Progress in Advanced Computing and Intelligent Engineering

The worldwide havoc of today’s world: depression, is increasing in this era. Depression is not any specific disease rather the determinant factor in the onset of numerous terrible diseases. With the increase in automation and artificial intelligence, it has become easier to predict depression before a much earlier time. The machine learning techniques are used in the classification of EEG for the prediction of different neuro-problems. EEG signals are the brain waves which can easily detect any abnormalities occurring in the brain waves, thereby making it easier to predict the seizure formation or depression. Proposed work uses the EEG signals for the analysis of brain waves, thereby predicting depression. In this paper, we have compared two widely used benchmark models, i.e., the k-NN and the ANN for the prediction of depression with an accuracy of 85%. This method will help doctors and medical associates in predicting diseases before the onset of its extreme phase, as well as assist them in providing the best treatments, possible in proper time.

This work endeavours to explore the relation between certain behavioural traits and prevalent diseases among the sample population,reported in a public health survey,by means of machine learning techniques. Predictive models are developed to ascertain the significance statistically while also checking the fitness of the models to predict the diseases in a non-invasive way. Our study focuses on cardiovascular stroke from the BRFSS database of CDC, USA. The proposed model achieves 0.71 AuC in predicting stroke from purely behavioural features. Further analysis reveals an interesting behavioural trait: proper maintenance of an individual’s work–life balance, apart from the three main conventional habits: regular physical activity, healthy diet, abstinence from heavy smoking and drinking as the most significant actors for reducing the risk of potential stroke.

In this research paper, we have engineered a multilingual automatic speech recognition engine in Indian perspective by employing language identification technique. Our motherland, India is treated as land of many tongues. Our vision is leading to develop a system that would aid in man–machine communication in Indian spoken languages. We have developed two vital models, namely language identification and speech recognition using array of pattern recognition techniques, viz. k-NN, SVM and HMM. We have tackled both LID and multilingual ASR tasks over three Indian spoken languages, namely Odia, Hindi and Indian English. We have experimented over short as well as long durational isolated spoken words for LID task purpose. Finally, we have integrated LID module with multilingual ASR in order to transcribe the words in desired spoken language.

In the present study, we presented ensemble classifier to predict the locality scope (National or International) of the student based on their motherland and sex toward Information and Communication Technology (ICT) and Mobile Technology (MT). For this, a primary dataset of 331 samples from Indian and Hungarian university was gathered during the academic year 2017–2018. The dataset contained 331 instances and 37 features which belonged to the four major ICT parameters attitude, development and availability, educational benefits and usability of modern ICT resources, and mobile technology in higher education. In addition to class balancing with Synthetic Minority Over-Sampling Technique (SMOTE), Adaptive Boosting (AdboostM1) and bagging ensemble technique is applied with Artificial Neural Network (ANN) and Random Forest (RF) classifiers in Weka tool. Findings of the study infer that the ANN achieved higher accuracy (92.94%) as compared to RF’s accuracy (92.25%). The author’s contribution is to apply ensemble methods with standard classifiers to provide more accurate and consistent results. On the one hand, with the use of bagging, the ANN achieved 92.94% accuracy, and on the other hand, AdboostM1 has also significantly improved the prediction accuracy and RF provided 92.25% accuracy. Further, the statistical T-test at the 0.05 significance level proved no significant difference between the accuracy of RF and ANN classifier to predict the locality scope of the student. Also, the authors found a significant difference between the CPU prediction time between bagging with ANN and AdboostM1 with RF.

The automatic detection and classification of insect pest is emerged as one of the interesting research areas in agriculture sector to ensure reduction of damages due to pest. From the general process of detection of pest, feature extraction plays a significant role. It extracts features from the segmented image obtained by segmentation process, and then extracted images are being transferred to a classifier for the operations. In this work, we studied and implemented two feature extraction techniques, i.e., Histogram of Oriented Gradient (HOG) and Local Binary Pattern techniques (LBP). The comparison result expressed that HOG performs better than its counterpart. The result comes with accuracy of 97% for HOG. Here, we are adopting SVM-based pest classification as a test case.

Lip reading involves the extraction of visual speech information contained in the inner and outer lip contour. Visibility of teeth and tongue during speech provides important speech cues. Particularly for fricatives, the place of articulation can often be determined visually, that is, for labiodentals (upper teeth or lower lip), interdentals (behind tongue or front teeth), and alveolar (tongue touching gun ridge). Other speech information might be contained in the protrusion and wrinkling of lips. Feature extraction is a remarkable process in lip reading as it holds an important role in lip reading classification. In Improved Speeded Up Robust Feature (ISURF), extraction for finding an exact edge is difficult because of more false corner ratio. In case of PSST, exact edges could be obtained with reduced false corner ratio. This paper provides the idea about PSST based on Harris algorithm and gives more precise edge detection in different illumination conditions.

Unambiguous vehicular sensing is one of the most important aspects in autonomous driving in vehicular ad-hoc networks. The conventional techniques such as communication-based technologies (e.g., GPS) or the reflection-based technologies (e.g., RADAR, LIDAR) have various limitations in detecting concealed vehicles in dense urban areas without line of sight which may trigger serious accidents for autonomous vehicles. To address this issue, this paper proposed a machine learning method based on stochastic Gaussian process regression (SGP) to position vehicles in a distributed vehicular system with received signal vector (RSV) information. To estimate the test vehicle position and respective position errors, the proposed SGP method records the RSV readings at neighboring locations with continuous approximation of the vehicle-to-vehicle (V2V) distance, angle of arrival (AoA), and path delay. Then, the subsequent averaging of the training RSVs minimizes the effects of the shadowing noise and multipath fading. The prediction performance of the proposed learning approach is measured in terms of the root mean square prediction error (RMSE) in a realistic environment. Finally, the prediction performance of the proposed learning method is compared with other existing fingerprinting methods for error-free location estimation of the vehicular network.

In this paper, Salp Swarm Algorithm (SSA) is employed in training the Higher Order Neural Network (HONN) for data classification task. In machine learning approach, to train artificial neural network is considered a difficult task which gains the attention of researchers recently. The difficulty of Artificial Neural Networks (ANNs) arises due to its nonlinearity nature and unknown set of initial parameters. Traditional training algorithms exhibit poor performance in terms of local optima avoidance and convergence rate, for which metaheuristic based optimization emerges as a suitable alternative. The performance of the proposed SSA-based HONN method has been verified by considering various classification measures over benchmark datasets chosen from UCI repository and the outcome obtained by the said method is compared with the state-of-art evolutionary algorithms. From the outcome reported, the proposed method outperforms over the recent algorithms which confirm its supremacy in terms of better exploration and exploitation capability.

In this work, we proposed a cover song recognition system using deep learning. From the literature, understand that most of the works extract the discriminate feature that classifies the cover song between a pair of songs and calculates the dissimilarity or similarity between the two songs based on the observation, which is a meaningful pattern between cover songs. Moreover, it inspires reformulating the cover song apperception obstacle in a machine learning framework. In other words, essentially builds the cover song recognition system using Convolution Neural Network (CNN) and Mel Frequency Cepstral Coefficients (MFCCs) features following the construction of the data set composed of cover song pairs. The prepared CNN yields the likelihood of being in the spread tune connection given a cross-closeness grid produced from any two bits of music and recognizes the spread tune by positioning on the likelihood. Test results display the prescribed methodology that has accomplished enhanced execution tantamount to the cutting edge endeavors.

In this paper, we propose an efficient algorithm for driver drowsiness detection and efficient alert system. The existing works mainly follow vehicle-based measures, physiological-based measures, behavioral-based measures. Moreover, the works based on behavioral measures mainly focused on eye movements, yawning, and head position. The proposed method uses more relevant and appropriate behavioral features such as significant variation in aspect ratio of eyes, mouth opening ratio, nose length bending, and the changes that happened in eyebrows, wrinkles, ear due to drowsiness. The binary SVM classifier is used for classification whether the driver is drowsy or not. The inclusion of these features helped in developing more efficient driver drowsiness detection system. The proposed system shows 97.5% accuracy and 97.8% detection rate.

The demand for multidisciplinary optimized products in industrial engineering is high due to growing competition. But it is a highly expensive and time-consuming process. The integration of artificial intelligence in engineering design is an area of high demand. So here, using the fusion of AI, a method has been proposed to solve a multidisciplinary problem using the case study of skidding tracks.

In this paper, an extractive text summarization approach using Assamese WordNet is proposed, and the difficulties faced while extracting summary in the Assamese document are discussed. The Assamese language is a low-level language. Synset is applied from Assamese WordNet. The various features used for identifying the most salient sentences to generate effective summary aspects such as TF-IDF, sentence length, sentence position and numerical identification are considered. Automatic Text Summarization in the Assamese language is still in an early stage and this language does not have its own approach. So, the text summarization approach is compared to the approaches applied in Bengali and Bangla language approaches as these languages share a script that is quite similar having slight variations in certain letters. The effectiveness of our proposed approach is demonstrated through a set of experiments carried out using ROUGE measure, and the evaluation is depicted in terms of Precision, Recall and F1-score.

Biometric person identification is getting more effective and popular because of Electroencephalography (EEG). EEG signals can be captured from human scalp invasively or non-invasively with the help of electrodes. EEG-based biometric system is more secure and unique for person identification. In this paper, we have used two different states to explore the adaptive and uniqueness of the EEG-based biometric system. We have used Eyes Open (EO) state as well as Eyes Closed (EC) state of a EEG motor imagery publicly available dataset of 109 users.The model is trained and tested with EO and EC states alternatively to prove the reliability and robustness of the model. The biometric person identification model has been designed using Support Vector machine (SVM) for classification. We achieved a notable person identification rate of 96% (EO) and 91.78% (EC) using SVM with Radial Basis Function (RBF) kernel. We have also used Ensemble Support Vector Machine (ESVM) to enhance the performance of person identification and observed the average performance accuracy of 96.16% with n number of classifier.

With the rapid growth of digital media content specifically in Videos, different genre of sports matches are among the foremost event of the Television industry. Currently, any live recording goes into a RAID system of sorts, where all the footage from various cameras is recorded and kept available for random access. The proposed work aims to achieve automation in the broadcasting industry by creating a Self-Acting application which generates the highlights package without any external people devoted to this cause.

Sentinel-2 optical time-series images obtained at high resolution are creditable for cropland mapping which is the key for sustainable agriculture. The presented work was conducted in a heterogeneous region in Sameerwadi with an aim to classify sugarcane crops, with mainly two groups so as to provide a sugarcane field map, using Sentinel-2 normalized difference vegetation index (NDVI) time-series data. The potential of two better-known machine learning (ML) classifiers, random forest (RF) and support vector machine (SVM), was investigated to identify seven classes including sugarcane, early sugarcane, maize, waterbody, fallow land, built-up and bare land, and a sugarcane crop map is produced. Both the classifiers were able to effectively classify sugarcane areas and other land covers from the time-series data. Our results show that RF achieved higher overall accuracy (88.61%) than SVM having an overall accuracy of 81.86%. This study demonstrated that utilizing the Sentinel-2 NDVI time-series with RF and SVM successfully classified sugarcane crop fields.

This paper presents an approach to solve an optimization problem using clustering by genetic algorithm approach. The central idea is to form clusters of patients’ nucleotide data sets. The genetic algorithm is applied to this initial cluster population. The fitness function for the genetic algorithm is calculated using intra-cluster and inter-cluster distances. Later genetic crossover functions are applied. This procedure is iterated until the stopping condition is reached. The superiority of this algorithm lies in comparing the performance with Ant Colony Optimization and simulated annealing algorithms.

Human activity is always a reflection of its external environmental conditions. If a group of people is in some emergency, then their activities and behaviour will be different as compared to normal conditions. To detect an emergency, Human Activity Recognition (HAR) can play an important role. Human activities such as shouting, running here and there, crying, searching for an exit door can be taken into consideration as an emergency indicator. By detecting the emergency and its degree, the Emergency Management System (EMS) can manage the situation efficiently. In this work, we use machine learning algorithms such as Random Forest (RF), IBK, Bagging, J48 and MLP on WISDM Smartphone and Smartwatch Activity and Biometric Dataset for human activity recognition and RF is found to be the best algorithm with classification accuracy 87.1977% among all other considered techniques.

In this paper, we have implemented an efficient and novel technique for multi-label class prediction using associative rule mining. Many of the research works for the classification have been carried out on single-label datasets, but it is not useful for all real-world application accounting to multi-label datasets like scene classification, text categorization, etc. Hence, we propose an algorithm for performing multi-label classification and solve the problems which come across in the domain pertaining to single-label classification. Our novel technique (ARM-MLC) will aim in enhancing the accuracy of any decision-making processes. Here, in multi-label classification, based on our work, we aim to predict the multiple characters of the instances.

Birth of neurons in the human brain relocates from their place of birth to other regions of the brain. Designing a model to read the structural changes in the brain will help scientists to understand more about the process of the life cycle of neurons. In this paper, Hypergraph-based model for recognizing the structural changes during the birth and death of neurons was developed and its performance was evaluated quantitatively with small-world network and robust connectivity measures. This neuron reconstruction model will operate as a treatment modality to cure brain diseases and disorders that affect the lives of millions of human being.

The objectives of this research are related to study the DBSCAN algorithm and engineer an enhancement to this algorithm addressing its flaws. DBSCAN is criticized for its requirement to input two parameters, namely—epsilon radius (ϵ) and minimum number of points (MinPts). It is difficult to know beforehand the optimum value of both parameters, and hence many trials are required until desired clusters are obtained. Also, in a dataset, a cluster’s density can vary. DBSCAN fails to identify clusters with density variations present. The proposed algorithm Adaptive Epsilon DBSCAN (AEDBSCAN), generates epsilon dynamically in accordance with the neighborhood of a point and thereafter adopts DBSCAN clustering with the corresponding epsilon to obtain the clusters. Experimental results are obtained from testing AEDBSCAN on artificial datasets. The experimental results confirm that the proposed AEDBSCAN algorithm efficiently carries out multi-density clustering than the original DBSCAN.

Association rule mining is a popular approach to find out the frequent itemset from a database and hence discover the association rules exist for those itemsets. It often turns out to be useful to explore the interestingness among the data. Student’s educational information is one such important area where mining algorithms can be applied to uncover useful hidden information for improving academics. In this regard, the association rule mining techniques have been used in the present work to study the importance of prerequisite subjects on academic results of dependent subjects. The dataset used in this study contains subject-wise semester marks collected throughout the eight semesters of 117 students of Computer Science and Engineering bachelor course of a university of West Bengal. The study reveals the significant impact of prerequisite subjects on the academic result of dependent subjects of students very clearly.

The instinct to know what others feel lays the foundation for the field of sentiment analysis which extracts opinion from text data and categorizes them as positive, negative or neutral. Beyond a report of the consolidated sentiment, the end-user is more interested to know what the product features that are talked about and what is the sentiment of the opinion holder towards each feature/aspect which leads to the task of aspect-level sentiment analysis. In this paper, the focus has been on the aspect extraction task of aspect-level sentiment analysis which extracts the features of the product that has been talked about in the reviews. The experiments have been reported on Bing Liu Customer Review Datasets consisting of five different categories DVD, Canon, MP3, Nikon and Cell phones. The strength of the model lies in the fact that a simple classifier that incorporates handling of imbalanced data, using a minimal set of robust features has been able to achieve comparable results with the state of art in aspect extraction task. The random forest classifier reported the best results across all domains with an F-measure ranging from 85.3 to 89.1.

The Visual Articulators like Teeth, Lips and tongue are correlated to one another and these correlation among those visual features are extracted with visual perceptions. The term visual perceptions indicates the features that are used as a parameter for representation learning and the description of visual information. These visual features are extracted and classified into different classes of Kannada Words. The movements of lips, tongue, and teeth are extracted by analyzing the inner and outer portion of lips along with movement of tongue and teeth. These parts teeth, lips, tongue are together used for feature extraction, as these features are correlated with resonances. These resonance information is extracted from every frames by analyzing and understanding the correlation that exists among them in different sequence of frames of a video. The proposed method of visual perceptions has yielded an accuracy of 82.83% over a dataset having different benchmark challenges. These benchmark challenges include facial tilt as a result of which the correlation may be less among teeth, tongue and lips. Thus, we have erected a new methodology of analyzing and understanding the visual features. The Kannada Words spoken by a person is indicated by assigning labels to the sequence of frames of a video in specific pattern. If these sequence of patterns of data is extracted and visualized from a video, the system recognizes the lip movements into different classes of words spoken.

In this paper, we have explored some unsupervised techniques for the task of Automatic Short Answer Grading. Three models are designed for the task in hand, with each model evaluating and grading students’ responses individually. The proposed method has shown quite promising correlation between scores generated by the method and that awarded by human scorers on a standard computer science dataset, with the overall correlation reaching the peak value at 0.805 which outperforms the state-of-the-art results reported on this dataset so far.

Mining of sentiments is the key aspect of Natural Language Processing. The analysis of sentiments has extended much consideration in recent years. In this paper, problem tackling of sentiment polarization is discussed, which deals with the high difficulties of analysis in terms of opinion/sentimental analysis. In this paper, the overall practice for sentiment polarity tagging is reviewed and also this paper discusses some recent approaches done on the sentimental analysis with detailed descriptions. Also the basic knowledge which is required to achieve effectual sentimental analysis is discussed in this review paper with their applications which deals with the sentimental analysis with various aspects. This paper discusses various tactics in brief to achieve computational behavior of sentimentalities and opinions. Several controlled practices in mining of the opinions in terms of the assets and disadvantages are discussed in this paper.

Deep Neural Networks have the generic layers and have appeared as a strong Machine Learning model as they use a different approach for classification of objects and can learn very complex models also. This paper tries to provide analysis of various related approaches (model optimization techniques such as MobileNets, MorphNet, SqueezNet, and so on) by which existing deep neural network architectures can be optimized. In order to aid the proposed approach of optimization, we built a tool on CO-LAB in order to deeply understand each and every model layer structure as well as visualized them closely using feature maps, which highlights each and every feature clearly and visibly. Keras and TensorFlow APIs are also used to understand the model building.

Cancer is a widespread hereditary disease in human beings and accounts for lots of deaths in the world. Early identification of the disease plays a significant role in picking the best treatment. Present work proposes a model which is based on the concept of Least Mean Square/Fourth (LMS/F) adaptive filtering algorithm along with the Volterra expansions of the input sequence. We have incorporated Trigonometric mapping along with (VLMS/F) filter to improve the prediction properties of breast cancer genes. Based on the value of MSE the decision is taken whether the anonymous target input sequence is cancer or healthy one. The proposed VLMS/F filter is tested on 10 breast cancers and 10 breast healthy benchmark genes available in GenBank. The MSE values for cancer and for all healthy case, the value is found to be >0.1 and <0.1, respectively. Thus the algorithm gives a satisfactory result.

Nowadays, there is a lot of urge for security everywhere due to various attacks over the Internet. Researchers try to find solutions but there are new exploits going on from time to time. This research provides security and privacy solutions for data mining using a Secured Crypto-Hybrid Algorithm. The proposed algorithm combines traditional algorithms such as K-means clustering and Local outlier algorithm combined with the AES-256 key encryption method on datasets for security analysis.

Satellite imagery data collected from various modern and older versions of satellites discover its applications in a variety of domains. One of the domains with great importance is the agriculture domain. Satellite imagery data can be significantly used in agricultural applications to increase the precision and efficiency of farming. These images are of great importance in applications like disease detection, crop classification, weather monitoring and farmland usage. In this paper, we propose a technique to classify sugarcane crops from the satellite imagery utilizing a supervised machine learning approach. Unlike unsupervised models, this technique relies on the ground truth data collected from the farm to train, test, and validate the model. The ground samples contain four stages, germination, tillering, grand growth, and maturity, of the sugarcane growth cycle. This collected information acts as an input to the U-Net architecture which will extract the features unique to the sugarcane field and further classify the sugarcane crop.

Modern busy lifestyles are acting as a catalyst to enhance the growth of various health-related issues among people. As a consequence, a massive amount of medical data are getting accumulated every day. So, it is becoming a challenging task for the medical community to handle those data. In such a situation, if a system exists that can effectively analyze those data and can retrieve the primary causes of a disease, then the disease can be prevented on time by taking the correct precautionary measures beforehand. Recently, machine learning algorithms have been receiving a lot of appreciation in building such an expert system, and the neural network is one of them which has attracted a lot of researchers due to its high performance. But the main obstacle which hinders the application of neural networks in the medical domain is its black-box nature, i.e. its incapability in making a transparent decision. So, as a solution to this problem, the rule extraction process is becoming very popular as it can extract comprehensible rules from neural networks with high accuracy. Many rule extraction algorithms exist in the literature, but this paper mainly assesses the performances of the algorithms that generate rules recursively from neural networks. Recursive algorithms recursively subdivide the subspace of a rule until the accuracy increases. So, they can provide comprehensible decisions along with high accuracy. Four medical datasets are collected from the UCI repository for assessing the performances of the algorithms in diagnosing a disease. Results prove the effectiveness of the recursive rule extraction algorithms in medical diagnosis.

Breast cancer is a rapidly growing cancerous disease, which leads to the main cause of death in women. The early identification of breast cancer is essential for improving patients’ prognosis. The proposed work aims at identifying the relationships between the attributes of breast cancer datasets obtained from HCG Hospital, Bengaluru (India). The work focuses on identifying the effect of attributes on three different classes, which are metastasis, progression, and death using Apriori algorithm, an association rule mining technique. To analyze the relation among the attributes with the value it takes for a particular class, more detailed rules are generated using decision tree-based rule mining technique. Rules are selected for each class based on specific threshold set for confidence, lift, and support.

The recent revolutionary technology transformations in the internet domain have enabled us to move from static web pages to ubiquitous computing web through social networking web. In return, this has enabled the recommender systems to leave their infancy and get matured while tackling the dynamic challenges arising for users. Recommender system anticipates user requirements before the user requires them. Recommender system in various domains proves its efficiency by providing appropriate recommendations according to the preferences of the users. It is a software solution in different online applications which helps the user to make appropriate decisions and also acts as a business tool in various domains. The proposed article covers the various types of recommender systems as well as the strategies and recent challenging research issues to improve the capabilities of recommender systems.

A balanced level of nutrients is very essential for healthy growth of plants. Deficiency of nutrients inhibits the growth of plants. It is needed to detect the infertile plants for the deficiency of nutrients at the early stage, so that proper fertilizers can be provided. In this paper, a framework is proposed by utilizing the images of nutrient-deficit leaves w.r.t. nitrogen (N), phosphorus (P), and potassium (K) of maize plant. A set of images contributes for bunch of dataset to be used as the training dataset. It is a non-invasive way of detecting nutrient deficiency in plants. The collected authentic training dataset of images is used to train the Inception V3 Convolutional Neural Network (CNN) model. The Inception V3 CNN uses transfer learning technique which is a research problem in machine learning. It concentrates on collecting the knowledge acquired while solving one problem and applying it to solve a related another problem. Therefore, features of maize leaf are extracted by the initial pretrained layers of CNN. Accurate and effective results are provided by speeding up the working of CNN. The given test image of maize leaf is provided to the trained CNN model which detects the nutrient deficiency in maize leaf as nitrogen, phosphorous, or potassium deficient accordingly. This framework can be applied in agricultural development in order to help farmers and to increase agricultural productivity.

This paper delivers a strategy to build a deep neural network, established by heaping layers of autoencoder, which in turn consists of both encoder and decoder layers, which are generally being locally trained to denoise the corrupted inputs and reconstruct an approximation to the original input. The outcome as an algorithm is a candid variation by stacking the ordinary autoencoder. It is basically a classification problem of machine learning yielding to obtain less classification error, and therefore spanning the performance gap with deep belief neural networks and in majority of the cases surpassing it. Results show that the reconstruction of the inputs depend upon the training parameters such as the upsurge of the epoch and batch size will increase the training period, thus increasing the accuracy in representing the denoised reconstruction.

In the last few years, there has been a tremendous change in the way users behave over the net. This is mainly because of the growth that has happened in the field of Web technology. In earlier times, the role a user over the net played was that of an information consumer, now it’s more of a data creator role. This role change has benefitted the world of politics, social network analysis, financial market analysis, etc., to name a few. Due to this huge creation of data, a mechanism that can automatically analyze and interpret this opinionated data is badly needed. Toward this research direction, unlike other summarization techniques, the paper proposes a novel method that is unsupervised and also domain-independent for generating opinion summaries. The final summaries that were generated are at four levels that range from being coarse to more granular ones. The proposed technique was tested on various data sets that were from nine different domains. The experimental results clearly indicated that 70–75% of the summaries generated were matching with the manually selected ones.

Managing a large number of textual documents is a critical and significant task and supports many applications ranging from information retrieval to clustering search engine results. The multilinguistic facility provided by websites makes Hindi a major language in the digital domain of information technology today. This work focuses on document management through document clustering for a big corpus and summarization of clusters. The objective is to overcome the scalability problem while managing the documents and summarizing the Hindi corpus by extracting tokens. The work is better in terms of scalability and supports the consistent quality of cluster for incremental dataset. Most of the past and contemporary research works have targeted English corpus document management. Hindi corpus has been mostly exploited by the researchers for exploring stemming, single-document summarization, and classifier design. Implementing unsupervised learning on the Hindi corpus for summarization of multiple documents through Word Cloud is still an untouched area. Technically speaking, the current work is an application of TF-IDF, cosine-based document similarity measures, and cluster dendrograms, in addition to various other Natural Language Processing (NLP) activities. Entropy and precision are used to evaluate the experiments carried on different live and available/tested datasets and results prove the robustness of the proposed approach for Hindi Corpus.

Medical health care (MHC) system is found to be most approachable and believable system, where utmost care has been taken by human intelligence with criteria like cure, prevent, and side effects. MHC is a new paradigm and in transition in integrating with smart clinical IoT devices powered with automated capabilities of data mining, artificial intelligence, and machine learning. Thus accurate prediction and classification from clinical datsets is the need of hour. Rough set theory (RST) plays a vital role in machine learning, inductive reasoning, and decision support expert systems. In this paper, we use RST-based feature selection method with a neural network to improve the classification accuracy in using different medical datasets. It is observed that a lot of objects or data is generally discarded (to make the dataset normal) during data preprocessing which would adversely affect the performance of classification. Our RST-based proposed method outperforms and opens a new dimension of applications in machine learning in the wide MHC domains including radiology, pathology, oncology, cardiology, neurology.

The growth of IoT explores new horizons in the field of healthcare industry. IoT has facilitated the delivery of electronic data among its users having dispersed demographic positions. Remote monitoring of data in the healthcare sector was possible by exploring new dimensions of IoT. ICT unleashes patient safety and enable health practitioners to deliver satisfactory care. This idea of IoT communication may be utilized in various sectors to deliver services to end users. India as a developing nation having large geographical jurisdiction and ethnic diversity has to afford huge establishments and manpower resources to deliver services to its citizens. Due to this situation, huge cumulative expenditure is mounted over the financial structure of the state. Moreover, the services delivered through traditional mode takes tremendous time to reach the user due to distant locations. To overcome these issues, electronic mode of message communication may be adopted to provide timely services in a budget-friendly manner over a distributed environment. The only concern is the security of sensitive information transmitted through public communication channel, i.e., internet. To handle it, hybrid cryptographic security protocols should be used to ensure Privacy, Integrity, Non-repudiation, and Authentication (PINA) during its implementation in real-world scenarios. Furthermore, to provide user-friendly system, a single-window-based service mechanism has been modeled in this work.

In IoT (internet of things) realm, sensors need an uninterrupted power supply for continuous operation. This paper presents an on-chip solar EHS (SEHS) design for IoT edge node devices. For matching the impedance between the solar cell and converter, CVM technique is adopted. The energy efficient hill-climbing algorithm (HCA) is adopted to follow the maximum power point (MPP). The control section takes care of the MPPT procedure, and computational load along with the charging of the supercapacitor. LDO (low dropout regulators) is used to generate various voltages needed by the sensors. The proposed system is capable of providing power supply to various edge node devices in IoT. The SEHS is designed in CMOS 180 nm technology. The output voltage is in the range of 1.2–3.55 V with an input of 1–1.5 V. The SEHS is consuming 25 $${\upmu }$$ W of power, which is within the ultra-low-power range in IoT.

It is well known that the current system of parking is rife with problems. The approach mentioned in this paper presents a smart parking system that reads details from an RFID tag belonging to the driver, and sends corresponding user/vehicle details to the cloud for storage. These details include the vehicle number along with the cost of parking. As time passes, the value of the cost is updated, and the driver is notified of the change, either via a push notification, or an email. This method works effectively, ensuring that the user is notified at regular intervals. Ultimately, this solves one of the problems associated with current parking systems, i.e., customers being unaware of the increased parking charges with time. It also eliminates human involvement to a certain extent.

Data is increasing drastically day by day specifically due to the usage of social networking websites like Facebook, Twitter, etc. It is very difficult for data owners to store and manipulate such a huge size of data as it incurs more cost of maintaining resources. To overcome this issue, data owners utilize cloud resources to limit the expenses. But as a third party, the cloud can be curious which may lead to the disclosure of personal data. This led researchers to use some techniques to provide privacy in cloud storage used by data owners and this is referred to as privacy-preserving data mining (PPDM). PPDM preserves the privacy of data owners in the cloud, so the private data remains private even after the mining process. This paper focuses on some of the important PPDM techniques like data distortion, encryption, etc. It brings out an extensive survey of privacy-preserving data mining techniques, their benefits and drawbacks, and put forth the open challenges for further research.

Day by day task scheduling becomes a more challenging issue as the user’s demand increases in cloud computing. It is a tedious task to deliver resources according to the user’s request with satisfying quality of service (QoS) requirement for both user and service provider. Many researchers have proved that meta-heuristic algorithms give better results for this problem. It inspired us to adopt a recently proposed Salp Swarm Algorithm to optimize request–resource mapping in cloud computing. This proposed QoS aware Binary Salp Swarm algorithm (QBSSA) has been inspired by the nature of salp during the searching and navigating for food in the sea. In this paper, QBSSA is simulated and compared with other most popular meta-heuristic algorithms, i.e., Ant Colony Optimization (ACO), and Grey Wolf Optimization (GWO). From the simulation results, it is proved that QBSSA outperforms others in terms of makespan and resource utilization, throughput, and average waiting time.

In emergency circumstances, mobile devices are very much helpful to gather the mandatory information in a powerful way. But it has the constraints like lower energy density and reduced computing capability. In order to reduce mobile phone workloads, high power-draining tasks need to be transferred to the cloud. Moreover, the absence of Internet access often renders it really challenging to transfer data to the destination cloud from the root mobile phone. To solve this issue, we propose an Emergency Management System using NSGA-II Optimization Technique which uses peer-to-peer network communication considering Bluetooth technology with Mobile Probing Service (MPS) and Mobile Ranking Service (MRS) for choosing the good smartphone. Also to find the mobile device which has maximized rank and minimized RNL value, the proposed E2M algorithm uses NSGA-II optimization technique.

Load balancing is an important metric for enhancing system performance. The distributed nature and heterogeneity of cloud resources makes scheduling and load balancing a challenging task. Scheduling of jobs to the appropriate virtual machines (VMs) can be done using different mechanisms, but balancing the load is the major problem that occurs due to fluctuation of load, and different VM specifications. This leads to imbalanced resource utilization and performance degradation of the system. This paper proposes a scheme for maximizing resource utilization by balancing the load across cloud system by distributing jobs to reliable VMs using firefly approach for better performance. CloudSim tool is used to simulate the scheme and results show that the scheme performs better than existing work.

The recent development in mobile computing resulted in widespread application of Internet of Things (IoT). IoT promises a world where smart and intelligent communication from most of the devices is possible through Internet anywhere, anytime with least possible human assistance. However, security and privacy are major concerns of IoT which could affect its sustainable development. In this work, we have dealt with IoT security from two main perspectives that are IoT architecture and protocols. We discuss different layers in IoT architecture and investigated the security concerns associated with different IoT layers along with their possible solutions. We have reviewed various protocols in IoT layered architecture and the security mechanism developed for each protocol. Also, we provide certain future directions of possible research for IoT security.