Search

Falls are unusual actions that cause a significant health risk among older people. The growing percentage of people of old age requires urgent development of fall detection and prevention systems. The emerging technology focuses on developing such systems to improve quality of life, especially for the elderly. A fall prevention system tries to predict and reduce the risk of falls. In contrast, a fall detection system observes the fall and generates a help notification to minimize the consequences of falls. A plethora of technical and review papers exist in the literature with a primary focus on fall detection. Similarly, several studies are relatively old, with a focus on wearables only, and use statistical and threshold-based approaches with a high false alarm rate. Therefore, this paper presents the latest research trends in fall detection and prevention systems using Machine Learning (ML) algorithms. It uses recent studies and analyzes datasets, age groups, ML algorithms, sensors, and location. Additionally, it provides a detailed discussion of the current trends of fall detection and prevention systems with possible future directions. This overview can help researchers understand the current systems and propose new methodologies by improving the highlighted issues. ispartof: SENSORS vol:21 issue:15 ispartof: location:Switzerland status: published

The field of human activity recognition (HAR) often utilizes wearable sensors and machine learning techniques in order to identify the actions of the subject. This paper considers the activity recognition of walking and running while using a support vector machine (SVM) that was trained on principal components derived from wearable sensor data. An ablation analysis is performed in order to select the subset of sensors that yield the highest classification accuracy. The paper also compares principal components across trials to inform the similarity of the trials. Five subjects were instructed to perform standing, walking, running, and sprinting on a self-paced treadmill, and the data were recorded while using surface electromyography sensors (sEMGs), inertial measurement units (IMUs), and force plates. When all of the sensors were included, the SVM had over 90% classification accuracy using only the first three principal components of the data with the classes of stand, walk, and run/sprint (combined run and sprint class). It was found that sensors that were placed only on the lower leg produce higher accuracies than sensors placed on the upper leg. There was a small decrease in accuracy when the force plates are ablated, but the difference may not be operationally relevant. Using only accelerometers without sEMGs was shown to decrease the accuracy of the SVM.

This paper considers the use of a post metadata-based approach to identifying intentionally deceptive online content. It presents the use of an inherently explainable artificial intelligence technique, which utilizes machine learning to train an expert system, for this purpose. It considers the role of three factors (textual context, speaker background, and emotion) in fake news detection analysis and evaluates the efficacy of using key factors, but not the inherently subjective processing of post text itself, to identify deceptive online content. This paper presents initial work on a potential deceptive content detection tool and also, through the networks that it presents for this purpose, considers the interrelationships of factors that can be used to determine whether a post is deceptive content or not and their comparative importance.

With the automotive industry moving towards automated driving, sensing is increasingly important in enabling technology. The virtual sensors allow data fusion from various vehicle sensors and provide a prediction for measurement that is hard or too expensive to measure in another way or in the case of demand on continuous detection. In this paper, virtual sensing is discussed for the case of vehicle suspension control, where information about the relative velocity of the unsprung mass for each vehicle corner is required. The corresponding goal can be identified as a regression task with multi-input sequence input. The hypothesis is that the state-of-art method of Bidirectional Long–Short Term Memory (BiLSTM) can solve it. In this paper, a virtual sensor has been proposed and developed by training a neural network model. The simulations have been performed using an experimentally validated full vehicle model in IPG Carmaker. Simulations provided the reference data which were used for Neural Network (NN) training. The extensive dataset covering 26 scenarios has been used to obtain training, validation and testing data. The Bayesian Search was used to select the best neural network structure using root mean square error as a metric. The best network is made of 167 BiLSTM, 256 fully connected hidden units and 4 output units. Error histograms and spectral analysis of the predicted signal compared to the reference signal are presented. The results demonstrate the good applicability of neural network-based virtual sensors to estimate vehicle unsprung mass relative velocity.

Four new algorithms (RFTA1, RFTA2, GFGF2A, and RFTA2GE) handling the event in wireless sensor and robot networks based on the Greedy-Face-Greedy (GFG) routing extended with auctions are proposed in this paper. In this paper we assume that all robots are mobile and after the event is found (reported by sensors), the goal is to allocate the task to the most suitable robot to act upon the event, using either distance or the robots' remaining energy as metrics. The proposed algorithms consist of two phases. The first phase of algorithms is based on face routing and we introduced the parameter called search radius (SR) at the end of this first phase. Routing is considered successful if the found robot is inside SR. After that, the second phase, based on auctions, is initiated by the robot found in SR trying to find a more suitable one. In the simulations, network lifetime and communication costs are measured and used for comparison. We compare our algorithms with two similar algorithms from the literature (k-SAAP and BFS) used for the task assignment. RFTA2 and RFTA2GE feature up to 7 times longer network lifetime with significant communication overhead reduction compared to k-SAAP and BFS. Among our algorithms, RFTA2GE features the best robot energy utilization., Comment: 21 p., submitted for journal publication

Recent advancements in information and communication technologies (ICT) have im‐proved the power grid, leading to what is known as the smart grid, which, as part of a critical economic and social infrastructure, is vulnerable to security threats from the use of ICT and new emerging vulner‐abilities and privacy issues. Access control is a fundamental element of a security infrastructure, and se‐curity is based on the principles of less privilege, zero‐trust, and segregation of duties. This work ad‐dresses how access control can be applied without disrupting the power grid’s functioning while also properly maintaining the security, scalability, and interoperability of the smart grid. The authentication in the platform presumes digital certificates using a web of trust. This paper presents the findings of the SealedGRID project, and the steps taken for implementing Attribute‐based access control policies specif‐ically customized to the smart grid. The outcome is to develop a novel, hierarchical architecture com‐posed of different licensing entities that manages access to resources within the network infrastructure. They are based on well‐drawn policy rules and the security side of these resources is placed through a context awareness module. Together with this technology, the IoT is used with Big Data (facilitating easy handling of large databases). Another goal of this paper is to present implementation and evaluations details of a secure and scalable security platform for the smart grid.

The development of low-cost mass sensors is of unique interest for the scientific community due to the wide range of fields requiring these kind of devices. In this paper, a full inkjet-printed mass sensor is proposed. The device is based on a PolyEthylene Terephthalate (PET) cantilever beam (operating in its first natural frequency) where a strain-sensor and a planar coil have been realized by a low-cost InkJet Printing technology to implement the sensing and actuation strategies, respectively. The frequency readout strategy of the sensor presents several advantages, such as the intrinsic robustness against instabilities of the strain sensor, the residual stress of the cantilever beam, the target mass material, and the distance between the permanent magnet and the actuation coil (which changes as a function of the target mass values). However, the frictionless actuation mode represents another shortcoming of the sensor. The paper describes the sensor design, realization, and characterization while investigating its expected behavior by exploiting dedicate models. The working span of the device is 0–0.36 g while its resolution is in the order of 0.001 g, thus addressing a wide range of potential applications requiring very accurate mass measurements within a narrow operating range.

This paper presents a non-random weight initialization method in convolutional layers of neural networks examined with the Fast Gradient Sign Method (FSGM) attack. This paper's focus is convolutional layers, and are the layers that have been responsible for better than human performance in image categorization. The proposed method induces earlier learning through the use of striped forms, and as such has less unlearning of the existing random number speckled methods, consistent with the intuitions of Hubel and Wiesel. The proposed method provides a higher performing accuracy in a single epoch, with improvements of between 3-5% in a well known benchmark model, of which the first epoch is the most relevant as it is the epoch after initialization. The proposed method is also repeatable and deterministic, as a desirable quality for safety critical applications in image classification within sensors. That method is robust to Glorot/Xavier and He initialization limits as well. The proposed non-random initialization was examined under adversarial perturbation attack through the FGSM approach with transferred learning, as a technique to measure the affect in transferred learning with controlled distortions, and finds that the proposed method is less compromised to the original validation dataset, with higher distorted datasets.

In intelligent vehicles, extrinsic camera calibration is preferable to be conducted on a regular basis to deal with unpredictable mechanical changes or variations on weight load distribution. Specifically, high-precision extrinsic parameters between the camera coordinate and the world coordinate are essential to implement high-level functions in intelligent vehicles such as distance estimation and lane departure warning. However, conventional calibration methods, which solve a Perspective-n-Point problem, require laborious work to measure the positions of 3D points in the world coordinate. To reduce this inconvenience, this paper proposes an automatic camera calibration method based on 3D reconstruction. The main contribution of this paper is a novel reconstruction method to recover 3D points on planes perpendicular to the ground. The proposed method jointly optimizes reprojection errors of image features projected from multiple planar surfaces, and finally, it significantly reduces errors in camera extrinsic parameters. Experiments were conducted in synthetic simulation and real calibration environments to demonstrate the effectiveness of the proposed method.

Video applications have become one of the major services in the engineering field, which are implemented by server–client systems connected via the Internet, broadcasting services for mobile devices such as smartphones and surveillance cameras for security. Recently, the majority of video encoding mechanisms to reduce the data rate are mainly lossy compression methods such as the MPEG format. However, when we consider special needs for high-speed communication such as display applications and object detection ones with high accuracy from the video stream, we need to address the encoding mechanism without any loss of pixel information, called visually lossless compression. This paper focuses on the Adaptive Differential Pulse Code Modulation (ADPCM) that encodes a data stream into a constant bit length per data element. However, the conventional ADPCM does not have any mechanism to control dynamically the encoding bit length. We propose a novel ADPCM that provides a mechanism with a variable bit-length control, called ADPCM-VBL, for the encoding/decoding mechanism. Furthermore, since we expect that the encoded data from ADPCM maintains low entropy, we expect to reduce the amount of data by applying a lossless data compression. Applying ADPCM-VBL and a lossless data compression, this paper proposes a video transfer system that controls throughput autonomously in the communication data path. Through evaluations focusing on the aspects of the encoding performance and the image quality, we confirm that the proposed mechanisms effectively work on the applications that needs visually lossless compression by encoding video stream in low latency.

This paper addresses the problem of unsupervised video summarization. Video summarization helps people browse large-scale videos easily with a summary from the selected frames of the video. In this paper, we propose an unsupervised video summarization method with piecewise linear interpolation (Interp-SUM). Our method aims to improve summarization performance and generate a natural sequence of keyframes with predicting importance scores of each frame utilizing the interpolation method. To train the video summarization network, we exploit a reinforcement learning-based framework with an explicit reward function. We employ the objective function of the exploring under-appreciated reward method for training efficiently. In addition, we present a modified reconstruction loss to promote the representativeness of the summary. We evaluate the proposed method on two datasets, SumMe and TVSum. The experimental result showed that Interp-SUM generates the most natural sequence of summary frames than any other the state-of-the-art methods. In addition, Interp-SUM still showed comparable performance with the state-of-art research on unsupervised video summarization methods, which is shown and analyzed in the experiments of this paper.

Recent progress in deep learning has led to accurate and efficient generic object detection networks. Training of highly reliable models depends on large datasets with highly textured and rich images. However, in real-world scenarios, the performance of the generic object detection system decreases when (i) occlusions hide the objects, (ii) objects are present in low-light images, or (iii) they are merged with background information. In this paper, we refer to all these situations as challenging environments. With the recent rapid development in generic object detection algorithms, notable progress has been observed in the field of deep learning-based object detection in challenging environments. However, there is no consolidated reference to cover the state of the art in this domain. To the best of our knowledge, this paper presents the first comprehensive overview, covering recent approaches that have tackled the problem of object detection in challenging environments. Furthermore, we present a quantitative and qualitative performance analysis of these approaches and discuss the currently available challenging datasets. Moreover, this paper investigates the performance of current state-of-the-art generic object detection algorithms by benchmarking results on the three well-known challenging datasets. Finally, we highlight several current shortcomings and outline future directions.

This paper presents an automatic classification of plastic material’s inorganic pigment using terahertz spectroscopy and convolutional neural networks (CNN). The plastic materials were placed between the THz transmitter and receiver, and the acquired THz signals were classified using a supervised learning approach. A THz frequency band between 0.1–1.2 THz produced a one-dimensional (1D) vector that is almost impossible to classify directly using supervised learning. This paper proposes a novel pre-processing of 1D THz data that transforms 1D data into 2D data, which are processed efficiently using a convolutional neural network. The proposed pre-processing algorithm consists of four steps: peak detection, envelope extraction, and a down-sampling procedure. The last main step introduces the windowing with spectrum dilatation that reorders 1D data into 2D data that can be considered as an image. The spectrum dilation techniques ensure the classifier’s robustness by suppressing measurement bias, reducing the complexity of the THz dataset with negligible loss of accuracy, and speeding up the network classification. The experimental results showed that the proposed approach achieved high accuracy using a CNN classifier, and outperforms 1D classification of THz data using support vector machine, naive Bayes, and other popular classification algorithms.

The forecast of electricity demand has been a recurrent research topic for decades, due to its economical and strategic relevance. Several Machine Learning (ML) techniques have evolved in parallel with the complexity of the electric grid. This paper reviews a wide selection of approaches that have used Artificial Neural Networks (ANN) to forecast electricity demand, aiming to help newcomers and experienced researchers to appraise the common practices and to detect areas where there is room for improvement in the face of the current widespread deployment of smart meters and sensors, which yields an unprecedented amount of data to work with. The review looks at the specific problems tackled by each one of the selected papers, the results attained by their algorithms, and the strategies followed to validate and compare the results. This way, it is possible to highlight some peculiarities and algorithm configurations that seem to consistently outperform others in specific settings. Xunta de Galicia | Ref. ED431B 2020/34 Ministerio de Educación y Ciencia | Ref. TIN2017-87604-R

Public aquariums and similar institutions often use video as a method to monitor the behavior, health, and status of aquatic organisms in their environments. These video footages take up a sizeable amount of space and require the use of autoencoders to reduce their file size for efficient storage. The autoencoder neural network is an emerging technique which uses the extracted latent space from an input source to reduce the image size for storage, and then reconstructs the source within an acceptable loss range for use. To meet an aquarium’s practical needs, the autoencoder must have easily maintainable codes, low power consumption, be easily adoptable, and not require a substantial amount of memory use or processing power. Conventional configurations of autoencoders often provide results that perform beyond an aquarium’s needs at the cost of being too complex for their architecture to handle, while few take low-contrast sources into consideration. Thus, in this instance, “keeping it simple” would be the ideal approach to the autoencoder’s model design. This paper proposes a practical approach catered to an aquarium’s specific needs through the configuration of autoencoder parameters. It first explores the differences between the two of the most widely applied autoencoder approaches, Multilayer Perceptron (MLP) and Convolution Neural Networks (CNN), to identify the most appropriate approach. The paper concludes that while both approaches (with proper configurations and image preprocessing) can reduce the dimensionality and reduce visual noise of the low-contrast images gathered from aquatic video footage, the CNN approach is more suitable for an aquarium’s architecture. As an unexpected finding of the experiments conducted, the paper also discovered that by manipulating the formula for the MLP approach, the autoencoder could generate a denoised differential image that contains sharper and more desirable visual information to an aquarium’s operation. Lastly, the paper has found that proper image preprocessing prior to the application of the autoencoder led to better model convergence and prediction results, as demonstrated both visually and numerically in the experiment. The paper concludes that by combining the denoising effect of MLP, CNN’s ability to manage memory consumption, and proper image preprocessing, the specific practical needs of an aquarium can be adeptly fulfilled.

The utilization of robotic systems has been increasing in the last decade. This increase has been derived by the evolvement in the computational capabilities, communication systems, and the information systems of the manufacturing systems which is reflected in the concept of Industry 4.0. Furthermore, the robotics systems are continuously required to address new challenges in the industrial and manufacturing domain, like keeping humans in the loop, among other challenges. Briefly, the keeping humans in the loop concept focuses on closing the gap between humans and machines by introducing a safe and trustworthy environment for the human workers to work side by side with robots and machines. It aims at increasing the engagement of the human as the automation level increases rather than replacing the human, which can be nearly impossible in some applications. Consequently, the collaborative robots (Cobots) have been created to allow physical interaction with the human worker. However, these cobots still lack of recognizing the human emotional state. In this regard, this paper presents an approach for adapting cobot parameters to the emotional state of the human worker. The approach utilizes the Electroencephalography (EEG) technology for digitizing and understanding the human emotional state. Afterwards, the parameters of the cobot are instantly adjusted to keep the human emotional state in a desirable range which increases the confidence and the trust between the human and the cobot. In addition, the paper includes a review on technologies and methods for emotional sensing and recognition. Finally, this approach is tested on an ABB YuMi cobot with commercially available EEG headset. publishedVersion

In the context of real-time control systems, it has become possible to obtain temporal resolutions of microseconds due to the development of embedded systems and the Internet of Things (IoT), the optimization of the use of processor hardware, and the improvement of architectures and real-time operating systems (RTOSs). All of these factors, together with current technological developments, have led to efficient central processing unit (CPU) time usage, guaranteeing both the predictability of thread execution and the satisfaction of the timing constraints required by real-time systems (RTSs). This is mainly due to time sharing in embedded RTSs and the pseudo-parallel execution of tasks in single-processor and multi-processor systems. The non-deterministic behavior triggered by asynchronous external interrupts and events in general is due to the fact that, for most commercial RTOSs, the execution of the same instruction ends in a variable number of cycles, primarily due to hazards. The software implementation of RTOS-specific mechanisms may lead to significant delays that can affect deadline requirements for some RTSs. The main objective of this paper was the design and deployment of innovative solutions to improve the performance of RTOSs by implementing their functions in hardware. The obtained architectures are intended to provide feasible scheduling, even if the total CPU utilization is close to the maximum limit. The contributions made by the authors will be followed by the validation of a high-performing microarchitecture, which is expected to allow a thread context switching time and event response time of only one clock cycle each. The main purpose of the research presented in this paper is to improve these factors of RTSs, as well as the implementation of the hardware structure used for the static and dynamic scheduling of tasks, for RTOS mechanisms specific to resource sharing and intertask communication.

A potential rise in interest in the Internet of Things in the upcoming years is expected in the fields of healthcare, supply chain, logistics, industries, smart cities, smart homes, cyber physical systems, etc. This paper discloses the fusion of the Internet of Things (IoT) with the so-called “distributed ledger technology” (DLT). IoT sensors like temperature sensors, motion sensors, GPS or connected devices convey the activity of the environment. Sensor information acquired by such IoT devices are then stored in a blockchain. Data on a blockchain remains immutable however its scalability still remains a challenging issue and thus represents a hindrance for its mass adoption in the IoT. Here a communication system based on IOTA and DLT is discussed with a systematic architecture for IoT devices and a future machine-to-machine (M2M) economy. The data communication between IoT devices is analyzed using multiple use cases such as sending DHT-11 sensor data to the IOTA tangle. The value communication is analyzed using a novel “micro-payment enabled over the top” (MP-OTT) streaming platform that is based on the “pay-as-you-go” and “consumption based” models to showcase IOTA value transactions. In this paper, we propose an enhancement to the classical “masked authenticated message” (MAM) communication protocol and two architectures called dual signature masked authenticated message (DSMAM) and index-based address value transaction (IBAVT). Further, we provided an empirical analysis and discussion of the proposed techniques. The implemented solution provides better address management with secured sharing and communication of IoT data, complete access control over the ownership of data and high scalability in terms of number of transactions that can be handled.

This paper proposes a general hierarchical dispatching strategy of mine water, with the aim of addressing the problems of low reuse rate of coal mine water, and insufficient data analysis. First of all, water quality and quantity data of the Narim River No. 2 mine were used as the research object, the maximum reuse rate of mine water and the system operation rate comprised the objective function, and mine water quality information, mine water standard, and mine water treatment speed were the constraints. A multi-objective optimization scheduling mathematical model of water supply system was established. Then, to address the problems of premature convergence and ease of falling into a local optimum in the iterative process of particle swarm optimization, the basic particle swarm optimization was improved. Using detailed simulation research, the superiority of the improved algorithm was verified. Eventually, the mine water grading dispatching strategy proposed in this paper is compared with the traditional dispatching method. The results show that the hierarchical dispatching system can significantly improve the mine water reuse rate and system operating efficiency.

Loop Closure Detection (LCD) is an important technique to improve the accuracy of Simultaneous Localization and Mapping (SLAM). In this paper, we propose an LCD algorithm based on binary classification for feature matching between similar images with deep learning, which greatly improves the accuracy of LCD algorithm. Meanwhile, a novel lightweight convolutional neural network (CNN) is proposed and applied to the target detection task of key frames. On this basis, the key frames are binary classified according to their labels. Finally, similar frames are input into the improved lightweight feature matching network based on Transformer to judge whether the current position is loop closure. The experimental results show that, compared with the traditional method, LFM-LCD has higher accuracy and recall rate in the LCD task of indoor SLAM while ensuring the number of parameters and calculation amount. The research in this paper provides a new direction for LCD of robotic SLAM, which will be further improved with the development of deep learning.

The health status of an elderly person can be identified by examining the additive effects of aging along with disease linked to it and can lead to ‘unstable incapacity’. This health status is determined by the apparent decline of independence in activities of daily living (ADLs). Detecting ADLs provides possibilities of improving the home life of elderly people as it can be applied to fall detection systems. This paper presents fall detection in elderly people based on radar image classification by examining their daily routine activities, using radar data that were previously collected for 99 volunteers. Machine learning techniques are used classify six human activities, namely walking, sitting, standing, picking up objects, drinking water and fall events. Different machine learning algorithms, such as random forest, K-nearest neighbours, support vector machine, long short-term memory, bi-directional long short-term memory and convolutional neural networks, were used for data classification. To obtain optimum results, we applied data processing techniques, such as principal component analysis and data augmentation, to the available radar images. The aim of this paper is to improve upon the results achieved using a publicly available dataset to further improve upon research of fall detection systems. It was found out that the best results were obtained using the CNN algorithm with principal component analysis and data augmentation together to obtain a result of 95.30% accuracy. The results also demonstrated that principal component analysis was most beneficial when the training data were expanded by augmentation of the available data. The results of our proposed approach, in comparison to the state of the art, have shown the highest accuracy.

For the last decade the Smart City concept has been under development, fostered by the growing urbanization of the world’s population and the need to handle the challenges that such a scenario raises. During this time many Smart City projects have been executed–some as proof-of-concept, but a growing number resulting in permanent, production-level deployments, improving the operation of the city and the quality of life of its citizens. Thus, Smart Cities are still a highly relevant paradigm which needs further development before it reaches its full potential and provides robust and resilient solutions. In this paper, the focus is set on the Internet of Things (IoT) as an enabling technology for the Smart City. In this sense, the paper reviews the current landscape of IoT-enabled Smart Cities, surveying relevant experiences and city initiatives that have embedded IoT within their city services and how they have generated an impact. The paper discusses the key technologies that have been developed and how they are contributing to the realization of the Smart City. Moreover, it presents some challenges that remain open ahead of us and which are the initiatives and technologies that are under development to tackle them. This research was partially funded by Spain State Research Agency (AEI) by means of the project FIERCE: Future Internet Enabled Resilient CitiEs (RTI2018-093475-A-I00). Prof. Song was supported by Smart City R&D project of the Korea Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land, Infrastructure and Transport (MOLIT), Ministry of Science and ICT (MSIT) (Grant 18NSPS-B149386-01).

This paper presents different prediction methods based on decision tree and ensemble learning to suggest possible next assembly steps. The predictor is designed to be a component of a sensor-based assembly assistance system whose goal is to provide support via adaptive instructions, considering the assembly progress and, in the future, the estimation of user emotions during training. The assembly assistance station supports inexperienced manufacturing workers, but it can be useful in assisting experienced workers, too. The proposed predictors are evaluated on the data collected in experiments involving both trainees and manufacturing workers, as well as on a mixed dataset, and are compared with other existing predictors. The novelty of the paper is the decision tree-based prediction of the assembly states, in contrast with the previous algorithms which are stochastic-based or neural. The results show that ensemble learning with decision tree components is best suited for adaptive assembly support systems.

The popularity of the Power Line Communication (PLC) system has decreased due to significant deficiencies in the technology itself, even though new wire installation is not required. In particular, regarding the request for high-speed throughput to fulfill smart-grid requirements, Broadband Power Line (BPLC) can be considered. This paper approaches PLC technology as an object of simulation experimentation in the Broadband Power Line Communication (BPLC) area. Several experimental measurements in a real environment are also given. This paper demonstrates these experimental simulation results as potential mechanisms for creating a complex simulation tool for various PLC technologies focusing on communication with end devices such as sensors and meters. The aim is to demonstrate the potential and limits of BPLC technology for implementation in Smart Grids or Smart Metering applications.

This paper proposes a methodology for correlating products derived by Synthetic Aperture Radar (SAR) measurements and laser profilometric road roughness surveys. The procedure stems from two previous studies, in which several Machine Learning Algorithms (MLAs) have been calibrated for predicting the average vertical displacement (in terms of mm/year) of road pavements as a result of exogenous phenomena occurrence, such as subsidence. Such algorithms are based on surveys performed with Persistent Scatterer Interferometric SAR (PS-InSAR) over an area of 964 km2 in the Tuscany Region, Central Italy. Starting from this basis, in this paper, we propose to integrate the information provided by these MLAs with 10 km of in situ profilometric measurements of the pavement surface roughness and relative calculation of the International Roughness Index (IRI). Accordingly, the aim is to appreciate whether and to what extent there is an association between displacements estimated by MLAs and IRI values. If a dependence exists, we may argue that road regularity is driven by exogenous phenomena and MLAs allow for the replacement of in situ surveys, saving considerable time and money. In this research framework, results reveal that there are several road sections that manifest a clear association among these two methods, while others denote that the relationship is weaker, and in situ activities cannot be bypassed to evaluate the real pavement conditions. We could wrap up that, in these stretches, the road regularity is driven by endogenous factors which MLAs did not integrate during their training. Once additional MLAs conditioned by endogenous factors have been developed (such as traffic flow, the structure of the pavement layers, and material characteristics), practitioners should be able to estimate the quality of pavement over extensive and complex road networks quickly, automatically, and with relatively low costs.

Intelligent wireless networks that comprise self-organizing autonomous vehicles equipped with punctual sensors and radio modules support many hostile and harsh environment monitoring systems. This work’s contribution shows the benefits of applying such networks to estimate clouds’ boundaries created by hazardous toxic substances heavier than air when accidentally released into the atmosphere. The paper addresses issues concerning sensing networks’ design, focussing on a computing scheme for online motion trajectory calculation and data exchange. A three-stage approach that incorporates three algorithms for sensing devices’ displacement calculation in a collaborative network according to the current task, namely exploration and gas cloud detection, boundary detection and estimation, and tracking the evolving cloud, is presented. A network connectivity-maintaining virtual force mobility model is used to calculate subsequent sensor positions, and multi-hop communication is used for data exchange. The main focus is on the efficient tracking of the cloud boundary. The proposed sensing scheme is sensitive to crucial mobility model parameters. The paper presents five procedures for calculating the optimal values of these parameters. In contrast to widely used techniques, the presented approach to gas cloud monitoring does not calculate sensors’ displacements based on exact values of gas concentration and concentration gradients. The sensor readings are reduced to two values: the gas concentration below or greater than the safe value. The utility and efficiency of the presented method were justified through extensive simulations, giving encouraging results. The test cases were carried out on several scenarios with regular and irregular shapes of clouds generated using a widely used box model that describes the heavy gas dispersion in the atmospheric air. The simulation results demonstrate that using only a rough measurement indicating that the threshold concentration value was exceeded can detect and efficiently track a gas cloud boundary. This makes the sensing system less sensitive to the quality of the gas concentration measurement. Thus, it can be easily used to detect real phenomena. Significant results are recommendations on selecting procedures for computing mobility model parameters while tracking clouds with different shapes and determining optimal values of these parameters in convex and nonconvex cloud boundaries.

Since architect Nicholas Negroponte first proposed a vision of responsive architecture smart environments have been widely investigated, especially in the fields of computer science and engineering. Despite growing interest in the topic, a comprehensive review of research about smart environments from the architectural perspective is largely missing. In order to provide a formal understanding of smart environments in architecture, this paper conducts a systematic literature review of scholarly sources over the last decade, focusing on four related subjects: (1) responsive architecture, (2) kinetic architecture, (3) adaptive architecture and (4) intelligent buildings. Through this review, the paper identifies and examines interactive and collective behaviors in smart environments, thereby contributing to defining the properties of creative, smart spaces in the contemporary digital ecosystem. In addition, this research offers a means of systematically characterizing and constructing smart environments as interactive and collective platforms, enabling occupants to sense, experience and understand smart spaces.

In the design and development process of fog computing solutions for the Industrial Internet of Things (IIoT), we need to take into consideration the characteristics of the industrial environment that must be met. These include low latency, predictability, response time, and operating with hard real-time compiling. A starting point may be the reference fog architecture released by the OpenFog Consortium (now part of the Industrial Internet Consortium), but it has a high abstraction level and does not define how to integrate the fieldbuses and devices into the fog system. Therefore, the biggest challenges in the design and implementation of fog solutions for IIoT is the diversity of fieldbuses and devices used in the industrial field and ensuring compliance with all constraints in terms of real-time compiling, low latency, and predictability. Thus, this paper proposes a solution for a fog node that addresses these issues and integrates industrial fieldbuses. For practical implementation, there are specialized systems on chips (SoCs) that provides support for real-time communication with the fieldbuses through specialized coprocessors and peripherals. In this paper, we describe the implementation of the fog node on a system based on Xilinx Zynq UltraScale+ MPSoC ZU3EG A484 SoC.

Two important tasks in many e-commerce applications are identity verification of the user accessing the system and determining the level of rights that the user has for accessing and manipulating system’s resources. The performance of these tasks is directly dependent on the certainty of establishing the identity of the user. The main research focus of this paper is user identity verification approach based on voice recognition techniques. The paper presents research results connected to the usage of open-source speaker recognition technologies in e-commerce applications with an emphasis on evaluating the performance of the algorithms they use. Four open-source speaker recognition solutions (SPEAR, MARF, ALIZE, and HTK) have been evaluated in cases of mismatched conditions during training and recognition phases. In practice, mismatched conditions are influenced by various lengths of spoken sentences, different types of recording devices, and the usage of different languages in training and recognition phases. All tests conducted in this research were performed in laboratory conditions using the specially designed framework for multimodal biometrics. The obtained results show consistency with the findings of recent research which proves that i-vectors and solutions based on probabilistic linear discriminant analysis (PLDA) continue to be the dominant speaker recognition approaches for text-independent tasks.

Lakes play an important role in the water ecosystem on earth, and are vulnerable to climate change and human activities. Thus, the detection of water quality changes is of great significance for ecosystem assessment, disaster warning and water conservancy projects. In this paper, the dynamic changes of the Poyang Lake are monitored by Synthetic Aperture Radar (SAR). In order to extract water from SAR images to monitor water change, a water extraction algorithm composed of texture feature extraction, feature fusion and target segmentation was proposed. Firstly, the fractal dimension and lacunarity were calculated to construct the texture feature set of a water object. Then, an iterated function system (IFS) was constructed to fuse texture features into composite feature vectors. Finally, lake water was segmented by the multifractal spectrum method. Experimental results showed that the proposed algorithm accurately extracted water targets from SAR images of different regions and different imaging modes. Compared with common algorithms such as fuzzy C-means (FCM), the accuracy of the proposed algorithm is significantly improved, with an accuracy of over 98%. Moreover, the proposed algorithm can accurately segment complex coastlines with mountain shadow interference. In addition, the dynamic analysis of the changes of the water area of the Poyang Lake Basin was carried out with the local hydrological data. It showed that the extracted results of the algorithm in this paper are a good match with the hydrological data. This study provides an accurate monitoring method for lake water under complex backgrounds.

For the first time, this paper reports a smart museum archive box that features a fully integrated wireless powered temperature and humidity sensor. The smart archive box has been specifically developed for microclimate environmental monitoring of stored museum artifacts in cultural heritage applications. The developed sensor does not require a battery and is wirelessly powered using Near Field Communications (NFC). The proposed solution enables a convenient means for wireless sensing with the operator by simply placing a standard smartphone in close proximity to the cardboard archive box. Wireless sensing capability has the advantage of enabling long-term environmental monitoring of the contents of the archive box without having to move and open the box for reading or battery replacement. This contributes to a sustainable preventive conservation strategy and avoids the risk of exposing the contents to the external environment, which may result in degradation of the stored artifacts. In this work, a low-cost and fully integrated NFC sensor has been successfully developed and demonstrated. The developed sensor is capable of wirelessly measuring temperature and relative humidity with a mean error of 0.37 °C and ±0.35%, respectively. The design has also been optimized for low power operation with a measured peak DC power consumption of 900 μW while yielding a 4.5 cm wireless communication range. The power consumption of the NFC sensor is one of the lowest found in the literature. To the author’s knowledge, the NFC sensor proposed in this paper is the first reporting of a smart archive box that is wirelessly powered and uniquely integrated within a cardboard archive box.

At present, pointer meters are still widely used because of their mechanical stability and electromagnetic immunity, and it is the main trend to use a computer vision-based automatic reading system to replace inefficient manual inspection. Many correction and recognition algorithms have been proposed for the problems of skew, distortion, and uneven illumination in the field-collected meter images. However, the current algorithms generally suffer from poor robustness, enormous training cost, inadequate compensation correction, and poor reading accuracy. This paper first designs a meter image skew-correction algorithm based on binary mask and improved Mask-RCNN for different types of pointer meters, which achieves high accuracy ellipse fitting and reduces the training cost by transfer learning. Furthermore, the low-light enhancement fusion algorithm based on improved Retinex and Fast Adaptive Bilateral Filtering (RBF) is proposed. Finally, the improved ResNet101 is proposed to extract needle features and perform directional regression to achieve fast and high-accuracy readings. The experimental results show that the proposed system in this paper has higher efficiency and better robustness in the image correction process in a complex environment and higher accuracy in the meter reading process.

To address the problem of low detection rate caused by the close alignment and multi-directional position of text words in practical application and the need to improve the detection speed of the algorithm, this paper proposes a multi-directional text detection algorithm based on improved YOLOv3, and applies it to natural text detection. To detect text in multiple directions, this paper introduces a method of box definition based on sliding vertices. Then, a new rotating box loss function MD-Closs based on CIOU is proposed to improve the detection accuracy. In addition, a step-by-step NMS method is used to further reduce the amount of calculation. Experimental results show that on the ICDAR 2015 data set, the accuracy rate is 86.2%, the recall rate is 81.9%, and the timeliness is 21.3 fps, which shows that the proposed algorithm has a good detection effect on text detection in natural scenes.

In this paper, a new method for gaining the control of standalone underwater sensor nodes based on sensing the power supply evolution is presented. Underwater sensor networks are designed to support multiple extreme scenarios such as network disconnections. In those cases, the sensor nodes involved should go into standalone, and its wired and wireless communications should be disabled. This paper presents how to exit from the standalone status and enter into debugging mode following a practical ultra-low power design methodology. In addition, the discharge and regeneration effects are analyzed and modeled to minimize the error using the sensor node self measurements. Once the method is presented, its implementation details are discussed including other solutions like wake up wireless modules or a pin interruption solution. Its advantages and disadvantages are discussed. The method proposed is evaluated with several simulations and laboratory experiments using a real aquaculture sensor node. Finally, all the results obtained demonstrate the usefulness of our new method to gain the control of a standalone sensor node. The proposal is better than other approaches when the hibernation time is longer than 167.45 μs. Finally, our approach requires two orders of magnitude less energy than the best practical solution.

In today’s data networks, the main protocol used to ensure reliable communications is the transmission control protocol (TCP). The TCP performance is largely determined by the used congestion control (CC) algorithm. TCP CC algorithms have evolved over the past three decades and a large number of CC algorithm variations have been developed to accommodate various network environments. The fifth-generation (5G) mobile network presents a new challenge for the implementation of the TCP CC mechanism, since networks will operate in environments with huge user device density and vast traffic flows. In contrast to the pre-5G networks that operate in the sub-6 GHz bands, the implementation of TCP CC algorithms in 5G mmWave communications will be further compromised with high variations in channel quality and susceptibility to blockages due to high penetration losses and atmospheric absorptions. These challenges will be particularly present in environments such as sensor networks and Internet of Things (IoT) applications. To alleviate these challenges, this paper provides an overview of the most popular single-flow and multy-flow TCP CC algorithms used in pre-5G networks. The related work on the previous examinations of TCP CC algorithm performance in 5G networks is further presented. A possible implementation of TCP CC algorithms is thoroughly analysed with respect to the specificities of 5G networks, such as the usage of high frequencies in the mmWave spectrum, the frequent horizontal and vertical handovers, the implementation of the 5G core network, the usage of beamforming and data buffering, the exploitation of edge computing, and the constantly transmitted always-on signals. Moreover, the capabilities of machine learning technique implementations for the improvement of TCPs CC performance have been presented last, with a discussion on future research opportunities that can contribute to the improvement of TCP CC implementation in 5G networks. This survey paper can serve as the basis for the development of novel solutions that will ensure the reliable implementation of TCP CC in different usage scenarios of 5G networks.

Plantar pressure, the pressure exerted between the sole and the supporting surface, has great potentialities in various research fields, including footwear design, biometrics, gait analysis and the assessment of patients with diabetes. This research designs an optical-based foot plantar pressure measurement system aimed for human postural control and person identification. The proposed system consists of digital cameras installed underneath an acrylic plate covered by glossy white paper and mounted with LED strips along the side of the plate. When the light is emitted from the LED stripes, it deflects the digital cameras due to the pressure exerted between the glossy white paper and the acrylic plate. In this way, the cameras generate color-coded plantar pressure images of the subject standing on the acrylic-top platform. Our proposed system performs personal identification and postural control by extracting static and dynamic features from the generated plantar pressure images. Plantar pressure images were collected from 90 individuals (40 males, 50 females) to develop and evaluate the proposed system. In posture balance evaluation, we propose the use of a posture balance index that contains both magnitude and directional information about human posture balance control. For person identification, the experimental results show that our proposed system can achieve promising results, showing an area under the receiver operating characteristic (ROC) curve of 0.98515 (98.515%), an equal error rate (EER) of 5.8687%, and efficiency of 98.515%.

Time-series data generally exists in many application fields, and the classification of time-series data is one of the important research directions in time-series data mining. In this paper, univariate time-series data are taken as the research object, deep learning and broad learning systems (BLSs) are the basic methods used to explore the classification of multi-modal time-series data features. Long short-term memory (LSTM), gated recurrent unit, and bidirectional LSTM networks are used to learn and test the original time-series data, and a Gramian angular field and recurrence plot are used to encode time-series data to images, and a BLS is employed for image learning and testing. Finally, to obtain the final classification results, Dempster–Shafer evidence theory (D–S evidence theory) is considered to fuse the probability outputs of the two categories. Through the testing of public datasets, the method proposed in this paper obtains competitive results, compensating for the deficiencies of using only time-series data or images for different types of datasets.

The Internet of vehicles (IoV) is a rapidly emerging technological evolution of Intelligent Transportation System (ITS). This paper proposes SafeDrive, a dynamic driver profile (DDP) using a hybrid recommendation system. DDP is a set of functional modules, to analyses individual driver’s behaviors, using prior violation and accident records, to identify driving risk patterns. In this paper, we have considered three synthetic data-sets for 1500 drivers based on their profile information, risk parameters information, and risk likelihood. In addition, we have also considered the driver’s historical violation/accident data-set records based on four risk-score levels such as high-risk, medium-risk, low-risk, and no-risk to predict current and future driver risk scores. Several error calculation methods have been applied in this study to analyze our proposed hybrid recommendation systems’ performance to classify the driver’s data with higher accuracy based on various criteria. The evaluated results help to improve the driving behavior and broadcast early warning alarm to the other vehicles in IoV environment for the overall road safety. Moreover, the propoed model helps to provide a safe and predicted environment for vehicles, pedestrians, and road objects, with the help of regular monitoring of vehicle motion, driver behavior, and road conditions. It also enables accurate prediction of accidents beforehand, and also minimizes the complexity of on-road vehicles and latency due to fog/cloud computing servers.

This paper is an extended version of our paper published in “Néstor Alzate Mejía, Germán Santos-Boada, José R. de Almeida Amazonas, Decision-Making Under Uncertainty for the Deployment of Future Networks in IoT Scenarios” 11th EAI International Conference on Broadband Communications, Networks, and Systems, 11–12 December 2020. Among the several emerging dimensioning, control and deployment of future communication network paradigms stands out the human-centric characteristic that creates an intricate relationship between telematics and human activities. The hard to model dynamics of user behavior introduces new uncertainties into these systems that give rise to difficult network resource management challenges. According to this context, this work reviews several decision-making computational methods under the influence of uncertainties. This work, by means of a systematic literature review, focuses on sensor-based Internet of Things scenarios such as Smart Spaces and Industry 4.0. According to our conclusions, it is mandatory to establish a means for modeling the human behavior context in order to improve resource assignment and management. This research was funded by Spanish Ministry of Economy and Competitiveness under contract TEC2017-90034-C2-1-R (ALLIANCE project) that received funding from FEDER. Moreover, it was partially supported by the Spanish Thematic Network under contract RED2018-102585-T (Go2Edge) and by the aid granted by the Sinfoni project INV2733 of the Cooperative University of Colombia.

With the development of the Internet of Things (IoT), Low Data Rate-Personal Area Networks (LR-WPAN) have been deployed for different applications. Now comes the need to integrate these networks in search of greater connectivity, performances, and geographic coverage. This integration is facilitated by the recent deployment of low power wide area networks (LPWAN) in the licensed bands, especially narrowband IoT (NB-IoT) and long-term evolution for machine-type communications (LTE-M), which are standardized technologies that will continue evolving as part of the fifth generation (5G) specifications. This paper proposes a design methodology for combined networks using LR-WPAN and LPWAN technologies. These networks are combined at the device level using a cluster-tree topology. An example is shown here, where an existing IEEE 802.15.4 network is combined with NB-IoT. To this end, new dual nodes are incorporated, acting as cluster heads. The paper discusses the different aspects of formation and operation of the combined network. A dynamic link selection (DLS) algorithm is also proposed, based on which cluster headers dynamically determine the preferred link, depending on link quality and type of traffic. Extensive simulations show that the DLS algorithm significantly increases battery life on dual nodes, which are the nodes with the highest power demands.

Proximity operations offer aggregate capability for a spacecraft operating in close proximity to another spacecraft, to perform on-orbit satellite servicing, or to a space object to perform debris removal. To utilize a spacecraft performing such advanced maneuvering operations and perceiving of the relative motion of a foreign spacecraft, these trajectories must be modeled accurately based on the coupled translational and rotational dynamics models. This paper presents work towards exploiting the dual-quaternion representations of spacecraft relative dynamics for proximity operations and developing a sub-optimal control law for efficient and robust maneuvers. A linearized model using dual-quaternions for the proximity operation was obtained, and its stability was verified using Monte Carlo simulations for the linear quadratic regulator solution. A sub-optimal control law using generalized higher order feedback gains in dual-quaternion form was developed based on small error approximations for the proximity operation and also verified through Monte Carlo simulations. Necessary information needed to understand the theory behind the use of the dual-quaternion is also overviewed within this paper, including the validity of using the dual-quaternions against their Cartesian or quaternion equivalents.

The main objective of a Cooperative Multiple-Input Multiple-Output (CMIMO) system is to improve network throughput and network coverage and save energy. By grouping wireless devices as virtual multi-antenna nodes, it can thus simulate the functions of multi-antenna systems. A Space-Time Block Code (STBC) was proposed to utilize the spatial diversity of MIMO systems to improve the diversity gain and coding gain. In this paper, we proposed a cooperative strategy based on STBC and CMIMO, which is referred to as Space-Time Block Coded Cooperative Multiple-Input Multiple-Output (STBC-CMIMO) to inherit the advantages from both STBC and CMIMO. The theoretical performance analysis for the proposed STBC-CMIMO is presented. The performance advantages of the STBC-CMIMO are also shown by simulations. In the simulations, it is demonstrated that STBC-CMIMO can obtain significant performance compared with the existing CMIMO system.

Unlike the fixed power grid cooperative networks, which are mainly based on the reception reliability parameter while choosing the best relay, the wireless-powered cooperative communication network (WPCCN) and in addition to the reception reliability the transmission requirement consideration is important for relay selection schemes. Hence, enabling efficient transmission techniques that address high attenuation of radio frequency (RF) signals according to the distance without increasing the total transmission power is an open issue worth studying. In this relation, a multiantennas power beacon (PB) that assists wireless-powered cooperative communication network (PB-WPCCN) is studied in this paper. The communication between source and destination is achieved with the aid of multiple relays, where both the source and the multiple relays need to harvest energy from the PB in the first place to enable their transmission functionalities. A novel relay selection scheme is proposed, named as two-round relay selection (2-RRS), where a group of relays that successfully decode the source information is selected in the first round selection. In the second round, the optimal relay is selected to forward the recorded information to the destination. The proposed 2-RRS scheme is compared with two existing relay selection schemes, i.e., partial relay selection (PRS) and opportunistic relay selection (ORS). The analytical closed-form expressions of outage probability and average system throughput are derived and validated by numerical simulation. The comparison results between different relay selection schemes show: (I) The superiority of the proposed 2-RRS scheme as it achieves around 17% better throughput compared to the conventional ORS scheme and 40% better than the PRS scheme, particularly when PB transmit power is 10 dB, (II) The proposed 2-RRS scheme guarantees the lowest outage probability, especially when the PB is equipped with multiantennas and performs beamforming technique, (III) The optimal localisation of the PB between the source and N relays depends on the adopted relay selection scheme, (IV) The exhaustive search of the maximum system throughput value shows that the proposed 2-RRS scheme required shorter energy harvesting time compared to other schemes. The increase in energy harvesting time and number of relays do not necessarily reflect positively on the system throughput performance, hence tradeoffs should be taken into consideration.

Target detection in hyperspectral imagery (HSI) aims at extracting target components of interest from hundreds of narrow contiguous spectral bands, where the prior target information plays a vital role. However, the limitation of the previous methods is that only single-layer detection is carried out, which is not sufficient to discriminate the target parts from complex background spectra accurately. In this paper, we introduce a hierarchical structure to the traditional algorithm matched filter (MF). Because of the advantages of MF in target separation performance, that is, the background components are suppressed while preserving the targets, the detection result of MF is used to further suppress the background components in a cyclic iterative manner. In each iteration, the average output of the previous iteration is used as a suppression criterion to distinguish these pixels judged as backgrounds in the current iteration. To better stand out the target spectra from the background clutter, HSI spectral input and the given target spectrum are whitened and then used to construct the MF in the current iteration. Finally, we provide the corresponding proofs for the convergence of the output and suppression criterion. Experimental results on three classical hyperspectral datasets confirm that the proposed method performs better than some traditional and recently proposed methods.

In this paper, we propose AirSign, a novel user authentication technology to provide users with more convenient, intuitive, and secure ways of interacting with smartphones in daily settings. AirSign leverages both acoustic and motion sensors for user authentication by signing signatures in the air through smartphones without requiring any special hardware. This technology actively transmits inaudible acoustic signals from the earpiece speaker, receives echoes back through both built-in microphones to &ldquo, illuminate&rdquo, signature and hand geometry, and authenticates users according to the unique features extracted from echoes and motion sensors. To evaluate our system, we collected registered, genuine, and forged signatures from 30 participants, and by applying AirSign on the above dataset, we were able to successfully distinguish between genuine and forged signatures with a 97.1% F-score while requesting only seven signatures during the registration phase.

This paper addresses the Multi-Athlete Tracking (MAT) problem, which plays a crucial role in sports video analysis. There exist specific challenges in MAT, e.g., athletes share a high similarity in appearance and frequently occlude with each other, making existing approaches not applicable for this task. To address this problem, we propose a novel online multiple athlete tracking approach which make use of long-term temporal pose dynamics for better distinguishing different athletes. Firstly, we design a Pose-based Triple Stream Network (PTSN) based on Long Short-Term Memory (LSTM) networks, capable of modeling long-term temporal pose dynamics of athletes, including pose-based appearance, motion and athletes&rsquo, interaction clues. Secondly, we propose a multi-state online matching algorithm based on bipartite graph matching and similarity scores produced by PTSN. It is robust to noisy detections and occlusions due to the reliable transitions of multiple detection states. We evaluate our method on the APIDIS, NCAA Basketball and VolleyTrack databases, and the experiment results demonstrate its effectiveness.

A vehicular network is composed of an in-vehicle network (IVN) and Internet of Vehicles (IoV). IVN exchanges information among in-vehicle devices. IoV constructs Vehicle-to-X (V2X) networks outside vehicles and exchanges information among V2X elements. These days, in-vehicle devices that require high bandwidth is increased for autonomous driving services. Thus, the spread of data for vehicles is exploding. This kind of data is exchanged through IoV. Even if the Ethernet backbone of IVN carries a lot of data in the vehicle, the explosive increase in data from outside the vehicle can affect the backbone. That is, the transmission efficiency of the IVN backbone will be reduced due to excessive data traffic. In addition, when IVN data traffic is transmitted to IoV without considering IoV network conditions, the transmission efficiency of IoV is also reduced. Therefore, in this paper, we propose an IoV access gateway to controls the incoming data traffic to the IVN backbone and the outgoing data traffic to the IoV in the network environment where IVN and IoV are integrated. Computer simulations are used to evaluate the performance of the proposed system, and the proposed system shows better performance in the accumulated average transmission delay.

As an effective means of solving collision problems caused by the limited perspective on board, the cooperative roadside system is gaining popularity. To improve the vehicle detection abilities in such online safety systems, in this paper, we propose a novel multi-sensor multi-level enhanced convolutional network model, called multi-sensor multi-level enhanced convolutional network architecture (MME-YOLO), with consideration of hybrid realistic scene of scales, illumination, and occlusion. MME-YOLO consists of two tightly coupled structures, i.e., the enhanced inference head and the LiDAR-Image composite module. More specifically, the enhanced inference head preliminarily equips the network with stronger inference abilities for redundant visual cues by attention-guided feature selection blocks and anchor-based/anchor-free ensemble head. Furthermore, the LiDAR-Image composite module cascades the multi-level feature maps from the LiDAR subnet to the image subnet, which strengthens the generalization of the detector in complex scenarios. Compared with YOLOv3, the enhanced inference head achieves a 5.83% and 4.88% mAP improvement on visual dataset LVSH and UA-DETRAC, respectively. Integrated with the composite module, the overall architecture gains 91.63% mAP in the collected Road-side Dataset. Experiments show that even under the abnormal lightings and the inconsistent scales at evening rush hours, the proposed MME-YOLO maintains reliable recognition accuracy and robust detection performance.

Non-orthogonal multiple access schemes with grant free access have been recently highlighted as a prominent solution to meet the stringent requirements of massive machine-type communications (mMTCs). In particular, the multi-user shared access (MUSA) scheme has shown great potential to grant free access to the available resources. For the sake of simplicity, MUSA is generally conducted with the successive interference cancellation (SIC) receiver, which offers a low decoding complexity. However, this family of receivers requires sufficiently diversified received user powers in order to ensure the best performance and avoid the error propagation phenomenon. The power allocation has been considered as a complicated issue especially for a decentralized decision with a minimum signaling overhead. In this paper, we propose a novel algorithm for an autonomous power decision with a minimal overhead based on a tight approximation of the bit error probability (BEP) while considering the error propagation phenomenon. We investigate the efficiency of multi-armed bandit (MAB) approaches for this problem in two different reward scenarios: (i) in Scenario 1, each user reward only informs about whether its own packet was successfully transmitted or not, (ii) in Scenario 2, each user reward may carry information about the other interfering user packets. The performances of the proposed algorithm and the MAB techniques are compared in terms of the successful transmission rate. The simulation results prove that the MAB algorithms show a better performance in the second scenario compared to the first one. However, in both scenarios, the proposed algorithm outperforms the MAB techniques with a lower complexity at user equipment.

Instrumental odour monitoring systems (IOMS) are intelligent electronic sensing tools for which the primary application is the generation of odour metrics that are indicators of odour as perceived by human observers. The quality of the odour sensor signal, the mathematical treatment of the acquired data, and the validation of the correlation of the odour metric are key topics to control in order to ensure a robust and reliable measurement. The research presents and discusses the use of different pattern recognition and feature extraction techniques in the elaboration and effectiveness of the odour classification monitoring model (OCMM). The effect of the rise, intermediate, and peak period from the original response curve, in collaboration with Linear Discriminant Analysis (LDA) and Artificial Neural Networks (ANN) as a pattern recognition algorithm, were investigated. Laboratory analyses were performed with real odour samples collected in a complex industrial plant, using an advanced smart IOMS. The results demonstrate the influence of the choice of method on the quality of the OCMM produced. The peak period in combination with the Artificial Neural Network (ANN) highlighted the best combination on the basis of high classification rates. The paper provides information to develop a solution to optimize the performance of IOMS.