Showing papers on "Intelligent sensor published in 2019"

Deep Learning for Reliable Mobile Edge Analytics in Intelligent Transportation Systems: An Overview

Abstract: Intelligent transportation systems (ITSs) will be a major component of tomorrow's smart cities. However, realizing the true potential of ITSs requires ultralow latency and reliable data analytics solutions that combine, in real time, a heterogeneous mix of data stemming from the ITS network and its environment. Such data analytics capabilities cannot be provided by conventional cloud-centric data processing techniques whose communication and computing latency can be high. Instead, edge-centric solutions that are tailored to the unique ITS environment must be developed. In this article, an edge analytics architecture for ITSs is introduced in which data is processed at the vehicle or roadside smart sensor level to overcome the ITS's latency and reliability challenges. With a higher capability of passengers' mobile devices and intravehicle processors, such a distributed edge computing architecture leverages deep-learning techniques for reliable mobile sensing in ITSs. In this context, the ITS mobile edge analytics challenges pertaining to heterogeneous data, autonomous control, vehicular platoon control, and cyberphysical security are investigated. Then, different deep-learning solutions for such challenges are revealed. The discussed deep-learning solutions enable ITS edge analytics by endowing the ITS devices with powerful computer vision and signal processing functions. Preliminary results show that the introduced edge analytics architecture, coupled with the power of deep-learning algorithms, provides a reliable, secure, and truly smart transportation environment.

IoT enabled intelligent sensor node for smart city: pedestrian counting and ambient monitoring

Abstract: An Internet of Things (IoT) enabled intelligent sensor node has been designed and developed for smart city applications. The fabricated sensor nodes count the number of pedestrians, their direction of travel along with some ambient parameters. The Field of View (FoV) of Fresnel lens of commercially available passive infrared (PIR) sensors has been specially tuned to monitor the movements of only humans and no other domestic animals such as dogs, cats etc. The ambient parameters include temperature, humidity, pressure, Carbon di Oxide (CO2) and total volatile organic component (TVOC). The monitored data are uploaded to the Internet server through the Long Range Wide Area Network (LoRaWAN) communication system. An intelligent algorithm has been developed to achieve an accuracy of 95% for the pedestrian count. There are a total of 74 sensor nodes that have been installed around Macquarie University and continued working for the last six months.

Using Compact Evolutionary Tabu Search algorithm for matching sensor ontologies

Abstract: To implement the semantic interoperability among intelligent sensor applications, it is necessary to match the identical entities across the sensor ontologies. Since sensor ontology matching problem requires matching thousands of sensor concepts and has many local optimal solutions, Evolutionary Algorithm (EA) becomes the state-of-the-art methodology for solving it. However, the premature convergence and long runtime are two drawbacks which make EA-based sensor ontology matchers incapable of effectively searching the optimal solution for sensor ontology matching problem. To improve the efficiency of EA-based sensor ontology matching technique, in this paper, a new optimal model of sensor ontology matching problem is first constructed, a novel sensor concept similarity measure is then presented to determine the identical sensor concepts, and finally, a problem-specific Compact Evolutionary Tabu Search algorithm (CETS) is presented to efficiently determine the sensor ontology alignment. In particular, CETS combines Compact Evolutionary Algorithm (global search) and Tabu Search algorithm (local search), and this marriage between global search and local search allows keeping high solution diversity via PV (reducing the possibility of the premature convergence) and increasing the convergence speed via the local search (reducing the runtime). The experimental results show that comparing with the state-of-the-art sensor ontology matching techniques, CETS can more efficiently determine the high-quality alignments.

Sensor Installation and Retrieval Operations Using an Unmanned Aerial Manipulator

Abstract: A wide range of applications for which unmanned aerial vehicles (UAVs) are ideally suited rely on the development of manipulators capable of exchanging forces with the environment. One such application is the installation and retrieval of intelligent sensors for monitoring wide-spread areas and locations that are difficult to access by any other means. Within this letter, we report on both indoor and outdoor flights tests of a novel force controlled lightweight compliant manipulator that allows a UAV to carry out this type of task. Installation and retrieval are both demonstrated with different scenarios, indoors and outdoors. Key results include interaction forces up to 22 N exerted by a small-sized multirotor, placement and retrieval operations carried out on flat as well as cylindrical surfaces, and an analysis of the overall system. The results of multiple flight experiments clearly demonstrate the potential of this approach for the deployment of sensors and other force-related tasks.

Smart Sensors: Analysis of Different Types of IoT Sensors

Abstract: Internet of Things (IoT) is a revolutionary technology. It is revolutionizing our world with trillions of sensors and actuators by creating a smart environment around us. In scientific research, sensors are considered as a prospective field. Ubiquitous sensing abilities offer shared information to develop a common operating picture. IoT sensors are efficiently used in various IoT applications for creating a smart environment. This paper presents several IoT sensors and also explains various sensor based IoT applications. Furthermore, after analyzing different sensor applications, this article enlightens which IoT application requires which type of sensor. In the future, this work will serve as the basis for further research work in the related area.

Recent Advances in Multifunctional Sensing Technology on a Perspective of Multi-Sensor System: A Review

Abstract: Due to rapid advancement in technology, recently a significant amount of work has been carried out in the field of multi-mode sensor and multifunctional sensor. A single unit of multifunctional sensor provides multiple measurements, which eventually reduces the cost of multiple sensors and makes the system compact. Though the risk of sensor failure and reliability of the multifunctional sensor is always imminent, researchers are working out different methods to make the sensor fault tolerant. Multifunctional sensors are getting widespread acceptance in a variety of fields. This paper provides a review of recent advances in multifunctional sensor technology in the perspective of a multi-sensor system. Different aspects of design and implementation of multifunctional sensor technology have been addressed in this paper. This paper can serve as a basic reading material for students and researchers pursuing research on a multifunctional sensor.

Distributed Sensing Using Smart End-User Devices: Pathway to Federated Learning for Autonomous IoT

Abstract: There is a dearth of research in developing low-cost solutions for distributed decision making in IoT networks. Most studies in the literature require the deployment of additional sensors for data collection. In this study, we propose to leverage available sensors built-in smartphones, to properly collect and broadcast data for different decision-making purposes in smart cities infrastructures, for example, intelligent transportation networks, smart health services, security and emergencies, industrial control, smart agriculture, home automation and so on. To this end, we first introduce our new platform (including software and mobile app implementation) to identify available sensors at each end-user device. We have identified a wide range of sensors including gyroscope, ambient light sensor, temperature, magnetic field sensor, orientation sensor, game rotation vector, linear acceleration, relative humidity, gravity, geomagnetic rotation vector, etc. As the sensors are already integrated within the phone, therefore, using these sensors can be beneficial considering the complexity, efficiency, and cost of the overall system. The challenge is to design a system that can trigger distributed devices to be self-activated and agreed to generate all available sensors data. Besides, as devices can send a continuous stream of data, therefore, size of data could be mounted and could be in the haphazard structure, which would give us hurdles to identify a device sensor data from another and to make an intelligent decision. To tackle all of these, we propose a distributed sensing approach that is capable to identify a device using token, can activate distributed end-user devices to send data to the cloud whenever it requires and store data in the cloud server maintaining proper format. This approach enables remote data collection leveraging available end-user devices and reduces the cost of installing new sensors for autonomous IoT applications. We then build on our efficient sensing platform to enable distributed intelligence among a network of smart devices. To this end, we leverage the computational capacity of these devices for local decision making, i.e., instead of broadcasting all sensing information to a centralized agent and solve a large-scale decision-making problem, each smart device communicates with a limited set of neighboring devices. This will also pave the way for implementing federated learning as a promising solution for distributed decision making.

Overview of Spintronic Sensors With Internet of Things for Smart Living

Abstract: Smart living is a trending and connected lifestyle that envisions efficient and sustainable energy utilization, stable and reliable power supply, intelligent and coordinated transportation and mobility, and personalized and cost-effective healthcare. Its realization needs the Internet of Things (IoT). IoT is a compelling platform connecting trillions of sensors and collecting data for connectivity and analytics. It is more advanced than traditional monitoring systems where limited sensors and wired communication can merely collect fragmented data in the application domains. Spintronic sensors with the superb measuring ability and multiple unique advantages can be one of the critical sensing devices supporting the IoT and enabling smart living. In this paper, we review successful applications of individual spintronic sensors in electrical current sensing, transmission and distribution lines monitoring, vehicle detection, and biodetection that can help to fulfill the promises of smart living in energy management, power delivery, transport, and healthcare. The wireless spintronic sensor networks (WSSNs) working at the massive interconnected network level are proposed and illustrated to provide pervasive monitoring systems, which facilitate the intelligent surveillance and management over building, power grid, transport, and healthcare. The database of collected information will be of great use to policy making in public services and city planning. This paper provides insights for realizing smart living through the integration of IoT with spintronic sensor technology.

A Smart Insect Pest Detection Technique With Qualified Underground Wireless Sensor Nodes for Precision Agriculture

Abstract: Wireless underground sensor networks are the new area of research. It is widely used in many engineering applications, from smart irrigation to security and precision agriculture. Some of the application areas of wireless underground sensor networks are underground with space, such as tunnel, cave, and so on, while some consist of no spaced underground solid areas as well. In this context, wireless underground sensor networks have recently become very important for precision agriculture purposes. In this paper, a smart insect pest detection technique with qualified underground wireless sensor nodes for precision agriculture has been investigated with a mathematical simulation model. In a simulated smart technique, insect pest detection is assumed to be carried out with a qualified acoustic sensor. In order to evaluate the performance of the underground network structure, the received signal strength and path loss parameters are examined. As the depth distance increases, the increase in path loss of communication has been revealed. The obtained performance evaluation result reveals the need for signal transmission with different transmitter power for depth-based communication in wireless underground sensor networks.

A Review of Semantic Sensor Technologies in Internet of Things Architectures

Abstract: Intelligent sensors should be seamlessly, securely, and trustworthy interconnected to enable automated high-level smart applications. Semantic metadata can provide contextual information to support the accessibility of these features, making it easier for machines and humans to process the sensory data and achieve interoperability. The unique overview of sensor ontologies according to the semantic needs of the layers of IoT solutions can serve a guideline of engineers and researchers interested in the development of intelligent sensor-based solutions. The explored trends show that ontologies will play an even more essential role in interlinked IoT systems as interoperability and the generation of controlled linkable data sources should be based on semantically enriched sensory data.

Green Cognitive Body Sensor Network: Architecture, Energy Harvesting, and Smart Clothing-Based Applications

Abstract: The human-centered body sensor network (BSN) becomes one of the Internet of Things (IoT) development directions in the future due to interdisciplinary advantages in the fields of wireless communication technology, embedded microelectronic technology, and mobile Internet technology Only depending on the terminal perception and transmission technology is not enough to make up the weak data storage, computing, and analysis capacity Thus, in combination with green sensors, smart clouds computing, artificial intelligence technology, and BSN, this paper proposes a concept of green cognitive BSN (Green-CBSN) Starting from the three aspects including green active sensor, energy harvesting and efficient data collection, and health big data recognition and interaction, this paper introduces the architecture and thought of Green-CBSN in detail Then, we invite some volunteers equipped with wearable devices, such as smart clothing and smartphone, and carry out the physiological signal collection, heart rate monitoring, and physiological data emotion analysis experiments of electrocardiograph and photoplethysmography At last, this paper summarizes the open issues and research directions about IoT security, health big data recognition algorithm optimization, and energy saving and green energy harvesting, to provide the reference for Green-CBSN

Integration of Wireless Sensor Networks and Smart UAVs for Precision Viticulture

Abstract: Precision viticulture (PV) aims to improve the grapevine production efficiency, quality, and profitability, while reducing the environmental impact. The promises of PV are realized only if large areas are monitored with high spatial and temporal resolutions. This paper considers the integration of a wireless sensor network and a smart unmanned aerial vehicle platform. To this end, local variations of factors that influence grape yield and quality are measured and site-specific management practices are applied. This approach achieves real-time, uninterrupted monitoring of the vine growth environment, and on-demand imaging and high-resolution data collection from any specific location, thereby optimizing the production efficiencies and the application of inputs in a cost-effective way.

Smart Sensor: SoC Architecture for the Industrial Internet of Things

Abstract: Nowadays, the concept of intelligent manufacturing is being introduced, based on the integration of new advanced technologies, such as the Internet of Things (IoT), distributed control, data analysis, and cyber-security in the manufacturing area, with the aim of improving manufacturing processes and the articles produced. In this sense, new intelligent devices (Smart Sensors) should be developed that integrate several detection methods (sensors), real-time (RT) data analysis, and wired and/or wireless connectivity. The main contribution of this paper is the design, implementation, and experimental verification of an architecture of a Smart Sensor that satisfies the operational requirements needed by the Industrial IoT (IIoT). Considering the software and hardware adaptability that a Smart Sensor should have, this paper takes advantage of the characteristics of the current field programmable gate arrays (FPGAs) and SoC to implement a Smart Sensor for the IIoT. In this sense, the proposed Smart Sensor architecture incorporates RT operation features, the ability to perform local data analysis, high availability communication interfaces, such as high-availability seamless redundancy (HSR) and parallel redundancy protocol (PRP), interoperability (industrial protocols), and cyber-security. The architecture was implemented with hardware available in the market, IP cores, and Python libraries developed by third parties. Finally, to validate the applicability of the architecture in the industry, two test environments were implemented. In the first case, interoperability, high availability, synchronization, and local data processing are validated. The second case aims to determine the delay when adding encryption (cyber-security) in layer 2 communications.

Application of MEMS-based accelerometer wireless sensor systems for monitoring of blast-induced ground vibration and structural health: a review

Abstract: Ubiquitous wireless sensor network (WSN) enables low-cost monitoring applications such as blast-induced ground vibration (BIGV) and structural health monitoring (SHM). In particular, monitoring and analysing the ambiguous BIGV waves are essential requisite to control and protect surrounding grievous damage structures. Similarly, improving health and longevity of structures using WSN is a new facet that owes to diminish the low-cost installation. Recent advances in WSNs are forging new prospects for sensors. A variety of intelligent sensors are integrated into the wireless system to monitor environmental, and health of civil infrastructures. Considering the current trends in the area of development of wireless monitoring prototypes, Micro-Electro-Mechanical-Systems (MEMS) accelerometer sensors are widely prevalent owing to the small size and inexpensive. In general, BIGV waves are less intensity and low-frequency signals. Hence, it is essential to select an appropriate accelerometer to detect micro-vibration waves. The study exemplifies a summarised review of recently made MEMS-based accelerometer wireless systems for intelligent and reliable monitoring of BIGV and SHM since the last decade. This research effort focuses on the numerous adopted accelerometers and their characteristics such as sensitivity, noise density, measurement range, bandwidth, resolution, network topologies, and performance of designed systems to analyse the micro-vibration levels comprehensively.

Intelligent Sensor-Cloud in Fog Computer: A Novel Hierarchical Data Job Scheduling Strategy.

Abstract: In the Fog Computer (FC), the process of data is prone to problems such as low data similarity and poor data tolerance. This paper proposes a hierarchical data job scheduling strategy Based on Intelligent Sensor-Cloud in Fog Computer (HDJS). HDJS dynamically adjusts the priority of the job to avoid job starvation and maximize the use of resources, uses the key frame to the resource occupied information, distributes the frame sequence to the unit, and then combines the intra frame distribution strategy to balance the load between the nodes. The experimental results show our proposed strategy may be possible to avoid the operation of hunger and resource fragmentation problems, make full use of the advantages of multi-core and multi-thread, improve system resource utilization, and shorten the execution time and response time.

A time-efficient data offloading method with privacy preservation for intelligent sensors in edge computing

Abstract: Over the past years, with the development of hardware and software, the intelligent sensors, which are deployed in the wearable devices, smart phones, and etc., are leveraged to collect the data around us. The data collected by the sensors is analyzed, and the corresponding measures will be implemented. However, due to the limited computing resources of the sensors, the overload resource usage may occur. In order to satisfy the requirements for strong computing power, edge computing, which emerges as a novel paradigm, provides computing resources at the edge of networks. In edge computing, the computing tasks could be offloaded from the sensors to the other sensors for processing. Despite the advantages of edge computing, during the offloading process of computing tasks between sensors, private data, including identity information and address, may be leaked, which threatens personal security. Hence, it is important to avoid privacy leakage in edge computing. In addition, the time consumption of offloading computing tasks affects the using experience of customers, and low time consumption makes contributions to the development of applications which are strict with time. To satisfy the above requirements, a time-efficient offloading method (TEO) with privacy preservation for intelligent sensors in edge computing is proposed. Technically, the time consumption and the offloading of privacy data are analyzed in a formalized way. Then, an improved of Strength Pareto Evolutionary Algorithm (SPEA2) is leveraged to optimize the average time consumption and average privacy entropy jointly. At last, abundant experimental evaluations are conducted to verify efficiency and reliability of our method.

IoT Based Intelligent Industry Monitoring System

Abstract: The Internet of Things (IoT) is a newly emerging field with a vision of connecting ‘things’, human and machines together making them an integral part of internet. The entire world is moving towards modernization and automation which may result in excessive pollution of environment. Determining the air quality is a prime need of the hour. This paper deals with the development of pollution monitoring system with deployment of intelligent sensors. Monitoring the gas leakage level from any part of the globe can be achieved by integration of big data to the Google Cloud via web servers. Analysis of the data is simplified thereby enabling ease of monitoring. Alerts can be triggered in case of drastic deterioration of air quality. The proposed method finds application in industry and also in monitoring of pollution caused by vehicles.

Polymer Optical Fiber-Based Sensor System for Smart Walker Instrumentation and Health Assessment

Abstract: This paper presents a polymer optical fiber (POF)-based sensor system for smart walker (SW) instrumentation. The system comprises an oximetry sensor working in reflectance mode, which is embedded in a 3D printed handle for the SW. In addition, there is also a POF-based smart textile that can be integrated in the users’ clothes and is placed on their chest. In this case, the smart textile can detect the displacement caused by the respiration, vibration due to heartbeat and bending induced in the gait. Results show that the proposed sensor system can detect the oxygen saturation, breathing rate, gait cadence, and heart rate with errors of about 1%. In addition, it is proposed an architecture for the SW in which the POF-based sensor system can be applied not only for remote healthcare applications, but also as sensor feedback in cloud robotics for some control paradigms for human–robot interaction. Furthermore, the proposed instrumentation presents the possibility of novel SW control, where the health conditions of the user are considered in the human–robot interaction.

An FPGA-Based Neuro-Fuzzy Sensor for Personalized Driving Assistance

Abstract: Advanced driving-assistance systems (ADAS) are intended to automatize driver tasks, as well as improve driving and vehicle safety. This work proposes an intelligent neuro-fuzzy sensor for driving style (DS) recognition, suitable for ADAS enhancement. The development of the driving style intelligent sensor uses naturalistic driving data from the SHRP2 study, which includes data from a CAN bus, inertial measurement unit, and front radar. The system has been successfully implemented using a field-programmable gate array (FPGA) device of the Xilinx Zynq programmable system-on-chip (PSoC). It can mimic the typical timing parameters of a group of drivers as well as tune these typical parameters to model individual DSs. The neuro-fuzzy intelligent sensor provides high-speed real-time active ADAS implementation and is able to personalize its behavior into safe margins without driver intervention. In particular, the personalization procedure of the time headway (THW) parameter for an ACC in steady car following was developed, achieving a performance of 0.53 microseconds. This performance fulfilled the requirements of cutting-edge active ADAS specifications.

Anonymous authentication key agreement scheme with pairing-based cryptography for home-based multi-sensor Internet of Things:

Abstract: Home-based multi-sensor Internet of Things, as a typical application of Internet of Things, interconnects a variety of intelligent sensor devices and appliances to provide intelligent services to i...

EMI-Free Bidirectional Real-Time Indoor Environment Monitoring System

Abstract: Indoor air quality, temperature, and relative humidity affect the thermal comfort and health of the inhabitants. Therefore, monitoring these parameters is essential to prevent indoor air pollution and to improve labor productivity. Most recently, the research conducted has used radio frequency wireless communications to monitor the indoor environment. However, long-term exposure to electromagnetic interference (EMI) causes a detrimental impact on the human body, especially on the elderly, patients, and infants, while it concurrently affects the operation of electronic devices. Thus, we propose a unique indoor environment monitoring system using an EMI-free bidirectional visible light communication technology. The sensing data from the smart sensor tag and the command data used to request the environmental sensing data are transferred bidirectionally between the base station and the smart sensor tag by being modulated into the light-emitting diode (LED) light beam. The proposed smart sensor tags are designed to measure five important parameters of indoor environments, such as CO2 concentration, volatile organic compound level, O2 concentration, temperature, and relative humidity, at multiple positions in real time. In addition, a proposed average-voltage tracking algorithm is adopted to allow the LED illumination to be used as a lighting system and as a long-range wireless communication system. As a result, the proposed system is demonstrated to be error-free when the distance between the base station and the smart sensor tags is 6 m. The measured live data are aggregated and visualized in a cloud platform by a graphical user interface. A web-based application and a mobile application are also developed to display the real-time data.

Design of sensor system for air pollution and human vital monitoring for connected cyclists

Abstract: This study addresses the design of smart sensor system aided bicycle that can be exploited as a platform for the acquisition of real-time data. In particular, in this work, the authors address the pressing issues like air pollution monitoring and health monitoring by using sensors that were seen as limitations in the already existing smart e-bike monitoring system. The sensor system presented in this study is capable of monitoring parameters such as location, heart rate of the rider and air quality levels in real-time. The data thus collected is fed into Thingspeak, an open Internet of Things platform powered by Matlab. The data is then visually represented in an Android application for riders to view and analyse the monitored parameters. The Android application designed for the system assists the user with location tracking, pollution mapping and health monitoring. Furthermore, security is also considered in this work which is addressed with the help of a fingerprint sensor and a global system for mobile/global positioning system module to alert the user in case of system theft. The system attached to the bicycle can be implemented on a large scale as a fleet/bike sharing system in order to map the pollution of an entire city with the help of IoT, thus aiding the development of greenfield smart city and additionally monitoring the vitals of the user riding the bicycle leading to intelligent transportation system. This study details the design and implementation of the hardware and software, enlists the outcomes of the system and explores the future scope and development.

An Elastomer-based Flexible Optical Force and Tactile Sensor

Abstract: Tactile and force sensing devices that are capable to interactively explore the external environment have attracted a lot of research interest. Optical-based tactile sensors are becoming popular because they do not suffer from electromagnetic interference and because improved signal processing techniques enable intelligent sensor data classification. However, there is still no implementation of a sensor that measures both force and tactile information concurrently in an efficient manner in terms of material efficiency. In this research, we present a novel design for an elastomer-based tactile and force sensing device that senses both information within one elastomer. In addition, the tactile information is measured in the form of pressure distribution from the surface of objects. The proposed sensor has a soft and compliant design employing an opaque elastomer. The optical sensing method is used to measure both force and tactile information simultaneously based on the deformation of the reflective elastomer structure and a flexure structure. Here, we present the fabrication and development principles of the overall sensor. The experimental evaluation shows that the prototype is capable of sensing normal forces up to 70 $\mathbf{N}$ with an error of 6.6%.

Building a Compact Convolutional Neural Network for Embedded Intelligent Sensor Systems Using Group Sparsity and Knowledge Distillation

Abstract: As artificial intelligence (AI)- or deep-learning-based technologies become more popular,the main research interest in the field is not only on their accuracy, but also their efficiency, e.g., theability to give immediate results on the users' inputs. To achieve this, there have been many attemptsto embed deep learning technology on intelligent sensors. However, there are still many obstacles inembedding a deep network in sensors with limited resources. Most importantly, there is an apparenttrade-off between the complexity of a network and its processing time, and finding a structure witha better trade-off curve is vital for successful applications in intelligent sensors. In this paper, wepropose two strategies for designing a compact deep network that maintains the required level ofperformance even after minimizing the computations. The first strategy is to automatically determinethe number of parameters of a network by utilizing group sparsity and knowledge distillation (KD)in the training process. By doing so, KD can compensate for the possible losses in accuracy causedby enforcing sparsity. Nevertheless, a problem in applying the first strategy is the unclarity indetermining the balance between the accuracy improvement due to KD and the parameter reductionby sparse regularization. To handle this balancing problem, we propose a second strategy: a feedbackcontrol mechanism based on the proportional control theory. The feedback control logic determinesthe amount of emphasis to be put on network sparsity during training and is controlled based onthe comparative accuracy losses of the teacher and student models in the training. A surprising facthere is that this control scheme not only determines an appropriate trade-off point, but also improvesthe trade-off curve itself. The results of experiments on CIFAR-10, CIFAR-100, and ImageNet32 X 32datasets show that the proposed method is effective in building a compact network while preventingperformance degradation due to sparsity regularization much better than other baselines.

Smart Sensor Networking and Green Technologies in Urban Areas

Abstract: The development trend of urbanization is growing at an exponential rate globally. Considering the shift of more citizens towards cities, urban centers around the world are rapidly enhancing their infrastructure considering their tight budget. Due to wireless technologies becoming fundamentally advanced, the spread of smart application is evident across the world. Smart sensor networks, which are the wireless sensor networks (WSNs), have developed a dynamic and flexible facet deployed in various forms of environments like suburban, rural, and urban areas. Every application instances are dissimilar from others, consequently smart sensors resolutions for every application need to be innovative and adaptive. Although the various benefits of the smart sensor are improving our general public, it ought to be reminded that they also devour vitality, embrace harmful contamination, including the E-wastes. Resultantly, more weight is subjected on the current global situation and the intelligent urban world. Fundamentally, this is purposed to stimulate the merits of intelligent sensors and lessen its harmfulness since there is a critical need for the world to develop green sensor networks. Green smart sensors are considered as the future aspect of intelligent sensors, whereby intelligent sensors, machine, and the web enhance vigor production and elimination of carbon emissions. Smart sensor deployment in an urban situation by considering the green energy challenges is interpreted as the linchpin in this chapter.

Collaborative UAV-WSN System for Data Acquisition and Processing in Agriculture

Abstract: Integration of airborne robotic platforms with networks of intelligent sensor systems on the ground has recently emerged as a robust solution for data collection, analysis and control in various specialised applications. The paper presents a hierarchical structure based on the collaboration between a team of unmanned aerial vehicles and a structure of federated wireless sensor networks for crop monitoring in precision agriculture. Key advantages lay in online data collection and relaying to a central monitoring point while effectively managing network load and latency through optimised UAV trajectories and in situ data processing. The experiments were carried out at the Fundulea National Research Institute where different crops and methods are developed. The results demonstrate the fact that the collaborative UAV-WSN approach implemented in the Romanian project MUWI increases the performances both in precision agriculture and ecological agriculture.

Vehicle Classification Based on Feature Selection With Anisotropic Magnetoresistive Sensor

Abstract: Vehicle classification based on magnetic sensors can be effectively applied to intelligent transportation and realize intelligent management of traffic. The use of representative vehicle signal features is a prerequisite and guarantee for accurate vehicle classification. This paper uses a single 3-axis magnetic sensor to acquire vehicle signals and extract a large number of features from the vehicle signals. In order to obtain a set of features that are simple and without loss of classification accuracy, we propose a Filtering algorithm based on Feature Pairing Elimination (FPE-Filter). In addition, choosing the right classifier is also crucial for models with high classification accuracy. In this paper, we compare four common classification models: SVM, RF, KNN, and C4.5. The experimental results show that the SVM performs best and the classification accuracy reaches 95%.

Intelligent Embedded Load Detection at the Edge on Industry 4.0 Powertrains Applications

Abstract: In the context of Industry 4.0, there has been great focus in developing intelligent sensors. Deploying them, condition monitoring and predictive maintenance have become feasible solutions to minimize operating and maintenance costs while also increasing safety. A critical aspect is the applied load to the supervised machinery system. Vibration data can be used to determine the current condition, but this needs signal processing specially developed and adapted to the monitored machine part for feature extraction. Artificial intelligence (AI) can, on one hand, simplify the development of such special purpose processing and on another hand be used to monitor and classify machine conditions by learning features directly from data. By bringing the AI computation as close as possible to the sensor (Edge-AI), data bandwidth can be minimized, system scalability and responsiveness can be improved and real-time requirements can be fulfilled. This work describes how Edge-AI on a STM32-bit microcontroller can be implemented. Our experimental setup demonstrates how AI can be effectively used to detect and classify the load on a powertrain. In order to do this, we use a MEMS capacity accelerometer to sense vibrations of the system. Also, this work demonstrates how Deep Neural Networks (DNN) for signal classification are build and trained by using an open-source deep learning framework and how the code library for the microcontroller is automatically generated afterwards by using STM32Cube. AI toolchain. We compare the classification accuracy of a memory compressed DNN against an uncompressed DNN.