Intelligent Sensor Research Articles

Physical and mental safety monitoring and protection of children with autism spectrum disorder: Intelligent clothing integrating early warning and rescue

Nowadays, the safety of special children has gradually become a hot spot of social concern. In this paper, aiming at the problems of autism spectrum disorder children who are easy to get lost and drown, intelligent monitoring clothing with lost warning and drowning rescue functions is designed. Firstly a clothing technology system based on multi-MCU and BeiDou dual-mode positioning was set up. Then according to their characteristics of physiology and psychology, CLO was used for virtual simulation design of color, pattern, and style of sample clothes. Finally, the product prototype of intelligent monitoring clothing was evaluated from various aspects. The results confirm that the clothing can meet the physical and psychological needs of these children. Its intelligent sensor positioning, data acquisition and transmission, and waterproof and rescue functions are designed accurately, which can not only play an early warning and protection role when children go beyond the fence and drown, but also reduce the monitoring burden of parents to a certain extent. This study also provides a reference for the design of intelligent monitoring clothing for special children.

FUNDAMENTAL ASPECTS OF METROLOGICAL SUPPORT IN IoT

The application of intelligent sensors, network technologies, and machine learning in IoT and industry is increas- ingly widespread as a part of the development and implementation of Industry 4.0, Industry 5.0, and Smart City. It is necessary to review the fundamental principles of metrological support for production. This includes calibration, estimation of measurement uncertainty, traceability, and processing of large data sets to reproduce and compare the results of measurements of physical quan- tities remotely. Modern smart sensors are cost-effective, which makes traditional sensor calibration methods increasingly uneco- nomical. The utilization of advanced networking technologies, along with machine learning, complicates the pre-processing of measured values. Therefore, new solutions are required when it comes to implementing digital metrology. In this article, a metrological framework for the full life cycle of measured data in IoT is presented. It ensures transparency, comparability, consistent quality and reliability of measured data, processing methods and results. The OPC-UA digital data com- munication standard is considered, which provides a single interface for exchanging digital data with devices from different manu- facturers or via different protocols. The syntax of a machine-readable representation of SI units and derived quantities as well as the structure of the sensor network metadata model are also described. Special emphasis is placed on dynamic calibration of sen- sors, determining measurement uncertainty in sensor networks, and implementing digital calibration certificates in IoT and industry.

DiamondNet: A Neural-Network-Based Heterogeneous Sensor Attentive Fusion for Human Activity Recognition.

With the proliferation of intelligent sensors integrated into mobile devices, fine-grained human activity recognition (HAR) based on lightweight sensors has emerged as a useful tool for personalized applications. Although shallow and deep learning algorithms have been proposed for HAR problems in the past decades, these methods have limited capability to exploit semantic features from multiple sensor types. To address this limitation, we propose a novel HAR framework, DiamondNet, which can create heterogeneous multisensor modalities, denoise, extract, and fuse features from a fresh perspective. In DiamondNet, we leverage multiple 1-D convolutional denoising autoencoders (1-D-CDAEs) to extract robust encoder features. We further introduce an attention-based graph convolutional network to construct new heterogeneous multisensor modalities, which adaptively exploit the potential relationship between different sensors. Moreover, the proposed attentive fusion subnet, which jointly employs a global-attention mechanism and shallow features, effectively calibrates different-level features of multiple sensor modalities. This approach amplifies informative features and provides a comprehensive and robust perception for HAR. The efficacy of the DiamondNet framework is validated on three public datasets. The experimental results demonstrate that our proposed DiamondNet outperforms other state-of-the-art baselines, achieving remarkable and consistent accuracy improvements. Overall, our work introduces a new perspective on HAR, leveraging the power of multiple sensor modalities and attention mechanisms to significantly improve the performance.

Reinforcement Learning for Intelligent Sensor Virtualization and Provisioning in Internet of Vehicles (IoV)

Reinforcement Learning for Intelligent Sensor Virtualization and Provisioning in Internet of Vehicles (IoV)

Multicolor vision perception of flexible optoelectronic synapse with high sensitivity for skin sunburn warning.

The development of flexible synaptic devices with multicolor signal response is important to exploit advanced artificial visual perception systems. The Sn vacancy-dominant memory and narrow gap characteristics of PEA2SnI4 make it suitable as a functional layer in ultraviolet-visible (UV-Vis) light-stimulated synaptic devices. However, such device tends to have high dark current and poor sensitivity, which is not conducive to subsequent information processing. Here, we proposed a self-powered flexible optoelectronic synapse based on PEA2SnI4 films. By introducing the electron transport layer (ETL), the dark current of the device is decreased by 5 orders of magnitude as compared to the Au/PEA2SnI4/ITO device, and the sensitivity is increased from 10.3% to 99.2% at 1.25 mW cm-2 light illumination (520 nm), indicating the vital role of the introduced ETL in promoting the separation of excitons in the interface and inhibiting the free carrier transfer. On this basis, the optoelectronic synaptic functions with integrated sensing, recognition, and memory features were realized. The array device exhibits UV-Vis light sensitivity and tunable synaptic plasticity, enabling its application for multicolor visual sensing and skin sunburn warning. This work provides an effective strategy for fabricating multicolor intelligent sensors and artificial vision systems, which facilitate the practical application of artificial optoelectronic synapses.

Cyber Granular-Enabled Intelligent Sensing for High Performance Flocking Control in Continuous Flat Pressing System

Cyber Granular-Enabled Intelligent Sensing for High Performance Flocking Control in Continuous Flat Pressing System

Retracted: A Study on Urban Spatial System Planning of Qingdao City Park Based on Intelligent Monitoring Sensors

Retracted: A Study on Urban Spatial System Planning of Qingdao City Park Based on Intelligent Monitoring Sensors

Diversified Teaching Strategies for College Swimming Courses in the Context of Artificial Intelligence

Abstract Swimming is a sport with a very significant exercise effect, so swimming courses in colleges and universities can promote the overall development of students’ physical fitness. In this paper, students’ swimming data are collected using intelligent sensors, and the collected data are noise-reduced and normalized by a low-pass filter. After the completion of data preprocessing, the swimming posture data features are extracted. The features are dimensionality reduced by the PCA method, combined with the BP neural network for training and accurate swimming posture recognition, and on this basis, a diversified teaching system for swimming courses in smart colleges and universities is constructed. After the students’ swimming data set was collected, the recognition effect of each swimming stroke was analyzed, and a comparison experiment was set up to investigate the practical effect and strategy of this teaching mode. The results show that the average accuracy of recognizing each stroke in this study can reach more than 0.988, and in the teaching test, the average difference between the performance of the experimental group and the control group is 7.6, and the P-value of the technical evaluation performance of the two groups of students in this project is 0.002<0.05, which significantly improves the swimming performance. This study can be combined with artificial intelligence technology to diversify the teaching of swimming courses in colleges and universities.

Realization of Vitality Optimization in Traditional Village Human Settlement Environment Supported by Intelligent Sensor Technology

The vitality of traditional villages (VTV) is a reference indicator for measuring the hollowing out of traditional villages. Human settlements in the world are based on the access and availability to the chief vitality factors of the geographical region. The traditional villages of China are the potential candidates for improving vitality optimization, as their development is still in the stage of infancy. This work proposes a framework that integrates complex subsystems of the traditional village human settlements with the vitality factors. The issues in these traditional villages are analyzed under the umbrella of social life, domestic life and agriculture, which is the primary occupation of people in traditional villages. Further, the work identifies the contemporary computing technologies and communication technologies used in various applications of intelligent sensor technology. This work associates the various subsystems of the villages, namely strategic, social, economic, resource and environment subsystem, and information subsystem, with the factors influencing dimensions of development, namely resources, service chain, sustainability, technology and institution. This framework can be further extended to include more elements of vitality factors.

(Invited) Wearable Intelligent Sensors and Electronic (WISE)- Problem, Progress and Perspective

Artificial intelligence (AI) and wearable sensors are crucial in achieving the goal of precision medicine, which is to customize the best treatment for each individual patient. The recent combination of these two fields is improving patient data acquisition and the design of wearable sensors for monitoring health, fitness, and surroundings. Wearable sensors aim to address the limitations of centralized and reactive healthcare by providing individuals with insight into their own physiology. However, the relationship between disease and therapeutic platforms is very complex, making it difficult to analyze their output. Integrating AI can bridge this gap by using pattern analysis and classification algorithms to improve diagnostic and therapeutic accuracy. The future of AI-biosensors (such as AI wearable sweat biosensors, AI ingestible biosensors, AI glass biosensors, AI implantable biosensors, etc.) will mainly focus on AI diagnosis (where the diagnostic algorithm in the microprocessor can verify the sensor output and present diagnostic information), big data processing (using self-contained space for historical data and various necessary parameters of data storage, significantly improving the controller's performance), and self-learning/adaptation (embedded microprocessors with advanced programming functions, allowing the AI-biosensor to reconstruct the structure and parameters according to certain behavioral criteria and have adaptive functions).

Research on electric energy measurement system based on intelligent sensor data in artificial intelligence environment

Abstract Electric power resources are the core energy for a country’s economic development and growth. China is at the peak of electric energy consumption at this stage. Improving the accuracy and integrity of electric energy metering technology is of great significance for evaluating the use and consumption of resources in China. Under the background of artificial intelligence, this research analyzes and studies the integrated module, demand status, performance optimization, and coupling degree of the electric energy metering system (hereinafter referred to as EES) through the application of two different types of sensors. The results show that the application of intelligent sensors has a better integration effect with the system management of electric energy metering, which plays a very important role in promoting the sustainable development of automation and informatization of the EES.

Design and Application of SPOC Hybrid Teaching for College Basketball Teaching Based on Artificial Intelligence Technology

Abstract Students love basketball, but traditional teaching approaches are no longer able to suit their demands. In this article, artificial intelligence is combined with innovative teaching methods to create a new type of learning. Firstly, under the SPOC teaching mode, intelligent sensors are used to collect basketball sports data, and Kalman filtering is used for processing and segmentation. Then, through the definition of basketball sports gesture, the data division of basketball sports gesture, designing the basketball sports gesture feature extraction method based on unit division, and using the SVM method to analyze the basketball sports gesture features, designing intelligent SPOC hybrid basketball teaching. Finally, the experiments on data collection and motion attitude resolution in basketball are designed to investigate the effects of intelligent SPOC hybrid basketball teaching. The results show that the deviations of the collected acceleration and angular velocity are within 10−2 orders of magnitude and 1.8°/s deviation, respectively, and the average recognition effect of various basketball postures is 0.925, which is able to effectively carry out basketball motion recognition. The experimental class 1’s physical quality improved by roughly seven after the teaching application was implemented, and the P-value for the improvement of different basketball sports was less than 0.05, indicating that the planned instruction can greatly enhance students’ physical quality and basketball abilities.

A POM/viologen-based supramolecular fluorescent probe for Ag+ detection and application of visible hydrogel based intelligent sensing system

Silver (Ag+) as a typical heavy metal ion has significant impacts on human health, so monitoring Ag+ level is an important issue. In this work, a new POM (polyoxometalates)/viologen-based supramolecular compound, [(HMSBP)2(γ-Mo8O26)]·4H2O (1) has been synthesized by hydrothermal method (MSBP = 1-(4-Methanesulfonyl-benzyl)-[4,4']bipyridinyl-1-ium). This POM/viologen-based supramolecular compound exhibits the unique supramolecular structure, excellent optical stability and superior fluorescence intensity, which is expected to become a promising fluorescent sensor. The coordination reaction between SO, pyridine N atom and Ag+ in compound 1 makes the detection of Ag+ achieved and the limit of detection (LOD) is 0.0411 μM in the range of 0.1–3 μM. Moreover, this supramolecular fluorescent probe has successfully realized the quantitative monitoring of Ag+ concentration in environmental water samples and commercially available disinfectant spray. Viologen is regarded as a good external stimulus responsive material, while its discoloration behavior can be exploited as an intelligent sensor system. The platform based on hydrogel and smartphones realizes the visualization and real-time quantification of Ag+, which provides an effective way for the rapid and convenient determination of Ag+. This provides a feasible way to promote the qualitative/semi quantitative detection of visual fluorescence POM/viologen sensors.

BLIND: A privacy preserving truth discovery system for mobile crowdsensing

Nowadays, an increasing number of applications exploit users who act as intelligent sensors and can quickly provide high-level information. These users generate valuable data that, if mishandled, could potentially reveal sensitive information. Protecting user privacy is thus of paramount importance for crowdsensing systems. In this paper, we propose BLIND, an innovative open-source truth discovery system designed to improve the quality of information (QoI) through the use of privacy-preserving computation techniques in mobile crowdsensing scenarios. The uniqueness of BLIND lies in its ability to preserve user privacy by ensuring that none of the parties involved are able to identify the source of the information provided. The system uses homomorphic encryption to implement a novel privacy-preserving version of the well-known K-Means clustering algorithm, which directly groups encrypted user data. Outliers are then removed privately without revealing any useful information to the parties involved. We extensively evaluate the proposed system for both server-side and client-side scalability, as well as truth discovery accuracy, using a real-world dataset and a synthetic one, to test the system under challenging conditions. Comparisons with four state-of-the-art approaches show that BLIND optimizes QoI by effectively mitigating the impact of four different security attacks, with higher accuracy and lower communication overhead than its competitors. With the optimizations proposed in this paper, BLIND is up to three times faster than the baseline system, and the obtained Root Mean Squared Error (RMSE) values are up to 42% lower than other state-of-the-art approaches.

CVII: Enhancing Interpretability in Intelligent Sensor Systems via Computer Vision Interpretability Index.

In the realm of intelligent sensor systems, the dependence on Artificial Intelligence (AI) applications has heightened the importance of interpretability. This is particularly critical for opaque models such as Deep Neural Networks (DNN), as understanding their decisions is essential, not only for ethical and regulatory compliance, but also for fostering trust in AI-driven outcomes. This paper introduces the novel concept of a Computer Vision Interpretability Index (CVII). The CVII framework is designed to emulate human cognitive processes, specifically in tasks related to vision. It addresses the intricate challenge of quantifying interpretability, a task that is inherently subjective and varies across domains. The CVII is rigorously evaluated using a range of computer vision models applied to the COCO (Common Objects in Context) dataset, a widely recognized benchmark in the field. The findings established a robust correlation between image interpretability, model selection, and CVII scores. This research makes a substantial contribution to enhancing interpretability for human comprehension, as well as within intelligent sensor applications. By promoting transparency and reliability in AI-driven decision-making, the CVII framework empowers its stakeholders to effectively harness the full potential of AI technologies.

Model-Based Approach for Leak Detection and Localization in Water Distribution Networks: A Literature Survey

Water loss poses a significant problem for water utilities and has received a lot of attention. To fulfill the increasing global demand for water, water supply system operations must be streamlined, making leak detection and location crucial. Water utilities have developed a number of techniques over time for finding leaks in water distribution networks (WDNs). These methodologies range from simple visual inspection to the use of hardware systems and now software using models and algorithms. Data from flow or pressure measurements, which are required for the analysis of water networks, is becoming more readily available with the introduction of intelligent sensor devices. Along with the introduction of geographic information systems (GIS) and supervisory control and data acquisition (SCADA) in the water sector, the deployment of model-driven methodologies for leak detection and localization has found extensive use. This paper aims to provide a concise introductory reference for early researchers in the development of a model-based approach for leak detection in WDNs. Thus, a survey of model-based approaches is presented, along with current research trends and applications of model-driven methodologies for leak detection in water supply networks. Several model-driven approaches and research studies for each case are discussed. Some challenges and research gaps are also discussed.

Progress of rapid detection of pesticides in fruits and vegetables

Pesticide residues in fruits and vegetables present a significant concern for human health and safety. By 2022, an average of 3 million people worldwide is poisoned by pesticides every year, and the mortality rate can reach about 20%. This comprehensive review summarizes recent research on the detection of pesticide residues, focusing on the main detection methods and their implications. The study highlights the growing importance of biosensors as a prominent technique, offering enhanced efficiency and accuracy in pesticide residue analysis. The review addresses the challenges associated with pretreatment methods and discusses the advantages and limitations of biosensors. Furthermore, it emphasizes the need for further research to optimize the adaptive capabilities of biosensors, particularly their anti-interference abilities. The findings underscore the significance of developing intelligent adaptive sensors for on-site pesticide residue detection, eliminating the need for complex sample pretreatment. This comprehensive review serves as a valuable reference, facilitating future advancements in pesticide residue analysis, ensuring food safety, and safeguarding consumer health in modern agriculture.

Metal-organic framework integrated hydrogel bioreactor for smart detection of metal ions

Bioreactors with environment responsiveness for smart detection has attracted widespread interest. Bioreactors that operate in liquid have excellent reaction speed and sensitivity, and those that operate at a solid interface have unique portability and stability. However, bioreactors that can simultaneously take advantage of both properties are still limited. Here, we developed a metal-organic framework (MOF) integrated hydrogel bioreactor that can accommodate both solid and liquid properties by using a hydrogel as a quasi-liquid medium. To enhance the stability and intelligence of the hydrogel bioreactor, we have opted for the utilization of europium metal-organic framework (Eu-MOF) as the optical output to withstand long-term storage challenges, and DNA as the highly programmable substance for intelligent target response. On this basis, smart detection of metal ions and biological micro-molecules have been achieved. Notably, this quasi-liquid hydrogel bioreactor has effectively tackled the intrinsic issues of inadequate dispersion stability of Eu-MOF in liquid systems and poor stability of DNA against environmental interference. Moreover, this MOF integrated hydrogel bioreactor has been applied to the construction of a portable hydrogel bioreactor, which enables platform-free and arrayed target detection via a smartphone, providing a new perspective for further promoting the application of quasi-liquid hydrogel bioreactors and intelligent nanobiological sensors.

Imaging spectroscopy for monitoring the crop status of tomato plants

The increasing complexity of greenhouse production systems requires the step to a more data-driven approach that is based on robust, intelligent sensors. Whereas climate sensors are widely available in greenhouse systems, control based on crop data is still in its infancy. There is a clear need among growers to monitor the status of the crop in the greenhouse in real time and non-destructively compared to current practice of cumbersome, expensive and slow laboratory measurements. This project aimed to use visible and near infrared imaging spectroscopy to determine the contents of sugars and starch, dry matter percentage, chlorophyll, and nutrient composition in both leaves and fruits of tomato plants. The results were promising, with Q2 values up to 0.97 for dry matter content in leaves, 0.86 for sugar and 0.99 for chlorophyll-a. The results also showed that pigments have a better correlation to the visible spectrum, while water content, sugars and nutrients showed a better correlation in the near infrared part of the spectrum.

Simultaneously Intelligent Sensing and Beamforming Based on an Adaptive Information Metasurface.

Due to its ability to adapt to a variety of electromagnetic (EM) environments, the sensing-enabled metasurface has garnered significant attention. However, large-scale EM-field sensing to obtain more information is still very challenging. Here, an adaptive information metasurface is proposed to enable intelligent sensing and wave manipulating simultaneously or more specifically, to realize intelligent target localization and beam tracking adaptively. The metasurface is composed of an array of meta-atoms, and each is loaded with two PIN diodes and a sensing-channel structure, for polarization-insensitive and programmable beamforming and sensing. By controlling the state of the PIN diode, the proposed meta-atom has 1-bit phase response in the designed frequency band, while the sensing loss keeps higher than -10dB for both "ON" and "OFF" states. Hence there is nearly no interaction between the beamforming and sensing modes. Experiments are conducted to show multiple functions of the metasurface, including intelligent target sensing and self-adaptive beamforming, and the measured results are in good agreement with the numerical simulations and theoretical calculations.