Search

In recent years, research in the fields of brain-computer interfacing techniques and related areas are developing at a very rapid rate with the help of exploding of Artificial Intelligence, Machine Learning and Deep Learning. A new concept of Ensemble Learnings has become popular research area among the researchers related to the field of automatic classification of electroencephalograph signals for predication of mental health issues like seizures. However effective feature extraction from EEG and accurately classify them with efficient classifiers is still an important task and attracted wide attention in this area. Therefore in this paper, we presented the detailed mathematical analysis of these methods and Ensemble Learnings based EEG signals classification method for seizures using Extreme Gradient Boosting Model.Time-frequency domain based non-linear features are selected from preprocessed EEG Dataset, and PCA (Principal Component Analysis) is used for dimensionality reduction for features engineering, then optimized feature based training and testing is done for two class classification in ensemble learning method (XGBoost) and Random Forest method. Finally, both models are tested with dataset of University of Bonn, Germany to classify the signals. In addition this paper highlights the Correlation Analysis Methodology to Identify Strong Predictor and Attributes Correlation-based Attribute Ranking for the Feature Engineering which has proved to be more efficient in EEG signals Classification and provide comparative analysis with other existing models for performance evaluation in terms of accuracy, specificity and sensitivity.

The Internet of Things (IoT) is an indispensable part of the healthcare system since it creates a link between the doctor and the patient for remote medical consultations. IoT-based seizure prediction detects the seizures and monitors the health of patients remotely. The disease seizure is categorized with the sudden and repeated malfunction of the neurons of the brain. To protect patient's lives, it's critical to recognise the risk of an epileptic seizure. In this research a hybrid cuckoo finch optimization is proposed tuned Deep-CNN (Deep-Convolutional Neural Network) classifier recognize and predict the occurrence of epileptic seizure using the electroencephalogram (EEG) signal data obtained through IoT. Initially, the gathered data is pre-processed and subjected to frequency band generation. Then there are the notable characteristics, such as Statistical features, Wavelet features, Entropy-based features, Spectral features, CPR (Common Spatial Patterns) and Logarithmic band power are extracted and concatenated. The optimal electrode selection is done by using the proposed hybrid cuckoo finch optimization that inherits characteristics of the intrusive and attentive search agents. The data is finally normalized and fed to proposed hybrid cuckoo finch optimization tuned Deep-CNN to classify the seizure disease. The specificity, accuracy and sensitivity of the proposed model is attained as 92.5212%, 97.7648%, and 95.6324%, which demonstrates efficient performance of the proposed seizure prediction model.

Social media materialized as an influential platform that allows people to share their views on global and local issues. Sentiment analysis can handle these massive amounts of unstructured reviews and convert them into meaningful opinions. Undoubtedly, COVID-19 originated as the enormous challenge across the world that physically and financially bruted humankind. Meanwhile, farmers' protests shook up the world against three pieces of legislation passed by the Indian government. Hence, an artificial intelligence-based sentiment model is needed for suggesting the right direction toward outbreaks. Although Deep Neural Network (DNN) gained popularity in sentiment analysis applications, these still have a limitation of sequential training, high-dimension feature space, and equal feature importance distribution. In addition, inaccurate polarity scoring and utility-based topic modeling are other challenging aspects of sentiment analysis. It motivates us to propose a Knowledge-Enriched Attention-based Hybrid Transformer (KEAHT) model by enriching the explicit knowledge of Latent Dirichlet Allocation (LDA) topic modeling and lexicalized domain ontology. A pre-trained Bidirectional Encoder Representation from Transformer (BERT) is employed to train within a minimum training corpus. It provides the facility of attention mechanism and can solve complex text problems accurately. A comparative study with existing baselines and recent hybrid models affirms the credibility of the proposed KEAHT in the field of Natural Language Processing (NLP). This model emphasizes artificial intelligence's role in handling the situation of the global pandemic and democratic dispute in a country. Furthermore, two benchmark datasets, namely "COVID-19-Vaccine-Labelled-Tweets" and "Indian-Farmer-Protest-Labelled-Tweets", are also constructed to accommodate future researchers for outlining the essential facts associated with the outbreaks.

The expeditious improvement and advancement in technology have shaped computers as ammunition, which may lead to a huge loss if used for wrong motives. The objective of computer forensics involves correctly examine and collect the digital evidence in such a manner so that they are justifiable in court. Due to the growing importance of cyber world security and the sincerity of cybercrime, it is essential for security professionals to know the technology used in forensics and keyword searching is the most handful technique for identifying potential evidence from the pool of files. This paper aims to provide a proper understanding of regular expressions keyword search technique used in computer forensics investigation. In this paper, we perform the experiments using Prodiscover tool to reduce the search space by identifying and filtering the known files to speed up the searching process of evidence identification.

Pandemic novel Coronavirus (Covid‐19) is an infectious disease that primarily spreads by droplets of nose discharge when sneezing and saliva from the mouth when coughing, that had first been reported in Wuhan, China in December 2019. Covid‐19 became a global pandemic, which led to a harmful impact on the world. Many predictive models of Covid‐19 are being proposed by academic researchers around the world to take the foremost decisions and enforce the appropriate control measures. Due to the lack of accurate Covid‐19 records and uncertainty, the standard techniques are being failed to correctly predict the epidemic global effects. To address this issue, we present an Artificial Intelligence (AI)‐based meta‐analysis to predict the trend of epidemic Covid‐19 over the world. The powerful machine learning algorithms namely Naïve Bayes, Support Vector Machine (SVM) and Linear Regression were applied on real time‐series dataset, which holds the global record of confirmed, recovered, deaths and active cases of Covid‐19 outbreak. Statistical analysis has also been conducted to present various facts regarding Covid‐19 observed symptoms, a list of Top‐20 Coronavirus affected countries and a number of coactive cases over the world. Among the three machine learning techniques investigated, Naïve Bayes produced promising results to predict Covid‐19 future trends with less Mean Absolute Error (MAE) and Mean Squared Error (MSE). The less value of MAE and MSE strongly represent the effectiveness of the Naïve Bayes regression technique. Although, the global footprint of this pandemic is still uncertain. This study demonstrates the various trends and future growth of the global pandemic for a proactive response from the citizens and governments of countries. This paper sets the initial benchmark to demonstrate the capability of machine learning for outbreak prediction.

Nowadays crimes are increasing at a high rate which is a great challenge for the police department of a city. A huge amount of data on different types of crimes taking place in different geographic locations is collected and stored annually. It is highly essential to analyze data so that potential solutions for solving and mitigating the crime incidents and predicting similar incident patterns for future becomes possible. Then it can be carried out using big data and various machine learning techniques in conjunction. The paper introduced a solution to the crime prediction problem using Naive Bayes classifier, which includes finding the most likely criminal of a particular crime incident when the history of similar crime incidents has been provided with the incident-level crime data. The incident-level crime data is provided as a crime dataset which includes incident date and location, crime type, criminal ID and the acquaintances are the attributes or crime parameters. The acquaintances are the suspects whose names are either directly involved in the incident or indirectly the acquaintances of the criminal. Acquiring a real-time crime dataset is a difficult process in practice due to confidentiality principle. So, crime dataset are used for the inputs using the state of the art methods. The proposed system is tested for the crime prediction problem using the data learning, and the experimental results show that the proposed system provides better results and finding of the potential solutions and crime patterns.

Honeypots and data mining are the major methods used as a safeguard of assets or for classifying the data. Each technique has positives and disadvantages of its own and is best applied in a particular position. Hybrid approach uses aspects of both techniques to upgrade performance and shortcomings. In this paper, we propose a hybrid approach based on Honeypot and Data Mining based Support Vector Machine technique, implemented in the dot net framework for preventing Denial of Service Attack. The proposed approach, HoneyDos tested in three interfaces. This paper presents an empirical comparison of the hybrid approach to the earlier methods used for preventing Denial of Service attack and draw useful conclusions upon their performance.

The research in marine sensors and the Internet of Things (IoT) has grown exponentially with the ample warehouse of natural materials in the sea. The growing activities in the marine sensor environment increased the threat of anomalies and cyber-attacks. Many Intrusion Detection Systems (IDS) and classical machine learning-based models have been proposed to secure the sensor-based IoT infrastructure. Still, these mechanisms have failed to achieve significant results for securing the marine sensor environment due to the discriminant requirements of the IoT appliances in deep oceans, such as distribution, information complexity, scalability, higher network bandwidth requirements, and low computational capacity. Hence, we propose a lightweight and robust ensemble model to secure the marine IoT environment from cyber-attacks and malicious activities. This paper established an optimized Light Gradient Boosting Machine (Light-GBM) algorithm for ocean IoT attack detection. The experiments were conducted on Distributed Smart Space Orchestration System (DS2OS) dataset. The proposed methodology includes a label encoding technique for best feature selection, hyper-parameter tuning, ensemble function, and a novel algorithm to develop an ocean IoT attack detection model. As an extension of traditional methods, the optimized Light-GBM model can handle the distributed IoT attacks in the deeper marine environments with low computational cost and with 98.52% detection accuracy. The comparative analysis confirms the effectiveness of the proposed model for marine sensor safety. Conclusively, the proposed model mitigates the threat of cyber-attacks in the marine sensor environment and presenting a promising future in real-time ocean-based IoT applications.

Sentiment Analysis (SA) is growing and becoming more interesting area for researcher in the field of Natural Language Processing (NLP). It is the calculative process in which opinions, subjectivity of text and sentiments are calculated. This survey handles an extensive study or sketch of the last updated ensemble methods in sentiment analysis. Most of the recently proposed ensemble methods of SA are studied and presented in brief in this study. These articles are classified on the basis of their benefaction in the various SA ensemble methods. There are various related fields to SA that attract researchers like (Building resources (BR), Emotion detection (ED), and Transfer learning (TL)), their concepts are presented. The main purpose of this study is to presents approximately each and every aspect of SA, ensemble technique and the entire vision in a brief manner. This survey also includes the sophisticated classification of many current updated articles and the interpretation of the recent tendency of research in the area of sentiment analysis and its related fields.

Researchers and analysts are rapidly going through with large even terabyte- and petabyte-sized data sets when carrying digital investigation, which is becoming one of the major challenges in digital forensics. With invariably rising network bandwidth, it can be highly difficult to operate and store network traffic. To have a control over this, new algorithmic approach and computational methods are needed; even though Big Data is a challenge for forensic researchers, it effectively helps them in investigating patterns to prevent or detect and resolve crime. This chapter brings up care toward challenges in forensic investigation related to Big Data and possible ways to help a forensic investigator figure out large data sets in order to carry out forensic analysis and investigation. World is intent across big social events which even raises a concern toward criminal activities involved there in and there by bounding across Big Data. There are many practical applications where one can process large amount of data, and this data comes moreover in unstructured form. Right from various events that are considered about big communities, there are various real-life postulates where large quantity of data is produced and processed which is required to be mined (Hambrick et al., J Anxiety Disord 18:825–839, 2004). Big Data analytics has provided a striking growth that has shown up as a result of the accessibility of large sum of data that is fitting across a varied range of application domains all so in the region of science, business, and government. This chapter has also paid attention toward different aspects of commerce with analytics mentioning Big Data in social events.

O presente trabalho visa a explorar e compartilhar a integração das TICs e a sua condição no novo programa de dois anos de bacharelado em educação (B.Ed.), o qual foi implementado em 2015, na Índia, por meio de um órgão regulatório chamado Conselho Nacional para a Formação de Professores (NCTE). O projeto de pesquisa convergente de método misto paralelo foi utilizado nesse estudo, no qual os pesquisadores coletaram dados qualitativos e quantitativos simultaneamente e compararam ou convergem ambos os tipos de dados para obter um entendimento aprofundado relacionado ao problema de pesquisa. Amostragem aleatória estratificada, amostragem intencional, amostragem aleatória sistemática e técnicas de amostragem convencional foram usadas de acordo com a necessidade de vários grupos de amostras. O resultado principal do estudo foi descrever os processos e as práticas atuais bem como as recomendações futuras para a integração de TICs no novo programa de bacharelado implementado em 2015 na Índia. Os esclarecimentos resultados desse estudo podem ser implementados em outros países ao redor do mundo.

Data Warehouse contains crucial information about organization. This information is utilized by decision maker to analyze the current status and planning the development of the organization. The data warehouse can be easily accessed by an authorized user or by an unauthorized user through unfair means. To preclude this data from unauthorized access, several measures have been taken and a lot of research is going on. In this paper, a framework is proposed to prevent the data from unauthorized access and thereby increases the security of data warehouse.

“Cryptography” is a blessing to cyber security. People can store information securely and communicate privately over long distances. It is rapidly advancing and improving, but it is also making a ladder for cryptography-based viral attacks. This paper gives better understanding of the concept of “Cryptovirology” which presents how cryptography can also be misused in the world of cyber crime. Cryptovirology gives malware enhanced privacy and such malwares are not easily reverse engineered. Moreover, it gives the attacker enhanced obscurity while the Cryptovirus is communicating with attacker. Loss of access, confidentiality and leakage of critical data can be achieved with the help of same cryptographic concepts. Analysis and understanding of such attacks leads us to many fascinating methodologies and conclusions.

Web applications are a fundamental pillar of today's world. Society depends on them for business and day to day tasks. Because of their extensive use, web applications are under constant attack by hackers that exploit their vulnerabilities to disrupt business and access confidential information. SQL Injection and Remote File Inclusion are the two most frequently used exploits and hackers prefer easier rather than complicated attack techniques. Every day as number of internet users are increasing, the vulnerabilities of a system being attacked is becoming easier. Sql Injection is one of the most common attack method that is being used these days. Havij is one of the tools used to implement SQL Injection which will be discussed in this paper. Our research objective is to analyse the use of Havij in penetration testing in IT industry and to compare various SQL Injection tools available in the market.

Honeypots act as security resources that are used to catch malign activities, so they may be anatomized and watched. During the past few years, they are called as a safeguard of assets of an organization. They are used to acquire information on interrupters in a network. This paper gives an introduction to the honeypots, their classification, detailed study of commercial as well as open source honeypots tools and comparison between them. This paper may be helpful for readers to secure their resources from intruders by using the freely available honeypots tools.

Routers can also function as firewalls and perform various operations on the incoming and outgoing packets. In case when all the packets share common header characteristics, it is termed as a packet flow. In order to classify a packet, routers perform a lookup on a classifier table using one or more fields from the packet header to classify the packet into its corresponding flow. A classifier is a set of rules which identify each flow and the appropriate actions to be taken for any packet belonging to that flow. The paper examines the problem of packet classification and various proposed techniques for the same.