Search

Due to the increasing use of the Internet and other online resources, there is tremendous growth in the data of text documents. It is not possible to manage this huge data manually. This has led to the growth of fields like text mining and text summarization. This paper presents a title prediction model for research papers using Recursive Recurrent Neural Network (Recursive RNN) and evaluates its performance by comparing it with sequence-to-sequence models. Research papers published between 2018 and 2020 were obtained from a standard repository, viz. Kaggle, to train the title prediction model. The performance of different versions of Recursive RNN and Seq2Seq was evaluated in terms of training and hold-out loss. The experimental results show that Recursive RNN models perform significantly better than the other models.

The given paper is focused on experimental study of one particular category of DoS attack (Denial of Service) in cloud computing network known as TCP SYN flood attack, and its effect on the resource availability and the cloud service factors. The attack typically takes up the general services of the cloud and the resources of the cloud, thus denying of proper services to the genuine users. The resources of the cloud server are drained and hence any other incoming requests would not be responded, thereby denying the access to the legitimate users. The assumption here is that the data being transmitted between client, and server is a multimedia data. In this paper, we have tried an experimental study on TCP SYN Flood attack and tried to see out the various parameters affected by the attack.

In recent years, Weibo and news commentary information on the Internet have shown a trend of massive growth. It has become very difficult for people to accurately analyze public opinion from massive data. In this paper, a new classification method of meteorological public opinion based on deep random forest is proposed, aiming at the difficulties of public opinion analysis and the scarcity of data features in Weibo meteorological domain data. The method is used to analyses the evaluation data of Weibo on the basis of the meteorological data of Sina Weibo, thus judge the tendency of network meteorological public opinion comments when natural disasters occur. Firstly, we acquired and trained meteorological commentary data. Then used the method of word2vec to vectorize comment information. At last, the vectors were classified by the deep random forest algorithm, meanwhile, continuously optimized the classifier until the training set size reaches the set threshold. The experimental results show that the method proposed in this paper can better judge the public opinion tendency of network meteorological comments and has achieved better results compared with traditional classification methods.

In any corporation, if a significant number of employees leave their job with a short notice period, it may lead to a reduction in overall throughput which in turn will certainly have an impact on the turnover. Companies need to spend additional efforts in terms of time and cost to fill up the vacant position without any substantial loss to the ongoing business. To avoid these situations, we can use machine learning techniques to predict employees who are planning to leave the company with the help of some related data. One more way is to identify the features which inspire employees to leave their job. Refining such features in the company also will result in reducing the employee attrition rate of the company. In this paper, we attempted to predict employee attrition rate using the classification algorithms, namely Decision tree, Random forest, K-Nearest Neighbourhood, Neural Networks, extreme gradient boosting and Ada-Boosting. We also have applied regularization for every algorithm to find the precise parameters to predict the employee’s attrition rate considering the HR-data set from the Kaggle website which consists of 35 features including 34 independent and one dependent feature which is our attrition feature with Yes/No values in it. In this paper, we are going through different steps to finally obtain an accuracy of 88% with good precision and recall values.

In computer vision systems, however, retrieving a necessary image for a normal user is difficult. Over the last two decades, several studies have been conducted to improve the efficiency of automated image annotation, which has mainly concentrated on content-based image retrieval (CBIR) and attempts to identify specific images from a large dataset that are close to a query image. Various hybrid feature descriptors based on image cues such color, texture, shape, and so on that depict images were examined. For more than a decade, machine learning has been gaining traction as a viable alternative to hand-designed feature engineering. Feature extraction techniques and mathematical models are used to improve the performance and complexity of the image retrieval process. Furthermore, using the existing AlexNet convolutional neural network classifier, to increase the accuracy and performance of retrieval of Corel and Wang Datasets. Present state-of-the-art methods are described from different viewpoints for a deeper understanding of the development. Over the last period, the survey paper has given a comprehensive overview of hybrid feature extraction methods and machine learning-based enhancements for CBIR. In this paper, we hope to include a succinct overview of recent developments in CBIR and hybrid feature extraction methods, as well as machine learning-based enhancements for content-based image retrieval.

Machine learning has rapidly gained traction in a variety of fields, including science, healthcare, engineering, and biotechnology, in recent years owing to its effective functioning mechanism. Health care has always been a key priority for any government as the industry has made significant progress by using machine learning, artificial intelligence, and deep learning for disease prediction and diagnosis. The central aspect of this paper is to evaluate different machine learning algorithms and classification techniques in order to detect and predict different chronic diseases. The paper discusses supervised classification strategies for detecting diseases such as cancer, psychological disorders, and cardiac disorders, as well as various bioinformatics and biomedical research challenges. The comparison between classification techniques like support vector machines, logistic regression, decision trees, random forest, and Naive Bayes classifiers has been observed in numerous diseases. The algorithms that are specifically applied in the medical applications and in healthcare sector enabled the clinical experts and physicians to watchdog, diagnose, and monitor the disease effectively and perform appropriate measures in the shortest possible duration. Decision support systems benefit the physicians for effective and timely decision-making capabilities in case of chronic diseases. The paper reviews the implementation of machine learning and deep learning which has undoubtedly contributed toward health informatics, healthcare systems including bioinformatics. After discussing the techniques and comparison of numerous classification algorithms in several diseases, the ones which have efficiently produced an appropriate result in an early detection of diseases have been highlighted. In order to emphasize the issues that must be considered while implementing the methodologies and classification algorithms for an early illness detection system, several future directions are described.

Stress is a mental condition that affects every aspect of life leading to sleep deprivation and various other diseases. Thus, it's necessary to analyse one's vitals to stay updated about one's mental health. This paper presents an effective method for detecting cognitive stress levels using data from a physical activity tracker device. The main goal of this system is to use sensor technology to detect stress using a machine learning approach. Individually, the impact of each stressor is assessed using ML models, followed by the construction of a NN model and assessment using ordinal logistic regression models such as logit, probit and complementary log-log. The paper uses heartbeat rate as one of the features to recognise stress and the Internet of Things (IoT) and Machine Learning (ML) to alert the situation when the person is in real danger. The patient's condition is predicted using machine learning and the patient's acute stress condition is relayed using IoT. Based on the heartbeat, a prediction of whether a person is under stress or not can be made. The paper presents a model that can predict stress levels based entirely on electrocardiogram (ECG) data, which can be measured with consumer-grade heart monitors The ECG's spectral power components, as well as time and frequency domain features of heart rate variability, are included in the model. The stress detector system takes the real-time data from the IoT device (sensor), then applies a machine learning model on the data to detect stress levels in an individual and eventually informs/alerts the individual about their stress condition. By collecting data, this system is tested and evaluated in a real-time environment with different machine learning models. Finally, a comprehensive comparative analysis has been depicted amongst the applied models with Random Forest Classifier showing the highest accuracy. The novelty of this work lies in the fact that a stress detection framework should be as unobtrusive to the user as possible.

According to survey in January 2020, over internet almost 1,295,973,827 web sites are hosted. Among them 72% websites are vulnerable to different attack like SQL Injection, Cross Site Scripting, Brute forcing attack, Phishing attack, password attack, birth day attack, malware attack and man in middle attack now days many hackers/attackers are trying to bypass the security mechanism by using new techniques so it’s challenging task to respond newly and unknown attack with an effective solution. In this paper i am trying to find out the techniques, tools, and solutions used to detect attacks, such as intrusion detection systems (IDS), Web Application Firewall (WAF), machine learning (ML) techniques, this tools and techniques is used to discuss analysis of traditional technologies, drawback and produce more effective solutions. In this paper we compared the different web application firewall correspond to its policy control and one proposed a new web application firewall. In the proposed web application firewall we have discussed three approaches.

With the rapid advancements of various information technologies in recent years, many new forms of e-learning schemes have emerged. Due to the various issues with such e-learning schemes, however, the commonly adopted teaching method is still the traditional face-to-face classroom in practice. In such a teaching mode, the three key elements of all teaching modes, i.e., theory, experiment, and practicing, are separate and independent of each other, which largely degrades the learning efficiency. To address such a practical issue, based on the objectives of professional personnel training for navigation and control, this paper presents a curriculum teaching model that integrates the three learning key elements together. Specifically, this paper shows the architecture of the curriculum construction mode first, and then presents the composition and function of the student dimension, teacher platform dimension, laboratory server dimension and laboratory equipment dimension in the navigation and control course group, respectively. Finally, with the course of “principle of inertial sensor” as a case study, this paper introduces the teaching process of using the teaching mode, which integrates the three key teaching elements together in the course. The practical teaching results show that this proposed teaching mode could not only make the teaching process of engineering courses intuitive and easy to understand, but also enable students to participate in the theorical, experimental, practical teaching and learning process throughout the presented mode. This mode could largely enhance both students’ learning enthusiasm and the efficiency.

This paper surveys several recent abstract summarization methods: T5, Pegasus, and ProphetNet. We implement the systems in two languages: English and Indonesian languages. We investigate the impact of pre-training models (one T5, three Pegasuses, three ProphetNets) on several Wikipedia datasets in English and Indonesian language and compare the results to the Wikipedia systems’ summaries. The T5-Large, the Pegasus-XSum, and the ProphetNet-CNNDM provide the best summarization. The most significant factors that influence ROUGE performance are coverage, density, and compression. The higher the scores, the better the summary. Other factors that influence the ROUGE scores are the pre-training goal, the dataset's characteristics, the dataset used for testing the pre-trained model, and the cross-lingual function. Several suggestions to improve this paper's limitation are: (1) assure that the dataset used for the pre-training model must be sufficiently large, contains adequate instances for handling cross-lingual purpose; (2) advanced process (fine-tuning) shall be reasonable. We recommend using the large dataset consisting of comprehensive coverage of topics from many languages before implementing advanced processes such as the train-infer-train procedure to the zero-shot translation in the training stage of the pre-training model.

Artificial Intelligence (AI) is a new field triggered in computer science in order to solve complex problems like cooperation, distribution, and communication. AI has many research areas for the development of complex systems. Multi-Agent Systems (MAS) are one of reach of using autonomous systems which have actors’ acts on their own based on user requirements to solve their problems. A new development of programming language called Agent-Oriented Programming (AOP) for programming autonomous agents and multi-agent system MAS. The agent in MAS acts in an autonomous way without any human or system interaction. The agent has the ability of automated action in order to reach its goal. An agent has the Belief-Desire-Intension (BDI) architecture in order to define the behavior of the system using Agent-Oriented Programming. This paper shows a proposed model which is an intelligent multi-agent system for e-bookstore that communicates with each other using a Foundation of Intelligent Physical Agent (FIPA). Also this paper shows the search performance within the communication results worked on Amazon Dataset and evaluates the quality of intelligent agents of E-bookstore system.

During the challenging times of COVID 19, major shifts in the learning and interaction process have been observed especially in the field of education and platforms of wider interactions like seminars. Online medium has been emerging as the order of the day. In this context, this paper looks at a new challenge that is being faced by various institutions while carrying out the interview process or interactions online or on a telephone. The recruiter might miss certain points when evaluating a candidate or sometimes the finer details of an interview are lost in communication, the interviewer might also not be able to recall the details of a particular interviewee at a later point in time. These are some of the challenges that would ultimately reduce the effectiveness of an interview process. We are developing a platform that extracts all the essential information delivered by the person who is being interviewed from the data received by the candidate during the process. The paper makes use of Natural Language Processing (NLP) to extract the key information from an interaction by extracting certain features or important key points by making suitable algorithms with the help of language dependencies. The paper also dealt with the outcome of the interview in the sense that, whether the candidate got selected or not based on her/his answers and how similar they are with the data provided by the company which clearly puts forward what they are looking for in an employee.

The huge collection of data under the domain of health informatics has always been of crucial importance in giving insights into human health and its sundry causes. With technology rising day after day, this data can be visualized under different lights which are depicted in the following paper. Data analysis is the answer to the challenges of the healthcare industry because of the plasticity offered in implementing its techniques in various frameworks and technologies. A notion about Machine learning and its association with big data has also been discussed here. The Machine learning techniques have always made analysis better; with a similar analogy, the paper gives a glimpse of ameliorating the patient’s lives who are looking for healthcare facilities in the Bengaluru region.

Internet of things (IoT) refers to a network where the devices included in that network are connected with each other through a common medium, in this case, the Internet, in order to share or exchange data with other devices in the network. The paper concentrates on Management of Security of these devices in the IoT network along with their maintenance, accessibility, etc. The main problems faced are data leakage, data alteration/modification, access to private data or important transactions, data loss, etc. This review paper refers to various ways to improve the existing IoT system with the use of different consensus algorithms and techniques. It also covers the security and data privacy of systems like smart homes and smart cities through modified blockchain systems.

With an increasing number of Indian manuscripts being digitized, the subject of their era prediction is readdressed to interpret the socio-economic fabric of different periods. This paper describes a novel approach to estimate the era of Indian manuscripts from their scanned images using convolutional neural networks (CNN). The method primarily uses image processing to harness visual features from small image patches and classifies them based on the difference in writing styles in terms of strokes and letter formation. We follow a two-step approach of language prediction followed by a separate era prediction model for each language to achieve optimal results. For this paper, we restrict consideration to six Indian language manuscripts written between the sixteenth and twentieth centuries. Conclusively, our model outperforms other well-known architectures and gave over 90% and 80% accuracy on the training and validation data, respectively.

Due to advancement of new edge medical technologies, many methods have been applied to solve medical issues including machine learning approach. Cardiac Arrhythmia is one of the common diseases which can be solved using various machine learning approaches. There are many approaches which have already been introduced to classify arrhythmia and abnormality detection. This paper has a solution, introduces supervised and unsupervised models in which supervised models generate a good classification result. However, in this paper, we have also introduced a deep neural network classifier and used for prediction of arrhythmia if present based on some predefined value. In this paper, we have also connected it to the user interface to which the native users can check the level of arrhythmia.

Medical and healthcare monitoring system has had rapid growth in not only hospitals but other health-related centers as well. Effect of a wrong prescription leads to death of a patient, also unnecessary medicine prescription is the burden for the guardians or caretakers. IoT (Internet of things) allows a variety of devices to interact with each other to enable monitoring, storage, analysis and display. This paper explores the developments taken in the field of patient monitoring systems to avoid wrong and unnecessary prescription, and through this research, we found that selecting IoT protocol to design the system is important and depends on the system requirements like number of data sending nodes (Data Producers), network traffic hitting the server, scalability, network latency and real-time requirement. This paper proposes the design of a real-time patient monitoring system with microservices architecture to send patient’s data from ICU to the doctors and guardians. The proposed system also helps to reduce unnecessary prescription and billing.

The last two decades of the Information Age have been characterized by widespread proliferation of the Internet of things (IoT) technology. Besides diverse applications in various consumer, industrial, agriculture, and health care, IoT has enabled solutions for better management of natural resources. This paper illustrates the productive use of the IoT concept to automate the irrigation of vermicompost, encompassing three prime domains—waste management, smart irrigation, and (mobile) app. The soil moisture content and temperature of the compost bed are critical factors that delimit the earthworms’ life expectancy. This paper includes an intelligent monitoring system for effective irrigation of the compost bed, at precise time intervals. The irrigation status and the compost bed's moisture content can be monitored ubiquitously through the Amrita Sparsham mobile application software, minimizing human intervention, facilitating water conservation. Thus, the multipurpose solution is the convergence of Amrita waste management through vermicompost and the automated smart irrigation system monitored using Amrita Sparsham mobile application.

Legal information processing attracts attention from a number of organizations globally which includes research institutions; specific areas of interest ranges from representation of legal data, such as prior court cases, for countries which adopt common law system. These legal datasets typically include legislative acts or statutes, which vary from one country to another. Mining this legal data in order to extract useful information poses formidable challenges, which include coming up with ways for storing datasets, which are continuously generated and growing exponentially every year. Additional challenges include keeping up with amendments of the statutes and invalidating old statutes. This paper details a system architecture containing several key subsystems toward design and development of Legal Humanities for Africa, which is digital, query-able and easy to use and navigate by both lay user and experienced professionals. The Legal Humanities of Africa architecture has three modules, namely, knowledge base, knowledge engine and HCI module. The knowledge base handles the legal data dictionary, glossary and metadata in a domain-specific manner, while the knowledge engine handles processing data from the legal cases or statutes. Various approaches to computational linguistics, such as natural language processing or information extraction, have been used for natural language processing, including finding part of speech in text that contains most informative terms that are useful in computing similarity between prior cases to user queries. Submodules in knowledge base are also employed as needed to help optimize the process of extracting useful information to users usually in terms of relevant cases relating to specific legal matters at hand. Other techniques employed include several aspects of machine learning, such as unsupervised learning approaches to identify and cluster prior cases so that similar cases are clustered together, thus, making the process of matching user queries to prior cases easy. The HCI module provides user-specific (lay vs. experts), domain-specific and other anchor desks as required in a typical large application that can be commonly used by many types of users. A parametric evaluation of the performance of the Cloud-based Legal Architecture indicates that the system can enhance its use by both professionals and commoners; details are provided in this paper. It is hoped that the Legal Humanities of Africa architecture will become the benchmark architecture for Africa at large.

Computer vision using deep learning has revolutionized the detection system and vehicle detection is no exception to it. The importance of vehicle classification and detection is in Intelligent Vehicle and Transportation systems which require making critical decisions based on this information; therefore it is a prominent area of work. This paper presents a vehicle detection model predicated on convolution neural network using bounding box annotations for marking the region of interest. The model is tuned to give best performance by evaluating the different parameter configurations. The implementation is done using Python and OpenCV and is trained upon Google Colab’s free GPU access. The paper presents an efficient stepwise explanation of the process flow in detecting cars in various real life scenes. The proposed model is trained on the combination of two benchmark dataset and attains 94.66% accuracy and 95.13% precision.

In recent years, malware has become more sophisticated. Security solutions based on signature-based detection and known behavior-based detection are not capable of detecting unknown malware. Anomaly detection is an effective strategy against unknown malware. In this paper we present a method to model the normal behavior of processes that run on a computer and detect whether a new process instance conforms with this normal behavior. In this paper we present unsupervised tree-based anomaly detector (UTAD) which is used in combination with autoencoder to detect anomalous process behavior. We evaluated the performance of model in separating behavior of genuine processes from one another. The ensemble model achieved good accuracy with low false positive rate.

Solar power is among one of the major renewable energy sources, and there are various applications depending on solar energy. These applications require continuous time series radiation data to access its usefulness, so missing values in solar dataset can have a significant effect on the performance of solar energy systems. This paper is focused on investigating a machine learning-based data imputation method using generative adversarial networks (GANs). Inspired by the success of GANs in other domains, it is being used for data imputation. The incomplete data adversely effects any time series study and forms hindrance in the path of advancements. The solar insolation missing values in the solar dataset are imputed in this work. The paper uses GAN with the concept of mask and hint matrix to ease the process of imputation. The work is demonstrated on the real-world solar dataset from three different regions. The competence of the model is judged by using the new imputed dataset for training different time series forecasting models. The performance of the model is also compared against frequently used imputation methods.

As the scientific know-how of the people around the world is expanding, the requirement of new technologies is also growing rapidly. This is evident by the number of papers being published and the new discoveries of scientists that are changing the definition of impossibility day by day. This paper explains one such technology which has made possible not only the recognition of natural language (i.e., human language) by computers but generation of speech and text which is natural language processing (NLP). When machine learning came into picture for assaying large amount data (statistical), deriving meaning from data became easy. Statistical prediction could be made for data containing millions of data points. However, analysis and prediction from textual data still remained a challenge. In 1950s, Alan Turing’s publication—Computing Machinery and Intelligence, introduced NLP in computational field which dealt with conversion of human language to machine-readable form and generated written or spoken output. NLP can be further be applied in bioinformatics for deducing the structure and function of a protein from its primary chain sequence or deriving end products of functional genes from their basal sequences as many researchers have found the sequences to be similar to human language calling it the ‘language of life’. Current studies are based upon using the rules of NLP in analyzing gene and protein sequences. This article is aimed at exploring the various applications of natural language processing in the field of bioinformatics and medical informatics.

Automatic fake news detection for categorizing the news as either fake or real is a complicated problem. Generally, the fake news does not fully contain false information. It is usually mixed with a substantial portion of genuine information. The accessibility to the Internet and willingness to distribute the data through social media is quick and easy. This makes it very easy to propagate fake news worldwide leading to dangerous and obnoxious impacts on society. Most of the current methods to tackle false news detection are based on deep learning approaches. But, these fake detection approaches did not exhibit remarkable improvement in identifying the fallacy because of the insufficiency of datasets. So, LIAR which is an efficient and benchmark dataset that is publicly available for carrying out research on fake news detection and has been used in the paper for detection of fake news. In this paper, CNN-based deep learning neural network model with attention mechanism has been considered for fake news detection system and the performance of the attention mechanism with seven different training optimization algorithms Stochastic, Adam, Nadam, Adamax, etc., has been evaluated and compared. Performance evaluation has been carried out in terms of accuracy, precision, recall, and f1-score with LIAR dataset.

This paper talks about how information technology can be used to create a system for the entertainment industry, which can help combat the losses incurred during the pandemic. IT is the abbreviated form of information technology. It deals with computer mechanisms such as networking, software, and hardware. Many firms these days opt for IT-based operations as it makes everything more convenient. It is used in a variety of fields like gaming, sports, education, and even entertainment. Among the vast list of subcategories in information technology, one is slowly gaining momentum, the Virtual Reality or VR industry. The paper also proposes a model to capture various images for further uses in Virtual Reality. Virtual Reality is a simulation in which a person can use a 3D surrounding using multiple peripherals. Depending upon its efficiency, it gives the user a real-life experience in the comfort of their seats.

In this research paper, machine learning-based models are used for predicting the number of countries that have been affected by the COVID-19 virus and what was the situation of them. Then, the analysis is performed whether the “Lockdown” is the savior or not, and how India faced the whole problem. After that the prediction model for India was also prepared. These are the selected ones that are comprised in this paper. The COVID virus has spread globally, causing thousands of deaths and having an enormous impact on our health systems and economies. As soon as the Covid-19 pandemic was hit hard worldwide, lots of researchers were trying to figure out lot more things, among them when and from where did the virus make its an outbreak. The whole analysis part is based on the data science and machine learning algorithms and utterly dependent on the data collected from various trusted sources. In this paper, decision tree-based linear (DTBL) model and Random Forest Regression (RFR) models are applied to ensure the accuracy of the models. The Auto-Regressive Integrated Moving Average (ARIMA) and Prophet Algorithm are used for the prediction model. Preventive measures to reduce the spread of the COVID virus in respective zones are also suggested. We hope that this research work will help in the understanding and eradication of the threatening disease. This study can be applied by other countries for predicting COVID-19 cases at the state or national level.

Mathematical expression or formula recognition system is evolving field in pattern recognition. Various methods are implemented by different researchers on wide areas. Handwritten mathematical expression field evolved in last decades rapidly. This paper aims to target and represent CNN as an application of the deep learning method for recognizing the handwritten mathematical symbols. The current trend of the deep learning architectures witnesses CNN is one of the most prominent and widely used techniques that have been successfully implemented in NLP, computer vision, and pattern recognition. The kinds of deep learning models have proven to produce a recognizable state of the art. In this paper, we recognize the handwritten mathematical symbols using CNN. This paper comprises stages involved in recognition process, challenges and proposed methodology used by the author to conduct their experiment and further result and future scope is discussed. Dataset used for this experiment is downloaded from the public available platform (HasyV2 Dataset 2018. A dataset of size 369 classes comprising 168,223 images has been used for experimentation, and the results relieve the accuracy of 76.17%. For further improvement, an extra dense net (fully connected layer) has been used. The DuosdenseNet model has been designed; the accuracy of recognizable results shows a decent work for consideration.

Identifying and curtailing the spread of fake news is a complex and challenging task. Automated stance detection can be an important first step in alleviating the tedious process of fact checking. In this paper, we try to evaluate various language representation, and statistical similarity technique to discern the best possible mathematical modeling of the sentences for the task of stance evaluation. Our work is based on the dataset of the fake news challenge 1. The paper expounds our implementation details, the features, and models that work best for the given task.

The rapid advancements in computation methodologies and cloud computing along with the rapid expansion of the Internet of things have resulted in tremendous advancements in Cyber-Physical Systems (CPS) especially in health care systems. The competencies for adaptation of advanced healthcare monitoring systems have been raised. In healthcare industries, today CPS ranges from providing smart feedback systems, automated updating of the patient data digitally, continuous passive monitoring of patients using biosensors, and much more. Cyber-Physical Systems are changing into life-saving decision-making systems. Moreover, CPS has developed an unbreakable bonding with Wireless Sensor Networks abbreviated as WSN. The main motive has been to consolidate the major works in the areas of data privacy and security in CPS and healthcare in the survey. In this paper, researchers’ contributions related to the security of Healthcare CPS have been discussed in general and included the latest updated papers in the domain, later, has extended the focus to Wireless Sensor Networks and the vulnerabilities faced along with their defense as an overview. The concept of Sensor Only Networks, an advancement to WSN based on the security policies has been overviewed.

At present, information technology is widely used, which has a strong impact on the traditional art. Before this, many researchers have not systematically studied the operation of computer software, completely ignoring that computer software can be used to implement based on art skills. In particular, the rapid development of computer art design industry, it appears that the basic skills of art in art design is important. Therefore, this paper puts forward the research on the development of the integration of basic art skills and computer art design under the background of the information age. This paper starts from the basic content of computer art design and analyzes the importance of solid basic art skills to computer art design. Based on the background of the information age, this paper combines the basic skills of fine arts and computer art design from the perspective of mutual integration, that is, the traditional artistic consciousness, and sublimates the artistic expression form on the original basis. The results show that the effect of the integration of the two has a qualitative leap compared with the traditional art forms and is deeply loved by the public.

No matter what kind of machine translation is based on, the quality of translation has always been concerned, and the computer is facing some difficulties in natural language processing in the process of translation. In the face of the above problems, this paper proposes an intelligent translation model based on human-computer coupling (HMCIT). The core strategy of HMCIT is to use natural language understanding to analyze the grammar and semantics of the text, and then use human-computer coupling intelligent translation technology to generate text summary after information fusion. Firstly, the Markov random field is used to map it to three tuples. Then, the semantic distance between the image and the sentence is calculated by similarity. Finally, the sentence with the closest semantics is selected from the sentence pool to generate the image description. In this paper, we compare HMCIT with the classical alignment model in terms of confusion. The results show that the confusion degree of the translation results of this model is 43% lower than that of the alignment based model, which indicates that the effect of HMCIT is better. HMCIT is to extract one sentence or several sentences from a document or document set to form a summary. Its advantages are simple and practical, and it is not easy to deviate from the main idea of the article. However, it may have some disadvantages, such as incoherent summary, poor word control, and unclear target sentence. The quality of the summary depends on the original text.

In this paper, the corpus based research method is used to study the register characteristics of tourism English, and the multi-dimensional analysis and corpus research method are used to carry out qualitative analysis and research on the quantitative data. Corpus linguistics mainly by providing real corpus of multidimensional character description and analysis on the tourism English text research, introducing corpus to tourism English text and the translation study, can in the past research on tourism text words, chapter case analysis, on the basis of multidimensional, multi-angle on the depth of tourism English text features of research and analysis of characteristics of the language. Therefore, this paper mainly combined with some tourist attractions in Anhui Province, based on the webpage text of these tourist attractions, and then used CAWS4 software to annotate the tourism English text corpus with part of speech, on this basis, combined with Wordsmith and Antconc corpus tools to retrieve and analyze these data. Then it analyzes whether there are differences in tourism English text features among different corpora.

Text classification is a basic problem in the field of natural language processing. It is a very active research direction in the field of machine learning, and has many important practical applications. This paper mainly studies the application of semantic analysis in text classification of computer technology. In view of the fact that most current methods ignore the important correlation between features, this paper adopts the LSA method, which fully considers the semantic relationship between features and reduces the dimension of feature space, so as to construct a new semantic space. Experimental results show that the proposed method can effectively reduce the dimension of feature space and improve the performance of text classification.

Distance education is a new form of education which has been evolving in the field of contemporary education. It has been developed vigorously under the promotion of Internet education platform. Distance education also promotes the cooperation and exchange of traditional teaching in different regions. It does not conflict in function, nor does it form commercial competition. It is a good complementary mechanism of education. The purpose of this paper is to design and implement the platform of distance education, so that learners can flexibly arrange their time for education according to their own situation and improve their learning efficiency. This paper analyzes the problems in the development process from the perspective of the practical application of software, describes and evaluates the specific requirements of the three roles of students, teachers and managers, and makes improvement and improvement. In the case of realizing the basic functions of distance education platform, a new evaluation system based on test paper generation algorithm is proposed and applied to the system to realize the function of online random test. Based on the traditional J2EE architecture, the B/S model based on web is adopted. The designer realizes a functional module which takes students, teachers and administrators as the main roles. Finally, after we have realized all the functions of remote sensing distance education platform, we have checked and tested its system function and software performance. It is found that when the system carries out information transmission with no more than 400, the feedback speed of the system or users is not high, usually less than 0.5 s, which indicates that the platform has good performance and meets the teaching and management requirements of distance education.

Under the background of the era of reading pictures, the major of visual communication design shows a new development trend, which not only shows that the tentacles of the professional discipline continue to extend to multiple fields, but also greatly expands the communication channels. This paper mainly studies the application of graphic language automatic arrangement algorithm in visual communication. Based on the study of the characteristics of the Internet, the development of media and the popular trend of dynamic layout design, this paper summarizes the design principles, design methods and forms of dynamic layout. In this paper, based on the current research status of resource allocation algorithms in automatic scheduling, a graphical language automatic scheduling algorithm is proposed. On this basis, an optical grid resource allocation algorithm based on multimode and a service scheduling algorithm based on port resource saving of optical network based on multimode are proposed.

In sports competitions, it is an important basic work to verify the qualifications of participants. With the rapid growth of data, it is too cumbersome to manually verify the qualifications of participants. Based on this, we need to build a complete set of population resources data analysis service platform through the technology of big data storage, calculation, analysis and excavation. The purpose of this paper is to use big data analysis technology to build an intelligent personnel information management system to verify the qualification of participants in sports competitions, and realize the function of centralized and intuitive display of electronic files of participants. This paper uses HDFS distributed file storage system with MySQL relational database to store data, uses spark distributed file computing engine to analyze and process data, and then uses web front-end technology and echart data visualization technology to design a personnel information management system with strong expansibility, high efficiency and fast data processing speed, strong practicability and simple operation. This paper describes the design of the system from the server and the client, and finally tests the function and performance of the system to ensure that it meets the requirements of users. After testing, it is found that when the test times of the system is 600, the connection time is less than 1 s, and the system passes the connection speed performance test.

Whilst the world is preoccupied in its struggle with the Coronavirus pandemic, cyber-criminals are busy every day, spreading their own viruses, by phishing emails, data breaches, frauds, denials of service, and taking advantage of the vulnerabilities created by this crisis. In many ways, we, as a nation, are handing over our data without realizing it, without fully thinking it through or even being aware of cyber threats, which will ultimately have a tremendous impact on the governments and citizens both personally and at work. The goal of this paper is to investigate the correlation between the cyberattacks before the coronavirus and during the coronavirus in order to build an understanding of what is happening. To optimize cyber security and provide effective ways to tackle cyber security attacks during COVID-19 or something similar, we need to consider extra precautions and take a more secure approach to protection. To minimize the universal risks of data breaches and other cyber incidents, we need to enforce practical steps to deal with and if possible limit those risks. This requires not only thoughtful consideration, but also a good understanding of the opportunities that COVID-19 provides to cyber-criminals. The aim of this research paper is to investigate the growth of and reasons for the increase of cyberattacks during the COVID-19 pandemic. In order to make better cyber security decisions, we need to address and maximize the level of cyber security awareness and precaution taken during COVID-19. A set of practical steps to minimize the risk of cyber-attack is provided to compensate for the vulnerabilities associated with COVID-19.

Blockchain is a technology that is initially used for cryptocurrencies like bitcoin. The biggest advantage of this technology is that it is immutable data stored in blocks that cannot be changed, rather a new block is added in the chain and a new record can be inserted into it. The previous record shall remain the same and the record of every transaction can be tracked. Many studies and surveys have been done on blockchain mentioning the implications and contributions of blockchain. This paper presents a detailed survey of blockchain mentioning its features, advantages and protocols. In this paper, the authors have presented the working, features and usage of blockchain technology. In the future, based on the characteristics of blockchain technology, the authors will implement blockchain with the cloud of things.

This paper presents the results of a new monitoring project of the US presidential election with the aim of establishing computer-based tools to track the popularity of the two main candidates. The innovative methods that have designed and developed allow us to extract the frequency of search queries sent to numerous search engines, social media, and e-shops. Based on these data, this paper demonstrates that Donald Trump is significantly more frequently searched than Joe Biden. When analyzing various political topics, it is observed that the US Internet users have shown a remarkable interest in subjects like Coronavirus, and Jobs in 2020. Other subjects such as Education or Healthcare were given less attention. Finally, some “flame” topics such as Black lives matter appeared to be very popular for a few days before returning to a low level of interest.

This paper focuses on comparing the various machine learning (ML) algorithms that can be applicable in wavelength division multiplexing (WDM) optical networks to provide better simulation outcomes. ML, combined with WDM optical networks, helps in network control and resource management that are useful in service provisioning and resource assignment. This paper gives a comprehensive review of machine learning approaches in WDM optical networks concerning support vector machine (SVM), K-nearest neighbour (K-NN), decision tree, random forest and neural networks algorithms. These algorithms’ performances are compared in terms of accuracy and AUC; further, the accuracy and AUC results show an average outcome of 99% and 0.98, respectively. Simulation can be performed on MATLAB and Net2plan tools using different data sets in terms of average accuracy and AUC for WDM optical networks. This research’s future directions can be towards ML utilization to provide optimal routing and wavelength assignment, increasing bandwidth utilization to reduce control overheads, reduce computational complexity, security, fault occurrence and monitoring schemes for WDM optical networks supporting 5G applications.

Blockchain is a substantive technology which provide reliable and convenient services by establishing trust in open environment. Blockchain basically relies upon two critical technological areas of cryptography and decentralization to perform transactions of confidential data. This technology is gaining traction since its discovery in 2008 due to its ability to accomplish immutable transactions without third party interfere. Owing to these astonishing features, it has become backbone of all industries and business including digital financing, e-Governance, smart grid, etc. Many banking and financial service providers have started to allot wallets to its customer where they can use money in highly secure environment. However, blockchain is considered the most secure technology available today, but its wallet is still not a temper proof. This paper aims to analyse various issues pertaining to blockchain wallet security. The existing developments in this area are studied in detail to pave a future direction of research in this regime. Section 1 is introduction of blockchain which includes blockchain wallets and their types, security issues in wallets and security practices used to resolve those issues. Section 2 includes wallet security challenges, vulnerabilities and recent review of literature on wallet security practices. Section 3 compare the related work and discuss growth in crypto crimes due to loss of cryptocurrency. Last section concludes the paper.

Sentimental analysis which is also known as opinion mining is one of the major tasks of natural language processing (NLP). Sentimental analysis is a technique which is used to identify a person’s sentiment, humor and their emotion. Sarcastic comments imply what a person wants to say in a conflicting manner. Sarcasm is being generally used among numerous informal communication and smaller scale blogging sites where individuals attack others which makes tricky for the person to state what it implies. For example, many sarcastic tweets which gives a positive impact like, “Technical talk right after lunch” but it describes an undesirable activity. There are number of researches done in sarcasm. In this paper feature extraction techniques were used, for instance, logistic regression, support vector machine (SVM), random forest, etc. to recognize sarcasm in tweets from the twitter gliding API. The perfect classifier is picked then joined along different pre-handling, separating methods utilizing sarcastic and non-sarcastic lexicon mapping to give the most ideal precision. A GPS tracking system is used collect the data and allocate to which location the Tweets are coming from. The sarcastic and non-sarcastic word reference being the shrewd idea introduced in this paper.

The enormous growth and availability of data poses a great challenge for extracting useful information from documents written in natural language. The information extraction task has become a vital activity in all domains. The process of identifying the names of organization, people, locations or other entities in text is called named entity recognition (NER). It is the subtask and plays an important part to discover and classify the names such as organization name, person name or the location. This is one of the trending fields and most important step in the natural language processing (NLP) for analysis of text. Research on NER changed a lot in the recent decade. NER can consequently examine the entire articles and reveal the individuals, associations, and spots talked about in text. Knowing the applicable labels for every single article help in naturally arranging the articles in all around characterized progressive systems and endorse smooth content disclosure. The pretension of this paper is to present survey on NER. The prime contribution of this research to present state-of-the-art NER is systematically reviewed according to techniques used in NER. This paper also provides tools, datasets, techniques, challenges and future directions in the field of NER with the aim of providing researchers the substantial knowledge for further work.

During the unprecedented global health emergency caused by the pandemic Covid-19, the governments and nationalized organizations of all countries are struggling to control its spread by enforcing various measures, and also manage its social economic impact through policy intervention. In such critical situation, it becomes imperative to take data driven decisions. User generated content over online social media is an untapped data source that can be leveraged to gain insights for effective governance and decision making; and can also serve as a first hand communication medium between the various government bodies and citizens. In this paper, we have proposed a novel governance framework that leverages user generated content on social media for effective decision making by the authorities. We have used topic modelling techniques to discover social-economic trends, and to understand the issues or concerns of public interest. We used information extraction techniques like noun and verb phrase extraction, and Named Entity Recognition to measure the geographical spread, identify Covid-19 hotspots, assist in contact tracing, and discovering new health conditions. From the available literature, we could not find any intelligent framework for effective governance during pandemics, where user generated content has been utilized for real time decision making. In this paper, we address this real world problem through our proposed decision support System, and demonstrate as a proof-of-concept of how it can be used for effective governance during the pandemics through its prototype implementation.

As the network is dramatically extended, security has become a significant issue. Various attacks like DoS, R2L, U2R are significantly increasing to affect these networks. Thus, detecting such intrusions or attacks is a major concern. Intrusions are the activities that breach the system's security policy. The paper's objective is to detect malicious network traffic using machine learning techniques by developing an intrusion detection system in order to provide a more secure network. This paper intends to highlight the performance comparison of various machine learning algorithms like SVM, K-Means Clustering, KNN, Decision tree, Logistic Regression, and Random Forest for the detection of malicious attacks based on their detection accuracies and precision score. A detailed analysis of the network traffic features and the experimental results reveal that Logistic Regression provides the most accurate results.

This paper belongs to a research work that develops a deterministic actor framework in Java named Theatre, which addresses the modeling, analysis, and implementation of time-critical, cyber-physical systems. Theatre distinguishes from other actor systems by being control-based, time-sensitive, and centered on not thread-based actors. Although its main orientation to real-time embedded systems, Theatre can also be exploited for building high-performance applications on nowadays multi-core machines with shared memory. This paper reports an experience of performance comparison of Theatre with the Akka actor toolkit, through a parallel and scalable version of the Iterated Prisoner's Dilemma multi-agent system. Akka is a well-known library implemented in Scala and Java, which efficiently supports classical actors and it is best suited to untimed distributed applications. The experimental work confirms the lightweight nature of Theatre and its concurrent/parallel lock-free computational model, are also a key for achieving high execution performance, even better than that provided by Akka and similar toolkits, when large-scale systems are considered.

The paper expands on our position paper Adjepon Yamoah and Wen (Assuring Dependable Cloud-Based System Engineering: A Cloud Accountability Method. Vasteras, Sweden, pp. 181, 2016), [2], to make two contributions: demonstrate cloud accountability by applying a novel method for assuring cloud dependability to a Reactive Architecture, Adjepon-Yamoah et al. (A Reactive Architecture for Cloud-based System Engineering. ACM, New York, USA, pp. 77, 2015), [3], and conduct an evidence-based stochastic (Markov chains) analysis of the Reactive Architecture with a Cloud Accountability System (CAS). This CAS facilitates the novel Cloud Accountability Method (CAM), which provides dependability assurance evidence for the Reactive Architecture. This is achieved using a virtual machine introspection (VMI) technique that counter-checks the dependability metrics (related to availability and reliability) provided by the cloud service providers (CSPs) as digital evidence. This work provides a means of addressing the perceived lack of trust for cloud-based services towards cloud accountability. Method: We evaluate CAM by implementing a prototype of the cloud accountability system (CAS) to facilitate the active monitoring of the Reactive Architecture. Our evaluation is performed using a cloud-based test-bed in the Amazon Web Service (AWS) Elastic Cloud Compute (EC2) environment comprising 5 Linux Virtual Machines (VMs) over a period of 3 h. The 5 instances are classified into two groups: the target VMs of the RA components and the monitoring VM of the CAS. The CAM facilitates the collection, examination, analysis, and reporting of dependability metrics as digital evidence to assure dependability of the AWS EC2 environment. Result: Introspecting our 5 VMs for 3 h, we identified some relevant but unreported dependability incidents on AWS, which cost the user about $65. We then conclude that the CAM is sufficiently capable of meaningfully assuring the dependability of deployed systems in the cloud.

Due to the coronavirus pandemic, COVID-19 reports are being generated frequently and volume is increasing exponentially. These reports provide innovative information to healthcare and medical science. Analysis of this information helps us to extract meaningful knowledge for improving our healthcare systems. An automated report summarizer is a model whose task is to rewrite a report into a very compact form without losing any of its important content. In the paper, the COVID-19 reports collected from the new release open-source, CORD-19 dataset, are applied in our proposed automated text summarizer. Initially, we have preprocessed the reports by Natural Language Processing (NLP) and subsequently, the Unified Medical Language System (UMLS) tool has been used to bring out only the medical terms along with the concepts corresponding to that medical terms. So, a set of concepts represent each sentence in a report and with the help of a word-to-vector-based neural network model that extracted concepts are converted into fixed dimension Word2vec vectors. Next, the fixed dimension real-valued vectors replace the set of concepts corresponding to each sentence using the summation scheme. Thus, the report is described by a real-valued dataset. Finally, the unsupervised learning (i.e. clustering algorithm) has been applied for the dataset to partition every sentence into different clusters and a representative from each cluster is identified based on Pearson correlation and clustering coefficient. The representative sentences collected using clusters are arranged according to their appearances in the report, which is the desired summary of the report. In the paper, different clustering algorithms are applied, so different summaries of a report are obtained, which are compared among themselves based on some evaluation criteria to signify the efficacy of the developed summarization technique.

In recent decades, blockchain is a leading central concept similar to the internet’s growth in 1990. However, it has some drawbacks, particularly in the security area. In this paper, the blockchain security structure had been summarized by conducting a detailed survey. The discussion on how to defend against particular security threats and challenges with blockchain technology’s security mechanism has been analyzed and presented. Moreover, the applications of blockchain system and their different security problems are also presented in this paper. Even though the blockchain technology concept is more consistent and provides trusted services, this novel approach regarding security and challenges plays a significant role.

The Speech Synthesis Markup Language (SSML) specification is one of the speech standard of W3C (World-Wide Web Consortium) and is aimed to provide a rich, XML (Extensible Markup Language) for assisting the generation of synthetic speech on Web and other applications. It enables authors a standard way to control various speech parameters in order to improve the quality and give natural voice to the speech synthesis applications such as TTS. Speech Recognition Grammar Specification (SRGS) is a W3C standard that enables developers to define the words and patterns of words that recognized by speech recognizer. W3C PLS (Pronunciation Lexicon Specification) represents the pronunciation information of the words for use in speech recognition and synthesis systems. Currently, these standards enable the output in a large numbers of Latin languages only. Therefore, it is essential to study the existing standards for Indian languages as Indian languages are morphologically rich languages. This paper presents the various aspects of these technologies that need to be identified for Indian languages. The papers proposed the some of the identified requirements/gaps in these speech standards.