查看更多>>摘要：Multimodal sensor fusion can make full use of the advantages of various sensors,make up for the shortcomings of a single sensor,achieve information verification or information security through information redundancy,and improve the reliabil-ity and safety of the system.Artificial intelligence(AI),referring to the simulation of human intelligence in machines that are pro-grammed to think and learn like humans,represents a pivotal frontier in modern scientific research.With the continuous devel-opment and promotion of AI technology in Sensor 4.0 age,multimodal sensor fusion is becoming more and more intelligent and automated,and is expected to go further in the future.With this context,this review article takes a comprehensive look at the recent progress on AI-enhanced multimodal sensors and their integrated devices and systems.Based on the concept and principle of sensor technologies and AI algorithms,the theoretical underpinnings,technological breakthroughs,and pragmatic applications of AI-enhanced multimodal sensors in various fields such as robotics,healthcare,and environmental monitoring are highlighted.Through a comparative study of the dual/tri-modal sensors with and without using AI technologies(especially machine learning and deep learning),AI-enhanced multimodal sensors highlight the potential of AI to improve sensor perfor-mance,data processing,and decision-making capabilities.Furthermore,the review analyzes the challenges and opportunities afforded by AI-enhanced multimodal sensors,and offers a prospective outlook on the forthcoming advancements.
查看更多>>摘要：In the era of Metaverse and virtual reality(VR)/augmented reality(AR),capturing finger motion and force interac-tions is crucial for immersive human-machine interfaces.This study introduces a flexible electronic skin for the index finger,addressing coupled perception of both state and process in dynamic tactile sensing.The device integrates resistive and giant magnetoelastic sensors,enabling detection of surface pressure and finger joint bending.This e-skin identifies three phases of fin-ger action:bending state,dynamic normal force and tangential force(sweeping).The system comprises resistive carbon nan-otubes(CNT)/polydimethylsiloxane(PDMS)films for bending sensing and magnetoelastic sensors(NdFeB particles,EcoFlex,and flexible coils)for pressure detection.The inward bending resistive sensor,based on self-assembled microstructures,exhibits directional specificity with a response time under 120 ms and bending sensitivity from 0° to 120°.The magnetoelastic sensors demonstrate specific responses to frequency and deformation magnitude,as well as sensitivity to surface roughness dur-ing sliding and material hardness.The system's capability is demonstrated through tactile-based bread type and condition recog-nition,achieving 92%accuracy.This intelligent patch shows broad potential in enhancing interactions across various fields,from VR/AR interfaces and medical diagnostics to smart manufacturing and industrial automation.
查看更多>>摘要：Artificial skin should embody a softly functional film that is capable of self-powering,healing and sensing with neuro-morphic processing.However,the pursuit of a bionic skin that combines high flexibility,self-healability,and zero-powered pho-tosynaptic functionality remains elusive.In this study,we report a self-powered and self-healable neuromorphic vision skin,fea-turing silver nanoparticle-doped ionogel heterostructure as photoacceptor.The localized surface plasmon resonance induced by light in the nanoparticles triggers temperature fluctuations within the heterojunction,facilitating ion migration for visual sens-ing with synaptic behaviors.The abundant reversible hydrogen bonds in the ionogel endow the skin with remarkable mechani-cal flexibility and self-healing properties.We assembled a neuromorphic visual skin equipped with a 5×5 photosynapse array,capable of sensing and memorizing diverse light patterns.
查看更多>>摘要：We demonstrate a bipolar graphene/F16CuPc synaptic transistor(GFST)with matched p-type and n-type bipolar prop-erties,which emulates multiplexed neurotransmission of the release of two excitatory neurotransmitters in graphene and F16CuPc channels,separately.This process facilitates fast-switching plasticity by altering charge carriers in the separated chan-nels.The complementary neural network for image recognition of Fashion-MNIST dataset was constructed using the matched relative amplitude and plasticity properties of the GFST dominated by holes or electrons to improve the weight regulation and recognition accuracy,achieving a pattern recognition accuracy of 83.23%.These results provide new insights to the construc-tion of future neuromorphic systems.
查看更多>>摘要：With the advancement of artificial intelligence,optic in-sensing reservoir computing based on emerging semiconduc-tor devices is high desirable for real-time analog signal processing.Here,we disclose a flexible optomemristor based on C27H30O15/FeOx heterostructure that presents a highly sensitive to the light stimuli and artificial optic synaptic features such as short-and long-term plasticity(STP and LTP),enabling the developed optomemristor to implement complex analogy signal pro-cessing through building a real-physical dynamic-based in-sensing reservoir computing algorithm and yielding an accuracy of 94.88%for speech recognition.The charge trapping and detrapping mediated by the optic active layer of C27H30O15 that is extracted from the lotus flower is response for the positive photoconductance memory in the prepared optomemristor.This work provides a feasible organic-inorganic heterostructure as well as an optic in-sensing vision computing for an advanced optic computing system in future complex signal processing.
查看更多>>摘要：Exploring electrode materials with larger capacity,higher power density and longer cycle life was critical for develop-ing advanced flexible lithium-ion batteries(LIBs).Herein,we used a controlled two-step method including electrospraying fol-lowed with calcination treatment by CVD furnace to design novel electrodes of Si/Six/C and Sn/C microrods array consisting of nanospheres on flexible carbon cloth substrate(denoted as Si/Six/C@CC,Sn/C@CC).Microrods composed of cumulated nanospheres(the diameter was approximately 120 nm)had a mean diameter of approximately 1.5 µm and a length of around 4.0 µm,distributing uniformly along the entire woven carbon fibers.Both of Si/Si/Six/C@CC and Sn/C@CC products were synthe-sized as binder-free anodes for Li-ion battery with the features of high reversible capacity and excellent cycling.Especially Si/Six/C electrode exhibited high specific capacity of about 1750 mA∙h∙g-1 at 0.5 A∙g-1 and excellent cycling ability even after 1050 cycles with a capacity of 1388 mA∙h∙g-1.Highly flexible Si/Six/C@CC//LiCoO2 batteries based on liquid and solid elec-trolytes were also fabricated,exhibiting high flexibility,excellent electrical stability and potential applications in flexible wear-able electronics.
查看更多>>摘要：The rapid industrial growth and increasing population have led to significant pollution and deterioration of the natu-ral atmospheric environment.Major atmospheric pollutants include NO2 and CO2.Hence,it is imperative to develop NO2 and CO2 sensors for ambient conditions,that can be used in indoor air quality monitoring,breath analysis,food spoilage detection,etc.In the present study,two thin film nanocomposite(nickel oxide-graphene and nickel oxide-silver nanowires)gas sensors are fabricated using direct ink writing.The nano-composites are investigated for their structural,optical,and electrical proper-ties.Later the nano-composite is deposited on the interdigitated electrode(IDE)pattern to form NO2 and CO2 sensors.The deposited films are then exposed to NO2 and CO2 gases separately and their response and recovery times are determined using a custom-built gas sensing setup.Nickel oxide-graphene provides a good response time and recovery time of 10 and 9 s,respectively for NO2,due to the higher electron affinity of graphene towards NO2.Nickel oxide-silver nanowire nano-compos-ite is suited for CO2 gas because silver is an excellent electrocatalyst for CO2 by giving response and recovery times of 11 s each.This is the first report showcasing NiO nano-composites for NO2 and CO2 sensing at room temperature.
万方数据
维普