Self-powered sensing systems with learning capability DOI Creative Commons
Avinash Alagumalai, Wan Shou, Omid Mahian

et al.

Joule, Journal Year: 2022, Volume and Issue: 6(7), P. 1475 - 1500

Published: June 20, 2022

Language: Английский

Artificial Intelligence of Things (AIoT) Enabled Floor Monitoring System for Smart Home Applications DOI
Qiongfeng Shi, Zixuan Zhang, Yanqin Yang

et al.

ACS Nano, Journal Year: 2021, Volume and Issue: 15(11), P. 18312 - 18326

Published: Nov. 1, 2021

To enable smart homes and relative applications, the floor monitoring system with embedded triboelectric sensors has been proven as an effective paradigm to capture ample sensory information from our daily activities, without camera-associated privacy concerns. Yet inherent limitations of such high susceptibility humidity long-term stability remain a great challenge develop reliable system. Here we robust through synergistic integration highly coding mats deep-learning-assisted data analytics. Two quaternary electrodes are configured, their outputs normalized respect reference electrode, leading stable detection that is not affected by ambient parameters operation manners. Besides, due universal electrode pattern design, all can be screen-printed only one mask, rendering higher facileness cost-effectiveness. Then distinctive implemented each mat external wiring, which permits parallel-array connection minimize output terminals complexity. Further integrating analytics, realized for various home interactions, including position/trajectory tracking, identity recognition, automatic controls. Hence, developed low-cost, large-area, reliable, shows promising advancement sensing technology in applications.

Language: Английский

Citations

126

Artificial Intelligence-Enabled Caregiving Walking Stick Powered by Ultra-Low-Frequency Human Motion DOI
Xinge Guo, Tianyiyi He, Zixuan Zhang

et al.

ACS Nano, Journal Year: 2021, Volume and Issue: 15(12), P. 19054 - 19069

Published: July 26, 2021

The increasing population of the elderly and motion-impaired people brings a huge challenge to our social system. However, walking stick as their essential tool has rarely been investigated into its potential capabilities beyond basic physical support, such activity monitoring, tracing, accident alert. Here, we report powered by ultra-low-frequency human motion equipped with deep-learning-enabled advanced sensing features provide healthcare-monitoring platform for users. A linear-to-rotary structure is designed achieve highly efficient energy harvesting from linear ultralow frequency. Besides, two kinds self-powered triboelectric sensors are proposed integrated extract stick. Augmented functionalities high accuracies have enabled deep-learning-based data analysis, including identity recognition, disability evaluation, status distinguishing. Furthermore, self-sustainable Internet Things (IoT) system global positioning tracing environmental temperature humidity amenity functions obtained. Combined aforementioned functionalities, this demonstrated in various usage scenarios caregiver real-time well-being monitoring. caregiving shows being an intelligent aid users help them live life adequate autonomy safety.

Language: Английский

Citations

125

A flexible triboelectric tactile sensor for simultaneous material and texture recognition DOI
Ziwu Song,

Jihong Yin,

Zihan Wang

et al.

Nano Energy, Journal Year: 2021, Volume and Issue: 93, P. 106798 - 106798

Published: Dec. 7, 2021

Language: Английский

Citations

117

Analysis of the Challenges of Artificial Intelligence of Things (AIoT) for the Smart Supply Chain (Case Study: FMCG Industries) DOI Creative Commons
Hamed Nozari, Agnieszka Szmelter-Jarosz, Javid Ghahremani-Nahr

et al.

Sensors, Journal Year: 2022, Volume and Issue: 22(8), P. 2931 - 2931

Published: April 11, 2022

In today's competitive world, supply chain management is one of the fundamental issues facing businesses that affects all an organization's activities to produce products and provide services needed by customers. The technological revolution in logistics experiencing a significant wave new innovations challenges. Despite current fast digital technologies, customers expect ordering delivery process be faster, as result, this has made it easier more efficient for organizations looking implement technologies. "Artificial Intelligence Things (AIoT)", which means using Internet perform intelligent tasks with help artificial intelligence integration, these expected can turn complex into integrated process. AIoT such data sensors RFID (radio detection technology), power analysis, information features tracking instant alerts improve decision making. Such become vital operations tasks. However, same evolving technology presence huge amount pose many challenges factors involved. study, conducting literature review interviewing experts active FMCG industries available case most important AIoT-powered were extracted. By examining nonlinear quantitative importance was examined their causal relationships identified. results showed cybersecurity lack proper infrastructure are AIoT-based chain.

Language: Английский

Citations

112

A Motion Capturing and Energy Harvesting Hybridized Lower‐Limb System for Rehabilitation and Sports Applications DOI Creative Commons
Shan Gao, Tianyiyi He, Zixuan Zhang

et al.

Advanced Science, Journal Year: 2021, Volume and Issue: 8(20)

Published: Aug. 19, 2021

Lower-limb motion monitoring is highly desired in various application scenarios ranging from rehabilitation to sports training. However, there still lacks a cost-effective, energy-saving, and computational complexity-reducing solution for this specific demand. Here, capturing energy harvesting hybridized lower-limb (MC-EH-HL) system with 3D printing demonstrated. It enables low-frequency biomechanical sliding block-rail piezoelectric generator (S-PEG) sensing ratchet-based triboelectric nanogenerator (R-TENG). A unique S-PEG proposed particularly designed mechanical structures convert into 1D linear on the rail. On one hand, high output power achieved working at very low frequency, which realizes self-sustainable systems wireless under Internet of Things framework. other R-TENG gives rise digitalized output, matching rotation angles pulse numbers. Additional physical parameters can be estimated enrich sensory dimension. Accordingly, demonstrative rehabilitation, human-machine interfacing virtual reality, are presented. This developed exhibits an economic energy-efficient support need tracking scenarios, paving way multidimensional near future.

Language: Английский

Citations

110

Recent Progress in the Energy Harvesting Technology—From Self-Powered Sensors to Self-Sustained IoT, and New Applications DOI Creative Commons
Long Liu, Xinge Guo, Weixin Liu

et al.

Nanomaterials, Journal Year: 2021, Volume and Issue: 11(11), P. 2975 - 2975

Published: Nov. 5, 2021

With the fast development of energy harvesting technology, micro-nano or scale-up harvesters have been proposed to allow sensors internet things (IoT) applications with self-powered self-sustained capabilities. Facilitation within smart homes, manipulators in industries and monitoring systems natural settings are all moving toward intellectually adaptable energy-saving advances by converting distributed energies across diverse situations. The updated developments major powered improved highlighted this review. To begin, we study evolution technologies from fundamentals various materials. Secondly, IoT discussed regarding current strategies for sensing. Third, subdivided classifications investigate typical new gas sensing, human monitoring, robotics, transportation, blue energy, aircraft, aerospace. Lastly, prospects cities 5G era summarized, along research application directions that emerged.

Language: Английский

Citations

107

Artificial intelligence enhanced sensors - enabling technologies to next-generation healthcare and biomedical platform DOI Creative Commons
Chan Wang, Tianyiyi He, Hong Zhou

et al.

Bioelectronic Medicine, Journal Year: 2023, Volume and Issue: 9(1)

Published: Aug. 2, 2023

The fourth industrial revolution has led to the development and application of health monitoring sensors that are characterized by digitalization intelligence. These have extensive applications in medical care, personal management, elderly sports, other fields, providing people with more convenient real-time services. However, these face limitations such as noise drift, difficulty extracting useful information from large amounts data, lack feedback or control signals. artificial intelligence provided powerful tools algorithms for data processing analysis, enabling intelligent monitoring, achieving high-precision predictions decisions. By integrating Internet Things, intelligence, sensors, it becomes possible realize a closed-loop system functions collection, online diagnosis, treatment recommendations. This review focuses on healthcare enhanced technologies aspects materials, device structure, integration, scenarios. Specifically, this first introduces great advances wearable respiration rate, heart pulse, sweat, tears; implantable cardiovascular nerve signal acquisition, neurotransmitter monitoring; soft electronics precise therapy. Then, recent volatile organic compound detection highlighted. Next, current developments human-machine interfaces, AI-enhanced multimode self-sustainable systems reviewed. Last, perspective future directions further research is also provided. In summary, fusion will provide intelligent, convenient, secure services next-generation biomedical applications.

Language: Английский

Citations

98

Machine Learning-Enhanced Flexible Mechanical Sensing DOI Creative Commons
Yuejiao Wang, Mukhtar Lawan Adam, Yunlong Zhao

et al.

Nano-Micro Letters, Journal Year: 2023, Volume and Issue: 15(1)

Published: Feb. 17, 2023

To realize a hyperconnected smart society with high productivity, advances in flexible sensing technology are highly needed. Nowadays, has witnessed improvements both the hardware performances of sensor devices and data processing capabilities device's software. Significant research efforts have been devoted to improving materials, mechanism, configurations systems quest fulfill requirements future technology. Meanwhile, advanced analysis methods being developed extract useful information from increasingly complicated collected by single or network sensors. Machine learning (ML) as an important branch artificial intelligence can efficiently handle such complex data, which be multi-dimensional multi-faceted, thus providing powerful tool for easy interpretation data. In this review, fundamental working mechanisms common types mechanical sensors firstly presented. Then how ML-assisted improves applications other closely-related various areas is elaborated, includes health monitoring, human-machine interfaces, object/surface recognition, pressure prediction, human posture/motion identification. Finally, advantages, challenges, perspectives associated fusion ML algorithms discussed. These will give significant insights enable advancement next-generation sensing.

Language: Английский

Citations

91

Machine-Learning-Assisted Recognition on Bioinspired Soft Sensor Arrays DOI
Yang Luo, Xiao Xiao, Jun Chen

et al.

ACS Nano, Journal Year: 2022, Volume and Issue: 16(4), P. 6734 - 6743

Published: March 24, 2022

Soft interfaces with self-sensing capabilities play an essential role in environment awareness and reaction. The growing overlap between materials sensory systems has created a myriad of challenges for sensor integration, including the design multimodal sensory, simplified system capable high spatiotemporal sensing resolution efficient processing methods. Here we report bioinspired soft array (BOSSA) that integrates pressure material based on triboelectric effect. Cascaded row + column electrodes embedded low-modulus porous silicone rubber allow rich information to be captured from further analyzed by data-driven algorithms (multilayer perceptrons) extract higher level features. BOSSA demonstrates ability identify 10 users (98.9%) placement or extraction objects (98.6%). Moreover, its scalable fabrication facilitates large-area arrays abilities yet less complex architecture. These features may promising development immersive networks intelligent monitoring stimuli response smart home/industry applications.

Language: Английский

Citations

88

Triboelectric nanogenerator as next-generation self-powered sensor for cooperative vehicle-infrastructure system DOI

Yafeng Pang,

Xingyi Zhu, Chengkuo Lee

et al.

Nano Energy, Journal Year: 2022, Volume and Issue: 97, P. 107219 - 107219

Published: March 31, 2022

Language: Английский

Citations

85