International Journal of Sensors, Wireless Communications and Control

Internet of Things (IoT), Cloud, Big Data and AI-Machine Learning are topics of contemporary research interest. They cover not only information and communication technology, but also all kinds of systems in our society, including business, finance, industry, manufacture, management, and environment. IoT connects the physical world to the Internet and generates big amount of data. Cloud computing environment facilitates the processing of large data and makes intelligent decisions based on large data analyses and machine learning. This Thematic Special Issue on IoT, Cloud, Big Data and Machine Learning: Recent Advances and Future Trends of the Journal International Journal of Sensors, Wireless Communications and Control incorporate thirteen (13) articles identified with the field. A short review about the commitments for this Thematic Special Issue is as follows: 1. P. Chandrashaker Reddy and A. Suresh Babu contribute an article entitled “An Enhanced Multiple Linear Regression Model for Seasonal Rainfall Prediction”. The main goal of this project is early and proper rainfall forecasting, that helpful to people who live in regions which are inclined natural calamities such as floods and it helps agriculturists for decision making in their crop and water management using big data analytics which produces high in terms of profit and production for farmers. In this project, we proposed an advanced automated framework called Enhanced Multiple Linear Regression Model (EMLRM) with MapReduce algorithm and Hadoop file system. We used climate data from IMD (Indian Metrological Department, Hyderabad) in 1901 to 2002 period. 2. Nguyen Thi Ngoc Anh, Nguyen Danh Tu, Vijender Kumar Solanki, Nguyen Linh Giang, Vu Hoai Thu, Luong Ngoc Son, Nguyen Duc Loc, Vu Thanh Nam contribute an article entitled “Integrating Employee Value Model with Churn Prediction”. The process of prediction integrating Churn, value of employee and machine learning are described detail in 6 steps. The pros of integrating model gives the more necessary results for company than Churn prediction model but the cons is complexity of model and algorithms and speed of computing. A case study of an organization with 1470 employee positions is carried out to demonstrate the whole integrating churn predict, EVM and machine learning process. The accuracy of the integrating model is high from 82% to 85%. Moreover, the some results of Churn and value employee are analyzed. 3. Charu Bhardwaj, Shruti Jain and Meenakshi Sood contribute an article entitled “Automated Diagnostic Hybrid Lesion Detection System for Diabetic Retinopathy Abnormalities”. In this research paper, an automated lesion detection diagnostic scheme has been proposed for early detection of retinal abnormalities of red and yellow pathological lesions. The algorithm of the proposed Hybrid Lesion Detection (HLD) includes retinal image pre-processing, blood vessel extraction, optical disc localization and detection stages for detecting the presence of diabetic retinopathy lesions. Automated diagnostic systems assist the ophthalmologists practice manual lesion detection techniques which are tedious and time-consuming. Detailed statistical analysis is performed on the extracted shape, intensity and GLCM features and the optimal features are selected to classify DR abnormalities. Exhaustive statistical investigation of the proposed approach using visual and empirical analysis resulted in 31 significant features. The results show that the HLD approach achieved good classification results in terms of three statistical indices: accuracy, 98.9%; sensitivity, 97.8%; and specificity, 100% with significantly less complexity. 4. Anurag Satpathy, Ganapati Panda, Rajasekhar Gogula and Renu Sharma contribute an article entitled “Low Complexity Adaptive Nonlinear Models for the Diagnosis of Periodontal Disease”. The paper addresses a specific clinical problem of diagnosis of periodontal disease with an objective to develop and evaluate the performance of low complexity adaptive nonlinear models (ANM) using nonlinear expansion schemes and describes the basic structure and development of ANMs in detail. Diagnostic data pertaining to periodontal findings of teeth obtained from patients have been used as inputs to train and validate the proposed models. 5. Sarat Chandra Nayak, Subhranginee Das and Mohd Dilsad Ansari contribute an article entitled “TLBO-FLN: Teachinglearning Based Optimization of Functional Link Neural Networks for Stock Closing Price Prediction”. Stock closing price prediction is enormously complicated. Artificial neural networks (ANN) are excellent approximation algorithms applied to this area. Several nature-inspired evolutionary optimization techniques are proposed and used in the literature to search the optimum parameters of ANN based forecasting models. However, most of them need fine-tuning of several control parameters as well as algorithm specific parameters to achieve optimal performance. Improper tuning of such parameters either leads toward additional computational cost or land at local optima. Teaching learning based optimization (TLBO) is a newly proposed algorithm which does not necessitate any parameters specific to it. The intrinsic capability of functional link artificial neural network (FLANN) to recognize the multifaceted nonlinear relationship present in the historical stock data made it popular and got wide applications to stock market prediction. This article presents a hybrid model termed as teaching learning based optimization of functional neural networks (TLBO-FLN) by combining the advantages of both TLBO and FLANN. 6. Sonal Agrawal and Pradeep Tripathi contribute an article entitled “Intuitionistic Fuzzy Score Function based Multi-Criteria Decision Making Method for Selection of Cloud Service Provider”. Cloud computing (CC) has received great attention from the scholarly researchers and IT companies. CC is a standard that offers services through the Internet. The standard has been manipulated by existing skills (such as collect, peer-to-peer and grid computing) and currently accepted by approximately all major associations. Various associations like as Microsoft and Facebook have revealed momentous investments in CC and currently offer services with top levels of reliability. The well-organized and precise evaluation of cloud-based communication network is an essential step in assurance both the business constancy and the continuous open services. 7. Syed Rameem Zahra and Mohammad Ahsan Chishti an article entitled “A Collaborative Edge-Cloud Internet of Things based Framework for Securing the Indian Healthcare System”. Today, 73 years after the independence and twenty years after the turn of the century, “Health for All” which should have been accomplished by now, remains a far-fetched and an elusive dream. Instead, the people of India are bequeathed a triple burden of disease: sustaining the weight of transmittable infections, expanding burden of nontransferable illnesses, and a healthcare system not efficient enough to handle them both. At present, India is home to one-third of the poor population around the world. After a high population growth rate, unregulated and inefficient healthcare is the major cause for this abjection and poverty. The global position of India vis-à-vis the health indicators like Infant Mortality Rate (IMR), Crude Birth Rate (CBR), Crude Death Rate (CDR) and life expectancy is shocking, shameful and on a downward trend. The objective of this paper was to identify the major issues in the Indian healthcare system and offer Internet of Things (IoT) based solutions. 8. Tausifa Jan Saleem and Mohammad Ahsan Chishti contribute an article entitled “Exploring the Applications of Machine Learning in Healthcare”. The objective of the research is to help the researchers in this field to get a comprehensive overview of the machine learning applications in healthcare. Apart from revealing the potential of machine learning in healthcare, this paper will serve as a motivation to foster advanced research in the domain of machine intelligence-driven healthcare. 9. Cerene Mariam Abraham, M. Sudheep Elayidom and T. Santhanakrishnan contribute an article entitled “Big Data Analysis for Trend Recognition using Machine Learning Techniques”. This paper performs big data analytics on the Indian derivative market and identifies a trend with the help of interdisciplinary areas such as cloud computing, machine learning and statistical computing. 10. Mohammad Irfan Bala and Mohammad Ahsan Chishti contribute an article entitled “Comparative Analysis of Load Balancing Algorithms for Cloud Computing in IoT”. This work focuses on multiple load balancing algorithms whose performance has been analysed and compared under varying load conditions. Cloud computing is a widely adopted computing paradigm and its importance has increased multi-folds in the recent past due to the inception of Internet of Things (IoT). 11. Ravinder Ahuja, Vineet Maheshwari, Siddhant Manglik, Abiha Kazmi, Rishika Arora and Anuradha Gupta contribute an article entitled “Malicious apps Identification in Android Devices Using Machine Learning Algorithms”. In this paper, malicious apps detection system is implemented using machine learning algorithms. For this 330 permission based features of 558 android applications are taken into consideration. The main motto of this work is to develop a model which can effectively detect the malicious and benign apps. In this we have used six feature selection techniques which will extract important features from 330 permission based features of 558 apps and further fourteen classification algorithms are applied using Python language. 12. Mohammad Khalid Pandit, Roohie Naaz Mir and Mohammad Ahsan Chishti contribute an article entitled “Adaptive Deep Neural Networks for the Internet of Things”. Deep neural networks have become the state of art technology for real world classification tasks due to their ability to learn better feature representations at each layer. However, the added accuracy that is associated with the deeper layers comes at a huge cost of computation, energy and added latency. The implementation of such architectures in resource constraint IoT devices is computationally prohibitive due to its computational and memory requirements. These factors are particularly severe in IoT domain. In this paper we propose adaptive deep neural network (ADNN) which gets split across the compute hierarchical layers i.e. edge, fog and cloud with all splits having one or more exit locations. At every location the data sample adaptively chooses to exit from the NN (based on confidence criteria) or get fed into deeper layers housed across different compute layers. 13. Midde Veenkateswarlu Naik, D. Vasumathi and A.P. Siva Kumar contribute an article entitled “An Improved Intelligent Approach to Enhance the Sentiment Classifier for Knowledge Discovery Using Machine Learning”. The objective of the research issue sentiment classifier accuracy has been hiked with the help of Kernel-based Support Vector Machine (SVM) based on parameter optimization is applied. The optimal feature selections to classify sentiment or opinion towards about review documents have been determined with the help of particle swarm optimization approach. The proposed method utilized three datasets to simulate the results such as airline sentiment data, weather sentiment data, and global warming data that are freely available datasets. We hope that the quality research work published in this special issue will be able to serve the concerned humanity, science and technology.

Welcome to the special issue on “Recent research in network security analytics” in International Journal of Sensors, Wireless Communications and Control. With the ripeness of network data and encroachment of security technologies, data analytics now-adays plays a very significant role in our day-to-day lives. Internet is one of the leading accomplishment of this epoch thus securing it is also a precedence. International Journal of Sensors, Wireless Communications and Control is a peer reviewed journal considers both theoretical and implementation based papers. Network security and Data analytics is an important call for present society where information technology and services pass through each facet of our lives. However, this is demanding to achieve, as technology is changing at a rapid speed and our systems turn into ever more complex. We are gradually more dependent upon such information and communications infrastructures, and the threats we face are organized and exploit our dependency by the attackers or cyber criminals. Moreover, cyber space is considered as fifth battlefield after land, air, water and space. The aim of this issue is to provide insight mechanisms while handling data; provide conceptual understanding of network security issues, challenges and mechanisms; develop basic skills of secure network architecture and explain the theory behind the security of networks, analytics and different cryptographic algorithms. It is to present the most recent challenges and developments in data analytics and networks. It also provides a forum for researchers, practitioners and educators to present and discuss the most recent innovations, trends, and concerns, practical challenges encountered and the solutions adopted in these fields. Original research papers and state of the art reviews will be accepted. We anticipate that the special issue will open new entrance for further research and technology improvements in this important area. In this regard, the first article is devoted to investigate that current wireless networks are based on unicast routing protocol derived from wired networks. The purpose of this paper is to implement and evaluate opportunistic routing protocols in new generation’s wireless network. This is a comparative study between two opportunistic protocols, which are ExOR (Extremely Opportunistic Routing protocol) and SOAR (Simple Opportunistic Adaptive Routing protocol). The main goal of this survey is to show the benefits required by using opportunistic approach to optimize the new generation’s wireless networks operations and implemented the most used protocols under MATLAB framework [1]. The second article proposed a defense model for wireless sensor network against worms attack based on the concept of epidemic theory. This model basically focused on mechanism which can be used for protection of sensor network against malware attack. They derived an expression for basic reproduction number this helps in study of worm dynamics and development of control mechanism. The stability of network depends on the value of basic reproduction number explained the worm free and endemic equilibrium. They also find the threshold value of communication radius and node density. Correlate the basic reproduction number and threshold value of communication radius and study its impact in the design of wireless sensor network. Explain the effect of quarantine and recovery on the infectious nodes with the variation of parameters and showed that if the rate of recovery increases the number of infected nodes decreases. The quarantine class of nodes helps in controlling of worm spread in the wireless sensor network. The proposed model is efficient in comparison to existing model proved by simulation. This is a good idea for the development of an antivirus for wireless sensor network against worm attack [2]. The third article focuses on the infrastructure less operating mechanism of MANETs is leading to their popularity and extending their role in the operations of certain real-time applications as well as certain multi- media applications. For MANETs being able to support such applications, the prime requirement is to support efficient routing as well as to incorporate efficient QOS mechanisms. This guides multiple research trends towards MANET for categories like: QOS (Quality of Service), efficient Routing etc. The approach proposed in this paper centers on the methods that can overcome the limitations faced by the Zone Routing Protocol when used for large networks and improve QOS thus making the use of MANET in real time applications feasible. The proffered scheme combines the advantages provided by aggregation of routes, introduce a central entity and optimize QOS based network performance. The algorithm divides the zones into bigger zones within the network and appoints a Zone Head node for each newly formed bigger zone which is a collection of nodes bigger than a ZRP zone with Zone Head as the central administrator. It then aggregates the routes at the Zone Head which works as a central entity and routes the traffic into the cluster by the help of Route aggregation mechanism thus, enhancing ZRP performance [3]. In the ever evolving field of software engineering the quality and predictability of success for a project has been of concern for Project Managers. The next article focused on this concern by proposing certain mathematical models, designated as process performance models (PPMs), which enhance the process improvement and improves predictability factor for a project success. Mathematical model selected can be like Queuing Theory, Time Series, Fuzzy logic etc. based on problem specified and nature of industry data. This PPMs approach can lead to solution for similar problems and avoids rebuilding solution every time. The benefit which accrues with design of PPM is the ability to predict and tune the parameters affecting performance of the project to achieve desired result. The building of these PPMs for various real life project situations has not been attempted by industry on a large scale. In case a model does not achieve the performance levels as specified by the project or baselines for similar projects, the model is rejected. In the real life problem discussed, authors work out Success of a given project based on Bayesian solution for a given network problem. Also, the authors demonstrate how to assess process capability. The solution shows that it is possible to display a network problem with non-numeric data by a relationship among variables as parentchild in a tree structure. The solution is based on developing conditional probability tables. PPMs can be developed for different emerging application areas like Cloud computing, e-Governance, Application Service Maintenance etc. and a library of models can be created by an IT company. The relevant model can be selected by a Manager from this Library. The authors opine that in future, building PPMs may become a necessity in High Maturity IT Organizations. The last article explored that RF energy harvesting is getting popular in research community because it provides useful electrical energy source for wireless sensor network applications. Its popularity is due to its physically separated power transmitter and power receiver topology. Although the energy received using the RF energy transfer has its own limitation of distance from the RF power transmitter but this technology provides enough power and energy to run an ultra-low power electronics circuits. Ambient RF sources (e.g. BTS towers, TV towers, Radio towers, Wi-Fi sources etc.) also motivate the researchers to develop RF energy harvesters which easily match with RF sources and starts to convert RF energy into useful electrical energy. In this article, multiple experiments have been performed over the RF energy harvesters on the base of number of stages of multiplier, matching networks, and equivalent practical resistive load. Different stages of RF energy harvester have been implemented and optimized. The optimization of the RF energy harvester has been performed using the inductor and capacitor circuit used in matching network [4].The circuit is optimized in terms of return power loss (S11) and total overall efficiency. In this article, the voltage multiplier is investigated without inductor and capacitor matching network due to which maximum efficiency of 60% at 12dBm is achieved at 9th stage of voltage multiplier and only 5% at -15dBm. Matching network with inductor (L) and capacitor (C) has been developed to achieve better S11 and efficiency. The maximum S11 of -49dB achieved for 3rd stage voltage multiplier while the efficiency at this value is less than 30% for -20dBm to 20dBm input RF power range. The value of L and C for such case is 21.24nH and 6.9pF respectively. In the next experiment, the efficiency is tried to get improved and the maximum efficiency of 3rd stage was 68% but this is found that for this case the value of S11 is -2.4dB. For improved efficiency the value of L and C is 26.5nH and 6.3pF, respectively. These results hold same theory for all stages of voltage multipliers. There is scope of research by finding the value of efficiency and S11 by using fabricated modules of simulated RF energy har- vesters. The comparison with the simulated values may provide more authenticate results and new dimension of designing of RF energy harvesters. The research helps the research community to design the more appropriate RF energy harvester for their applications. Finally, we would like to thank all the reviewers for their excellent work and the authors for their contribution. We expect that International Journal of Sensors, Wireless Communications and Control will provide the best platform for the authors and the readers, with a comprehensive overview of the most recent developments in information management research.

In this special issue of “International Journal of Sensors, Wireless Communications and Control”, the projection is to publish research contributions that significantly advance the state-of-the-art research, and six research articles explore new designing techniques, methodologies, concepts and protocols. Singh et al, presents a cloud based environment parameter monitoring system. Wireless Sensor Area Network is developed using ZigBee and NodeMCU. Mehta et al, analysed the benefits of Clustering when it comes to scalability and proposes an algorithm using the clustering mechanism. Sharma et al, examined the dataset PIDD (Pima Indian Diabetes dataset) for the model. Dataset was trained offline using the predictive techniques SVM, Naive Bayes and K-NN. Performance analysis was performed on the basis of response time and waiting time of a request. Gerg et al, validated and analyzed the performance of our algorithm by using the CloudSim toolkit to simulate the cloud environment. Verma, focused on the second option to design an efficient RSA variant. An improved RSA variant is designed by adding MultiPrime feature to Dual RSA on the decryption side to increase the decryption speed. Bazaz and Zafar, presented a technique of using GA based approach in cloud network for QOS optimization of parameters like packet drop rate and hop count.

No Text Found