Search

Flying insect detection, identification, and counting are the key components of agricultural pest management. Insect identification is also one of the most challenging tasks in agricultural image processing. With the aid of machine vision and machine learning, traditional (manual) identification and counting can be automated. To achieve this goal, a particular data acquisition device and an accurate insect recognition algorithm (model) is necessary. In this work, we propose a new embedded system-based insect trap with an OpenMV Cam H7 microcontroller board, which can be used anywhere in the field without any restrictions (AC power supply, WIFI coverage, human interaction, etc.). In addition, we also propose a deep learning-based insect-counting method where we offer solutions for problems such as the “lack of data” and “false insect detection”. By means of the proposed trap and insect-counting method, spraying (pest swarming) could then be accurately scheduled.

Optimal operation of energy storage systems plays an important role in enhancing their lifetime and efficiency. This paper combines the concepts of the cyber–physical system (CPS) and multi-objective optimization into the control structure of the hybrid energy storage system (HESS). Owing to the time-varying characteristics of HESS, combining real-time data with physical models via CPS can significantly promote the performance of HESS. The multi-objective optimization model designed in this paper can improve the utilization of supercapacitors, reduce energy consumption, and prevent the state of charge (SOC) of HESS from exceeding the limitation. The new control scheme takes the characteristics of the components of HESS into account and is beneficial in reducing battery short-term power cycling and high discharge currents. The rain-flow counting algorithm is applied for battery life prediction to quantify the benefits of the HESS under the control scheme proposed. A much better power-sharing relationship between the supercapacitor and the lithium–ion battery (LiB) can be observed from the SIMULINK results and the case study with our new control scheme. Moreover, compared to the traditional low-pass filter control method, the battery lifetime is quantifiably increased from 3.51 years to 10.20 years while the energy efficiency is improved by 1.56%.

Anomaly detection and multi-attack classification are major concerns for cyber defense. Several publicly available datasets have been used extensively for the evaluation of Intrusion Detection Systems (IDSs). However, most of the publicly available datasets may not contain attack scenarios based on evolving threats. The development of a robust network intrusion dataset is vital for network threat analysis and mitigation. Proactive IDSs are required to tackle ever-growing threats in cyberspace. Machine learning (ML) and deep learning (DL) models have been deployed recently to detect the various types of cyber-attacks. However, current IDSs struggle to attain both a high detection rate and a low false alarm rate. To address these issues, we first develop a Center for Cyber Defense (CCD)-IDSv1 labeled flow-based dataset in an OpenStack environment. Five different attacks with normal usage imitating real-life usage are implemented. The number of network features is increased to overcome the shortcomings of the previous network flow-based datasets such as CIDDS and CIC-IDS2017. Secondly, this paper presents a comparative analysis on the effectiveness of different ML and DL models on our CCD-IDSv1 dataset. In this study, we consider both cyber anomaly detection and multi-attack classification. To improve the performance, we developed two DL-based ensemble models: Ensemble-CNN-10 and Ensemble-CNN-LSTM. Ensemble-CNN-10 combines 10 CNN models developed from 10-fold cross-validation, whereas Ensemble-CNN-LSTM combines base CNN and LSTM models. This paper also presents feature importance for both anomaly detection and multi-attack classification. Overall, the proposed ensemble models performed well in both the 10-fold cross-validation and independent testing on our dataset. Together, these results suggest the robustness and effectiveness of the proposed IDSs based on ML and DL models on the CCD-IDSv1 intrusion detection dataset.

Aiming at addressing the problem whereby existing image fusion models cannot reflect the demand of diverse attributes (e.g., type or amplitude) of difference features on algorithms, leading to poor or invalid fusion effect, this paper puts forward the construction and combination of difference features fusion validity distribution based on intuition-possible sets to deal with the selection of algorithms with better fusion effect in dual mode infrared images. Firstly, the distances of the amplitudes of difference features between fused images and source images are calculated. The distances can be divided into three levels according to the fusion result of each algorithm, which are regarded as intuition-possible sets of fusion validity of difference features, and a novel construction method of fusion validity distribution based on intuition-possible sets is proposed. Secondly, in view of multiple amplitude intervals of each difference feature, this paper proposes a distribution combination method based on intuition-possible set ordering. Difference feature score results are aggregated by a fuzzy operator. Joint drop shadows of difference feature score results are obtained. Finally, the experimental results indicate that our proposed method can achieve optimal selection of algorithms that has relatively better effect on the fusion of difference features according to the varied feature amplitudes.

With the increasing use of mobile devices, malware attacks are rising, especially on Android phones, which account for 72.2% of the total market share. Hackers try to attack smartphones with various methods such as credential theft, surveillance, and malicious advertising. Among numerous countermeasures, machine learning (ML)-based methods have proven to be an effective means of detecting these attacks, as they are able to derive a classifier from a set of training examples, thus eliminating the need for an explicit definition of the signatures when developing malware detectors. This paper provides a systematic review of ML-based Android malware detection techniques. It critically evaluates 106 carefully selected articles and highlights their strengths and weaknesses as well as potential improvements. Finally, the ML-based methods for detecting source code vulnerabilities are discussed, because it might be more difficult to add security after the app is deployed. Therefore, this paper aims to enable researchers to acquire in-depth knowledge in the field and to identify potential future research and development directions.

In this paper, we propose an FPGA-based enhanced-SIFT with feature matching for stereo vision. Gaussian blur and difference of Gaussian pyramids are realized in parallel to accelerate the processing time required for multiple convolutions. As for the feature descriptor, a simple triangular identification approach with a look-up table is proposed to efficiently determine the direction and gradient of the feature points. Thus, the dimension of the feature descriptor in this paper is reduced by half compared to conventional approaches. As far as feature detection is concerned, the condition for high-contrast detection is simplified by moderately changing a threshold value, which also benefits the reduction of the resulting hardware in realization. The proposed enhanced-SIFT not only accelerates the operational speed but also reduces the hardware cost. The experiment results show that the proposed enhanced-SIFT reaches a frame rate of 205 fps for 640 × 480 images. Integrated with two enhanced-SIFT, a finite-area parallel checking is also proposed without the aid of external memory to improve the efficiency of feature matching. The resulting frame rate by the proposed stereo vision matching can be as high as 181 fps with good matching accuracy as demonstrated in the experimental results.

Information security is considered one of the most important issues in various infrastructures related to the field of data communication where most of the modern studies focus on finding effective and low-weight secure approaches. Digital watermarking is a trend in security techniques that hides data by using data embedding and data extraction processes. Watermarking technology is integrated into different frames without adding an overheard as in the conventional encryption. Therefore, it is efficient to be used in data encryption for applications that run over limited resources such as the Internet of Things (IoT). In this paper, different digital watermarking algorithms and approaches are presented. Additionally, watermarking requirements and challenges are illustrated in detail. Moreover, the common architecture of the watermarking system is described. Furthermore, IoT technology and its challenges are highlighted. Finally, the paper provides the motivations, objectives and applications of the recent secure watermarking techniques in IoT and summarises them into one table. In addition, the paper highlights the potential to apply the modified watermark algorithms to secure IoT networks.

The recent development and adoption of unmanned aerial vehicles (UAVs) is due to its wide variety of applications in public and private sector from parcel delivery to wildlife conservation. The integration of UAVs, 5G, and satellite technologies has prompted telecommunication networks to evolve to provide higher-quality and more stable service to remote areas. However, security concerns with UAVs are growing as UAV nodes are becoming attractive targets for cyberattacks due to enormously growing volumes and poor and weak inbuilt security. In this paper, we propose a UAV- and satellite-based 5G-network security model that can harness machine learning to effectively detect of vulnerabilities and cyberattacks. The solution is divided into two main parts: the model creation for intrusion detection using various machine learning (ML) algorithms and the implementation of ML-based model into terrestrial or satellite gateways. The system identifies various attack types using realistic CSE-CIC IDS-2018 network datasets published by Canadian Establishment for Cybersecurity (CIC). It consists of seven different types of new and contemporary attack types. This paper demonstrates that ML algorithms can be used to classify benign or malicious packets in UAV networks to enhance security. Finally, the tested ML algorithms are compared for effectiveness in terms of accuracy rate, precision, recall, F1-score, and false-negative rate. The decision tree algorithm performed well by obtaining a maximum accuracy rate of 99.99% and a minimum false negative rate of 0% in detecting various attacks as compared to all other types of ML classifiers.

Computer games have been regarded as an important field of artificial intelligence (AI) for a long time. The AlphaZero structure has been successful in the game of Go, beating the top professional human players and becoming the baseline method in computer games. However, the AlphaZero training process requires tremendous computing resources, imposing additional difficulties for the AlphaZero-based AI. In this paper, we propose NoGoZero+ to improve the AlphaZero process and apply it to a game similar to Go, NoGo. NoGoZero+ employs several innovative features to improve training speed and performance, and most improvement strategies can be transferred to other nonspecific areas. This paper compares it with the original AlphaZero process, and results show that NoGoZero+ increases the training speed to about six times that of the original AlphaZero process. Moreover, in the experiment, our agent beat the original AlphaZero agent with a score of 81:19 after only being trained by 20,000 self-play games’ data (small in quantity compared with 120,000 self-play games’ data consumed by the original AlphaZero). The NoGo game program based on NoGoZero+ was the runner-up in the 2020 China Computer Game Championship (CCGC) with limited resources, defeating many AlphaZero-based programs. Our code, pretrained models, and self-play datasets are publicly available. The ultimate goal of this paper is to provide exploratory insights and mature auxiliary tools to enable AI researchers and computer-game communities to study, test, and improve these promising state-of-the-art methods at a much lower cost of computing resources.

The timely identification and early prevention of crop diseases are essential for improving production. In this paper, deep convolutional-neural-network (CNN) models are implemented to identify and diagnose diseases in plants from their leaves, since CNNs have achieved impressive results in the field of machine vision. Standard CNN models require a large number of parameters and higher computation cost. In this paper, we replaced standard convolution with depth=separable convolution, which reduces the parameter number and computation cost. The implemented models were trained with an open dataset consisting of 14 different plant species, and 38 different categorical disease classes and healthy plant leaves. To evaluate the performance of the models, different parameters such as batch size, dropout, and different numbers of epochs were incorporated. The implemented models achieved a disease-classification accuracy rates of 98.42%, 99.11%, 97.02%, and 99.56% using InceptionV3, InceptionResNetV2, MobileNetV2, and EfficientNetB0, respectively, which were greater than that of traditional handcrafted-feature-based approaches. In comparison with other deep-learning models, the implemented model achieved better performance in terms of accuracy and it required less training time. Moreover, the MobileNetV2 architecture is compatible with mobile devices using the optimized parameter. The accuracy results in the identification of diseases showed that the deep CNN model is promising and can greatly impact the efficient identification of the diseases, and may have potential in the detection of diseases in real-time agricultural systems.

In recent years, privacy awareness is concerned due to many Internet services have chosen to use encrypted agreements. In order to improve the quality of service (QoS), the network encrypted traffic behaviors are classified based on machine learning discussed in this paper. However, the traditional traffic classification methods, such as IP/ASN (Autonomous System Number) analysis, Port-based and deep packet inspection, etc., can classify traffic behavior, but cannot effectively handle encrypted traffic. Thus, this paper proposed a hybrid traffic classification (HTC) method based on machine learning and combined with IP/ASN analysis with deep packet inspection. Moreover, the majority voting method was also used to quickly classify different QoS traffic accurately. Experimental results show that the proposed HTC method can effectively classify different encrypted traffic. The classification accuracy can be further improved by 10% with majority voting as K = 13. Especially when the networking data are using the same protocol, the proposed HTC can effectively classify the traffic data with different behaviors with the differentiated services code point (DSCP) mark.

With the development of the economy and society, the demand for social security and stability increases. However, traditional security systems rely too much on human resources and are affected by uncontrollable community security factors. An intelligent security monitoring system can overcome the limitations of traditional systems and save human resources, contributing to public security. To build this system, a RISC-V SoC is first designed in this paper and implemented on the Nexys-Video Artix-7 FPGA. Then, the Linux operating system is transplanted and successfully run. Meanwhile, the driver of related hardware devices is designed independently. After that, three OpenCV-based object detection models including YOLO (You Only Look Once), Haar (Haar-like features), and LBP (Local Binary Pattern) are compared, and the LBP model is chosen to design applications. Finally, the processing speed of 1.25 s per frame is realized to detect and track moving objects. To sum up, we build an intelligent security monitoring system with real-time detection, tracking, and identification functions through hardware and software collaborative design. This paper also proposes a video downsampling technique. Based on this technique, the BRAM resource usage on the hardware side is reduced by 50% and the amount of pixel data that needs to be processed on the software side is reduced by 75%. A video downsampling technology is also proposed in this paper to achieve better video display effects under limited hardware resources. It provides conditions for future function expansion and improves the models’ processing speed. Additionally, it reduces the run time of the application and improves the system performance.

The evolution of power electronics led to rapid development in wireless charging technology, as a result, a single active switch topology was introduced. The present market utilizes inductive wireless power transfer (IPT), because of the disadvantages of cost, size, and safety concerns, research on wireless power transfer was diverted towards capacitive wireless power transfer (CPT). This paper studies the optimal impedance tracking of the capacitive wireless power transfer system for maximum power transfer. Compared to prior methods developed for maximum power point tracking in power control, this paper proposes a new approach by means of finding impedance characteristics of the CPT system for a certain range of frequencies. Considering the drone battery as an application, a single active switch Class-E2 resonant converter with circular coupling plates is utilized. Impedance characteristics are identified with the help of equations related to the input and resonant impedance. The impedance tracking is laid out for various resonant inductors, and the difference in current peak is observed for each case. Simulations verify and provide additional information on the reactive type. Additionally, hardware tests provide the variation of input current and output voltage for a range of frequencies from 70 kHz to 300 kHz. Efficiency at the optimal impedance points for a resonant inductor with 50 μH and 100 μH are tested and analyzed. It is noted that the efficiency for a resonant inductor with 50 μH is 8% higher compared to the CPT with a 100 μH resonant inductor. Further hardware tests were performed to investigate the impact of frequency and duty cycle variation. Zero-voltage-switching (ZVS) limits have been discussed with respect to both frequency and duty cycle.

In recent times, visible light communication is an emerging technology that supports high speed data communication for wireless communication systems. However, the performance of the visible light communication system is impaired by inter symbol interference, the time dispersive nature of the channel, and nonlinear features of the light emitting diode that significantly reduces the bit error rate performance. To address these problems, many environments offer a rich infrastructure of light sources for end-to-end communication. In this research paper, an effective routing protocol named the modified grasshopper optimization algorithm is proposed to reduce communication interruptions, and to provide alternative routes in the network without the need of previous topology knowledge. In this research paper, the proposed routing protocol is implemented and analyzed using the MATLAB environment. The experimental result showed that the proposed routing protocol adapts to dynamic changes in the communication networks, like obstacles and shadows. Hence, the proposed protocol achieved better performance in data transmission in terms of throughput, packet delivery ratio, end-to-end delay, and routing overhead. In addition, the performance is analyzed by varying the number of nodes like 50, 100, 250, and 500. From the experimental analysis, the proposed routing protocol achieved maximum of 16.69% and minimum of 2.20% improvement in packet delivery ratio, and minimized 0.80 milliseconds of end-to-end delay compared to the existing optimization algorithms.

In this paper, we propose a robotic arm grasping system suitable for complex environments. For a robotic arm, in order to achieve its accurate grasp of the target object, not only the vision but also a certain tracking ability should be provided. To improve the grasp quality, we propose a robotic arm grasping system using YOLOv4 combined with a particle filter (PF) algorithm, which can be applied in a nonlinear and non-Gaussian environment. Firstly, the coordinates of the bounding box in the image can be obtained through the YOLOv4 object detection algorithm. Secondly, the coordinates in the world system can be obtained through the eye-to-hand calibration system. Thirdly, a PF model can be established based on the coordinate changes of the target object. Finally, according to the predicted output of the PF, the robotic arm and the target object can reach the specific position at the same time and complete the grab. As the target object, the bowl is applied to experiments for the sake of achieving a more convincing demonstration. The experimental results show that the robotic arm grasping system proposed in this paper can accomplish the successful grasp at a rate of nearly 88%, even at a higher movement speed, which is of great significance to robot applications in various fields.

This paper aims to present carefully selected scientific papers that have pushed the boundaries in the application of advanced computational intelligence–based methods in power engineering, mainly in optimal power system management. Contemporary development of the Smart Grid and detailed framework for power grid digitalization enabled the real and efficient application of advanced optimization algorithms presented in this paper. Papers that are not directly related to Smart Grid management are also considered, since they solve the partial challenges of planning and development with metaheuristic procedures, and according to the authors, they are highly applicable and represent a fundamental starting point for wider application. This paper covers papers and research whose results are reproducible and can be realized in production-grade software. The emphasis of the paper is on the considerate and impartial way of providing a concise overview of the methods for solving technical challenges within the accepted Smart Grid architecture. The paper is the result of many years of research and commitment to this field and represents the foundation for present research and development.

Due to the COVID-19 pandemic, the world has faced a significant challenge in the increase of the rate of morbidity and mortality among people, particularly the elderly aged patients. The risk of acquiring infections may increase during the visit of patients to the hospitals. The utilisation of technology such as the “Internet of Things (IoT)” based on Fog Computing and Cloud Computing turned out to be efficient in enhancing the healthcare quality services for the patients. The present paper aims at gaining a better understanding and insights into the most effective and novel IoT-based applications such as Cloud Computing and Fog Computing and their implementations in the healthcare field. The research methodology employed the collection of the information from the databases such as PubMed, Google Scholar, MEDLINE, and Science Direct. There are five research articles selected after 2015 based on the inclusion and exclusion criteria set for the study. The findings of the studies included in this paper indicate that IoT-based Fog Computing and Cloud Computing increase the delivery of healthcare quality services to patients. The technology showed high efficiency in terms of convenience, reliability, safety, and cost-effectiveness. Future studies are required to incorporate the models that provided the best quality services using the Fog and Cloud Computation techniques for the different user requirements. Moreover, edge computing could be used to significantly enhance the provision of health services at home., This research was funded by Taif University Researchers supporting project number (TURSP-2020/55), Taif University, Taif, Saudi Arabia. Omar Cheikhrouhou thanks Taif university for its support under the project Taif University Researchers supporting project number (TURSP-2020/55), Taif University, Taif, Saudi Arabia.

In this paper, a method to enhance the dynamic characteristics of one-dimension (1D) chaotic maps is first presented. Linear combinations and nonlinear transform based on existing chaotic systems (LNECS) are introduced. Then, a numerical chaotic map (LCLS), based on Logistic map and Sine map, is given. Through the analysis of a bifurcation diagram, Lyapunov exponent (LE), and Sample entropy (SE), we can see that CLS has overcome the shortcomings of a low-dimensional chaotic system and can be used in the field of cryptology. In addition, the construction of eight functions is designed to obtain an S-box. Finally, five security criteria of the S-box are shown, which indicate the S-box based on the proposed in this paper has strong encryption characteristics. The research of this paper is helpful for the development of cryptography study such as dynamic construction methods based on chaotic systems.

A blockchain is a decentralized peer to peer platform which provides security services based on some key concepts, namely authentication, confidentiality, integrity and authorization. It is the process of recording and keeping track of the resources without the intervention of a centralized authority. This paper provides an overview of blockchains, the structure of blockchains, consensus algorithms, etc., It compares the algorithms based on their utility and limitations. Though blockchains provide secure communication, there are some minimal data leaks which are discussed. Various security issues in blockchains are discussed such as denial of service attacks, etc., In addition to security, some other blockchain challenges are presented like scalability, reliability, interoperability, privacy and consensus mechanisms for integration with AI, IoT and edge computing. This paper also explains about the importance of blockchains in the fields of smart healthcare, smart grid, and smart financial systems. Overall, this paper gives the glimpse of various protocols, algorithms, applications, challenges and opportunities that are found in the blockchain domain.

This paper aims at realizing upper limb rehabilitation training by using an fNIRS-BCI system. This article mainly focuses on the analysis and research of the cerebral blood oxygen signal in the system, and gradually extends the analysis and recognition method of the movement intention in the cerebral blood oxygen signal to the actual brain-computer interface system. Fifty subjects completed four upper limb movement paradigms: Lifting-up, putting down, pulling back, and pushing forward. Then, their near-infrared data and movement trigger signals were collected. In terms of the recognition algorithm for detecting the initial intention of upper limb movements, gradient boosting tree (GBDT) and random forest (RF) were selected for classification experiments. Finally, RF classifier with better comprehensive indicators was selected as the final classification algorithm. The best offline recognition rate was 94.4% (151/160). The ReliefF algorithm based on distance measurement and the genetic algorithm proposed in the genetic theory were used to select features. In terms of upper limb motion state recognition algorithms, logistic regression (LR), support vector machine (SVM), naive Bayes (NB), and linear discriminant analysis (LDA) were selected for experiments. Kappa coefficient was used as the classification index to evaluate the performance of the classifier. Finally, SVM classification got the best performance, and the four-class recognition accuracy rate was 84.4%. The results show that RF and SVM can achieve high recognition accuracy in motion intentions and the upper limb rehabilitation system designed in this paper has great application significance.

The second-harmonic input impedance plays a critical role on the performance of GaN power amplifiers. In a recent paper, a drain efficiency enhancement for a continuous-mode power amplifiers was reported to be achieved using active broadband second-harmonic injection at the PA input. In this paper, the strategy for selecting the second-harmonic input impedance and the necessity for using active injection in such broadband PAs are discussed in detail. Additionally, the methodology for designing an embedded broadband diplexer in the input matching network is reported. Finally, the importance of the phase of the second-harmonic signal injected is demonstrated for both CW and modulated signals using both simulation and measurement, respectively. The effectiveness of the CW and modulated active second-harmonic injection methodology presented here are validated by previously reported measurements that demonstrated an average drain efficiency improvement of 9.4% from 1.3 to 2.4 GHz for CW signals and of 9.7% at 2 GHz for a frequency-modulated 30 MHz chirp radar signal.

Many security problems in software systems are because of vulnerabilities caused by improper configurations. A poorly configured software system leads to a multitude of vulnerabilities that can be exploited by adversaries. The problem becomes even more serious when the architecture of the underlying system is static and the misconfiguration remains for a longer period of time, enabling adversaries to thoroughly inspect the software system under attack during the reconnaissance stage. Employing diversification techniques such as Moving Target Defense (MTD) can minimize the risk of exposing vulnerabilities. MTD is an evolving defense technique through which the attack surface of the underlying system is continuously changing. However, the effectiveness of such dynamically changing platform depends not only on the goodness of the next configuration setting with respect to minimization of attack surfaces but also the diversity of set of configurations generated. To address the problem of generating a diverse and large set of secure software and system configurations, this paper introduces an approach based on Reinforcement Learning (RL) through which an agent is trained to generate the desirable set of configurations. The paper reports the performance of the RL-based secure and diverse configurations through some case studies.

International audience; In modulation identification issues, like in any other classification problem, the performance of the classification task is significantly impacted by the feature characteristics. Feature weighting boosts the performance of machine learning algorithms, particularly the class of instance-based learning algorithms such as the Minimum Distance (MD) classifier, in which the distance measure is highly sensitive to the magnitude of features. In this paper, we propose an improved version of the Salp Swarm optimization Algorithm (SSA), called ISSA, that will be applied to optimize feature weights for an MD classifier. The aim is to improve the performance of a blind digital modulation detection approach in the context of multiple-antenna systems. The improvements introduced to SSA mainly rely on the opposition-based learning technique. Computer simulations show that the ISSA outperforms the SSA as well as the algorithms that derive from it. The ISSA also exhibits the best performance once it is applied for feature weighting in the above context.; In modulation identification issues, like in any other classification problem, the performance of the classification task is significantly impacted by the feature characteristics. Feature weighting boosts the performance of machine learning algorithms, particularly the class of instance-based learning algorithms such as the Minimum Distance (MD) classifier, in which the distance measure is highly sensitive to the magnitude of features. In this paper, we propose an improved version of the Salp Swarm optimization Algorithm (SSA), called ISSA, that will be applied to optimize feature weights for an MD classifier. The aim is to improve the performance of a blind digital modulation detection approach in the context of multiple-antenna systems. The improvements introduced to SSA mainly rely on the opposition-based learning technique. Computer simulations show that the ISSA outperforms the SSA as well as the algorithms that derive from it. The ISSA also exhibits the best performance once it is applied for feature weighting in the above context.

With opportunities brought by Internet of Things (IoT), it is quite a challenge to assure privacy preservation when a huge number of resource-constrained distributed devices is involved. Blockchain has become popular for its benefits, including decentralization, persistence, immutability, auditability and consensus. With the implementation of blockchain in IoT, the benefits provided by blockchain can be derived in order to make IoT more efficient and maintain trust. In this paper, we discuss some applications of IoT in different fields and privacy-related issues faced by IoT in resource-constrained devices. We discuss some applications of blockchain in vast majority of areas, and the opportunities it brings to resolve IoT privacy limitations. We, then, survey different researches based on the implementation of blockchain in IoT. The goal of this paper is to survey recent researches based on the implementation of blockchain in IoT for privacy preservation. After analyzing the recent solutions, we see that the blockchain is an optimal way for preventing identity disclosure, monitoring, and providing tracking in IoT.

Satellite-based navigation is an essential part of all the technology-dependent applications, such as road transport, cell phones, the medical field, aviation or the shipping industry, etc. The performance of the navigation systems depends upon how quickly they can acquire and process the received signals for positioning solutions. However, in dense urban or indoor environments, signal acquisition can be a challenging task due to fading as a result of multipath and/or interference. This paper presents post-processing acquisition results on Global Positioning System (GPS) signals to study the relationship between data lengths used for signal acquisition and the achieved signal power using a Fast Fourier Transform (FFT)-based circular correlation method. Based on this study, the detection performance of the FFT-based method has also been analyzed by intentionally degrading the signal power levels. A new Adaptive Data length (ADL) method for acquisition has been proposed in this paper, which can be used for speeding up the acquisition process and uses adaptive data lengths rather than fixed data lengths. The ADL method works by estimating the threshold level based on the noise present in the signal and then comparing it with the signal power levels. Less difference between the threshold level and signal power level means less data length will be used while more difference means that more data length will be used for acquisition. The proposed algorithm can be used in commercially available receivers for adopting to an adaptive acquisition process for increased efficiency.

This paper suggests an algorithm for extracting the location of a building from satellite imagery and using that information to modify the roof content. The materials are determined by measuring the conditions where the building is located and detecting the position of a building in broad satellite images. Depending on the incomplete roof or material, there is a greater possibility of great damage caused by disaster situations or external shocks. To address these problems, we propose an algorithm to detect roofs and classify materials in satellite images. Satellite imaging locates areas where buildings are likely to exist based on roads. Using images of the detected buildings, we classify the material of the roof using a proposed convolutional neural network (CNN) model algorithm consisting of 43 layers. In this paper, we propose a CNN structure to detect areas with buildings in large images and classify roof materials in the detected areas.

Three-dimensional (3D) data are easily collected in an unconscious way and are sensitive to lead biological characteristics exposure. Privacy and ownership have become important disputed issues for the 3D data application field. In this paper, we design a privacy-preserving computation system (SPPCS) for sensitive data protection, based on distributed storage, trusted execution environment (TEE) and blockchain technology. The SPPCS separates a storage and analysis calculation from consensus to build a hierarchical computation architecture. Based on a similarity computation of graph structures, the SPPCS finds data requirement matching lists to avoid invalid transactions. With TEE technology, the SPPCS implements a dual hybrid isolation model to restrict access to raw data and obscure the connections among transaction parties. To validate confidential performance, we implement a prototype of SPPCS with Ethereum and Intel Software Guard Extensions (SGX). The evaluation results derived from test datasets show that (1) the enhanced security and increased time consumption (490 ms in this paper) of multiple SGX nodes need to be balanced, (2) for a single SGX node to enhance data security and preserve privacy, an increased time consumption of about 260 ms is acceptable, (3) the transaction relationship cannot be inferred from records on-chain. The proposed SPPCS implements data privacy and security protection with high performance.

Machine learning (ML) technology has shown its unique advantages in many fields and has excellent performance in many applications, such as image recognition, speech recognition, recommendation systems, and natural language processing. Recently, the applicability of ML in wireless sensor networks (WSNs) has attracted much attention. As resources are limited in WSNs, identifying how to improve resource utilization and achieve power-efficient load balancing is becoming a critical issue in WSNs. Traditional green routing algorithms aim to achieve this by reducing energy consumption and prolonging network lifetime through optimized routing schemes in WSNs. However, there are usually problems such as poor flexibility, a single consideration factor, and a reliance on accurate mathematical models. ML techniques can quickly adapt to environmental changes and integrate multiple factors for routing decisions, which provides new ideas for intelligent energy-efficient routing algorithms in WSNs. In this paper, we survey and propose a theoretical hypothetic model formulation of ML as an effective method for creating a power-efficient green routing model that can overcome the limitations of traditional green routing methods. In addition, the study also provides an overview of past, present, and future progress in green routing schemes in WSNs. The contents of this paper will appeal to a wide range of audiences interested in ML-based WSNs.

Electric power systems are subject to failures, due to both deliberate and fortuitous events. This paper addresses the first case in which a disruptive agent aims at maximizing the damage to the network (expressed through the total cost of operation), while the system operator takes the necessary measures to mitigate the effects of this attack. The interaction between these two agents is modeled by means of a bi-level optimization problem. On one hand, the disruptive agent is positioned in the upper-level optimization problem and must decide which elements to render out of service (lines and generators), given a limited destructive budget. On the other hand, the system operator, located in a lower-level optimization problem, reacts to the attack by deploying mitigation measures in order to minimize cost overruns in system operation. Based on the aforementioned dynamic, this paper proposes a novel approach to maximize the resiliency of the power system under intentional attacks through the implementation of distributed energy resources (DERs), namely, distributed generation (DG) and demand response (DR). Three metrics are proposed to assess resilience by assigning DERs in islands generated by the destruction of lines and generators. The results obtained in a didactic 5-bus test system and the IEEE RTS-24 bus test system demonstrate the applicability and effectiveness of the proposed methodology.

Due to the constant changes of the environment and load, the insulated-gate bipolar transistor (IGBT) module is subjected to a large amount of junction temperature (Tj) fluctuations, which often leads to damage to the bond wires. The monitoring parameters of IGBTs are often coupled with Tj, which increases the difficulty of monitoring IGBTs’ health status online. In this paper, based on the collector current (Ic) and collector-emitter on-state voltage (Vce_on) online monitoring circuit, an online monitoring method of IGBT bond wire aging against interference is proposed. First, the bond wire aging model is established, and the Vce_on is selected as the monitoring parameter. Secondly, taking a three-phase inverter circuit as an example, the Vce_on and Ic waveforms of the IGBT module are monitored in real time, and the process of online monitoring is introduced accordingly. Finally, the experimental results output by RT-LAB indicate that the method proposed in this paper can accurately identify the aging state of IGBT bond wires under different conditions.

Open-source libraries are widely used in software development, and the functions from these libraries may contain security vulnerabilities that can provide gateways for attackers. This paper provides a function similarity technique to identify vulnerable functions in compiled programs and proposes a new technique called Cross-Compiler Bipartite Vulnerability Search (CCBVS). CCBVS uses a novel training process, and bipartite matching to filter SVM model false positives to improve the quality of similar function identification. This research uses debug symbols in programs compiled from open-source software products to generate the ground truth. This automatic extraction of ground truth allows experimentation with a wide range of programs. The results presented in the paper show that an SVM model trained on a wide variety of programs compiled for Windows and Linux, x86 and Intel 64 architectures can be used to predict function similarity and that the use of bipartite matching substantially improves the function similarity matching performance.

The two most critical deciding factors for power consumption are energy efficiency and cost. Power electronic circuits are widely used and play an important role in achieving high efficiency in power distribution to customers and power transfer from source to load. Furthermore, solar energy is abundant, sustainable, and pollution-free in nature. Power electronic circuits are used in high-power applications with voltages ranging from a few millivolts to thousands of volts and wattages ranging from a few mW to megawatts. This paper examines a variety of inverter topologies and their modeling, as well as a comparison of single-stage and multi-stage/inverter topologies depending on the application. The main aim of control techniques is to keep Total Harmonic Distortion (THD) to a minimum and the switching frequency within the permissible range so that inverters for renewable energy sources, electric vehicles, uninterruptible power supply (UPS) systems, and hybrid energy storage systems can work efficiently. Plug-and-play, adaptability, self-awareness, and other features should all be included in a smart inverter. Based on the findings of this comparative analysis, selection criteria are established. This comparative analysis can be used to develop selection criteria for choosing inverter circuits for the various applications described in this paper.

In this paper, we investigate the performance of a detector recently proposed by us that is applied in the relay station receiving signals from two terminals concurrently exchanging data in the two-way relaying system. This is one of the potential configurations to save resources in fifth-generation systems, similar to non-orthogonal multiple access, which is also considered for such systems. Two-way relaying can be implemented using physical network coding. This technique originates from the network coding idea, in which network nodes can perform some mathematical operations. The idea of the investigated detector lies in the application of tentative decisions about weaker signals in the detection of stronger ones and then, after improved detection of stronger user signals, achieving more reliable decisions about the weaker ones. We compare the performance of the proposed detector with the performance of a detector in which the relay makes decisions on the data symbols received from the stations participating in two-way relaying on a symbol-by-symbol basis. Simulation results performed for two-way relaying with physical network coding reported in this paper confirm the superiority of the proposed detector when compared with the standard physical network coding solution applied in the relay node.

The limitedness of the nonrenewable local energy resources in Israel, even in the background of the later gas fields’ findings, continues to force the state to devote various efforts towards ‘green’ energy development. These efforts include installations, both for the solar and for wind energy, thus improving the diversity of energy sources. While the standard discounted cash flow (DCF) method using the net present value (NPV) criterion is extensively adopted to evaluate investments, the standard DCF method is inappropriate for the rapidly changing investment climate and for the managerial flexibility in investment decisions. In recent years, the real options analysis (ROA) technique has been widely applied in many studies for the valuation of renewable energy investment projects. Taking into account the above background, we apply, in this study, the real options analysis approach for the valuation of wind energy turbines and apply it to the analysis of wind energy economic potential in Israel, which is the context of our work. We hypothesize that due to nature of wind energy production uncertainties, the ROA method is better than the alternative. The novelty of this paper includes the following: real world wind statistics of the Merom Golan site in Israel (velocity 3.73 m/s, with a standard deviation of 2.03 m/s), a realistic power generation estimation (power generation of 1205.84 kW with a standard deviation of about 0.5% in annual value which is worth about 1.3 M$ per annum), and an economic model to evaluate the profitability of such a project. We thus discuss the existing challenges of diversifying renewable energy sources in Israel by adding wind installations. Our motivation is to introduce a method which will allow investors and officials to take into account uncertainties when deciding in investing in such wind installations. The outcomes of the paper, which are obtained using the method of Weibull statistics and the Black–Scholes ROA technique, include the result that market price volatility adds to the uncertainties much more than any wind fluctuations, provided that the analysis is integrated over a long enough time.

Development of 5G networks requires a substantial increase to both spectral and power efficiency of transmitters. It is known that these two parameters are subjected to a mutual trade-off. To increase the linearity without losing power efficiency, linearization techniques are applied to power amplifiers. This paper aims to compare most popular linearization techniques to date and evaluate their applicability to upcoming 5G networks. The history of each respective linearization technique is followed by the main principle of operation, revealing advantages and disadvantages supported by concluding the latest research results. Three main groups of linearization methods currently known are feedforward, feedback, and predistortion, each with its own tradeoffs. Although digital predistortion seems to be the go-to method currently, other techniques with less research attention are still non-obsolete. A generalized discussion and a direct comparison of techniques analyzed are presented at the end of this paper. The article offers a systematic view on PA linearization problems which should be useful to researchers of this field. It is concluded that there are still a lot of problems that need to be addressed in every linearization technique in order to achieve 5G specifications.

One of the essential points of food manufacturing in the industry and shelf life of the products is to improve the food traceability system. In recent years, the food traceability mechanism has become one of the emerging blockchain applications in order to improve the anti-counterfeiting area&rsquo, s quality. Many food manufacturing systems have a low level of readability, scalability, and data accuracy. Similarly, this process is complicated in the supply chain and needs a lot of time for processing. The blockchain system creates a new ontology in the traceability system supply chain to deal with these issues. In this paper, a blockchain machine learning-based food traceability system (BMLFTS) is proposed in order to combine the new extension in blockchain, Machine Learning technology (ML), and fuzzy logic traceability system that is based on the shelf life management system for manipulating perishable food. The blockchain technology in the proposed system has been developed in order to address light-weight, evaporation, warehouse transactions, or shipping time. The blockchain data flow is designed to show the extension of ML at the level of food traceability. Finally, reliable and accurate data are used in a supply chain to improve shelf life.

This paper presents a time-slotted channel hopping (TSCH) multiple slotframe scheduling (TMSS) protocol to ensure the timeliness of energy harvesting and data transmission for sensor devices with different transmission periods in Internet of Things (IoT) networks enabled with time-switching simultaneous wireless information and power transfer (TS-SWIPT). The TMSS uses a modified three-step 6P transaction to allocate power and data cells within the slotframe. The sensor device sets the slotframe length equal to the transmission period and estimates the number of power and data cells for allocation in the configured slotframe and requests cell allocation to the hybrid access point (HAP). Upon request from a sensor device, the HAP executes a cell-overlapping prevention (COP) algorithm to resolve the cell-overlapping problem and responds to the sensor device with a candidate cell list. Upon receiving the response from HAP, the sensor device determines its power and data cells by referring to the cell list. We conducted experimental simulations and compared the TMSS performance to that of the legacy TSCH medium access control (MAC) with a single slotframe and the harvest-then-transmit-based modified enhanced distributed coordination function (EDCF) MAC protocol (HE-MAC). The results showed that TMSS outperforms legacy TSCH MAC and HE-MAC in terms of delay, effective throughput and energy utilization.

This article belongs to the Special Issue Applications and Trends in Social Robotics. “Hello, I’m the TERMINATOR, and I’ll be your server today”. Diners might soon be feeling this greeting, with Optimus Prime in the kitchen and Wall-E then sending your order to C-3PO. In our daily lives, a version of that future is already showing up. Robotics companies are designing robots to handle tasks, including serving, interacting, collaborating, and helping. These service robots are intended to coexist with humans and engage in relationships that lead them to a better quality of life in our society. Their constant evolution and the arising of new challenges lead to an update of the existing systems. This update provides a generic vision of two questions: the advance of service robots, and more importantly, how these robots are applied in society (professional and personal) based on the market application. In this update, a new category is proposed: catering robotics. This proposal is based on the technological advances that generate new multidisciplinary application fields and challenges. Waiter robots is an example of the catering robotics. These robotic platforms might have social capacities to interact with the consumer and other robots, and at the same time, might have physical skills to perform complex tasks in professional environments such as restaurants. This paper explains the guidelines to develop a waiter robot, considering aspects such as architecture, interaction, planning, and execution. This research was funded by HUMASOFT project, with reference DPI2016-75330-P, funded by the Spanish Ministry of Economy and Competitiveness, the SHARON project, with reference SHARON-CM-UC3M, funded by the Carlos III University of Madrid, and from the RoboCity2030-DIH-CM Madrid Robotics Digital Innovation Hub ("Robotica aplicada a la mejora de la calidad de vida de los ciudadanos, Fase IV"; S2018/NMT-4331), funded by "Programas de Actividades I+D en la Comunidad de Madrid" and cofunded by Structural Funds of the EU.

This paper presents a miniaturized bandpass filter, which uses half mode substrate integrated waveguide (HMSIW) structure with embedded step impedance structure (SIS). By embedding the stepped impedance structure into the top metal of the waveguide cavity, the center frequency can be quickly shifted to a lower frequency. The operating center frequency of the proposed bandpass filter (BPF) using HMSIW resonators with embedded SIS is tunable as functions of the parameters of the SIS. The design curve is provided. A filter example of the center frequency of the filter at 3.5 GHz is fabricated and measured, having the insertion loss |S21| less than 3 dB, and the return loss |S11| greater than 10 dB. The transmission zeros are located at 2.95 GHz and 3.95 GHz on both sides of the passband, both of which are lower than 30 dB. The simulation result and the measured response conform to the proposed design concept. The proposed HMSIW filter design is in line with the current 5G communication trend.

Several recent studies have shown that artificial intelligence (AI) systems can malfunction due to intentionally manipulated data coming through normal channels. Such kinds of manipulated data are called adversarial examples. Adversarial examples can pose a major threat to an AI-led society when an attacker uses them as means to attack an AI system, which is called an adversarial attack. Therefore, major IT companies such as Google are now studying ways to build AI systems which are robust against adversarial attacks by developing effective defense methods. However, one of the reasons why it is difficult to establish an effective defense system is due to the fact that it is difficult to know in advance what kind of adversarial attack method the opponent is using. Therefore, in this paper, we propose a method to detect the adversarial noise without knowledge of the kind of adversarial noise used by the attacker. For this end, we propose a blurring network that is trained only with normal images and also use it as an initial condition of the Deep Image Prior (DIP) network. This is in contrast to other neural network based detection methods, which require the use of many adversarial noisy images for the training of the neural network. Experimental results indicate the validity of the proposed method.

In this paper, we proposed a novel structure enabling the low voltage operation of three-dimensional (3D) NAND flash memory. The proposed structure has a ferroelectric thin film just beneath the control gate, where the inserted ferroelectric material is assumed to have two stable polarization states. A voltage for ferroelectric polarization (VPF) that is lower than the program or erase voltage is used to toggle the polarization state of the ferroelectric thin film, whose impact on the channel potential profile is analyzed to optimize operation voltage reduction. The channel potential of select word line (WL), where the natural local self-boosting (NLSB) effect occurs, increases due to the polarization state. Model parameters for the ferroelectric thin film of 8 nm are fixed to 15 &micro, C/cm2 for remanent polarization (Pr), 30 &micro, C/cm2 for saturation polarization (Ps), and 2 MV/cm for coercive field (Ec). Within our simulation conditions, a program voltage (VPGM) reduction from 18 V to 14 V is obtained.

Evolutionary fuzzers generally work well with typical software programs because of their simple algorithm. However, there is a limitation that some paths with complex constraints cannot be tested even after long execution. Fuzzers based on concolic execution have emerged to address this issue. The concolic execution fuzzers also have limitations in scalability. Recently, the gradient-based fuzzers that use a gradient to mutate inputs have been introduced. Gradient-based fuzzers can be applied to real-world programs and achieve high code coverage. However, there is a problem that the existing gradient-based fuzzers require heavyweight analysis or sufficient learning time. In this paper, we propose a new type of gradient-based fuzzer, MaxAFL, to overcome the limitations of existing gradient-based fuzzers. Our approach constructs an objective function through fine-grained static analysis. After constructing a well-made objective function, we can apply the gradient-based optimization algorithm. We use a modified gradient-descent algorithm to minimize our objective function and propose some probabilistic techniques to escape local optimum. We introduce an adaptive objective function which aims to explore various paths in the program. We implemented MaxAFL based on the original AFL. MaxAFL achieved increase of code coverage per time compared with three other fuzzers in six open-source Linux binaries. We also measured cumulative code coverage per total execution, and MaxAFL outperformed the other fuzzers in this metric. Finally, MaxAFL can also find more bugs than the other fuzzers.

This paper is an initial endeavor to bridge the gap between powerful Deep Reinforcement Learning methodologies and the problem of exploration/coverage of unknown terrains. Within this scope, MarsExplorer, an openai-gym compatible environment tailored to exploration/coverage of unknown areas, is presented. MarsExplorer translates the original robotics problem into a Reinforcement Learning setup that various off-the-shelf algorithms can tackle. Any learned policy can be straightforwardly applied to a robotic platform without an elaborate simulation model of the robot's dynamics to apply a different learning/adaptation phase. One of its core features is the controllable multi-dimensional procedural generation of terrains, which is the key for producing policies with strong generalization capabilities. Four different state-of-the-art RL algorithms (A3C, PPO, Rainbow, and SAC) are trained on the MarsExplorer environment, and a proper evaluation of their results compared to the average human-level performance is reported. In the follow-up experimental analysis, the effect of the multi-dimensional difficulty setting on the learning capabilities of the best-performing algorithm (PPO) is analyzed. A milestone result is the generation of an exploration policy that follows the Hilbert curve without providing this information to the environment or rewarding directly or indirectly Hilbert-curve-like trajectories. The experimental analysis is concluded by evaluating PPO learned policy algorithm side-by-side with frontier-based exploration strategies. A study on the performance curves revealed that PPO-based policy was capable of performing adaptive-to-the-unknown-terrain sweeping without leaving expensive-to-revisit areas uncovered, underlying the capability of RL-based methodologies to tackle exploration tasks efficiently. The source code can be found at: https://github.com/dimikout3/MarsExplorer.

The time-series forecasting is a vital area that motivates continuous investigate areas of intrigued for different applications. A critical step for the time-series forecasting is the right determination of the number of past observations (lags). This paper investigates the forecasting accuracy based on the selection of an appropriate time-lag value by applying a comparative study between three methods. These methods include a statistical approach using auto correlation function, a well-known machine learning technique namely Long Short-Term Memory (LSTM) along with a heuristic algorithm to optimize the choosing of time-lag value, and a parallel implementation of LSTM that dynamically choose the best prediction based on the optimal time-lag value. The methods were applied to an experimental data set, which consists of five meteorological parameters and aerosol particle number concentration. The performance metrics were: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and R-squared. The investigation demonstrated that the proposed LSTM model with heuristic algorithm is the superior method in identifying the best time-lag value.

In this paper, we present a novel incremental learning technique to solve the catastrophic forgetting problem observed in the CNN architectures. We used a progressive deep neural network to incrementally learn new classes while keeping the performance of the network unchanged on old classes. The incremental training requires us to train the network only for new classes and fine-tune the final fully connected layer, without needing to train the entire network again, which significantly reduces the training time. We evaluate the proposed architecture extensively on image classification task using Fashion MNIST, CIFAR-100 and ImageNet-1000 datasets. Experimental results show that the proposed network architecture not only alleviates catastrophic forgetting but can also leverages prior knowledge via lateral connections to previously learned classes and their features. In addition, the proposed scheme is easily scalable and does not require structural changes on the network trained on the old task, which are highly required properties in embedded systems.

In the past few years, people’s attitudes toward early childhood education (PAUD) have undergone a complete transformation. Personalized and intelligent communication methods are highly praised, which also promotes the further focus on timely and effective human–computer interaction. Since traditional English learning that relies on parents consumes more time and energy and is prone to errors and omissions, this paper proposes a system based on a convolution neural network (CNN) and automatic speech recognition (ASR) to achieve an integrated process of object recognition, intelligent speech interaction, and synchronization of learning records in children’s education. Compared with platforms described in the literature, not only does it shoot objects in the real-life environment to obtain English words, their pronunciation, and example sentences corresponding to them, but also it combines the technique of a three-dimensional display to help children learn abstract words. At the same time, the cloud database summarizes and tracks the learning progress by a horizontal comparison, which makes it convenient for parents to figure out the situation. The performance evaluation of image and speech recognition demonstrates that the overall accuracy remains above 96%. Through comprehensive experiments in different scenarios, we prove that the platform is suitable for children as an auxiliary method and cultivates their interest in learning English.

Convolutional neural networks (CNNs) have shown great success in a variety of real-world applications and the outstanding performance of the state-of-the-art CNNs is primarily driven by the elaborate architecture. Evolutionary convolutional neural network (ECNN) is a promising approach to design the optimal CNN architecture automatically. Nevertheless, most of the existing ECNN methods only focus on improving the performance of the discovered CNN architectures without considering the relevance between different classification tasks. Transfer learning is a human-like learning approach and has been introduced to solve complex problems in the domain of evolutionary algorithms (EAs). In this paper, an effective ECNN optimization method with cross-tasks transfer strategy (CTS) is proposed to facilitate the evolution process. The proposed method is then evaluated on benchmark image classification datasets as a case study. The experimental results show that the proposed method can not only speed up the evolutionary process significantly but also achieve competitive classification accuracy. To be specific, our proposed method can reach the same accuracy at least 40 iterations early and an improvement of accuracy for 0.88% and 3.12% on MNIST-FASHION and CIFAR10 datasets compared with ECNN, respectively.

In a radio frequency (RF) system, it is possible to use variable inductors for providing tunable or selective frequency range. Variable inductors can be implemented by the microelectromechanical system (MEMS) process or by using transistors as switches to change the routing of coils or coupling quantities. In this paper, we investigated the design method of a variable inductor by using MOS transistors to switch the main coil paths and the secondary coupled coils. We observed the effects of different metal layers, turn numbers, and layout arrangements for secondary-coupled coils and compared their characteristics on the inductances and quality factors. We implemented two chips in the 0.18 μm CMOS process technology for each kind of arrangement for verification. One inductor can achieve inductance values from about 300 pH to 550 pH, and the other is between 300 pH and 575 pH, corresponding to 59.3% and 62.5%, respectively, inductance variation range at 4 GHz frequency. Additionally, their fine step sizes of the switched inductances are from 0.5% to 6% for one design, and 1% to 12.5% for the other. We found that both designs achieved a large inductance tuning range and moderate inductance step sizes with a slight difference behavior on the inductance variation versus frequency.

Vehicular ad Hoc networks (VANETs) support a variety of applications ranging from critical safety applications to “infotainment” or “comfort” applications. In North America, 75 MHz of the spectrum in the 5.9 GHz band has been allocated for vehicular communication. Safety applications rely on event-driven “alert” messages as well as the periodic broadcast of Basic Safety Messages (BSMs) containing critical information, e.g., position, speed, and heading from participating vehicles. The limited channel capacity and high message rates needed to ensure an adequate level of awareness make the reliable delivery of BSMs a challenging problem for VANETs. In this paper, we propose a decentralized congestion control algorithm that uses variable transmission power levels to reduce the channel busy ratio while maintaining a high level of awareness for nearby vehicles. The simulation results indicate that the proposed approach is able to achieve a suitable balance between awareness and bandwidth usage.

In the current paper, we propose a machine learning forecasting model for the accurate prediction of qualitative weather information on winter precipitation types, utilized in Apache Spark Streaming distributed framework. The proposed model receives storage and processes data in real-time, in order to extract useful knowledge from different sensors related to weather data. In following, the numerical weather prediction model aims at forecasting the weather type given three precipitation classes namely rain, freezing rain, and snow as recorded in the Automated Surface Observing System (ASOS) network. For depicting the effectiveness of our proposed schema, a regularization technique for feature selection so as to avoid overfitting is implemented. Several classification models covering three different categorization methods namely the Bayesian, decision trees, and meta/ensemble methods, have been investigated in a real dataset. The experimental analysis illustrates that the utilization of the regularization technique could offer a significant boost in forecasting performance.