Abstract: WSN requires huge energy to run the sensor nodes for continuous process of sensing, actuating, processing, and transmission. Energy can be given to the devices either from the direct energy source or from the battery. An indoor wireless network can be operated by the direct energy sources, while the outdoor or remote or moving wireless sensor network can be operated through the battery power source. The biggest challenge in a battery-operated system is frequent replacement of batteries due to limited life and huge consumption of energy. Therefore, Energy Harvesting will be a better option to charge the batteries to avoid frequent change or replacement. This solution provides a longer lifespan and sustainable wireless sensor network. This paper provides a comprehensive review or guidance to a researcher about the possible energy sources in the wireless sensor network applications and hybrid approach to produce energy from the multiple sources for maximizing lifespan and sustainability of WSNs.

Abstract: Despite there has been an increasing energy price due to factors such as supply, demand, government regulation, among others, users do not like to spend their time to analyze their power consumption and establish actions to save money. Hence, there is a need for smart solutions that help users to save energy at home in an easy way. The smart home concept is attracting the attention of both academia and industry to address this need. Nowadays, high volumes of data are available in the smart home context, facilitated by the growth of internet of things (IoT)‐based devices and advanced sensing infrastructure. Therefore, it is necessary to automatically extract useful knowledge from this information to cost‐effective use of energy at home. In this sense, this work presents IntelliHome, a smart‐home system that aims to reduce electrical energy consumption at home. To this end, IntelliHome uses big data analytics technologies and Machine Learning and statistical techniques to provide users with a meaningful perspective of their electricity consumption habits aiming to actively involve them in the energy‐saving process through real‐time information and energy‐saving recommendations. This work also discusses a case study and an evaluation aligned with the objectives of this work. The obtained results verify the effectiveness of the proposed system regarding electrical energy saving.

Abstract: Rental bike sharing is an urban mobility model that is affordable and ecofriendly. The public bike sharing model is widely used in several cities across the world over the past decade. Because bike use is rising constantly, understanding the system demand in prediction is important to boost the operating system readiness. This article presents a prediction model to meet user demands and efficient operations for rental bikes using Random Forest (RF), which is a homogeneous ensemble method. The approach is carried out in Seoul, South Korea to predict the hourly use of rental bikes. RF is compared with Support Vector Machine with Radial Basis Function Kernel, k‐nearest neighbor and Classification and Regression Trees to verify RF supremacy in rental bike demand prediction. Performance Index measures the efficiency of RF compared to the other predictive models. Also, the variable importance analysis is performed to assess the most important characteristics during different seasons by creating a predictive model using RF for each season. The results show that the influence of variables changes depending on the seasons that suggest different operating conditions. RF models trained with yearly and seasonwise models show that bike sharing demand can be further improved by considering seasonal change.

Abstract: Nowadays social Networking and micro-blogging sites like Twitter are very popular and millions of users are registered on these websites. The users present on these website use these websites as a platform to express their thoughts and opinions. Our analysis of content posted on Twitter shows that users often post crime related information on Twitter. Among these crime related tweets some tweets are the crime messages that need police attention. Detection of such tweets can be beneficial in utilizing pattroling resources. The analysis of the data present on these websites can have an enormous impact. In this paper,the work is done on analyzing Twitter data to identify crime tweet that need police attention. Text mining based approach is used for classification of 369 tweets into crime and not-crime class. Classifiers such as Naive Bayesian, Random Forest, J48 and ZeroR are used. Among all of these four classifiers, Random forest classifier give the best accuracy of 98.1%.

Abstract: With large scale generation and exchange of data between IoT devices and constrained IoT security to protect data communication, it becomes easy for attackers to compromise data routes. In IoT networks, IPv6 Routing Protocol is the de facto routing protocol for Low Power and Lossy Networks (RPL). RPL offers limited security against several RPL-specific and WSN-inherited attacks in IoT applications. Additionally, IoT devices are limited in memory, processing, and power to operate properly using the traditional Internet and routing security solutions. Several mitigation schemes for the security of IoT networks and routing, have been proposed including Machine Learning-based, IDS-based, and Trust-based approaches. In existing trust-based methods, mobility of nodes is not considered at all or its insufficient for mobile sink nodes, specifically for security against RPL attacks. This research work proposes a conceptual design, named SMTrust, for security of routing protocol in IoT, considering the mobility-based trust metrics. The proposed solution intends to provide defense against popular RPL attacks, for example, Blackhole, Greyhole, Rank, Version Number attacks, etc. We believe that SMTrust shall provide better network performance for attacks detection accuracy, mobility and scalability as compared to existing trust models, such as, DCTM-RPL and SecTrust-RPL. The novelty of our solution is that it considers the mobility metrics of the sensor nodes as well as the sink nodes, which has not been addressed by the existing models. This consideration makes it suitable for mobile IoT environment. The proposed design of SMTrust, as secure routing protocol, when embedded in RPL, shall ensure confidentiality, integrity, and availability among the sensor nodes during routing process in IoT communication and networks.

Abstract: Prediction of respiratory diseases such as COPD(Chronic obstructive pulmonary disease), URTI(upper respiratory tract infection), Bronchiectasis, Pneumonia, Bronchiolitis with the help of deep neural networks or deep learning. We have constructed a deep neural network model that takes in respiratory sound as input and classifies the condition of its respiratory system. It not only classifies among the above-mentioned disease but also classifies if a person’s respiratory system is healthy or not with higher accuracy and precision.

Abstract: Calcific tendinitis is the leading cause of shoulder pain. Among patients with calcific tendinitis, 2.7%-20% are asymptomatic, and 35%-45% of patients whose calcific deposits are inadvertently discovered develop shoulder pain. If symptoms are present, complications such as decreased range of motion of the shoulder joint should be minimized while managing pain. Patients with acute calcific tendinitis respond well to conservative treatment and rarely require surgery. In contrast, patients with chronic calcific tendinitis often do not respond to conservative treatment and do require surgery. Clinical improvement takes time, even after surgical treatment. This review article summarizes the processes related to the diagnosis and treatment of calcific tendinitis with the aim of helping clinicians choose appropriate treatment options for their patients.

Abstract: Big Data and IoT based applications are promising and being necessary for almost all the fields. IoT applications provide us with beneficial services, and also they gather and transmit data to Big Data databases where data can be stored and analyzed. Big Data and IoT started to be involved in smart homes, smart healthcare, education, shopping and even in agriculture field. These Big Data and IoT based applications are growing rapidly. The more these technologies are giving us great applications and making our life better; the more cybersecurity attacks start against them. These applications are the target for attackers due to the useful and massive amount of data they have. Cybersecurity is a significant issue for these technologies. Cybersecurity threats and attacks can stop these technologies from growing, which is considered to be a negative point for us and these promising technologies. Cybersecurity threats weaken these technologies to gain full access over the user’s data. Understanding the possible applications and benefits that we could learn from these technologies is important Also, understanding and being aware of the possible threats that could threaten the various Big Data and IoT based applications is more critical Understanding the possible cybersecurity attacks and threats can help us to know about how to protect these technologies and applications from cybersecurity attacks. This research presents critical cybersecurity impacts in the form of security threats, and attacks that could be initiated against Big Data and IoT based applications and affect their growth. These impacts are elaborated using a case study of a healthcare system with its possible cybersecurity attacks, which shows the relation between cybersecurity attacks and the growth of Big Data and IoT technologies.

Abstract: In vehicular ad hoc networks (VANETs), the frequent change in vehicle mobility creates dynamic changes in communication link and topology of the network. Hence, the key challenge is to address and resolve longer transmission delays and reduced transmission stability. During the establishment of routing path, the focus of entire research is on traffic detection and road selection with high traffic density for increased packet transmission. This reduces the transmission delays and avoids carry‐and‐forward scenarios; however, these techniques fail in obtaining accurate traffic density in real‐time scenario due to rapid change in traffic density. Thus, it is necessary to create a model that efficiently monitors the traffic density and assist VANETs in route selection in an automated way with increased accuracy. In this article, a novel machine learning architecture using deep reinforcement learning (DRL) model is proposed to monitor and estimate the data essential for the routing protocol. In this model, the roadside unit maintains the traffic information on roads using DRL. The DRL predicts the movement of the vehicle and makes a suitable routing path for transmitting the packets with improved transmission capacity. It further uses predicted transmission delays and the destination location to choose the forwarding directions between two road safety units (RSUs). The application of DRL over VANETs yields increased network performance, which provides on‐demand routing information. The simulation results show that the DRL‐based routing is effective in routing the data packets between the source and destination vehicles than other existing method.

Abstract: Implementation of Maximum Power Point Tracking (MPPT) to utilize maximum output power of PV system more accurately is presented in this paper. By using MPPT, maximum possible power is taken out from Photovoltaic (PV) array. In this MPPT technique P&O algorithm is used to take out maximum solar power output with approximately no oscillation in output PV power. P&O algorithm is facile to analyze and implement. By using DC-DC boost converter and MPPT algorithm the conversion efficiency of PV system is improved. Boost convertor steps up the PV voltage level by varying its duty cycle. MPPT algorithms have been written in MATLAB and implemented in simulation. PV array and Boost converter are modeled using Sim Power System blocks.

Abstract: In today's world, large group migration of applications to the fog computing is registered in the information technology world. The main issue in fog computing is providing enhanced quality of service (QoS). QoS management consists of various method used for allocating fog‐user applications in the virtual environment and selecting suitable method for allocating virtual resources to physical resource. The resources allocation in effective manner in the fog environment is also a major problem in fog computing; it occurs when the infrastructure is build using light‐weight computing devices. In this article, the allocation of task and placement of virtual machine problems is explained in the single fog computing environment. The experiment is done and the result shows that the proposed framework improves QoS in fog environment.

Abstract: The pervasive smart grids and power markets are salient topics in the modernization of electricity networks in developed countries, which have attracted special attention during the last years. Power systems are experiencing the transition of entering the digital era because the technological growth in telecommunications and particularly, in artificial intelligence, has had an accelerated pace during the last decade. Recently, the exclusive traits of the Internet of things (IoT) have underlain the extensive application of this cutting-edge concept in the infrastructures of various technological fields. Many scholars have explained the architectures and hierarchical paradigms of deployment of this new concept for different purposes, the energy section included. The utilization of this technology can evolve the traditional ways of energy management in smart grids and power markets. By the use of IoT, the traditional methods of energy management will become obsolete so that the modernized IoT-equipped grids will demonstrate a decentralized peer-to-peer structure with a high level of autonomy all over the entire system. To achieve the targeted aim, it is recommended to integrate IoT technology with cloud technology. This integration is called CloudIoT, and it exhibits magnificent benefits in alignment with the aims of smart grids in addition to posing new challenges. In the extant study, first, an elaborate review of CloudIoT is presented. Then the opportunities, open challenges, and possible solutions are comprehensively discussed.

Abstract: Spotted hyena optimizer (SHO) is a recently developed swarm‐based algorithm in the field of metaheuristic research, for solving realistic engineering design constraint and unconstrained difficulties. To resolve complicated nonlinear physical world tasks, at times, SHO reveals deprived performance concerning to explorative strength. So, to enhance the explorative strength along with exploitation in the search region, an attempt has been made by proposing the enhanced version of classical SHO. The suggested method is designated as space transformation search (STS)‐SHO. In STS‐SHO, a new evolutionary technique named as STS technique has been incorporated with original SHO. The suggested method has been assessed by IEEE CEC 2017 benchmark problems. The efficacy of the said method has been proven by using standard measures such as given performance metrics in CEC 2017, complexity analysis, convergence analysis, and statistical implications. Further as real‐world application, the said algorithm has been applied to train pi‐sigma neural network by means of 13 benchmark datasets considered from UCI depository. From the article it can be concluded that the suggested method STS‐SHO is an effective and trustworthy algorithm, which has the ability to resolve real‐life optimization complications.

Abstract: Existing blood management systems in India function as Information Management systems that lack dynamic updates of blood usage and detailed blood trail information, starting from donation to consumption. There exists no communication platform for surplus blood in one region to be requested from another region where blood is scarce, leading to wastage of blood. Lack of transparency and proper blood quality checks have led to several cases of blood infected with diseases such as HIV being used for transfusion. This paper aims at mitigating these issues using a blockchain-based blood management system. The issue of tracking the blood trail is modelled as a supply-chain management issue. The proposed system, implemented in the Hyperledger Fabric framework, brings more transparency to the blood donation process by tracking the blood trail and also helps to curb unwarranted wastage of blood by providing a unified platform for the exchange of blood and its derivatives between blood banks. For ease of use, a web application is also built for accessing the system.

Abstract: One of the fundamental challenges of the robotics field is robot's movement. That is, why route planning is an eminent issue of robotics research and it is used to enhance autonomy of moving robots in complex environments. The objective of route planning problem is to find the shortest route without collide from initiation point to destination point so that the amount of energy consumption by robot would not exceed a predefined amount. Because neither the amount of energy consumption nor the robot's passed distance index cannot be measured precisely due to environmental conditions, and fuzzy data is used for modeling the problem and the problem would be called “Robot Fuzzy Constrained shortest Route” problem. The main contributions of this study are fivefold: (i) The mathematical model of fuzzy constrained shortest route problem (FCSRP) is formulated; (ii) An elite artificial bees' colony (EABC) algorithm is used to solve the robot's FSCRP; (iii) The proposed EABC algorithm is simulated with two fuzzy networks; (iv) The performance of the proposed approach is compared with the performance of genetic algorithm and particle swarm optimization algorithm; and (v) The results show the convergence speed of the EABC algorithm is higher than the existing algorithms.

Abstract: Due to its wide application, human activity recognition (HAR) has become a common subject for research specially with the development of deep learning. Many researchers believe that deep convolutional neural networks (DCNN) are ideal for feature extraction from signal inputs. This has gained widespread interest in using these methods to identify human actions on the mobile phone in real time. A deep network architecture using random search one dimensional convolutional neural network (RS-1D-CNN) is proposed to find best networks connections and hyper-parameters to enhance model performance. Batch normalization (BN) layer was added to speed up the convergence. Moreover, we have applied a global average pooling (GAP) for dimensionality reduction and to reduce model hyper-parameters, followed two dense connected layers. The final dense layer has a softmax activation function and a node for each potential object category. Public UCI-HAR dataset was used to evaluate model performance. Random search has been utilized to perform hyper parameter tuning to determine the optimal model parameters. Proposed model will automatically extract and classify human behaviours. Daily human activities that provided by UCI-HAR include (walking, jogging, sitting, standing, upstairs and downstairs). Results has shown that our approach outperforms both CNN, LSTM method and other state-of-the-art approaches.

Abstract: Internet of things (IoT) is a global information infrastructure that supports access to thousands of monitoring devices and user terminals. A large amount of monitoring data generated by IoT is integrated to cloud computing through the network to improve the quality of life of citizens. Fine‐grained and accurate traffic information is important for IoT network management. Software‐defined networking (SDN) is a centralized control plane as a logical control center, making network management more flexible and efficient. Then, we collect fine‐grained traffic information in SDN‐based IoT networks to improve network management. To acquire the traffic information with low overhead and high accuracy, first, we collect the statistics of coarse‐grained traffic of flows and fine‐grained traffic of links, and then we utilize the intelligent optimization methods to estimate the network traffic. To improve the granularity and accuracy of the acquired traffic information, we construct an optimization function with constraints to decrease the estimation errors. As the optimization function of traffic information is a non‐deterministic polynomial‐hard problem, we present a heuristic algorithm to obtain the optimal solution of the fine‐grained measurement. Finally, we conduct some simulations to verify the proposed measurement scheme. Simulation results show that our approach can improve the granularity and accuracy of traffic information with intelligent optimization methods.

Abstract: Credit score classification is a prominent research problem in the banking or financial industry, and its predictive performance is responsible for the profitability of financial industry. This paper addresses how Spiking Extreme Learning Machine (SELM) can be effectively used for credit score classification. A novel spike‐generating function is proposed in Leaky Nonlinear Integrate and Fire Model (LNIF). Its interspike period is computed and utilized in the extreme learning machine (ELM) for credit score classification. The proposed model is named as SELM and is validated on five real‐world credit scoring datasets namely: Australian, German‐categorical, German‐numerical, Japanese, and Bankruptcy. Further, results obtained by SELM are compared with back propagation, probabilistic neural network, ELM, voting‐based Q‐generalized extreme learning machine, Radial basis neural network and ELM with some existing spiking neuron models in terms of classification accuracy, Area under curve (AUC), H‐measure and computational time. From the experimental results, it has been noticed that improvement in accuracy and execution time for the proposed SELM is highly statistically important for all aforementioned credit scoring datasets. Thus, integrating a biological spiking function with ELM makes it more efficient for categorization.

Abstract: The rapid development of internet of things (IoT) is to be the next generation of the IoT devices are a simple target for attackers due to the lack of security. Attackers can easily hack the IoT devices that can be used to form botnets, which can be used to launch distributed denial of service (DDoS) attack against networks. Botnets are the most dangerous threat to the security systems. Software‐defined networking (SDN) is one of the developing filed, which introduce the capacity of dynamic program to the network. Use the flexibility and multidimensional characteristics of SDN used to prevent DDoS attacks. The DDoS attack is the major attack to the network, which makes the entire network down, so that normal users might not avail the services from the server. In this article, we proposed the DDoS attack detection model based on SDN environment by combining support vector machine classification algorithm is used to collect flow table values in sampling time periods. From the flow table values, the five‐tuple characteristic values extracted and based on it the DDoS attack can be detected. Based on the experimental results, we found the average accuracy rate is 96.23% with a normal amount of traffic flow. Proposed research offers a better DDoS detection rate on SDN.

Abstract: Face recognition system is broadly used for human identification because of its capacity to measure the facial points and recognize the identity in an unobtrusive way. The application of face recognition systems can be applied to surveillance at home, workplaces, and campuses, accordingly. The problem with existing face recognition systems is that they either rely on the facial key points and landmarks or the face embeddings from FaceNet for the recognition process. In this paper, we propose a hierarchical network (HN) framework which uses pre-trained architecture for recognizing faces followed by the validation from face embeddings using FaceNet. We also designed a real-time face recognition security door lock system connected with raspberry pi as an implication of the proposed method. The evaluation of the proposed work has been conducted on the dataset collected from 12 students from Faculty of Engineering and Technology, University of Sindh. The experimental results show that the proposed method achieves better results over existing works. We also carried out a comparison on random faces acquired from the Internet to perform face recognition and results shows that the proposed HN framework is resilient to the randomly acquired faces.

Abstract: The classification of the hydrocarbon reserve is a significant challenge for both oil and gas producing firms. The factor of reservoir recovery contributes to the proven reservoir growth potential which leads to a good preparation of field development and production. However, the high dimensionality or irrelevant measurements/features of the reservoir data leads to less classification accuracy of the factor reservoir recovery. Therefore, feature selection techniques become a necessity to eliminate the said irrelevant measurements/ features. In this paper, a wrapper-based feature selection method is proposed to select the optimal feature subset. A Binary Grey Wolf Optimization (BGWO) is applied to find the best features/measurements from big reservoir data obtained from U.S.A. oil & gas fields. To our knowledge, this is the first time applying the Grey Wolf Optimizer (GWO) as a search technique to search for the most important measurements to achieve high classification accuracy for reservoir recovery factor. The wrapper K-Nearest Neighbors (KNN) classifier is used to evaluate the selected features. In addition, to examine the efficiency of the proposed method, two recent algorithms namely: Whale Optimization algorithm (WAO) and Dragonfly Algorithm (DA) are implemented for comparison. The experimental results showed that, the proposed BGWO-KNN significantly outperforms benchmarking methods in terms of feature reduction as well as increasing the classification accuracy. The proposed method shows a great potential for solving the real oil & gas problems.

Abstract: The present work demonstrates the features and basic steps of applying the Dynamic Imaging of Coherent Sources (DICS) technique for Localizing oscillatory sources in a brain by MEG data during cognitive activity. As the example, we consider the problem of identification of the sources responsible for producing this oscillatory activity registering in the MEG experiment during the visual processing in a brain. The DICS technique has been shown to be effective in terms of localizing a region of activity in a brain related to cognitive processes. It revealed the areas in the occipital part of the brain that are responsible for processing visual stimuli. This approach allows one to obtain additional important information in the analysis of MEG data.