Showing papers in "Wireless Personal Communications in 2018"
TL;DR: The paper looks at the evolution of the Industrial revolution and the technologies that have impacted their growth and described how the proposed features of 5G technologies impact the Industries of the future, leading to Industries 4.0.
Abstract: Manufacturing has evolved over the course of centuries from the days of handmade goods to the adoption of water- and steam-powered machines, the invention of mass production, the introduction of electronic automation, and now beyond. Today, the benchmark for companies to keep up with, is Industry 4.0. Here, Manufacturing systems go beyond simple connection, to also communicate, analyse and use collected information to drive further intelligent actions. It represents an integration of IoT, analytics, additive manufacturing, robotics, artificial intelligence, advanced materials, and augmented reality. The paper looks at the evolution of the Industrial revolution and the technologies that have impacted their growth. The proposed features of 5G technologies are listed and described how these features impact the Industries of the future, leading to Industries 4.0. 5G promises to be a key enabler for Factories of the Future, providing unified communication platform needed to disrupt with new business models and to overcome the shortcomings of current communication technologies.
216 citations
TL;DR: A Bayesian hidden Markov model (HMM) with Gaussian Mixture (GM) Clustering approach is used to model the DNA copy number change across the genome and is compared with various existing approaches such as Pruned Exact Linear Time method, binary segmentation method and segment neighborhood method.
Abstract: The change in the DNA is a form of genetic variation in the human genome. In addition, the DNA copy number change is also linked with the progression of many emerging diseases. Array-based Comparative Genomic Hybridization (CGH) is considered as a major task when measuring the DNA copy number change across the genome. Moreover, DNA copy number change is an essential measure to diagnose the cancer disease. Next generation sequencing is an important method for studying the spread of infectious disease qualitatively and quantitatively. CGH is widely used in continuous monitoring of copy number of thousands of genes throughout the genome. In recent years, the size of the DNA sequence data is very large. Hence, there is a need to use a scalable machine learning approach to overcome the various issues in DNA copy number change detection. In this paper, we use a Bayesian hidden Markov model (HMM) with Gaussian Mixture (GM) Clustering approach to model the DNA copy number change across the genome. The proposed Bayesian HMM with GM Clustering approach is compared with various existing approaches such as Pruned Exact Linear Time method, binary segmentation method and segment neighborhood method. Experimental results demonstrate the effectiveness of our proposed change detection algorithm.
182 citations
TL;DR: The security threats and vulnerabilities imposed by the distinctive open nature of WSNs are examined and a comprehensive survey of various routing and middleware challenges for wireless networks is presented.
Abstract: Advances in hardware manufacturing technology, wireless communications, micro electro-mechanical devices and information processing technologies enabled the development of WSNs. These consist of numerous, low cost, small sensor nodes powered by energy constrained batteries. WSNs have attracted much interest from both industry and academia due to its wide range of applications such as environment monitoring, battlefield awareness, medical healthcare, military investigation and home appliances management. Thus information in sensor network needs to be protected against various attacks. Attackers may employ various security threats making the WSN systems vulnerable and unstable. This paper examines the security threats and vulnerabilities imposed by the distinctive open nature of WSNs. We first summarize the requirements in WSNs that includes both the survivality and security issues. Next, a comprehensive survey of various routing and middleware challenges for wireless networks is presented. Next, paper explores the potential security threats at different protocol layers. Here various security attacks are identified along with their countermeasures that were investigated by different researchers in recent years. We also provide a detailed survey of data aggregation and the energy-efficient routing protocols for WSNS. And finally, few unsolved technical challenges and the future scope for WSN security has been outlined.
127 citations
TL;DR: The proposed features of 5G technologies and how 5G could be the best answer for successful, implementation of Smart Cities are discussed and a few Smart City Use Cases which are enabled by 5G are listed.
Abstract: The concept of "Smart Cities" is very important as it aims to uplift the living standards of the residents by greatly improving the City's Infrastructure, Traffic management, Governance, Water and Waste management, Power management, Health systems, Safety and Security systems, Education systems etc. This paper describes the concept of Smart Cities and enumerates its various benefits. It describes various Services and Applications required to make a City Smart and the role of ICT technologies in their implementation. Further, the challenges in the current ICT systems are discussed in their role to Smart City implementation. The paper discusses the proposed features of 5G technologies and describes how 5G could be the best answer for successful, implementation of Smart Cities. It lists down a few Smart City Use Cases which are enabled by 5G. 5G will act as the backbone of IoT and pave the way for the development of Smart Cities.
112 citations
TL;DR: The most energy efficient routing protocols for homogeneous proactive networks were studied and compared and proved that energy overhead and route selection are the most effective aspects of network lifetime and network efficiency.
Abstract: Wireless sensor network (WSN) is a group of small power-constrained nodes that sense data and communicate it to the base station (BS). These nodes cover a vast region of interest (ROI) for several purposes according to the application need. The first challenge encountered in WSNs is how to cover the ROI perfectly and send the monitored data to the BS. Although the energy introduced during setup phase and the violation of energy fairness constraint of dynamic routing topologies, they achieve high network performance in terms of coverage and connectivity. In this paper, we categorize the applications of WSN based on different aspects to show the major protocol design issues. Thus, the energy efficiency of the recent proactive routing protocols is studied from different angles. The energy overhead and energy fairness of each protocol were carefully analyzed. The most energy efficient routing protocols for homogeneous proactive networks were studied and compared to highlight the research challenges and existing problems in this area. The results proved that energy overhead and route selection are the most effective aspects of network lifetime and network efficiency.
111 citations
TL;DR: A two-level resource scheduling model is proposed based on the theory of the improved non-dominated sorting genetic algorithm II (NSGA-II), which considers the diversity of different devices and can reduce the service latency and improve the stability of the task execution effectively.
Abstract: In conventional cloud computing technology, cloud resources are provided centrally by large data centers. For the exponential growth of cloud users, some applications, such as health monitoring and emergency response with the requirements of real-time and low-latency, cannot achieve efficient resource support. Therefore, fog computing technology has been proposed, where cloud services can be extended to the edge of the network to decrease the network congestion. In fog computing, the idle resources within many distributed devices can be used for providing services. An effective resource scheduling scheme is important to realize a reasonable management for these heterogeneous resources. Therefore, in this paper, a two-level resource scheduling model is proposed. In addition, we design a resource scheduling scheme among fog nodes in the same fog cluster based on the theory of the improved non-dominated sorting genetic algorithm II (NSGA-II), which considers the diversity of different devices. MATLAB simulation results show that our scheme can reduce the service latency and improve the stability of the task execution effectively.
108 citations
TL;DR: This paper reviews and summarizes artificial neural network, and emphatically analyzes its application in information, medicine, economy, control, transportation and psychology, and introduces four major characteristics of artificial Neural network, such as the non-linear, non-limitative,non-qualitative and non-convex.
Abstract: Artificial neural network is a very important part in the new industry of artificial intelligence. In China, there are many researches on artificial neural network and artificial intelligence are developing rapidly. Therefore, this paper reviews and summarizes artificial neural network, and hopes that readers can get a deeper understanding of artificial neural network. This paper first reviews the development history of artificial neural network and its related theory, and introduces four major characteristics of artificial neural network, such as the non-linear, non-limitative, non-qualitative and non-convex. Then it emphatically analyzes its application in information, medicine, economy, control, transportation and psychology. Finally, the future development trend of artificial neural network is prospected and summarized.
108 citations
TL;DR: An energy-aware clustering-based routing protocol was proposed in WSNs which is able to cluster the network and select optimal cluster heads and is better than other algorithms such as low energy adaptive clustering hierarchical (LEACH), application-specific low power routing, LACH-EP and LEACH with distance-based threshold.
Abstract: Since sensor nodes make use of battery energy, energy consumption and limitation of sensor nodes is regarded as a fundamental challenge and problem in wireless sensor nodes. Recently, in wireless sensor networks (WSNs), clustering-based energy-aware routing protocols divide neighboring nodes into separate clusters and select local cluster heads so as to combine and transmit information of each of the clusters to the central station. In this way, they attempt to maintain energy consumption balance by the network nodes. When compared with other methods, clustering methods have been able to achieve the best efficiency with regard to the enhancement of network lifetime. In this paper, using cuckoo optimization algorithm, an energy-aware clustering-based routing protocol was proposed in WSNs which is able to cluster the network and select optimal cluster heads. The proposed method considered four criteria with regard to selecting cluster heads in the targeted cuckoo algorithm, namely the remaining energy of nodes, distance to the base station, within-cluster distances and between cluster distances. The results of simulating the proposed method in Matlab environment indicated it is better than other algorithms such as low energy adaptive clustering hierarchical (LEACH), application-specific low power routing, LACH-EP and LEACH with distance-based threshold with regard to the first node die on average and packet delivery rate for six scenario.
95 citations
TL;DR: This paper could obliterate DBSCAN’s problem in selecting input parameters by benefiting from coefficient correlation, and improves detection accuracy through simultaneous analysis of those three features of temperature, humidity, and voltage.
Abstract: Anomaly is an important and influential element in Wireless Sensor Networks that affects the integrity of data. On account of the fact that these networks cannot be supervised, this paper, therefore, deals with the problem of anomaly detection. First, the three features of temperature, humidity, and voltage are extracted from the network traffic. Then, network data are clustered using the density-based spatial clustering of applications with noise (DBSCAN) algorithm. It also analyzes the accuracy of DBSCAN algorithm input data with the help of density-based detection techniques. This algorithm detects the points in regions with low density as anomaly. By using normal data, it trains support vector machine. And, finally, it removes anomalies from network data. The proposed algorithm is evaluated by the standard and general data set of Intel Berkeley Research lab (IRLB). In this paper, we could obliterate DBSCAN's problem in selecting input parameters by benefiting from coefficient correlation. The advantage of the proposed algorithm over previous ones is in using soft computing methods, simple implementation, and improving detection accuracy through simultaneous analysis of those three features.
93 citations
TL;DR: The importance of sensor in PA and the importance of WSN technologies for remote monitoring in the various applications of the agriculture field are surveyed.
Abstract: Precision agriculture (PA) is an interdisciplinary concept of integrating information technology in agriculture to increase the production and quality of the crops. One of the most important and interesting information of technology is Wireless Sensor Network (WSN). This technology is used to collect, monitor and analyse the data from the field of agriculture. This interdisciplinary technology will boost the crop productivity and maintain quality for example, monitoring the pest and disease control, animal tracking and strength of the crop. In this paper, we have surveyed the importance of sensor in PA and the importance of WSN technologies for remote monitoring in the various applications of the agriculture field.
90 citations
TL;DR: Both wavelet decomposition and reconstruction of financial time series can improve the generalization ability of the LSTM prediction model and the prediction accuracy of long-term dynamic trend.
Abstract: By combining wavelet analysis with Long Short-Term Memory (LSTM) neural network, this paper proposes a time series prediction model to capture the complex features such as non-linearity, non-stationary and sequence correlation of financial time series. The LSTM is then applied to the prediction of the daily closing price of the Shanghai Composite Index as well as the comparison of its prediction ability with machine learning models such as multi-layer perceptron, support vector machine and K-nearest neighbors. The empirical results show that the LSTM performs a better prediction effect, and it shows excellent effects on the static prediction and dynamic trend prediction of the financial time series, which indicates its applicability and effectiveness to the prediction of financial time series. At the same time, both wavelet decomposition and reconstruction of financial time series can improve the generalization ability of the LSTM prediction model and the prediction accuracy of long-term dynamic trend.
TL;DR: The primary objective of the proposed work is to enhance the lifetime of the network and to increase the packet delivered to mobile sink in the network in this proposed Energy Efficient Clustering Scheme (EECS).
Abstract: The participants in the Wireless Sensor Network (WSN) are highly resource constraint in nature. The clustering approach in the WSN supports a large-scale monitoring with ease to the user. The node near the sink depletes the energy, forming energy holes in the network. The mobility of the sink creates a major challenge in reliable and energy efficient data communication towards the sink. Hence, a new energy efficient routing protocol is needed to serve the use of networks with a mobile sink. The primary objective of the proposed work is to enhance the lifetime of the network and to increase the packet delivered to mobile sink in the network. The residual energy of the node, distance, and the data overhead are taken into account for selection of cluster head in this proposed Energy Efficient Clustering Scheme (EECS). The waiting time of the mobile sink is estimated. Based on the mobility model, the role of the sensor node is realized as finite state machine and the state transition is realized through Markov model. The proposed EECS algorithm is also been compared with Modified-Low Energy Adaptive Clustering Hierarchy (MOD-LEACH) and Gateway-based Energy-Aware multi-hop Routing protocol algorithms (M-GEAR). The proposed EECS algorithm outperforms the MOD-LEACH algorithm by 1.78 times in terms of lifetime and 1.103 times in terms of throughput. The EECS algorithm promotes unequal clustering by avoiding the energy hole and the HOT SPOT issues.
TL;DR: Radio over fiber communication system technology modulation techniques are presented in this study in order to enhance the performance behavior of optical fiber communication systems.
Abstract: Radio over fiber communication system technology modulation techniques are presented in this study in order to enhance the performance behavior of optical fiber communication systems. The proposed modulation techniques used to meet this aim mainly consist from a mixture of traditional modulation technologies. The proposed modulation technologies include merging modulation techniques such as pulse amplitude frequency modulation, quadrature amplitude frequency modulation, differential phase shift keying amplitude modulation, offset quadrature phase shift keying amplitude modulation and frequency phase modulation are applied on different optical communication system models. The different types of modulation techniques are illustrated and discriminated in current research paper that provides measured quantities details that namely received power, maximum Q-factor and minimum bit error rate regarding to simulation results. Optiwave Simulation Version 13 software is the basic tool which is used to study proposed models.
TL;DR: A PSO based improved localization algorithm is offered in this paper that reduces the error and error variance of localization whereas improves the accuracy in comparison with the existing localization algorithms.
Abstract: Wireless sensor network (WSN) is consisted of enormous amount of miniature devices recognized as sensor nodes empowered with sensing, processing, and computing abilities. The main role of WSN is sensing, gathering, and transmission of data to the destination. In several applications, the location of collected data is of much significance. Such type of information is acquired by a localization technique. So, localization is a vital issue in various applications of WSNs. On account of range estimates, the localization techniques can be divided into range based and range free. The range based schemes require added device, thus costly to implement in practice. Range free schemes reduce the expenditure because they do not need additional ranging device. Therefore, the range free methods are practiced as worthwhile alternatives to range based schemes. However, these schemes comprised more localization error as compared to range based schemes. Hence, to overcome the existing drawback of conventional DV-Hop, a PSO based improved localization algorithm is offered in this paper. Simulation results confirm that our proposed algorithm reduces the error and error variance of localization whereas improves the accuracy in comparison with the existing localization algorithms.
TL;DR: In this paper, the implementation of a research honeypot is presented which is used to learn the recent tactics and ethics used by black-hat community to attack on IoT devices, and the aim of this research work is to implement novel based secret eye server known as HIoTPOT which will make the IoT environment more safe and secure.
Abstract: Honeypot Internet of Things (IoT) (HIoTPOT) keep a secret eye on IoT devices and analyzes the various recent threats which are dangerous to IoT devices. In this paper, implementation of a research honeypot is presented which is used to learn the recent tactics and ethics used by black hat community to attack on IoT devices. As IoT is open and easy for accessing, all the intruders are highly attracted towards IoT. Recently Telnet based attacks are very famous on IoT devices to get easy access and attack on other devices. To reduce these kinds of threats, it is necessary to know in details about intruder, therefore the aim of this research work is to implement novel based secret eye server known as HIoTPOT which will make the IoT environment more safe and secure.
TL;DR: A new method for the construction of substitution boxes(S-boxes) based on points on elliptic curve over prime field is presented, which generates cryptographically strong S-boxes as compared to some of the other exiting techniques.
Abstract: Elliptic curve cryptography provides better security and is more efficient as compared to other public key cryptosystems with identical key size. In this article, we present a new method for the construction of substitution boxes(S-boxes) based on points on elliptic curve over prime field. The resistance of the newly generated S-box against common attacks such as linear, differential and algebraic attacks is analyzed by calculating their non-linearity, linear approximation, strict avalanche, bit independence, differential approximation and algebraic complexity. The experimental results are further compared with some of the prevailing S-boxes presented in Shi et al. (Int Conf Inf Netw Appl 2:689–693, 1997), Jakimoski and Kocarev (IEEE Trans Circuits Syst I 48:163–170, 2001), Guoping et al. (Chaos, Solitons Fractals 23:413–419, 2005), Guo (Chaos, Solitons Fractals 36:1028–1036, 2008), Kim and Phan (Cryptologia 33: 246–270, 2009), Neural et al. (2010 sixth international conference on natural computation (ICNC 2010), 2010), Hussain et al. (Neural Comput Appl. https://doi.org/10.1007/s00521-012-0914-5
, 2012). Comparison reveals that the proposed algorithm generates cryptographically strong S-boxes as compared to some of the other exiting techniques.
TL;DR: A reliable, efficient in terms of power consumption and high stable network is proposed for Wireless Body Area Sensor Networks using multi-hopping to reduce the distance of data communication and to save energy consumption.
Abstract: In this paper a reliable, efficient in terms of power consumption and high stable network is proposed for Wireless Body Area Sensor Networks. Eight sensor nodes are used from which two are recording critical data. These two sensors are not apart of multi-hopping but send data direct to the sink. Remaining six sensors are computed to become a forwarder node. Forwarder nodes gathers data from sensors and after aggregating sends ti the sink. Two parameters are set for cost function so that a forwarder node is selected. If a sensor is having minimum distance and maximum energy as compared to the entire nodes then it will be selected as forwarder node. Multi-hopping is used to reduce the distance of data communication and to save energy consumption. Simulation is carried out and shows stable results.
TL;DR: It is observed that multi level QAM has presented better performance than multi level PSK and finally multi level DPSK in optical OFDM systems and OSNR, SNR, and BER are improved using 4-QAM OFDM system than either QPSK or 4-DPSK.
Abstract: This paper shows the trade off between different modulation techniques such as multi level quadrature amplitude modulation, multi level phase shift keying, and multi level differential phase shift keying for upgrading direct detection optical orthogonal frequency division multiplexing systems with possible transmission distance up to 15,000 km and total bit rate of 2.56 Tb/s. The 2.56 Tb/s signal is generated by multiplexing 64 OFDM signals with 40 Gb/s for each OFDM. Variations of optical signal to noise ratio (OSNR), signal to noise ratio (SNR), and bit error rate (BER) are studied with the variations of transmission distance. Maximum radio frequency power spectrum, and output electrical power after decoder are measured for different multi level modulation techniques with carrier frequency. It is observed that multi level QAM has presented better performance than multi level PSK and finally multi level DPSK in optical OFDM systems. Maximum output power after decoder is enhanced with both 32-PSK, and 64-QAM. Quadrature signal amplitude level at encoder is upgraded with 64-QAM. It is noticed that OSNR, SNR, and BER are improved using 4-QAM OFDM system than either QPSK or 4-DPSK.
TL;DR: A protocol in form of Cluster-head Restricted Energy Efficient Protocol (CREEP) has been proposed to overcome this limitation and to further improve the network lifetime by modifying the CH selection thresholds in a two-level heterogeneous WSN.
Abstract: A magnanimous number of collaborative sensor nodes make up a Wireless Sensor Network (WSN). These sensor nodes are outfitted with low-cost and low-power sensors. The routing protocols are responsible for ensuring communications while considering the energy constraints of the system. Achieving a higher network lifetime is the need of the hour in WSNs. Currently, many network layer protocols are considering a heterogeneous WSN, wherein a certain number of the sensors are rendered higher energy as compared to the rest of the nodes. In this paper, we have critically analysed the various stationary heterogeneous clustering algorithms and assessed their lifetime and throughput performance in mobile node settings also. Although many newer variants of Distributed Energy-Efficiency Clustering (DEEC) scheme execute proficiently in terms of energy efficiency, they suffer from high system complexity due to computation and selection of large number of Cluster Heads (CHs). A protocol in form of Cluster-head Restricted Energy Efficient Protocol (CREEP) has been proposed to overcome this limitation and to further improve the network lifetime by modifying the CH selection thresholds in a two-level heterogeneous WSN. Simulation results establish that proposed solution ameliorates in terms of network lifetime as compared to others in stationary as well as mobile WSN scenarios.
TL;DR: A novel web enabled disease detection system (WEDDS) based on compressed sensing (CS) is proposed to detect and classify the diseases in leaves and statistical based thresholding strategy is proposed for segmentation of the diseased leaf.
Abstract: Plant disease detection attracts significant attention in the field of agriculture where image based disease detection plays an important role. To improve the yield of plants, it is necessary to detect the onset of diseases in plants and advice the farmers to act based on the suggestions. In this paper, a novel web enabled disease detection system (WEDDS) based on compressed sensing (CS) is proposed to detect and classify the diseases in leaves. Statistical based thresholding strategy is proposed for segmentation of the diseased leaf. CS measurements of the segmented leaf are uploaded to the cloud to reduce the storage complexity. At the monitoring site, the measurements are retrieved and the features are extracted from the reconstructed segmented image. The analysis and classification is done using support vector machine classifier. The performance of the proposed WEDDS has been evaluated in terms of accuracy and is compared with the existing techniques. The WEDDS was also evaluated experimentally using Raspberry pi 3 board. The results show that the proposed method provides an overall detection accuracy of 98.5% and classification accuracy of 98.4%.
TL;DR: The performance of LTBRD is proven theoretically and the result shows that the proposed algorithm outperforms well when compared with the existing algorithms such as RED and LSM.
Abstract: As wireless sensor networks (WSNs) are widely used in unattended environments, various physical attacks are occurred easily In this paper, location and trust based replica detection (LTBRD) method is introduced to identify the replication attack in the wireless sensor network As sensor nodes are not tamper proof, all the credentials can be copied into any number of nodes In order to solve this issue, behavior based and certificate based trust along with location information is followed in our proposed LTBRD approach Depending upon the location mismatch and the trust value the malicious node will be identified and it will be revoked from the network In this approach, the efficiency of the algorithm is been achieved by aggregation as well as without aggregation The performance of LTBRD is evaluated with the help of detection probability, energy consumption, network delay, memory requirement The performance of LTBRD is proven theoretically and the result shows that the proposed algorithm outperforms well when compared with the existing algorithms such as RED and LSM
TL;DR: This paper explores retailer's adoption of the mobile payment system; based on an extended model of technology–organization–environment (TOE) framework, eleven factors were theorized to describe retailer’s acceptance of MP systems and revealed that external pressure and relative advantages are the most important antecedents of the intention to use MP.
Abstract: The development of mobile commerce depends on extensively accepted mobile payment (MP) systems Even though new MP methods have been gradually induced in the market, but their adoption has stayed modest Little research has been conducted to examine and explain views of owners or managers of on the new payment technology This paper explores retailer’s adoption of the mobile payment system; based on an extended model of technology–organization–environment (TOE) framework, eleven factors were theorized to describe retailer’s acceptance of MP systems Data was collected from 188 retails stores First, structural equation modeling (SEM) was applied to check which factor had a significant influence on MP adoption Following, the neural network technique was used to rank the significant predictors attained from SEM The results revealed that external pressure and relative advantages are the most important antecedents of the intention to use MP The results of this study will be useful for MP providers/suppliers in making optimum strategies Implications, limitation and future research are discussed
TL;DR: A new energy-efficient clustering routing protocol—WPO-EECRP is proposed, which considers multiple clustering factors related to energy consumption to select cluster head such as residual energy, distance from node to base station, neighbors and number of neighbors through weighting.
Abstract: Clustering is an important way to realize energy saving in wireless sensor network. Combining the revelation of previous clustering protocols, we propose a new energy-efficient clustering routing protocol--WPO-EECRP. In order to achieve the goal of energy conservation, this protocol considers multiple clustering factors related to energy consumption to select cluster head such as residual energy, distance from node to base station, neighbors and number of neighbors through weighting, and finally transforms the question of efficient Clustering into the optimization of two parameters: neighbor communication range R and weight coefficient W of clustering factors. So the network is divided into clusters under the configuration of optimal parameters $$R_{opt}$$Ropt and $$W_{opt}$$Wopt, and operates until it completes data communication. Simulation results show that our proposed protocol can extend the network lifetime over 1.4 times as long as EECF and EACHP, two very representative clustering protocols published recently, significantly reduces the energy consumption, which has a good performance.
TL;DR: A deep learning-based fully convolutional encoder-decoder network for segmenting lung fields from chest radiographs that is especially suitable for lung field segmentation is presented.
Abstract: Segmentation of lung fields is an important pre-requisite step in chest radiographic computer-aided diagnosis systems as it precisely defines the region-of-interest on which different operations are applied. However, it is immensely challenging due to extreme variations in shape and size of lungs. Manual segmentation is also prone to large inter-observer and intra-observer variations. Thus, an automated method for lung field segmentation with sufficiently high accuracy is unsparingly required. This paper presents a deep learning-based fully convolutional encoder-decoder network for segmenting lung fields from chest radiographs. The major contribution of this work is in the unique design of the encoder-decoder network that makes it especially suitable for lung field segmentation. The proposed network is trained, tested and evaluated on publicly available standard datasets. The result of evaluation indicates that the performance of the proposed method, i.e. accuracy of 98.73% and overlap of 95.10%, is better than state-of-the-art methods.
TL;DR: The objective of this paper, is to automate the whole wireless sensor network (WSN) system with a control over water pumps and dripper valves to achieve optimal water supply control and surveillance.
Abstract: In a developing country like India, there is an exponential rise in population nutrition requirement. To meet up with both the ends, the agricultural techniques should be perfected for optimal yield and quality. Irrigation and soil property monitoring system using sensors can be automated and operated wirelessly to achieve optimal water supply control and surveillance. The objective of this paper, is to automate the whole wireless sensor network (WSN) system with a control over water pumps and dripper valves. The humidity, temperature and pH sensor’s percepts provide a feedback, to control the water content of the soil. The system has an low-cost and energy reliable ZigBee for sensor data transformation, high-range GPRS system for data storing and analysis, and the whole system is powered by Solar panels which makes it self-sustainable. Customizable options for different crop with different requirements make it a versatile WSN system for automated irrigation based water management.
TL;DR: A mathematical model is proposed that studies the epidemic behavior of digital worms with various communication radius and node distributed density and shows that the proposed model is efficient as it has the low rate of the infectious node for different communication radius.
Abstract: The wireless sensor networks (WSNs) have imminent constrains that makes security a crucial issue. Weak defense capability makes WSN a soft target against worm attacks. A single compromised node can spread the worm via communication in the entire network. In this paper, we propose a mathematical model that studies the epidemic behavior of such digital worms. Furthermore, we study the effect of these worms with various communication radius and node distributed density. We investigate the proposed model using the stability theory of differential equations. Basic reproduction number is found that helps us to find the threshold values for communication radius and node density distribution. The proposed model is checked and validated through extensive simulation results. Finally, we compare our scheme with the existing schemes. Comparison analysis shows that the proposed model is efficient as it has the low rate of the infectious node for different communication radius.
TL;DR: Two Nature Inspired Algorithm based improved variants of Distance Vector Hop are proposed to reduce the problem of high localization error for 2-dimensional and 3-dimensional WSNs and prove the superiority of proposed algorithms over traditional DV-Hop in terms of localization error.
Abstract: Localization is a significant challenge in the area of wireless sensor networks (WSNs). Distance Vector Hop (DV-Hop) algorithm is most preferable algorithm due to its low cost, distributed nature, and its feasibility for all kinds of sensor networks, but it suffers from high localization error. In order to reduce the problem of high localization error for 2-dimensional and 3-dimensional WSNs, two Nature Inspired Algorithm based improved variants have been proposed. The first one uses Grey-Wolf optimization (GWO-DV-Hop) to identify a better estimate of average distance per hop and second one, a weighted Grey-Wolf optimization (Weighted GWO-DV-Hop), finds average distance per hop as computed by each beacon node using grey wolf algorithm and then, a weighted approach is applied by each node to get weighted average distance per hop (weights based on distance from each beacon) so as to consider impact of all types of beacons. The results prove the superiority of proposed algorithms over traditional DV-Hop in terms of localization error.
TL;DR: A setup and configuration task of a control plane to work as an SDN controller is explained in this paper and a performance comparison of two OpenFlow-enabled controllers, namely, POX and Floodlight, is tested over different network topologies.
Abstract: Software-Defined Networking (SDN) is an emerging network architecture that is adaptable, dynamic, cost-effective, and manageable. The SDN architecture is a form of network virtualization where the network controlling functions and forwarding functions are decoupled. A setup and configuration task of a control plane to work as an SDN controller is explained in this paper. This paper includes a brief survey of different SDN based OpenFlow-enabled controllers available in various programmable languages. This paper mainly focuses on two OpenFlow-enabled controllers, namely, POX--a Python-based controller and Floodlight--a Java-based controller. A performance comparison of both controllers is tested over different network topologies by analyzing network throughput and round-trip delay using an efficient network simulator called Mininet. A single, linear, tree and custom (user-defined) topologies are designed in Mininet by enabling external controllers. It is obtained that, a percentage improvement in round-trip time for Floodlight over POX is 11.5, 13.9, 19.6 and 14.4% for single, linear, tree and custom topology respectively. Similarly, a percentage improvement in throughput for Floodlight over POX is 5.4, 8.9, 3.8 and 4.9% for single, linear, tree and custom topology respectively.
TL;DR: The proposed hybrid cuckoo search (CS) and harmony search (HS) algorithm is hybrid as CHSA to improve the optimization problem and a new multi-objective function is proposed by combining cost, energy consumption, memory usage, credit and penalty.
Abstract: Cloud Computing is a gathering of physical and virtualized assets gave to the clients according to request and pay per uses bases via internet. Basically, the task scheduling and resource allocation two features are considered such as cost and makespan. In order to achieve better performance in task scheduling, resource allocation and task scheduling must be precisely organized and optimized jointly. Several works have been published in the literature to do the scheduling in cloud. In this paper, for enhancing the scheduling process cuckoo search (CS) and harmony search (HS) algorithm is hybrid as CHSA to improve the optimization problem. These two algorithms are effectively combined to do intelligent process scheduling. According to this, a new multi-objective function is proposed by combining cost, energy consumption, memory usage, credit and penalty. Finally, the performance of the CHSA algorithm is compared with different algorithms such as existing hybrid cuckoo gravitational search algorithm, individual CS and HS algorithm with various multi-objective parameters. By analyzing the result our proposed CHSA algorithm attain minimum cost, minimum memory usage, minimum energy consumption, minimum penalty and maximum credit compared to existing techniques.
TL;DR: An improved DEA model is evaluated, which is a combination of traditional C2R model and fuzzy mathematics, which forms a new fuzzy DEA model that overcomes the strong objective factors that in the traditional DEA model and not support fuzzy input and output.
Abstract: In this paper, we evaluate the developer’s efficiency by an improved DEA model. It is a combination of traditional C2R model and fuzzy mathematics, which forms a new fuzzy DEA model. The model overcomes the strong objective factors that in the traditional DEA model and not support fuzzy input and output. It is conducive to improve the efficiency of the developer, which is very important for decision of makers.