Recent progress on artificial intelligence-enhanced multimodal sensors integrated devices and systems DOI
Haihua Wang, Mingjian Zhou, Xiaolong Jia

et al.

Journal of Semiconductors, Journal Year: 2025, Volume and Issue: 46(1), P. 011610 - 011610

Published: Jan. 1, 2025

Abstract Multimodal sensor fusion can make full use of the advantages various sensors, up for shortcomings a single sensor, achieve information verification or security through redundancy, and improve reliability safety system. Artificial intelligence (AI), referring to simulation human in machines that are programmed think learn like humans, represents pivotal frontier modern scientific research. With continuous development promotion AI technology Sensor 4.0 age, multimodal is becoming more intelligent automated, expected go further future. this context, review article takes comprehensive look at recent progress on AI-enhanced sensors their integrated devices systems. Based concept principle technologies algorithms, theoretical underpinnings, technological breakthroughs, pragmatic applications fields such as robotics, healthcare, environmental monitoring highlighted. Through comparative study dual/tri-modal with without using (especially machine learning deep learning), highlight potential performance, data processing, decision-making capabilities. Furthermore, analyzes challenges opportunities afforded by offers prospective outlook forthcoming advancements.

Language: Английский

Machine Learning‐Enabled Tactile Sensor Design for Dynamic Touch Decoding DOI Creative Commons
Yuyao Lu, Depeng Kong, Geng Yang

et al.

Advanced Science, Journal Year: 2023, Volume and Issue: 10(32)

Published: Sept. 22, 2023

Abstract Skin‐like flexible sensors play vital roles in healthcare and human–machine interactions. However, general goals focus on pursuing intrinsic static dynamic performance of skin‐like themselves accompanied with diverse trial‐and‐error attempts. Such a forward strategy almost isolates the design from resulting applications. Here, machine learning (ML)‐guided tactile sensor system is reported, enabling high classification accuracy (≈99.58%) perception six touch modalities. Different intuition‐driven design, such ML‐guided optimization realized by introducing support vector machine‐based ML algorithm along specific statistical criteria for fabrication parameters selection to excavate features deeply concealed raw sensing data. This inverse merges into phase hardware, bridging gap between device structures algorithms. Using optimized sensor, high‐quality recognizable signals handwriting applications are obtained. Besides, additional data processing, robot hand assembled able complete real‐time touch‐decoding an 11‐digit braille phone number accuracy.

Language: Английский

Citations

85

Geometric deep optical sensing DOI
Shaofan Yuan, Chao Ma, Ethan Fetaya

et al.

Science, Journal Year: 2023, Volume and Issue: 379(6637)

Published: March 16, 2023

Geometry, an ancient yet vibrant branch of mathematics, has important and far-reaching impacts on various disciplines such as art, science, engineering. Here, we introduce emerging concept dubbed “geometric deep optical sensing” that is based a number recent demonstrations in advanced sensing imaging, which reconfigurable sensor (or array thereof) can directly decipher the rich information unknown incident light beam, including its intensity, spectrum, polarization, spatial features, possibly angular momentum. We present physical, mathematical, engineering foundations this concept, with particular emphases roles classical quantum geometry neural networks. Furthermore, discuss new opportunities scheme enable challenges associated future developments.

Language: Английский

Citations

71

Porous materials as effective chemiresistive gas sensors DOI Creative Commons
Akashdeep Sharma, Sunil Babu Eadi, Hemanth Noothalapati

et al.

Chemical Society Reviews, Journal Year: 2024, Volume and Issue: 53(5), P. 2530 - 2577

Published: Jan. 1, 2024

This review emphasizes the crucial role of chemiresistive gas sensors (CGS) in detection. It underscores porous materials as alternatives, showcasing their exceptional attributes. The explores CGS-based real-life applications.

Language: Английский

Citations

64

Snapshot multispectral imaging using a diffractive optical network DOI Creative Commons
Deniz Mengü,

Anika Tabassum,

Mona Jarrahi

et al.

Light Science & Applications, Journal Year: 2023, Volume and Issue: 12(1)

Published: April 6, 2023

Abstract Multispectral imaging has been used for numerous applications in e.g., environmental monitoring, aerospace, defense, and biomedicine. Here, we present a diffractive optical network-based multispectral system trained using deep learning to create virtual spectral filter array at the output image field-of-view. This imager performs spatially-coherent over large spectrum, same time, routes pre-determined set of channels onto an pixels plane, converting monochrome focal-plane or sensor into device without any filters recovery algorithms. Furthermore, responsivity this is not sensitive input polarization states. Through numerical simulations, different network designs that achieve snapshot with 4, 9 16 unique bands within visible based on passive spatially-structured surfaces, compact design axially spans ~72 λ m , where mean wavelength band interest. Moreover, experimentally demonstrate 3D-printed creates its plane spatially repeating 2 × = 4 terahertz spectrum. Due their form factor computation-free, power-efficient polarization-insensitive forward operation, imagers can be transformative various sensing parts electromagnetic spectrum high-density wide-area pixel arrays are widely available.

Language: Английский

Citations

59

Machine learning toward high-performance electrochemical sensors DOI Open Access
Gabriela F. Giordano, Larissa Fernanda Ferreira, Ítalo R. S. Bezerra

et al.

Analytical and Bioanalytical Chemistry, Journal Year: 2023, Volume and Issue: 415(18), P. 3683 - 3692

Published: Jan. 13, 2023

Language: Английский

Citations

49

Editors’ Choice—Challenges and Opportunities for Developing Electrochemical Biosensors with Commercialization Potential in the Point-of-Care Diagnostics Market DOI Creative Commons
A. Akhlaghi, Harmanjit Kaur, Bal Ram Adhikari

et al.

ECS Sensors Plus, Journal Year: 2024, Volume and Issue: 3(1), P. 011601 - 011601

Published: March 1, 2024

There is a plethora of electrochemical biosensors developed for ultrasensitive detection clinically relevant biomarkers. However, many these systems lose their performance in heterogeneous clinical samples and are too complex to be operated by end users at the point-of-care (POC), prohibiting commercial success. Integration with sample processing technology addresses both challenges; however, it adds manufacturing complexity overall cost systems. Herein, we review different components biosensor avenues creating fully integrated In context integration, focus on discussing trade-offs between sensing performance, cost, scalable guide readers toward designing new commercialization potential.

Language: Английский

Citations

41

Roadmap on electromagnetic metamaterials and metasurfaces DOI Creative Commons
Tie Jun Cui, Shuang Zhang, Andrea Alù

et al.

Journal of Physics Photonics, Journal Year: 2024, Volume and Issue: 6(3), P. 032502 - 032502

Published: Jan. 3, 2024

properties of the optical surface plasmons in microwave and terahertz frequencies using subwavelength artificial structures to construct negative permittivity.The spoof also benefit from realization ultrathin corrugated metallic strips [14], as they are compatible with printed circuit boards (PCBs) integrated technologies.Since propagating localized were experimentally realized PCBs 2013 2014 [14, 15], this area flourishes prospective applications emerging circuits, sensing, wireless communications [16]. Roadmap Organization AimIn Roadmap, leading experts various significant branches metamaterials metasurfaces present comprehensive overviews these anticipate their trends.The key areas research technology addressed roadmap include: 1. Effective medium metamaterials: In Section 2, Luo Lai firstly introduce effective theories for non-Hermitian 2.1.Wang, Lin, Chen review refraction 2.2; while Wu discuss perfect lens superlens based on 2.3.Then 2.4, Yin, Zhao, investigate advances transformation optics, which provides precise control EM fields an engineered physical space.In 2.5, Wegener introduces challenges recent three-dimensional metamaterials.In 2.6, Li, Zhou, Engheta extreme parameters, especially epsilon-near-zero (ENZ) that have exhibited potential applications.In 2.7, Asadchy, Simovski, Tretyakov chiral bianisotropic 2.8, Yang Zhang photonic topological metamaterials. Metasurfaces -Physics applications:In 3, Sun Zhou light-bending both transmission reflection configurations generalized Snell's law 3.1.In 3.2, Xu impact advanced fabrication technologies high-performance metasurfaces.Then 3.3, complexamplitude metasurfaces, been widely investigated beam forming, Airy Beam generation, meta-holograms.In 3.4, et al. metasurface-assisted polarization a new platform develop devices micrometer-scale footprint unusual functionality.The real application advantages metalens reviewed by Li Zhu 3.5.Zhou describe multi-functional edge imaging 3.6.In 3.7, holographic imaging, offer excellent tool realize 3.8, Xiao discusses active tuning functions after fabrication, highly desirable promising platforms 6G communications, remote radar 3.9, Liu focus introducing metasurface biosensors.In 3.10, geometric phase-controlled nonlinear Tang al., exhibiting great flexibilities controlling phase, polarization, amplitude generated waves.In 3.11, Koshelev Kivshar provide brief summary some observed effects metasurfaces.In 3.12, can act novel demonstrate marvelous effects.In 3.13, Wang, Tsai, overview applied quantum technologies, provided wide variety source state manipulation, information processing, quantumA c e p t d M n u s r i metasurface, i.e., reconfigurable intelligent surfaces massive MIMO transceivers, sensing. Concluding RemarksFrom roadmap, we glad see big progresses achieved ranging optics microwaves.After decades fast developments, not only EM-wave manipulations, but bring out disciplines sciences communication technologies.The future looks bright, there exciting opportunities ahead fundamental engineering applications.

Language: Английский

Citations

33

Pretreatment-free SERS sensing of microplastics using a self-attention-based neural network on hierarchically porous Ag foams DOI Creative Commons
Olga Guselnikova,

Andrii Trelin,

Yunqing Kang

et al.

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: May 28, 2024

Abstract Low-cost detection systems are needed for the identification of microplastics (MPs) in environmental samples. However, their rapid is hindered by need complex isolation and pre-treatment methods. This study describes a comprehensive sensing platform to identify MPs samples without requiring independent separation or protocols. It leverages physicochemical properties macroporous-mesoporous silver (Ag) substrates templated with self-assembled polymeric micelles concurrently separate analyze multiple MP targets using surface-enhanced Raman spectroscopy (SERS). The hydrophobic layer on Ag aids stabilizing nanostructures environment mitigates biofouling. To monitor demultiplex numerous overlapping patterns, we develop neural network (NN) algorithm called SpecATNet that employs self-attention mechanism resolve dependencies patterns SERS data six common types MPs: polystyrene, polyethylene, polymethylmethacrylate, polytetrafluoroethylene, nylon, polyethylene terephthalate. uses multi-label classification multi-component mixtures even presence various interference agents. combination self-attention-based NN technology holds potential enable field monitoring generating rich datasets machines can interpret analyze.

Language: Английский

Citations

29

Miniaturized spectrometer with intrinsic long-term image memory DOI Creative Commons
Gang Wu,

Mohamed Abid,

Mohamed Zerara

et al.

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: Jan. 23, 2024

Abstract Miniaturized spectrometers have great potential for use in portable optoelectronics and wearable sensors. However, current strategies miniaturization rely on von Neumann architectures, which separate the spectral sensing, storage, processing modules spatially, resulting high energy consumption limited speeds due to storage-wall problem. Here, we present a miniaturized spectrometer that utilizes single SnS 2 /ReSe van der Waals heterostructure, providing photodetection, spectrum reconstruction, imaging, long-term image memory, signal capabilities. Interface trap states are found induce gate-tunable wavelength-dependent photogating effect non-volatile optoelectronic memory effect. Our approach achieves footprint of 19 μm, bandwidth from 400 800 nm, resolution 5 > 10 4 s memory. single-detector computational represents path beyond architectures.

Language: Английский

Citations

27

Artificial Intelligence in Point-of-Care Biosensing: Challenges and Opportunities DOI Creative Commons
Connor D. Flynn, Dingran Chang

Diagnostics, Journal Year: 2024, Volume and Issue: 14(11), P. 1100 - 1100

Published: May 25, 2024

The integration of artificial intelligence (AI) into point-of-care (POC) biosensing has the potential to revolutionize diagnostic methodologies by offering rapid, accurate, and accessible health assessment directly at patient level. This review paper explores transformative impact AI technologies on POC biosensing, emphasizing recent computational advancements, ongoing challenges, future prospects in field. We provide an overview core their use POC, highlighting issues challenges that may be solved with AI. follow can applied including machine learning algorithms, neural networks, data processing frameworks facilitate real-time analytical decision-making. explore applications each stage biosensor development process, diverse opportunities beyond simple analysis procedures. include a thorough outstanding field AI-assisted focusing technical ethical regarding widespread adoption these technologies, such as security, algorithmic bias, regulatory compliance. Through this review, we aim emphasize role advancing inform researchers, clinicians, policymakers about reshaping global healthcare landscapes.

Language: Английский

Citations

24