that for large lattice constant(>2000 nm),the Bragg gap moves to the IR regime and leads to MWCNTs arrays acting as a total absorber.For a structure with lattice constant of 3500 nm and filling factor of 12%,an enhanced absorption coefficient up to 99%is achieved in the range of 0.35 eV(λ=3.5μm)nominated in the MIR regime.Also,the absorption spectrum peak can be tuned in the range of 0.27—0.38 eV(λ=4.59—3.26μm)with a changing filling factor.Our results and methodology can be used to design new MWCNTs based photonic devices for applications like night-vision,thermal detector,and total IR absorbers.展开更多
Alzheimer’s disease (AD) is a brain disorder that eventually causes memory loss and the ability to perform simple cognitive functions;research efforts within pharmaceuticals and other medical treatments have minimal ...Alzheimer’s disease (AD) is a brain disorder that eventually causes memory loss and the ability to perform simple cognitive functions;research efforts within pharmaceuticals and other medical treatments have minimal impact on the disease. Our preliminary biological studies showed that Repeated Electromagnetic Field Stimulation (REFMS) applying an EM frequency of 64 MHz and a specific absorption rate (SAR) of 0.4 - 0.9 W/kg decrease the level of amyloid-β peptides (Aβ), which is the most likely etiology of AD. This study emphasizes uniform E/H field and SAR distribution with adequate penetration depth penetration through multiple human head layers driven with low input power for safety treatments. In this work, we performed numerical modeling and computer simulations of a portable Meander Line antenna (MLA) to achieve the required EMF parameters to treat AD. The MLA device features a low cost, small size, wide bandwidth, and the ability to integrate into a portable system. This study utilized a High-Frequency Simulation System (HFSS) in the design of the MLA with the desired characteristics suited for AD treatment in humans. The team designed a 24-turn antenna with a 60 cm length and 25 cm width and achieved the required resonant frequency of 64 MHz. Here we used two numerical human head phantoms to test the antenna, the MIDA and spherical head phantom with six and seven tissue layers, respectively. The antenna was fed from a 50-Watt input source to obtain the SAR of 0.6 W/kg requirement in the center of the simulated brain tissue layer. We found that the E/H field and SAR distribution produced was not homogeneous;there were areas of high SAR values close to the antenna transmitter, also areas of low SAR value far away from the antenna. This paper details the antenna parameters, the scattering parameters response, the efficiency response, and the E and H field distribution;we presented the computer simulation results and discussed future work for a practical model.展开更多
Today, mammography is the best method for early detection of breast cancer. Radiologists failed to detect evident cancerous signs in approximately 20% of false negative mammograms. False negatives have been identified...Today, mammography is the best method for early detection of breast cancer. Radiologists failed to detect evident cancerous signs in approximately 20% of false negative mammograms. False negatives have been identified as the inability of the radiologist to detect the abnormalities due to several reasons such as poor image quality, image noise, or eye fatigue. This paper presents a framework for a computer aided detection system that integrates Principal Component Analysis (PCA), Fisher Linear Discriminant (FLD), and Nearest Neighbor Classifier (KNN) algorithms for the detection of abnormalities in mammograms. Using normal and abnormal mammograms from the MIAS database, the integrated algorithm achieved 93.06% classification accuracy. Also in this paper, we present an analysis of the integrated algorithm’s parameters and suggest selection criteria.展开更多
Human body with curved and soft interfaces requests advanced flexible materials and structures for the interaction with organs and signal collection from targets in applications such as bioengineering and diagnostic d...Human body with curved and soft interfaces requests advanced flexible materials and structures for the interaction with organs and signal collection from targets in applications such as bioengineering and diagnostic devices.Among them,it is highly demanded to achieve creative design in flexible materials and structures with great stretchable capability for required applications.To this end,both inorganic and organic materials could be adopted and designed with assembly and self-assembly methods for flexible electronics and electrodes.Soft or flexible materials and structures inspired by nature can lead to highly conformal contacts between devices and the human body.These approaches hold great potential for applications in flexible electronics,medical imaging technology and portable disease diagnostics.Novel strategy on related sensors/actuator and energy storage/generation devices could overcome certain limitations on flexible materials engineering and thus advance the field as well.All these methods would deliver a profound impact to our future intelligent society.展开更多
Single cylindrical submicron pores in PMMA polymer membranes are micropatterned by electron beam lithography and integrated into all PMMA-based electrophoretic flow detector systems. Pore dimensions are 450 nm in diam...Single cylindrical submicron pores in PMMA polymer membranes are micropatterned by electron beam lithography and integrated into all PMMA-based electrophoretic flow detector systems. Pore dimensions are 450 nm in diameter and 1 μm in length. The pores are electrically characterized in aqueous KCl electrolyte, exhibiting a stable time-independent ionic current through the pore with a noise level of less than 1% of the open-pore current. The current-voltage curves are linear and scale with electrolyte concentration. The negative surface charge of the membrane over-proportionally decreases pore conductance at low electrolyte concentrations (≤0.1 M) that are still beyond those typically applied in biological experiments. Pores do not exhibit rectification of current flowing through them, allowing for operation with either polarity. To allow for detection of yet much smaller particles, the described PMMA-based system also was successfully equipped with pores of 1.5 nm instead of 450 nm in diameter. This was achieved by introducing naturally occurring biological protein pores of α-hemolysin on a lipid bilayer into the prepatterned PMMA membrane of an assembled PMMA-based electrophoretic flow detector system. Characteristics of translocation events of single-stranded linear plasmid DNA molecules through the pores were recorded, and ionic current deductions during biomolecule translocation were clear and distinguished. Based on the presented submicron scale open pore ionic current transport properties, as well as the observed passage of DNA molecules through protein pores inserted into PMMA membranes, our current research proposes that all PMMA electrophoretic flow detectors exhibit an excellent potential for future use as biomedical resistive-pulse sensors, as long as pore dimensions match those of biomolecules to be detected.展开更多
A method for balancing thermal and electrical packaging requirements for gallium nitride (GaN) high power amplifier (HPA) modules is presented. The goal is to find a design approach that minimizes the junction tempera...A method for balancing thermal and electrical packaging requirements for gallium nitride (GaN) high power amplifier (HPA) modules is presented. The goal is to find a design approach that minimizes the junction temperature of the GaN so that it is reliable and has interconnects that meet electrical performance requirements. One benefit of GaN is that it can simultaneously achieve high power density and operate at microwave and millimeter-wave frequencies. However, the power density can be so high that the necessary thermal solutions can have negative impact on electrical performance. This is especially a concern for the electrical interconnects required for the input/ output ports on high power amplifier devices. This is because the signal interconnects must operate at GHz frequencies, which means that special care must be taken to avoid problems such as undesired signal coupling and ground path inductance. Therefore, this work focuses on GaN packaging and its integration into a module. The results show that an optimum thickness for the GaN heat spreader exits for thermal performance but the electrical design is impacted negatively if the optimum thermal design is chosen. Therefore, a balanced design is chosen which meets overall system level requirements.展开更多
During the prodromal stage of Alzheimer’s disease (AD), neurodegenerative changes can be identified by measuring volumetric loss in AD-prone brain regions on MRI. Cognitive assessments that are sensitive enough to me...During the prodromal stage of Alzheimer’s disease (AD), neurodegenerative changes can be identified by measuring volumetric loss in AD-prone brain regions on MRI. Cognitive assessments that are sensitive enough to measure the early brain-behavior manifestations of AD and that correlate with biomarkers of neurodegeneration are needed to identify and monitor individuals at risk for dementia. Weak sensitivity to early cognitive change has been a major limitation of traditional cognitive assessments. In this study, we focused on expanding our previous work by determining whether a digitized cognitive stress test, the Loewenstein-Acevedo Scales for Semantic Interference and Learning, Brief Computerized Version (LASSI-BC) could differentiate between Cognitively Unimpaired (CU) and amnestic Mild Cognitive Impairment (aMCI) groups. A second focus was to correlate LASSI-BC performance to volumetric reductions in AD-prone brain regions. Data was gathered from 111 older adults who were comprehensively evaluated and administered the LASSI-BC. Eighty-seven of these participants (51 CU;36 aMCI) underwent MR imaging. The volumes of 12 AD-prone brain regions were related to LASSI-BC and other memory tests correcting for False Discovery Rate (FDR). Results indicated that, even after adjusting for initial learning ability, the failure to recover from proactive semantic interference (frPSI) on the LASSI-BC differentiated between CU and aMCI groups. An optimal combination of frPSI and initial learning strength on the LASSI-BC yielded an area under the ROC curve of 0.876 (76.1% sensitivity, 82.7% specificity). Further, frPSI on the LASSI-BC was associated with volumetric reductions in the hippocampus, amygdala, inferior temporal lobes, precuneus, and posterior cingulate.展开更多
Artificial Intelligence(AI)has shown the power to enhance the functionality of sensors and enable intelligent human‐machine interfaces through machine learning‐based data analysis.However,the good performance of AI ...Artificial Intelligence(AI)has shown the power to enhance the functionality of sensors and enable intelligent human‐machine interfaces through machine learning‐based data analysis.However,the good performance of AI is always accompanied by a large amount of data and high computational complexity.Though cloud computing appears to be the right solution to this issue with the advent of the 5G era,a certain intelligence of the edge terminal is also important to make the entire integrated intelligent system more efficient.The current development of microelectronic,wearable,AI,and neuromorphic technologies pave the way to realize advanced edge computing by integrating silicon‐based high‐computing‐power neuromorphic chips with anthropomorphic wearable sensory devices and show the potential to achieve human‐like self‐sustainable decentralized intelligence to enable the next‐generation of AI.Hence,in this review,we systematically introduce the related progress in terms of wearable electronics that can mimic the biological features of humans'sensory systems and the development of neuromorphic/in‐sensor computing technologies.Discussion on implementing the integrated human‐like perception and sensation system with silicone‐based computing chips and non‐silicone‐based wearable functional units and our perspectives are also provided.展开更多
文摘The rapid growth of IoT networks necessitates efficient Intrusion Detection Systems(IDS)capable of addressing dynamic security threats under constrained resource environments.This paper proposes a hybrid IDS for IoT networks,integrating Support Vector Machine(SVM)and Genetic Algorithm(GA)for feature selection and parameter optimization.The GA reduces the feature set from 41 to 7,achieving a 30%reduction in overhead while maintaining an attack detection rate of 98.79%.Evaluated on the NSL-KDD dataset,the system demonstrates an accuracy of 97.36%,a recall of 98.42%,and an F1-score of 96.67%,with a low false positive rate of 1.5%.Additionally,it effectively detects critical User-to-Root(U2R)attacks at a rate of 96.2%and Remote-to-Local(R2L)attacks at 95.8%.Performance tests validate the system’s scalability for networks with up to 2000 nodes,with detection latencies of 120 ms at 65%CPU utilization in small-scale deployments and 250 ms at 85%CPU utilization in large-scale scenarios.Parameter sensitivity analysis enhances model robustness,while false positive examination aids in reducing administrative overhead for practical deployment.This IDS offers an effective,scalable,and resource-efficient solution for real-world IoT system security,outperforming traditional approaches.
基金financial supports from the National Natural Science Foundation of China(Grant No.6227511362405124).
文摘We present a novel method for scale-invariant 3D face recognition by integrating computer-generated holography with the Mellin transform.This approach leverages the scale-invariance property of the Mellin transform to address challenges related to variations in 3D facial sizes during recognition.By applying the Mellin transform to computer-generated holograms and performing correlation between them,which,to the best of our knowledge,is being done for the first time,we have developed a robust recognition framework capable of managing significant scale variations without compromising recognition accuracy.Digital holograms of 3D faces are generated from a face database,and the Mellin transform is employed to enable robust recognition across scale factors ranging from 0.4 to 2.0.Within this range,the method achieves 100%recognition accuracy,as confirmed by both simulation-based and hybrid optical/digital experimental validations.Numerical calculations demonstrate that our method significantly enhances the accuracy and reliability of 3D face recognition,as evidenced by the sharp correlation peaks and higher peak-to-noise ratio(PNR)values than that of using conventional holograms without the Mellin transform.Additionally,the hybrid optical/digital joint transform correlation hardware further validates the method's effectiveness,demonstrating its capability to accurately identify and distinguish 3D faces at various scales.This work provides a promising solution for advanced biometric systems,especially for those which require 3D scale-invariant recognition.
基金supported by the Fundamental Research Funds for the Central Universities (YJSJ25013,ZYTS25235,ZYTS25229)the National Natural Science Foundation of China (62274132, 62204189,62004151,62274126)+3 种基金the National Key R&D Program of China (2021YFF0500504,2021YFF0500501)the Natural Science Basic Research Plan in Shaanxi Province of China (2024GX-YBXM514)the Young Talent Fund of Association for Science and Technology in Shaanxi,China (20220115)the Interdisciplinary Cultivation Program of Xidian University (21103240003)。
文摘Scalable fabrication of homogeneous perovskite films remains crucial for bridging the efficiency gap between lab-scale solar cells and commercial solar modules.To tackle this issue,we introduce NCyano-4-methyl-N-phenylbenzenesulfonamide(CMPS) additives into perovskite precursors,enabling slot-die coating of large-area modules under ambient conditions.CMPS suppresses colloidal aggregation and delays crystallization,yielding high-quality uniform films.Small-area devices(0.07 cm^(2) aperture area) incorporating CMPS exhibited a significant efficiency increase from 22.07 % to 24.58 %.Corresponding encapsulated devices maintained 85 % of their initial power conversion efficiency(PCE,average 23.56 %) after 1500 h of continuous maximum power point(MPP) tracking under one-sun illumination at 50-55℃.Furthermore,we demonstrate impressive efficiency of perovskite solar modules,achieving 20.57 %(52 cm^(2) aperture area) for 10 cm × 10 cm mini-modules and 17.02 %(260 cm^(2) aperture area) for 21 cm × 21 cm sub-modules,representing the state-of-the-art performance for solutionprocessed devices at these scales.
文摘Optimizing routing and resource allocation in decentralized unmanned aerial vehicle(UAV)networks remains challenging due to interference and rapidly changing topologies.The authors introduce a novel framework combining double deep Q-networks(DDQNs)and graph neural networks(GNNs)for joint routing and resource allocation.The framework uses GNNs to model the network topology and DDQNs to adaptively control routing and resource allocation,addressing interference and improving network performance.Simulation results show that the proposed approach outperforms traditional methods such as Closest-to-Destination(c2Dst),Max-SINR(mSINR),and Multi-Layer Perceptron(MLP)-based models,achieving approximately 23.5% improvement in throughput,50% increase in connection probability,and 17.6% reduction in number of hops,demonstrating its effectiveness in dynamic UAV networks.
文摘Federated Learning(FL)has become a leading decentralized solution that enables multiple clients to train a model in a collaborative environment without directly sharing raw data,making it suitable for privacy-sensitive applications such as healthcare,finance,and smart systems.As the field continues to evolve,the research field has become more complex and scattered,covering different system designs,training methods,and privacy techniques.This survey is organized around the three core challenges:how the data is distributed,how models are synchronized,and how to defend against attacks.It provides a structured and up-to-date review of FL research from 2023 to 2025,offering a unified taxonomy that categorizes works by data distribution(Horizontal FL,Vertical FL,Federated Transfer Learning,and Personalized FL),training synchronization(synchronous and asynchronous FL),optimization strategies,and threat models(data leakage and poisoning attacks).In particular,we summarize the latest contributions in Vertical FL frameworks for secure multi-party learning,communication-efficient Horizontal FL,and domain-adaptive Federated Transfer Learning.Furthermore,we examine synchronization techniques addressing system heterogeneity,including straggler mitigation in synchronous FL and staleness management in asynchronous FL.The survey covers security threats in FL,such as gradient inversion,membership inference,and poisoning attacks,as well as their defense strategies that include privacy-preserving aggregation and anomaly detection.The paper concludes by outlining unresolved issues and highlighting challenges in handling personalized models,scalability,and real-world adoption.
基金the Engineering and Physical Sciences Research Council(EPSRC)for funding the researchUK India Education Research Initiative(UKIERI)for funding support.
文摘This review provides an insightful and comprehensive exploration of the emerging 2D material borophene,both pristine and modified,emphasizing its unique attributes and potential for sustainable applications.Borophene’s distinctive properties include its anisotropic crystal structures that contribute to its exceptional mechanical and electronic properties.The material exhibits superior electrical and thermal conductivity,surpassing many other 2D materials.Borophene’s unique atomic spin arrangements further diversify its potential application for magnetism.Surface and interface engineering,through doping,functionalization,and synthesis of hybridized and nanocomposite borophene-based systems,is crucial for tailoring borophene’s properties to specific applications.This review aims to address this knowledge gap through a comprehensive and critical analysis of different synthetic and functionalisation methods,to enhance surface reactivity by increasing active sites through doping and surface modifications.These approaches optimize diffusion pathways improving accessibility for catalytic reactions,and tailor the electronic density to tune the optical and electronic behavior.Key applications explored include energy systems(batteries,supercapacitors,and hydrogen storage),catalysis for hydrogen and oxygen evolution reactions,sensors,and optoelectronics for advanced photonic devices.The key to all these applications relies on strategies to introduce heteroatoms for tuning electronic and catalytic properties,employ chemical modifications to enhance stability and leverage borophene’s conductivity and reactivity for advanced photonics.Finally,the review addresses challenges and proposes solutions such as encapsulation,functionalization,and integration with composites to mitigate oxidation sensitivity and overcome scalability barriers,enabling sustainable,commercial-scale applications.
文摘Accurate blood pressure(BP)monitoring is essential for preventing and managing cardiovascular disease.Advancements in materials science,medicine,flexible electronic,and artificial intelligence(AI)have enabled cuffless,unobtrusive BP monitoring systems,offering an alternative to traditional sphygmomanometers.However,extending these advances to real-world cardiovascular care particularly in resource-limited settings remains challenging due to constraints in computational resources,power efficiency,and deployment scalability.This review presents a comprehensive synthesis of AI-enhanced wearable BP monitoring,emphasizing its potential for personalized,scalable,and accessible healthcare.We systematically analyze the end-to-end system architecture,from mechano-electric sensing principles and AI-based estimation models to edge-aware deployment strategies tailored for low-resource environments.We further discuss clinical validation metrics and implementation barriers and prospective strategies.To bridge lab-to-field translation,we propose an innovative"sensor-model-deployment-assessment"co-design framework.This roadmap highlights how AI-enhanced BP technologies can support proactive hypertension control and promote cardiovascular health equity on a global scale.
基金funded by the Research,Development,and Innovation Authority(RDIA)—Kingdom of Saudi Arabia(Grant No.13292-psu-2023-PSNU-R-3-1-EF-).
文摘Colorectal cancer is the third most diagnosed cancer worldwide,and immune checkpoint inhibitors have shown promising therapeutic outcomes in selected patient groups.This study performed a comprehensive analysis of multi-omics data from The Cancer Genome Atlas colorectal adenocarcinoma cohort(TCGA-COADREAD),accessed through cBioPortal,to develop machine learning models for predicting progression-free survival(PFS)following immunotherapy.The dataset included clinical variables,genomic alterations in Kirsten Rat Sarcoma Viral Oncogene Homolog(KRAS),B-Raf Proto-Oncogene(BRAF),and Neuroblastoma RAS Viral Oncogene Homolog(NRAS),microsatellite instability(MSI)status,tumor mutation burden(TMB),and expression of immune checkpoint genes.Kaplan–Meier analysis showed that KRAS mutations were significantly associated with reduced PFS,while BRAF and NRAS mutations had no significant impact.MSI-high tumors exhibited elevated TMB and increased immune checkpoint expression,reflecting their immunologically active phenotype.We developed both survival and classification models,with the Extra Trees classifier achieving the best performance(accuracy=0.86,precision=0.67,recall=0.70,F1-score=0.68,AUC=0.84).These findings highlight the potential of combining genomic and immune biomarkers with machine learning to improve patient stratification and guide personalized immunotherapy decisions.An interactive web application was also developed to enable clinicians to input patient-specific molecular and clinical data and visualize individualized PFS predictions,supporting timely,data-driven treatment planning.
文摘Over the past years,many efforts have been accomplished to achieve fast and accurate meta-heuristic algorithms to optimize a variety of real-world problems.This study presents a new optimization method based on an unusual geological phenomenon in nature,named Geyser inspired Algorithm(GEA).The mathematical modeling of this geological phenomenon is carried out to have a better understanding of the optimization process.The efficiency and accuracy of GEA are verified using statistical examination and convergence rate comparison on numerous CEC 2005,CEC 2014,CEC 2017,and real-parameter benchmark functions.Moreover,GEA has been applied to several real-parameter engineering optimization problems to evaluate its effectiveness.In addition,to demonstrate the applicability and robustness of GEA,a comprehensive investigation is performed for a fair comparison with other standard optimization methods.The results demonstrate that GEA is noticeably prosperous in reaching the optimal solutions with a high convergence rate in comparison with other well-known nature-inspired algorithms,including ABC,BBO,PSO,and RCGA.Note that the source code of the GEA is publicly available at https://www.optim-app.com/projects/gea.
基金financially supported via Australian Research Council(FT180100705)the support by the National Natural Science Foundation of China(22209103)+3 种基金the support from UTS Chancellor's Research Fellowshipsthe support from Open Project of State Key Laboratory of Advanced Special Steel,the Shanghai Key Laboratory of Advanced Ferrometallurgy,Shanghai University(SKLASS 2021-**)Joint International Laboratory on Environmental and Energy Frontier MaterialsInnovation Research Team of High-Level Local Universities in Shanghai。
文摘Electrochemical carbon dioxide reduction reaction(CO_(2)RR)provides a promising way to convert CO_(2)to chemicals.The multicarbon(C_(2+))products,especially ethylene,are of great interest due to their versatile industrial applications.However,selectively reducing CO_(2)to ethylene is still challenging as the additional energy required for the C–C coupling step results in large overpotential and many competing products.Nonetheless,mechanistic understanding of the key steps and preferred reaction pathways/conditions,as well as rational design of novel catalysts for ethylene production have been regarded as promising approaches to achieving the highly efficient and selective CO_(2)RR.In this review,we first illustrate the key steps for CO_(2)RR to ethylene(e.g.,CO_(2)adsorption/activation,formation of~*CO intermediate,C–C coupling step),offering mechanistic understanding of CO_(2)RR conversion to ethylene.Then the alternative reaction pathways and conditions for the formation of ethylene and competitive products(C_1 and other C_(2+)products)are investigated,guiding the further design and development of preferred conditions for ethylene generation.Engineering strategies of Cu-based catalysts for CO_(2)RR-ethylene are further summarized,and the correlations of reaction mechanism/pathways,engineering strategies and selectivity are elaborated.Finally,major challenges and perspectives in the research area of CO_(2)RR are proposed for future development and practical applications.
基金the National Natural Science Foundation of China(62271485,61903363,U1811463,62103411,62203250)the Science and Technology Development Fund of Macao SAR(0093/2023/RIA2,0050/2020/A1)。
文摘DURING our discussion at workshops for writing“What Does ChatGPT Say:The DAO from Algorithmic Intelligence to Linguistic Intelligence”[1],we had expected the next milestone for Artificial Intelligence(AI)would be in the direction of Imaginative Intelligence(II),i.e.,something similar to automatic wordsto-videos generation or intelligent digital movies/theater technology that could be used for conducting new“Artificiofactual Experiments”[2]to replace conventional“Counterfactual Experiments”in scientific research and technical development for both natural and social studies[2]-[6].Now we have OpenAI’s Sora,so soon,but this is not the final,actually far away,and it is just the beginning.
文摘The coronavirus(COVID-19)is a lethal virus causing a rapidly infec-tious disease throughout the globe.Spreading awareness,taking preventive mea-sures,imposing strict restrictions on public gatherings,wearing facial masks,and maintaining safe social distancing have become crucial factors in keeping the virus at bay.Even though the world has spent a whole year preventing and curing the disease caused by the COVID-19 virus,the statistics show that the virus can cause an outbreak at any time on a large scale if thorough preventive measures are not maintained accordingly.Tofight the spread of this virus,technologically developed systems have become very useful.However,the implementation of an automatic,robust,continuous,and lightweight monitoring system that can be efficiently deployed on an embedded device still has not become prevalent in the mass community.This paper aims to develop an automatic system to simul-taneously detect social distance and face mask violation in real-time that has been deployed in an embedded system.A modified version of a convolutional neural network,the ResNet50 model,has been utilized to identify masked faces in peo-ple.You Only Look Once(YOLOv3)approach is applied for object detection and the DeepSORT technique is used to measure the social distance.The efficiency of the proposed model is tested on real-time video sequences taken from a video streaming source from an embedded system,Jetson Nano edge computing device,and smartphones,Android and iOS applications.Empirical results show that the implemented model can efficiently detect facial masks and social distance viola-tions with acceptable accuracy and precision scores.
文摘In this paper,we design a total infrared(IR)absorber based on a dispersive band structure of two-dimensional(2D)multiwall carbon nanotube(MWCNTs)square array working from near IR(NIR)to mid IR(MIR)regime.The absorption characteristics have been investigated by the 2D finite-difference time domain(FDTD)method in square lattice photonic crystal(PC)of the multipole Drude-Lorentz model inserted to the dispersive dielectric function of MWCNTs.Dispersive photonic band structure and scattering parameters for the wide range of lattice constants from 15 nm to 3500 nm with various filling ratios have been calculated.The results show that for large lattice constant(>2000 nm),the Bragg gap moves to the IR regime and leads to MWCNTs arrays acting as a total absorber.For a structure with lattice constant of 3500 nm and filling factor of 12%,an enhanced absorption coefficient up to 99%is achieved in the range of 0.35 eV(λ=3.5μm)nominated in the MIR regime.Also,the absorption spectrum peak can be tuned in the range of 0.27—0.38 eV(λ=4.59—3.26μm)with a changing filling factor.Our results and methodology can be used to design new MWCNTs based photonic devices for applications like night-vision,thermal detector,and total IR absorbers.
文摘Alzheimer’s disease (AD) is a brain disorder that eventually causes memory loss and the ability to perform simple cognitive functions;research efforts within pharmaceuticals and other medical treatments have minimal impact on the disease. Our preliminary biological studies showed that Repeated Electromagnetic Field Stimulation (REFMS) applying an EM frequency of 64 MHz and a specific absorption rate (SAR) of 0.4 - 0.9 W/kg decrease the level of amyloid-β peptides (Aβ), which is the most likely etiology of AD. This study emphasizes uniform E/H field and SAR distribution with adequate penetration depth penetration through multiple human head layers driven with low input power for safety treatments. In this work, we performed numerical modeling and computer simulations of a portable Meander Line antenna (MLA) to achieve the required EMF parameters to treat AD. The MLA device features a low cost, small size, wide bandwidth, and the ability to integrate into a portable system. This study utilized a High-Frequency Simulation System (HFSS) in the design of the MLA with the desired characteristics suited for AD treatment in humans. The team designed a 24-turn antenna with a 60 cm length and 25 cm width and achieved the required resonant frequency of 64 MHz. Here we used two numerical human head phantoms to test the antenna, the MIDA and spherical head phantom with six and seven tissue layers, respectively. The antenna was fed from a 50-Watt input source to obtain the SAR of 0.6 W/kg requirement in the center of the simulated brain tissue layer. We found that the E/H field and SAR distribution produced was not homogeneous;there were areas of high SAR values close to the antenna transmitter, also areas of low SAR value far away from the antenna. This paper details the antenna parameters, the scattering parameters response, the efficiency response, and the E and H field distribution;we presented the computer simulation results and discussed future work for a practical model.
文摘Today, mammography is the best method for early detection of breast cancer. Radiologists failed to detect evident cancerous signs in approximately 20% of false negative mammograms. False negatives have been identified as the inability of the radiologist to detect the abnormalities due to several reasons such as poor image quality, image noise, or eye fatigue. This paper presents a framework for a computer aided detection system that integrates Principal Component Analysis (PCA), Fisher Linear Discriminant (FLD), and Nearest Neighbor Classifier (KNN) algorithms for the detection of abnormalities in mammograms. Using normal and abnormal mammograms from the MIAS database, the integrated algorithm achieved 93.06% classification accuracy. Also in this paper, we present an analysis of the integrated algorithm’s parameters and suggest selection criteria.
文摘Human body with curved and soft interfaces requests advanced flexible materials and structures for the interaction with organs and signal collection from targets in applications such as bioengineering and diagnostic devices.Among them,it is highly demanded to achieve creative design in flexible materials and structures with great stretchable capability for required applications.To this end,both inorganic and organic materials could be adopted and designed with assembly and self-assembly methods for flexible electronics and electrodes.Soft or flexible materials and structures inspired by nature can lead to highly conformal contacts between devices and the human body.These approaches hold great potential for applications in flexible electronics,medical imaging technology and portable disease diagnostics.Novel strategy on related sensors/actuator and energy storage/generation devices could overcome certain limitations on flexible materials engineering and thus advance the field as well.All these methods would deliver a profound impact to our future intelligent society.
文摘Single cylindrical submicron pores in PMMA polymer membranes are micropatterned by electron beam lithography and integrated into all PMMA-based electrophoretic flow detector systems. Pore dimensions are 450 nm in diameter and 1 μm in length. The pores are electrically characterized in aqueous KCl electrolyte, exhibiting a stable time-independent ionic current through the pore with a noise level of less than 1% of the open-pore current. The current-voltage curves are linear and scale with electrolyte concentration. The negative surface charge of the membrane over-proportionally decreases pore conductance at low electrolyte concentrations (≤0.1 M) that are still beyond those typically applied in biological experiments. Pores do not exhibit rectification of current flowing through them, allowing for operation with either polarity. To allow for detection of yet much smaller particles, the described PMMA-based system also was successfully equipped with pores of 1.5 nm instead of 450 nm in diameter. This was achieved by introducing naturally occurring biological protein pores of α-hemolysin on a lipid bilayer into the prepatterned PMMA membrane of an assembled PMMA-based electrophoretic flow detector system. Characteristics of translocation events of single-stranded linear plasmid DNA molecules through the pores were recorded, and ionic current deductions during biomolecule translocation were clear and distinguished. Based on the presented submicron scale open pore ionic current transport properties, as well as the observed passage of DNA molecules through protein pores inserted into PMMA membranes, our current research proposes that all PMMA electrophoretic flow detectors exhibit an excellent potential for future use as biomedical resistive-pulse sensors, as long as pore dimensions match those of biomolecules to be detected.
文摘A method for balancing thermal and electrical packaging requirements for gallium nitride (GaN) high power amplifier (HPA) modules is presented. The goal is to find a design approach that minimizes the junction temperature of the GaN so that it is reliable and has interconnects that meet electrical performance requirements. One benefit of GaN is that it can simultaneously achieve high power density and operate at microwave and millimeter-wave frequencies. However, the power density can be so high that the necessary thermal solutions can have negative impact on electrical performance. This is especially a concern for the electrical interconnects required for the input/ output ports on high power amplifier devices. This is because the signal interconnects must operate at GHz frequencies, which means that special care must be taken to avoid problems such as undesired signal coupling and ground path inductance. Therefore, this work focuses on GaN packaging and its integration into a module. The results show that an optimum thickness for the GaN heat spreader exits for thermal performance but the electrical design is impacted negatively if the optimum thermal design is chosen. Therefore, a balanced design is chosen which meets overall system level requirements.
文摘During the prodromal stage of Alzheimer’s disease (AD), neurodegenerative changes can be identified by measuring volumetric loss in AD-prone brain regions on MRI. Cognitive assessments that are sensitive enough to measure the early brain-behavior manifestations of AD and that correlate with biomarkers of neurodegeneration are needed to identify and monitor individuals at risk for dementia. Weak sensitivity to early cognitive change has been a major limitation of traditional cognitive assessments. In this study, we focused on expanding our previous work by determining whether a digitized cognitive stress test, the Loewenstein-Acevedo Scales for Semantic Interference and Learning, Brief Computerized Version (LASSI-BC) could differentiate between Cognitively Unimpaired (CU) and amnestic Mild Cognitive Impairment (aMCI) groups. A second focus was to correlate LASSI-BC performance to volumetric reductions in AD-prone brain regions. Data was gathered from 111 older adults who were comprehensively evaluated and administered the LASSI-BC. Eighty-seven of these participants (51 CU;36 aMCI) underwent MR imaging. The volumes of 12 AD-prone brain regions were related to LASSI-BC and other memory tests correcting for False Discovery Rate (FDR). Results indicated that, even after adjusting for initial learning ability, the failure to recover from proactive semantic interference (frPSI) on the LASSI-BC differentiated between CU and aMCI groups. An optimal combination of frPSI and initial learning strength on the LASSI-BC yielded an area under the ROC curve of 0.876 (76.1% sensitivity, 82.7% specificity). Further, frPSI on the LASSI-BC was associated with volumetric reductions in the hippocampus, amygdala, inferior temporal lobes, precuneus, and posterior cingulate.
基金supported by NRF‐CRP28‐2022‐0038“Integrating Wideband Tuneable Acoustic Filters on Silicon for High‐Speed Wireless Communication”(WBS:grant no.A‐8001503‐00‐00)National University of Singapore(NUS),Singapore,and RIE2025 IAF‐ICP under I2301E0027“Piezo Specialty Lab‐in‐Fab 2.0(LiF 2.0)-Enabling Unrivalled Power Efficient Transducers Beyond Material Limits”at National University of Singapore(NUS),Singapore.
文摘Artificial Intelligence(AI)has shown the power to enhance the functionality of sensors and enable intelligent human‐machine interfaces through machine learning‐based data analysis.However,the good performance of AI is always accompanied by a large amount of data and high computational complexity.Though cloud computing appears to be the right solution to this issue with the advent of the 5G era,a certain intelligence of the edge terminal is also important to make the entire integrated intelligent system more efficient.The current development of microelectronic,wearable,AI,and neuromorphic technologies pave the way to realize advanced edge computing by integrating silicon‐based high‐computing‐power neuromorphic chips with anthropomorphic wearable sensory devices and show the potential to achieve human‐like self‐sustainable decentralized intelligence to enable the next‐generation of AI.Hence,in this review,we systematically introduce the related progress in terms of wearable electronics that can mimic the biological features of humans'sensory systems and the development of neuromorphic/in‐sensor computing technologies.Discussion on implementing the integrated human‐like perception and sensation system with silicone‐based computing chips and non‐silicone‐based wearable functional units and our perspectives are also provided.
