Search

The current wave of technologies with increased awareness among customers and retaining customers has a vital role in the growth of the company. A good indicator of service satisfaction of customers and service quality is customer churn. In order to enable the organizations to understand customers for churning, intelligible and accurate models are needed. There have been several techniques of data mining that were applied for the prediction of churn. The extensive research in Artificial Intelligence has made it feasible to study and learn the aspects accounting for such customer churn. The work presents effective solutions to all these challenging problems in Customer Churn Prediction (CCP). The study uses datasets in the telecommunication industry, the Artificial Neural Networks (ANN), and the Random Forests (RF) to determine the factors that influence consumer churn. A hybrid ANN-based work is proposed for predicting CCP. The results of the experiment proved that the proposed method achieves better levels of performance. The classification accuracy of ANN-4 hidden layers improves its result compared to RF and ANN-2 hidden layers. The maximum accuracy attained by ANN-2 hidden layers is 88.14% and by ANN-4 hidden layers is 90.34%.

Human identification plays a prominent role in terms of security. In modern times security is becoming the key term for an individual or a country, especially for countries which are facing internal or external threats. Gait analysis is interpreted as the systematic study of the locomotive in humans. It can be used to extract the exact walking features of individuals. Walking features depends on biological as well as the physical feature of the object; hence, it is unique to every individual. In this work, gait features are used to identify an individual. The steps involve object detection, background subtraction, silhouettes extraction, skeletonization, and training 3D Convolution Neural Network (3D-CNN) on these gait features. The model is trained and evaluated on the dataset acquired by CASIA—B Gait, which consists of 15,000 videos of 124 subjects’ walking pattern captured from 11 different angles carrying objects such as bag and coat. The proposed method focuses more on the lower body part to extract features such as the angle between knee and thighs, hip angle, angle of contact, and many other features. The experimental results are compared with amongst accuracies of silhouettes as datasets for training and skeletonized image as training data. The results show that extracting the information from skeletonized data yields improved accuracy.

Intelligent robots, as an important type of Cyber–Physical systems, have promising potential to take the central stage in the development of the next-generation of efficient smart systems. Robotic calligraphy is such an attempt, and the current research focuses on the control algorithms of the robotic arms, which usually suffers from significant human inputs and limited writing styles. This paper presents an autonomous robotic writing system for Chinese calligraphy empowered by the proposed automatic stroke matching and generation mechanisms. Thanks to these mechanisms, the robot is able to effectively learn to write any Chinese characters in a style that is sampled by a small amount of handwritten Chinese characters with a certain target writing style. This is achieved by firstly disassembling each given Chinese character into individual strokes using the proposed character disassemble method; then, the writing style of the dissembled strokes is learned by a stroke generation module, which is built upon a generative adversarial learning model. From this, the robot can apply the learned writing style to any Chinese character from a given database, by dissembling the character and then generating the stroke trajectories based on the learned writing style. The experiments confirm the effectiveness of the proposed system in learning writing a certain style of characters based on a small style dataset, as evidenced by the high similarity between the robotic writing results and the handwritten ones according to the Frechet Inception Distance.

Vehicular Ad Hoc Networks (VANETs) is the most growing research area in wireless communication and has been gaining significant attention over recent years due to its role in designing intelligent transportation systems. Wireless multi-hop forwarding in VANETs is challenging since the data has to be relayed as soon as possible through the intermediate vehicles from the source to destination. This paper proposes a modified fuzzy-based greedy routing protocol (MFGR) which is an enhanced version of fuzzy logic-based greedy routing protocol (FLGR). Our proposed protocol applies fuzzy logic for the selection of the next greedy forwarder to forward the data reliably towards the destination. Five parameters, namely distance, direction, speed, position, and trust have been used to evaluate the node’s stability using fuzzy logic. The simulation results demonstrate that the proposed MFGR scheme can achieve the best performance in terms of the highest packet delivery ratio (PDR) and minimizes the average number of hops among all protocols.

The agriculture industry is of great importance in many countries and plays a considerable role in the national budget. Also, there is an increased interest in plantation and its effect on the environment. With vast areas suitable for farming, countries are always encouraging farmers through various programs to increase national farming production. However, the vast areas and large farms make it difficult for farmers and workers to continually monitor these broad areas to protect the plants from diseases and various weather conditions. A new concept dubbed Precision Farming has recently surfaced in which the latest technologies play an integral role in the farming process. In this paper, we propose a SMART Drone system equipped with high precision cameras, high computing power with proposed image processing methodologies, and connectivity for precision farming. The SMART system will automatically monitor vast farming areas with precision, identify infected plants, decide on the chemical and exact amount to spray. Besides, the system is connected to the cloud server for sending the images so that the cloud system can generate reports, including prediction on crop yield. The system is equipped with a user-friendly Human Computer Interface (HCI) for communication with the farm base. This multidrone system can process vast areas of farmland daily. The Image processing technique proposed in this paper is a modified ResNet architecture. The system is compared with deep CNN architecture and other machine learning based systems. The ResNet architecture achieves the highest average accuracy of 99.78% on a dataset consisting of 70,295 leaf images for 26 different diseases of 14 plants. The results obtained were compared with the CNN results applied in this paper and other similar techniques in previous literature. The comparisons indicate that the proposed ResNet architecture performs better compared to other similar techniques.

An Artificial Neural Network (ANN) based Space Vector Pulse Width Modulation (SVPWM) for five level cascaded H-bridge inverter (CHBI) fed grid connected photovoltaic (PV) system. The multilevel inverter topologies are offers better performance compare conventional two level inverter like reduced total harmonic distortion, less electromagnetic interferences and voltage stresses across switches are low. The ANN based SVPWM generates the switching pulses for cascaded H-bridge inverter; it improves the accuracy in reference vectors tuning and identification, which leads to improve the inverter output voltage, better utilization of dc-link voltage and controlled output current. The ANN control makes the implementation of SVPWM becomes simple and minimizes the intricacy in tracking reference vector and calculation of switching time; it is suitable for any type of non-linear systems. This proposed system is energized using PV system and it is boosted using dc-dc boost converter, and the output of CHBI is synchronized with grid connected system using coupled inductor. The simulation and experimental results of ANN based SVPWM for CHBI is verified using simulink-matlab and DSP processor.

Due to the wide acceptance of White Blood Cells (WBCs) in disease diagnosis, detection and classification of WBC are hot topic. Existing methodologies have some drawbacks such as significant degree of error, higher accuracy, time bound and higher misclassification rate. A WBCs detection and classification called, Jenks Optimized Logistic Convolutional Neural Network (JO-LCNN) method has proposed. Initally, Eulers Principal Axis is used as a convolution model to obtain a rotation invariant form of image by differentiating the background and RBCs, then eliminating them which leaves only the WBCs. By eliminating the wanton features, inherent features are detected contributing to minimum misclassification rate. According to above, Jenks Optimization function is used as a pooling model to obtain feature map for lower resolution. Therefore JO-LCNN is used for removing tiny objects in image and complete nuclei. Finally, Multinomial Logistic classifier is used to classify five types of classes by means of loss function and updating weight according to the loss function, therefore classifying with higher accuracy rate. Using LISC database for WBCs with different parameters as classification accuracy, false positive rate and time complexity are performed. Result shows that JO-LCNN, efficiently improves accuracy with less time, misclassification rate than the state-of-art methods.

Service Level Agreement (SLA) is an agreement between the service provider and consumer to provide the verifiable quality of services. Using the valuable metrics in SLA, a service consumer could easily evaluate the service provider. Though there are different types of SLA models are available between the consumer and provider, the proposed approach describes the Fuzzy rule base SLA agreement generation among multiple service providers. A negotiation system is designed in this work to collect the different sets of provider services. With their desired quality metrics, a common Fuzzy based SLA report is generated and compared against the existing consumer requirements. From the analysis of the common agreement report, consumers can easily evaluate the best service with the desired Impact service, cost and Quality. The main advantage of this approach is that it reduces the time consumption of a consumer. Moreover, the best service provider can be selected among multiple providers with the desired QoS parameters. At the same time, the bilateral negotiation is enhanced with the approach of multilateral negotiation to improve the searching time of consumers.

Vehicular Adhoc Networks (VANET) are thought-about as a mainstay in Intelligent Transportation System (ITS). For an efficient vehicular Adhoc network, broadcasting i.e. sharing a safety related message across all vehicles and infrastructure throughout the network is pivotal. Hence an efficient TDMA based MAC protocol for VANETs would serve the purpose of broadcast scheduling. At the same time, high mobility, influential traffic density, and an altering network topology makes it strenuous to form an efficient broadcast schedule. In this paper an evolutionary approach has been chosen to solve the broadcast scheduling problem in VANETs. The paper focusses on identifying an optimal solution with minimal TDMA frames and increased transmissions. These two parameters are the converging factor for the evolutionary algorithms employed. The proposed approach uses an Adaptive Discrete Firefly Algorithm (ADFA) for solving the Broadcast Scheduling Problem (BSP). The results are compared with traditional evolutionary approaches such as Genetic Algorithm and Cuckoo search algorithm. A mathematical analysis to find the probability of achieving a time slot is done using Markov Chain analysis.

It is essential to understand the quality of power being delivered to the industries that have equipment sensitive to power disturbances. Implementing IoT based power quality monitoring systems is a widespread practice in industries to prolong the process without any interruption. IoT based system looks very costly due to the data accumulation process which is carried over a long period requiring large data storage. Hence the paper proposes an intelligent power quality algorithm that alters data accumulation process more efficient by managing the power quality event data logging with pre-and-post value. The proposed system logs the drive’s mechanical quantities along with the power quality event data in Firebase cloud, which limits the space requirement and save time in analyzing the power quality events. Moreover, the power quality standards could be chosen by the end-users. Overall, the developed system is faster, economical and accurate and easier to operate, which can be used for many real-time applications.

With time, AI technologies have matured well and resonated in various domains of applied sciences and engineering. The sub-domains of AI, machine learning (ML), deep learning (DL), and associated statistical tools are getting more attention. Therefore, various machine learning models are being created to take advantage of the data available and accomplish tasks, such as automatic prediction, classification, clustering, segmentation and anomaly detection, etc. Tasks like classification need labeled data used to train the models to achieve a reliable accuracy. This study shows the systematic review of promising research areas and applications of DL models in medical diagnosis and medical healthcare systems. The prevalent DL models, their architectures, and related pros, cons are discussed to clarify their prospects. Many deep learning networks have been useful in the field of medical image processing for prognosis and diagnosis of life-threatening ailments (e.g., breast cancer, lung cancer, and brain tumor, etc.), which stand as an error-prone and tedious task for doctors and specialists when performed manually. Medical images are processed using these DL methods to solve various tasks like prediction, segmentation, and classification with accuracy bypassing human abilities. However, the current DL models have some limitations that encourage the researchers to seek further improvement.

Background:Vehicular Ad-hoc Network is the subset of Mobile Ad-hoc Network, Intelligent Transport System and Internet of Things. The acting nodes in VANET are the vehicles on the road at any moment.Objective:The anonymity character of these vehicles is opening the opportunity for malicious attacks. Malicious routes increase the data retransmission and hence, the performance of routing will be degraded. The main objective this work is to identify the malicious routes, avoid the data transmission using these routes and increase the packet delivery ratio.Methods:In the proposed system called Geographic Routing Protocol with Masked data, two binary- codes called mask and share have been generated to identify the malicious route. The original data is encoded using these binary-codes and routed to the destination using the geographic routing protocol. It is reconstructed at the destination node and based on the encoding technique the malicious routes and malicious nodes are identified. Simulations were conducted with varying speed and varying network size in 20 km2 geographical area.Results:The average packet delivery ratio with varying speed is 0.817 and with varying networksize is 0.733.Conclusion:The proposed geographical routing protocol with masked data technique outperforms than traditional geographic protocol and Detection of Malicious Node protocol, by 0.102 and 0.264 respectively with different speeds and by 0.065 and 0.1616 respectively with different network size.

Data security in centralized storage needs advancement in privacy standards because of all of the cloud. The data security in the cloud has been well provided by security industries like cloud network security, data center security, distributed security and soon, also their exist numerous techniques to preserve the privacy of cloud users. The earlier methods enforce user privacy by restricting the malicious access from various users. Data authentication is provable access to keep privacy among other standards. However, the privacy of cloud users has been breached on several occasions. To improve cloud security and enforce efficient privacy preservation, a multi-level micro access restriction algorithm has been presented in this paper. The cloud data has been indexed in multiple levels, the data present in each level has been restricted using the profile and set if encryption standards. The user request has been evaluated for its trusted access according to the access grant present in profile data. Similarly, the cloud data has been encrypted with the user key and the key belongs to the data owner. The method estimates micro access trust weight (MATW), which has been used to restrict the user from malicious access and to preserve user privacy. The method improves the performance of cloud security and introduces higher privacy preservation accuracy.

Nowadays, highly sensitive medical images are vulnerable to data threats and privacy attacks. They must be kept secure while transmitting them across insecure channels precisely for this purpose. The robust image steganography is focused on this work by exploiting Redundant Integer Wavelet Transform (RIWT), Laplacian Pyramid, Arnold scrambling and Histogram shifting algorithm to facilitate secure communication of secret images in the context. Stego images thus generated are subjected to a deep learning approach to assess if it can be classified as a cover or not. If not, the HS parameter is modified to generate stego images in such a way to classify it as a cover image. Thus it is difficult to suspect the existence of a secret image by the Human Visual System (HVS). The efficiency of our method is analyzed by comparing it with related methods present in the literature. Average NCC values between the original secret image and the extracted secret image are 0.8917 which is higher than the schemes in the literature. Average PSNR values of the stego image are 36.375 even when the embedding rate is increased to 4 bits per pixel. The analysis was done on security and robustness also reveals better results. From the experimental analysis, it is proved that the proposed method is superior to the related methods of the literature.

Detection of abnormal events in the traffic scene is very challenging and is a significant problem in video surveillance. The authors proposed a novel scheme called super orientation optical flow (SOOF)-based clustering for identifying the abnormal activities. The key idea behind the proposed SOOF features is to efficiently reproduce the motion information of a moving vehicle with respect to superorientation motion descriptor within the sequence of the frame. Here, the authors adopt the mean absolute temporal difference to identify the anomalies by motion block (MB) selection and localisation. SOOF features obtained from MB are used as motion descriptor for both normal and abnormal events. Simple and efficient K-means clustering is used to study the normal motion flow during the training. The abnormal events are identified using the nearest-neighbour searching technique in the testing phase. The experimental outcome shows that the proposed work is effectively detecting anomalies and found to give results better than the state-of-the-art techniques.

Background: With the immense significance of cloud computing over the decade, different IT companies offer varieties of cloud services. Objective: The selection of cloud services from the expanding range of Cloud Service Providers (CSPs) makes it difficult for the Cloud Consumers (CCs) to choose a CSP based on their preferences. Methods: In this context, this paper proposes an efficient trust management architecture for cloud service selection and put forward Combined Preference Ranking Algorithm (CPRA) for initial ranking of CSPs and their services before doing any transaction in the past based on CCs requirements. Results: The proposed trust management architecture prompts the CSPs to improve the Quality of Service (QoS) by adhering to Service Level Agreement (SLA). Conclusion: The experimental results show that compared with other ranking approaches CPRA generates the accurate ranking list of CSPs with minimal execution time.

Cloud computing is widely accepted by both individuals and enterprises alike for the storage of multimedia contents. It is due to the introduction of a new architecture where the cost of computation, storage, and services needed for maintenance for storage of multimedia are less. Cloud computing addresses the scarcity of resources for clients by offering options to pay for services only as they are used. But once the organization’s multimedia contents are uploaded into cloud space, the user loses control over their contents which may no longer be safe. The cloud user has to take some measure to avoid privacy issues. Steganography is preferred over encryption for providing multimedia security as content concealed in a cover image is not revealed. The multimedia content is transformed using Discrete Rajan Transform (DRT) and embedded into a chosen cover image which is created by Integer Wavelet using Diamond Encoding Scheme. Generated stego images are stored in the cloud. When the multimedia content is required, stego images are downloaded from the cloud and are subjected to inverse transform of IWT. SVM provides Good learning ability to our extraction process which makes our algorithm more robust to various attacks, viz., salt and pepper noise, Gaussian noise, cropping, compression, etc. Experimental values for Peak Signal to Noise Ratio (PSNR) for two secret images are 53 and 50 respectively which is better over the available schemes in the literature. Similarly for robustness and security evaluation, our scheme provides a better result.

In recent years, fog computing emerges as a proactive solution for healthcare service as it facilitates continuous monitoring of remote patient health and early detection of mosquito-borne diseases. In addition, fog computing reduces the latency and communication cost that is normally an immense concern of cloud computing. The key objective of the proposed intelligent system is to detect and control the mosquito-borne diseases at the early stage. For this purpose, wearable and IoT sensors are used to gather the required information and fog computing is used to analyze, categorize and share medical information among the user and healthcare service providers. We utilize similarity coefficient to differentiate the various mosquito-borne diseases based on patient's symptoms, and the fuzzy k-nearest neighbor approach is employed to categorize the user into infected or uninfected class. Further, on the cloud layer, Social Network Analysis (SNA) is employed to represent the outbreak of mosquito-borne diseases. The likelihood of the registered user to receive or spread the disease is measured by computing PDO (Probability of Disease Outbreak) which is used to provide the location-based awareness to avert the outbreak. The experimental evaluation reveals the improved performance of the proposed F-HMRAS with 95.9% classification accuracy.

Due to increased attraction in cloud computing, mobile devices could store or acquire private and confidential information from everywhere at any point in time. In parallel, the information safety issues over mobile computing become rigorous and retard increased advancements in the mobile cloud. Crucial analysis were performed to enhance the safety in cloud computing. Most of them are not appropriate for mobile cloud computing due to limited energy resource, thus mobile devices are unable to perform assessments and complex tasks. The crucial requirement of mobile cloud application is to provide solution with minimum computational overhead. Thus the aim of the research is to design a trivial information relaying scheme (TIRS) for mobile cloud computing. The proposed scheme implements Ciphertext Policy Attribute-based Encryption (CP-ABE) to alter the general framework of access governance hierarchy to make it appropriate for mobile cloud environment. The TIRS displaces immense segments of the assessment concentrated access governance hierarchy modifications in CP-ABE from smart devices to the peripheral proxy servers. Furthermore, TIRS initiates element portrayal field to plan indolent cancellation which is a thriving dispute for CP-ABE system. The experimental analysis depicts that TIRS successfully minimize the overheads during user relaying information over the mobile cloud environment.

Sophisticated wireless attacks such as Wifiphishing, Evil twin and so on are a serious threat to Wi-Fi networks. These attacks are tricky enough to spoof users by launching a fake access point (AP) pretending to be a legitimate one. The existing intrusion detection schemes are prone to a high rate of false positives as they depend on restricted features. Hence, an efficient intrusion detection system, which considers many more features is needed. Kernel density estimation (KDE) statistically models the distribution of data and detects the attacks in active mode. However, in passive mode (without any connectivity to the AP), detecting the attack is complicated and it requires prior knowledge of attack signatures. The other intrusion detection model which is used in passive mode, namely hidden Markov model (HMM), does not need knowledge of initial probabilities. In this study, a novel wireless intrusion detection system is proposed, by combining KDE and HMM through a tandem queue with feedback. The proposed KDE-HMM technique/method combines the advantages of both statistical and probabilistic properties to yield better results. The performance of the proposed KDE-HMM technique has been experimentally validated and it is found that the proposed KDE-HMM detects the aforementioned attacks with 98% accuracy.

The invention of geometrically stable low-dimensional semiconductors along with excellent electronic properties is significant to future optoelectronic devices. Using Ab initio technique, we predict the monolayer silicon phosphide nanosheet (SiP-NS) as a good candidate for near and far-infrared optoelectronic devices due to its excellent dynamical stabilities, more chance for experimental exfoliation, fine-tune the electronic properties with the substitution of proper dopant atoms and prominent anisotropy. The structural and dynamical stability of pristine, Al and B substituted SiP-NS are verified by the cohesive energy and phonon-band-structure. The electronic properties of SiP-NS are demonstrated with the support of the density of states spectrum and energy band structure. The direct energy gap value of pristine SiP-NS is found to be 1.34 eV. The main objective of the proposed research article is to fine tune the electronic characteristics of SiP-NS by the substitution of Al and B atom. Pristine Al and B substituted SiP-NS, with dynamical stability and direct band gap, is a promising material for two dimensional near and mid-infrared optoelectronic devices.

The advances in computer technologies and the Internet have made rapid strides and breakthroughs in the field of data communication, which nowadays, is easily accessed. Unfortunately, this easy access offers almost endless opportunities for pirating copyrighted and confidential medical imagery. Many methods are proposed in the literature, however, most of them lack in robustness and perceptibility, and are prone to attacks. Hence, this study proposes a robust image steganographic approach that combines Redundant Integer Wavelet Transform (RIWT), Discrete Wavelet Transforms (DCT) and Singular Value Decomposition (SVD) and the logistic chaotic map. RIWT being a shift invariant, reversibility and robustness were achieved in this proposed technique. Better level of imperceptibility was achieved using SVD and DCT, with embedding carried out on singular values. Extra security was provided using the logistic chaotic map for encryption of secret medical images, which also enhanced the robustness of the technique. The effectiveness of our proposed scheme was compared with similar schemes available in the literature using common parameters such as imperceptibility, robustness and resistance to several geometric transformation attacks. This technique proved superior to other existing methods. The UCID benchmarking database was used during validation.

Environmental warning is caused by IT industry which critically leads the global pollution with huge amount of toxic carbon emission which is drastically increasing day by day due to demand and usage raised. Due to the environmental warning the industries are in awful need of reducing the carbon foot print by inducing green computing. This paper has achieved green computing by implementing two different algorithms (1) Water Shower Model (WSM) and (2) Trigger—WSM load balancing algorithms, and two different techniques (3) Recommending Containers over virtual machine techniques and 4. DVFS (Dynamic Voltage Frequency Scaling) modeling. The observation between the recommendation systems for container over virtual machine for a sample of four containers with one application each and four virtual machine with one application each is monitored for carbon emission equivalent in kg co2 for about 1 week is 14 kg co2 for container and 84.4 kg co2 for virtual machine, where a drastic difference in the amount of carbon emission is seen. So recommending container will be the best possible solution for the IT based on applications, by enforcing these ideas and techniques the carbon emission can be drastically decreased and the amount of carbon footprint in the atmosphere will also be reduced. The amount of power consumption utilized for the same model is 15.71367 W for container and 94.72667 W for virtual machine is also observed; in the field of IT the power consumption also to be taken into consideration for reducing carbon emission. The recommendation system along with the proposed algorithm will reduce the amount of carbon footprint in the environment.

The development of Recommender Systems (RSs) aims to generate recommendations with high quality, and on the other hand, the privacy of the user is not considered as a significant issue. Especially, when the RS utilizes the cloud platform for the recommendation generation process, the privacy of the user is needed to be preserved to ensure the security of user’s sensitive data. In this paper, we present an Improved MORE approach as a Fully Homomorphic Encryption algorithm to secure user’s data in the cloud environment. To generate secure location recommendations to the users, we present SECure RECommendation SYstem (SECRECSY) framework by protecting user’s sensitive privacy information in the cloud during the recommendation generation process. To meet the increasing demands of group recommendations, we extend our SECRECSY as Group Recommendation Model to suggest POIs to the group of users. The experimental results and findings are helpful to the researchers for developing better RSs for both individual and group users.

In recent times, the modern developments of internet technologies and social networks have attracted global researchers to explore the recommender systems for generating personalized location-based services. Recommender Systems (RSs) as proven decision support tools have gained immense popularity to solve information overloading problem among various real-time applications of e-commerce, travel and tourism, movies and e-learning. RSs emerge as a popular and reliable information filtering approach that is capable of suggesting relevant items, movies, and locations to the active target user based on dynamic preferences and interests. Beyond the development of many feature-rich recommendation algorithms, the need for a better full-fledged RS to produce precise and highly relevant recommendations based on ratings and preferences provided by the target user is very high. With the specific focus to the travel domain, the global research community has been involved in the development of a complete travel recommender system that is immune to the sparsity and cold start problems. In this paper, we present a new Hybrid Location-based Travel Recommender System (HLTRS) through exploiting ensemble based co-training method with swarm intelligence algorithms to enhance the personalized travel recommendations. The proposed HLTRS is experimentally validated on the real-world large-scale dataset, and we have made an extensive user study to determine the ability of developed RS to produce user satisfiable recommendations in real-time scenarios. The obtained results and analyses demonstrate the improved performance of the proposed Hybrid Location-based Travel Recommender System over existing baselines of recommender systems research.

Diabetes is featured by the high prevalence and low control resulting in high premature mortality rate. Maintaining the blood glucose level can bring considerable medical benefits and reduces the risk of diabetes. In real-time, continuous monitoring of blood glucose level is the major challenge. However, monitoring only glucose level without considering other factors such as ECG and physical activities can mislead to improper medication. Therefore, the ever-growing requirement for omnipresent healthcare system has engaged promising technologies such as the Internet of Things and cloud computing. Utilization of these techniques result with the computational complexity, high latency, and mobility problems. To address the aforesaid issues, we propose an energy efficient fog-assisted healthcare system to maintain the blood glucose level. The J48Graft decision tree is used to predict the risk level of diabetes with higher classification accuracy. By deploying fog computing, an emergency alert is generated immediately for precautionary measures. Experimental results illustrate the improved performance of the proposed system in terms of energy efficiency, prediction accuracy, computational complexity, and latency.

The research and development of recommender systems are traditionally focused on the enhancement and guaranteeing the recommendation accuracy to achieve user satisfaction. On the other hand, the alternative recommendation qualities such as diversity and novelty have received significant attention from researchers in recent times. In this paper, we present a detailed study of the diversity in recommender systems to help researchers in the development of recommendation approaches to generate efficient recommendations. We have also analyzed the existing works for assessment of impact and quality of diversified recommendations. Based on our detailed investigation of the diversity in recommendations, we shift the generic focus from accuracy objectives to explore beyond the accuracy of recommendations. The need for recommender systems producing diversified recommendations without compromising the accuracy is very high to meet the growing demands of users. To address the personalization problem in travel recommender systems, we present the hybrid swarm intelligence clustering ensemble-based recommendation framework to generate diverse and accurate Point of Interest recommendations. Our proposed recommendation approach employs multiple swarm optimization algorithms to frame a clustering ensemble for the generation of efficient user clustering. We have evaluated our proposed recommendation approach over a real-time large-scale dataset of TripAdvisor to estimate the quality of recommendations in terms of diversity and accuracy. The experimental results demonstrate the enhanced efficiency of the proposed recommendation approach over state-of-the-art techniques.

Fall causes serious perils for the elder people when they are living alone. A mathematical model, optimized ANFIS using frequent pattern mining (OAFPM) for activity recognition, is proposed in this paper, which uses fuzzy inference system, adaptive neural network and frequent pattern mining (FPM) to identify the activity of a person accurately. Accelerometer values are given as input to the proposed model in real time which forms the premise part of the model, whereas the consequence is defined by the rules generated out of input and output linear relation. Initial rule identification is done through membership functions of each activity, and the number of rules is reduced using FPM approach. During the learning phase, the optimal premise parameters are selected using gradient descent method and the choice of consequent parameters is based on the least-square estimation method. The optimal values of premise and consequent parameters along with the reduced rule matrix made the OAFPM model to achieve an accuracy rate of 95.8 $$\%$$ and also reduce the computational complexity by triggering less number of nodes for each activity.

In distribution system, wind power plants are becoming popular renewable energy sources. It employs Doubly Fed Induction Generator (DFIG) to generate power constructed on wind conversion. Short and long transmission lines, presence of faults and presence of Static Synchronous Compensator (STATCOM) are highlighted issues in this paper. Basically, this research develops investigations on some electrical variables such as voltage and current to control them. Distribution Static Synchronous Compensator (DSTATCOM) is proposed in this paper. Wind farm acts as a source while DSTATCOM is associated with the distribution system with a DFIG based wind farm. The controller proposed is DSTATCOM is modeled and simulated in MATLAB/SIMULINK and the results are given. A microgrid based small signal analysis is performed in the laboratory using MATLAB and different comparisons are made and simulation case studies are presented and validated.

The internet of things (IoT) is an internet among things through advanced communication without human’s operation. The effective use of data classification in IoT to find new and hidden truth can enhance the medical field. In this paper, the big data analytics on IoT based healthcare system is developed using the Random Forest Classifier (RFC) and MapReduce process. The e-health data are collected from the patients who suffered from different diseases is considered for analysis. The optimal attributes are chosen by using Improved Dragonfly Algorithm (IDA) from the database for the better classification. Finally, RFC classifier is used to classify the e-health data with the help of optimal features. It is observed from the implementation results is that the maximum precision of the proposed technique is 94.2%. In order to verify the effectiveness of the proposed method, the different performance measures are analyzed and compared with existing methods.

Recent developments in Information and Communication Technologies (ICT) and online healthcare services have created a huge volume of health data. With the advancements in machine learning approaches, the research on Disease Prediction Support System (DPSS) has attracted many researchers globally. In this article, we present a hybrid reasoning-based methodology on predicting diseases. The combinatorial advantage of Fuzzy sety theory, k-nearest neighbor and case-based reasoning helps to yield enhanced prediction results. Though DPSS facilitates promising healthcare services, data security and privacy are still crucial challenging issues to be addressed. The DPSS is extended as a Privacy-Aware Disease Prediction Support System (PDPSS) using Paillier Homomorphic Encryption to preserve patients’ sensitive information from unauthorized user access. The proposed prediction model is evaluated with the statistical evaluation metrics, and the experimental results reveal the improved performance of PDPSS in enhanced prediction accuracy and better security.

recent years have witnessed the enormous development of robotics and autonomous systems. Moreover, its application has been inevitable in the evolving modern science and technology. In particular, industries are significantly upgraded by incorporating robotic technologies for various applications. Henceforth, it is equally important to make it more efficient and accurate. Here, the proposed research work will design and develop a manipulator with DAQ and stereo vision for tracking the object.

Multiplier plays an important role in the design of FIR filters in digital signal processors (DSP). In VLSI the multipliers performance speed affects the overall speed of the system. Moreover, multiplication process uses execution time in most of the DSP devices. Hence, high speed is required in multiplier. This paper presents the analysis of a high speed new radix-4 multiplier using Shannon adder. The proposed hybrid adder is implemented in order to achieve higher reduction of power in the high speed parallel radix-4 multiplier. Hence this modified radix-4 multiplier is a suitable candidate for obtaining less propagation delay, low power consumption and better power delay product. The circuit simulations are done using Synopsys H-Spice software. The obtained simulation results exhibit that the proposed structure performance is better in terms of Propagation delay, low power consumption and Power delay product when compared with the advanced technology in CMOS.

This paper presents a method of text characters and numbers recognition system in number plates of moving vehicles. The system includes a camera connected to Raspberry-Pi which captures the video of moving vehicles. Frames containing the number plate pictures of the vehicles are extracted from the video and then preprocessed for improving the clarity and reduce blur. The region containing the text is segmented and applied to classification network. In this work, deep residual network or ResNet-34 Convolutional neural network architecture, which consists of 34 layers, is employed for feature extraction and identification of characters in the vehicle number plate images. Automatic vehicle number detection systems have widespread applications in Highway Toll collection, Tracking entry and exit of vehicles in Official places, apartments, etc. and could reduce manpower and reduces inconvenience caused to passengers..

Modern mobile communication networks need the possibility of managing and control the electrical down tilt of antennas remotely. As a result, most antennas need to be equipped with Remote Control Units (RCUs) to change the down tilt without physical involvement. Using standard remote electrical tilt equipment (RET) requires more time to shift the equipment near to the base station and are much costlier. With the help of RET equipment, technicians can adjust the beam pattern of antennas, RF power transmitted and intermodulation distortions without network shutdown. In this paper, the design and implementation of a low cost prototype remote control system for antenna tilt alignment is presented. In this work, Raspberry Pi board and servo motors based hardware mechanism for remote electrical tilting of antenna is described. To adjust the angular posservo motors controls the position of antenna unit PWM commands to the Raspberry Pi controller, the servo motors angular position can be controlled from a remote place through Ethernet or WI-Fi network.

Raja Ramanna Centre for Advanced Technology (RRCAT) has an ongoing program to develop 650 MHz, 5-cell elliptical superconducting RF (SCRF) cavities under the Indian Institutes and Fermilab Collaboration. The elliptical multi-cell SCRF cavity fabrication process involves forming of half-cells and their precise machining and joining by electron beam welding to form end groups and dumbbells, which are then joined to make the final cavity. To ensure that the final welded cavity achieves physical lengths and resonant frequencies within design tolerance and has good field flatness, the measurement and correction of resonant frequency are carried out for dumbbells and end groups. A novel method to identify the frequency of individual half-cells in a dumbbell cavity and a dedicated tuning fixture to correct them had been developed. The paper details the RF characterization and correction procedure employed during fabrication of the first six 650 MHz cavities at RRCAT.

In the recent times, the massive amount of user-generated data acquired from Internet has become the main source for recommendation generation process in various real-time personalization problems. Among various types of recommender systems, collaborative filtering-based approaches are found to be more effective in generating better recommendations. The recommendation models that are based on this collaborative filtering approach are used to predict items highly similar to the interest of an active target user. Thus, a new hybrid user clustering-based travel recommender system (HUCTRS) is proposed by integrating multiple swarm intelligence algorithms for better clustering. The proposed HUCTRS is experimentally assessed on the large-scale datasets to demonstrate its performance efficiency. The results obtained also proved the potential of proposed HUCTRS over traditional approaches by means of improved user satisfaction.

The swift growth in usage of Location-based social networks (LBSNs) has driven to the availability of a large volume of check-in data of the users. This provides a great opportunity to provide various location-aware utilities in the Smart Cities. Future will be smart, each and every places/location will be connected to the network and it will make the cities smart and advanced. One such service includes the Point-of-Interest recommender that is used to recommend the venues where a person has not been before. Various methods have been lately analyzed and implemented to provide this service. By the Location based POI method in smart cities will provide ultimate recommendation based on the social network interactivity in the smart cities. This chapter aims to provide various techniques used in POI recommendation systems for LBSNs. We aim to propose the implementation of an adaptive POI recommendation algorithm in this chapter. The proposed method incorporates the spatial feature along with the user activity and social feature. This model is implemented on a large-scale check-in dataset, Foursquare.

we have become too dependent on technology owing to which the quantity of e-waste produced at the end of their life cycle has increased at a rapid pace. In later centuries, there would be an equivalent amount of carbon footprint by the smartphone sector as to that of transportation industry. The approximate estimation of the total carbon footprint while taking the other existing abundant electronic gadgets is enormous. Considering the growing volume of e-waste, the possibilities of these non-biodegradable elements contaminating the atmosphere are towering. The e-waste generated in all these recent years is being taken seriously by various nations and effective steps are being taken to overcome this challenge. To overcome this challenge, an effective e-waste management technique by means of blockchain in the 5G scenario is proposed. The proposed solution tracks the e-waste produced and motivates people by providing incentives to them for channelizing the e-waste via agencies managed by the government that effectively dispose the waste in an environmentfriendly way. Henceforth, a partnership model is proposed for the implementation of this method which leads to increase in jobs as well as proper organization of unplanned setup that is with a large amount of prospective potential.

Modern transportation systems are highly depend on quality and complete source of data for traffic state identification, prediction and forecasting processes. Due to device (sensor, camera, and detector) failures, communication problems, some sources inevitably miss the data, which leads to the degradation of traffic data quality. Data pre processing is an important one for transport related applications. Imputation is the process of finding missing data and make available as complete data. Both Spatial and temporal information has been a high impact on impute the traffic data. In this paper deep learning based stacked denoise autoencoder (one autoencoder at a time) is proposed to impute the traffic data with less computational complexity and high performance. Experimental results demonstrate that autoencoder performs well in random corruption aspect with less complexity.

A recommender system plays a vital role in information filtering and retrieval, and its application is omnipresent in many domains. There are some drawbacks such as the cold-start and the data sparsity problems which affect the performance of the recommender model. Various studies help with drastically improving the performance of recommender systems via unique methods, such as the traditional way of performing matrix factorization (MF) and also applying deep learning (DL) techniques in recent years. By using DL in the recommender system, we can overcome the difficulties of collaborative filtering. DL now focuses mainly on modeling content descriptions, but those models ignore the main factor of user–item interaction. In the proposed hybrid Bayesian stacked auto-denoising encoder (HBSADE) model, it recognizes the latent interests of the user and analyzes contextual reviews that are performed through the MF method. The objective of the model is to identify the user’s point of interest, recommending products/services based on the user’s latent interests. The proposed two-stage novel hybrid deep learning-based collaborative filtering method explores the user’s point of interest, captures the communications between items and users and provides better recommendations in a personalized way. We used a multilayer neural network to manipulate the nonlinearities between the user and item communication from data. Experiments were to prove that our HBSADE outperforms existing methodologies over Amazon-b and Book-Crossing datasets.

In recent years, internet technologies and its rapid growth have created a paradigm of digital services. In this new digital world, users suffer due to the information overload problem and the recommender systems are widely used as a decision support tool to address this issue. Though recommender systems are proven personalization tool available, the need for the improvement of its recommendation ability and efficiency is high. Among various recommendation generation mechanisms available, collaborative filtering-based approaches are widely utilized to produce similarity-based recommendations. To improve the recommendation generation process of collaborative filtering approaches, clustering techniques are incorporated for grouping users. Though many traditional clustering mechanisms are employed for the users clustering in the existing works, utilization of bio-inspired clustering techniques needs to be explored for the generation of optimal recommendations. This article presents a new bio-inspired clustering ensemble through aggregating swarm intelligence and fuzzy clustering models for user-based collaborative filtering. The presented recommendation approaches have been evaluated on the real-world large-scale datasets of Yelp and TripAdvisor for recommendation accuracy and stability through standard evaluation metrics. The obtained results illustrate the advantageous performance of the proposed approach over its peer works of recent times.

A cloud data center consumes more energy for computation and switching servers between modes. Virtual Machine (VM) migration enhances the execution of cloud server farm in terms of energy proficiency, adaptation to internal failure, and accessibility. Cloud suppliers, be that as it may, ought to likewise enhance for amounts like energy consumption and administrations costs and in this manner, trying to have all the Virtual Machines with the least measures of physical equipment machines conceivable. The part of virtualization is critical and its execution is subjected to VM migration and machine allotment. A greater amount of the energy is caught up in the cloud; consequently, the use of various calculations is required for sparing energy and productivity upgradation in the proposed work. In the proposed work, the Naive Bayes classifier with hybrid optimization using Artificial Bee Colony–Bat Algorithm (ABC–BA) was implemented to reduce the energy consumption in VM migration. The proposed method was evaluated in CloudSim and the performances were compared using performance index such as success &failure rate, and energy consumption. It is observed from the implementation results that the proposed method reduces energy consumption compared to other existing methods. From the implementation outcomes of the proposed work, it was understood that the model was able to achieve the minimum energy consumption and failure rate i.e., 1000–1200 kWh, 0.2 with maximum success rate and accuracy of 1 and 97.77%.