Dr. Tryambak A Hiwarkar | Sardar Patel University (original) (raw)

Papers by Dr. Tryambak A Hiwarkar

International Journal on Recent and Innovation Trends in Computing and Communication

This study delves into the realm of leveraging unconventional sources within the domain of Big Da... more This study delves into the realm of leveraging unconventional sources within the domain of Big Data for conducting insightful social and economic analyses. Employing a Data Lifecycle Approach, the research focuses on harnessing the potential of linear regression, random forest, and XGBoost techniques to extract meaningful insights from unconventional data sources. The study encompasses a structured methodology involving data collection, preprocessing, feature engineering, model selection, and iterative refinement. By applying these techniques to diverse datasets, encompassing sources like social media content, sensor data, and satellite imagery, the study aims to provide a comprehensive understanding of social and economic trends. The results obtained through these methods contribute to an enhanced comprehension of the intricate relationships within societal and economic systems, further highlighting the importance of unconventional data sources in driving valuable insights for deci...

International journal of computer science and mobile computing, Jul 30, 2022

The use of the internet as an electronic delivery method for banking services and products is a g... more The use of the internet as an electronic delivery method for banking services and products is a general extension of traditional banking. With the use of IT, banking has been redefined and reengineered today, and the future of banking will undoubtedly offer more. Customers receive advanced services thanks to ongoing product and process improvements. Thus From a seller's market to a buyer's market, there occurs a paradigm change. Banks therefore modify their strategy of "Mass banking to Class" and "Conventional banking to Convenience banking" Banking". The report looks at a number of pertinent problems regarding the use of IT in banking and proposes implementing IT and other cyber regulations, protecting the privacy and confidentiality of data correctly. This will ensure that IT plays a growing role in the financial sector.

International Journal of Advanced Research in Science, Communication and Technology, Dec 19, 2022

Changes and improvements to human existence have been made possible by recent advancements in com... more Changes and improvements to human existence have been made possible by recent advancements in communication and information technology, notably the internet of things (IoT). The IoT system is vulnerable to cyber-physical security and privacy assaults such denial of service, spoofing, phishing, obfuscations, and jamming because of the widespread availability and rising demand for smart devices. Cyber dangers to IoT systems, such as eavesdropping, attacks, and more. The new threats to cyber-physical security cannot be effectively avoided or mitigated using the same old methods. Keeping IoT systems safe calls on security measures that are not only effective, but also flexible and up-to-date. Among the various approaches to cyber-physical system security, machine learning (ML) is widely regarded as the most cutting-edge and promising since it has spawned several new lines of inquiry into the problem (CPS). This literature study provides an overview of the structure of Internet of Things (IoT) systems, explores the many attacks that may be launched against them, and discusses the current thinking on how to best use machine learning to ensure the security and safety of IoT infrastructure. It also covers the probable future research obstacles that may arise while implementing security measures in IoT systems.

Journal of Control and Decision, Aug 25, 2022

International Journal of Advanced Research in Science, Communication and Technology, Nov 28, 2022

Instability in important socioeconomic indicators can have far-reaching effects on global develop... more Instability in important socioeconomic indicators can have far-reaching effects on global development. This thesis offers a set of one-of-a-kind big data analytics algorithms that operate on unstructured Web data streams to automatically infer events, knowledge graphs, and predictive models, allowing for a better understanding, definition, and anticipation of the volatility of socioeconomic indicators. This paper we presents four major results that expand previous knowledge. Given a large volume of diverse unstructured news streams, we first describe novel models for collecting events and learning spatio-temporal features of events from news streams. We explore two different kinds of event models: one that is based on the concept of event triggers, and another that is probabilistic and learns a generic class of meta-events by extracting named entities from text streams. The second piece of work investigates the challenge of gleaning knowledge graphs from time-sensitive data like news and events as they happen. Event graphs produce a condensed depiction of a chronology of events pertinent to a news query by characterizing linkages between them using "event-phenomenon graphs," while spatio-temporal article graphs capture innate links between news stories. In this paper we present the various result outcome for predictive result analysis.

International journal of computer science and mobile computing, Nov 30, 2022

Cloud computing is a new approach to data storage and processing in the field of computer science... more Cloud computing is a new approach to data storage and processing in the field of computer science. Computing in the cloud refers to the use of a network's or the internet's hosted servers and other associated resources. Cloud computing is an expansion of other computing methods such as grid computing and distributed computing. Currently, cloud computing is utilized by both industries and universities. The cloud is a service that helps its users by giving them access to online virtual resources. There are always new methods being developed, and cloud computing is a sector that is growing rapidly. In tandem with the growth of the cloud computing environment comes a corresponding rise in the difficulty of ensuring the system's safety. Users trust the cloud with their data, but if their data isn't secure, they may stop using it. Some of the concerns with cloud security, such as multi-tenancy, will be explored in this paper. Mobility, adaptability, availability, etc. Current security methods and strategies for a safe cloud environment are also discussed in the article. The information presented in this paper will help researchers and practitioners get more familiar with the various security threats and the models and methods provided to combat them.

International journal of computer science and mobile computing, Aug 30, 2022

Recent years have seen a meteoric rise in research attention paid to the big data across all area... more Recent years have seen a meteoric rise in research attention paid to the big data across all areas of computer science. Methods of instruction in particular communicate vital prospects and possibility of radical change in a number of fields of thought and novel instructional approaches that tackle a wide range of problems. Recent developments in machine learning are discussed in this paper. Learning in the age of big data. New machine concepts are also discussed. Approaches to education, with a concentration on more approaches to learning are presented, such as representation active learning, deep learning, transfer learning, and other types of learning. An overview and discussion of the current state of machine learning tools, accompanying difficulties, and possible solutions are in addition to being shown and contrasted with the viewpoint data mining

International journal of innovations in engineering and science, Jul 2, 2022

The term "cryptography," which literally translates to "secret writing," has emerged as the funda... more The term "cryptography," which literally translates to "secret writing," has emerged as the fundamental building block for supplying security for numerous communication applications. There is a need to conceal sensitive information, such as passwords, encryption keys, recipes, etc. in many applications, especially in group communication. Here, effective key management policies are needed to protect the group's confidential information. Because it can be exceedingly difficult to preserve a group's secret information, especially in two situations: when there are more group members and when they are dispersed across different locations with different defences in place. the cloud computing model, where application services are delivered online. A flexible, affordable, and tested platform for delivering commercial or consumer IT services over the internet is cloud computing. Along with more computer power, the cloud also offers network infrastructure that facilitates group communication scenarios. Several security methods are needed to communicate with the various cloud services and to store the data produced/processed by those services. This paper examines the fundamental issue of cloud computing key management in this context and provides support for communication between cloud cryptography clients and cloud key management servers. Cloud key management, including its development and subsequent use to lower infrastructure costs, hazards, and complexity associated with managing encryption keys, as well as to improve the functionality of both private and public storage clouds, is covered. This study explores an extensive assessment of current key management methods used to secure cloud computing.

International journal of computer science and mobile computing, Jun 30, 2022

As network infrastructure maintenance becomes more complex, network traffic monitoring becomes an... more As network infrastructure maintenance becomes more complex, network traffic monitoring becomes an increasingly vital part of the process. Many specialized solutions for online network traffic monitoring are available to fight against common (and well-known) assaults by quickly limiting portions of the traffic. It is possible, however, that there are unknown hazards in network traffic with slow-in-time changing characteristics. On-line tools are unlikely to pick up on non-rapidly changing variable values. Using data mining, it is still possible to discover these shifts. An approach for anomaly identification in network traffic monitoring, the Red-Blue State Merging Algorithm and the RTI Algorithm with process, are discussed in the study. The results of this study are based on genuine data from github, which is used in the paper.

International journal of computer science and mobile computing, Jun 30, 2022

Anomaly detection in network traffic is a promising and effective technique to enhance network se... more Anomaly detection in network traffic is a promising and effective technique to enhance network security. In addition to traditional statistical analysis and rule-based detection techniques, machine learning models are introduced for intelligent detection of abnormal traffic data. A Denial of Service (DoS) attack is a malicious effort to keep endorsed users of a website or web service from accessing it, or limiting their ability to do so. A Distributed Denial of Service (DDoS) attack is a type of DoS attack in which many computers are used to cripple a web page, website or web based service. Fault either in users' implementation of a network or in the standard specification of protocols has resulted in gaps that allow various kinds of network attack to be launched of the type of network attacks, denial-of-service flood attacks have reason the most severe impact. This analysis study on flood attacks and Flash Crowd their improvement, classifying such attacks as either high-rate flood or low-rate flood. Finally, the attacks are appraised against principle related to their characteristics, technique and collision. This paper discusses a statistical approach to analysis the distribution of network traffic to recognize the normal network traffic behavior. This paper also discusses a various method to recognize anomalies in network traffic.

International journal of computer science and mobile computing, Nov 30, 2022

Big data is a fantastic resource for disseminating system-generated insights to external stakehol... more Big data is a fantastic resource for disseminating system-generated insights to external stakeholders. However, automation is required to manage such a large body of information, and this has spurred the development of data processing and machine learning tools. Just as in other fields of study and business, the ICT industry is serving and developing platforms and solutions to help professionals treat their knowledge and learn automatically. Large companies like Google and Microsoft, as well as the Apache Foundation's incubator, are the primary providers of these platforms. Spark is an open-source platform for handling Big Data insights that have been tainted by contamination. This unified framework provides a variety of methods for dealing with unstructured or structured text data, graph data, and real-time streaming data. Spark relies on MLlib to create customised ML algorithms. To parallelize a huge cluster of machines for data

International journal of computer science and mobile computing, Jun 30, 2022

Supervised Machine Learning (SML) is the quest for algorithms that reason from externally given c... more Supervised Machine Learning (SML) is the quest for algorithms that reason from externally given cases to develop general hypotheses, which subsequently make predictions about future instances. Supervised categorization is one of the jobs most commonly carried out by the intelligent systems. This article presents numerous Supervised Machine Learning (ML) classification strategies, evaluates various supervised learning algorithms as well as finds the most effective classification algorithm depending on the data set, the number of instances and variables (features) (features). Seven alternative machine learning methods were considered: Decision Table, Random Forest (RF) , Naïve Bayes (NB) , Support Vector Machine (SVM), utilizing Waikato Environment for Knowledge Analysis (WEKA)machine learning program. To develop the algorithms, Diabetes data set was utilized for the classification with 786 cases with eight attributes as independent variable and one as dependent variable for the analysis. The findings suggest that SVM was determined to be the method with maximum precision and accuracy. Naïve Bayes and Random Forest classification algorithms were shown to be the next accurate after SVM appropriately. The research demonstrates that time spent to create a model and precision (accuracy) is a factor on one hand; while kappa statistic and Mean Absolute Error (MAE) is another element on the other side. Therefore, ML techniques demands precision, accuracy and least error to have supervised predictive machine learning.

International journal of innovative technology and exploring engineering, Sep 30, 2019

As the technology improving, huge volumes of different types of data is being generated rapidly. ... more As the technology improving, huge volumes of different types of data is being generated rapidly. Mining such data is a challenging task. One of the important tasks of mining is to group similar objects or similar data into cluster which is very much useful for analysis and prediction. K-means clustering method is a popular partition based approach for clustering data as it leads to good quality of results. This paper focuses on K-means clustering algorithm by analyzing the E-commerce big data. In this research, geographical location and unique identification number of the customer are considered as constraints for clustering.

Zenodo (CERN European Organization for Nuclear Research), Nov 26, 2022

Sentiment analysis (SA), a buzzword in the fields of artificial intelligence (AI) and natural lan... more Sentiment analysis (SA), a buzzword in the fields of artificial intelligence (AI) and natural language processing (NLP), is gaining popularity. Due to numerous SA applications, there is an increasing need to automate the procedure of analysing the user's feelings concerning any products or services. Multimodal Sentiment Analysis (MSA), a branch of sentiment analysis that uses many modalities, is a rapidly growing topic of study as more and more opinions are expressed through videos rather than just text. Recent advances in machine learning are used by MSA to advance. At each stage of the MSA, the most recent developments in machine learning and deep learning are used, including sentiment polarity recognition, multimodal features extraction, and multimodal fusion with reduced error rates and increased speed. This research paper categorises several recent developments in MSA designs into 10 categories and focuses mostly on the primary taxonomy and recently published Multimodal Fusion architectures. The 10 categories are: early fusion, late fusion, hybrid, model-level fusion, tensor fusion, hierarchical, bi-modal, attention-based, quantum-based, and word-level fusion. The primary contribution of this manuscript is a study of the advantages and disadvantages of various architectural developments in MSA fusion. It also talks about future scope, uses in other industries, and research shortages.

International journal of innovations in engineering and science, Jun 1, 2022

Cloud computing has originated with the exponential development of internet connectivity and infr... more Cloud computing has originated with the exponential development of internet connectivity and infrastructure access. Cloud is a modern model for providing diverse applications to people on the internet, also referred to as the 'cloud,' for example web production frameworks, servers, storage and content. Cloud infrastructure often offers customers and companies different tools to use cloud technology in an easy and reliable way, without growing computing resources costs. Business may select between private, public or hybrid cloud implementation, depending on specific business requirements and security considerations. Most organizations follow this fastgrowing paradigm to satisfy their computing requirements and develop their market. Cloud infrastructure offers tools for digital networks and other software used both by a customer and the businesses of the cloud service provider, such as network capability, storage and server utility. Instead of buying new hardware or services for its commercial uses, this enables consumers to use the cloud network as a commodity, technology and software as a service.

International journal of computer science and mobile computing, Jun 30, 2022

Although conventional network security measures have been effective up until now, machine learnin... more Although conventional network security measures have been effective up until now, machine learning techniques are a strong contender in the present network environment due to their flexibility. In this study, we evaluate how well the latter can identify security issues in a corporative setting Network. In order to do so, we configure and contrast a number of models to determine which one best our demands. In addition, we spread the computational load and storage to support large quantities of data. Our model-building methods, Random Forest and Naive Bayes.

International Journal of Advanced Research in Science, Communication and Technology, Nov 25, 2022

The ever-increasing quality and quantity of data generated from day-today business operations, in... more The ever-increasing quality and quantity of data generated from day-today business operations, in conjunction with the continuously imported related social data, has rendered the traditional statistical approaches inadequate to deal with such data floods. This inadequacy can be attributed to the fact that traditional statistical methods were developed before the advent of the internet. Because of this, academics have been compelled to design and develop advanced and complex analytics that may be incorporated to acquire useful insights that are beneficial to the commercial area. This chapter shines a light on fundamental characteristics that are the building blocks for social big data analytics and lays out those building blocks. In particular, the importance of predictive analytics within the scope of SBD is examined, and this analysis is bolstered by the presentation of a framework for SBD predictive analytics. After that, a number of different predictive analytical algorithms are discussed, along with their implementation in a number of essential applications, top-tier tools, and APIs. Experiments are presented alongside a case study that demonstrates how predictive analytics may be used to social data. This is done to demonstrate the significance and practicality of predictive analytics.

International Journal of Advanced Research in Science, Communication and Technology, Jan 23, 2023

Some indicators of social and economic health, especially those pertaining to developing countrie... more Some indicators of social and economic health, especially those pertaining to developing countries, can swing wildly. A country's economy might take a hit if major economic indices like commodity prices, unemployment, currency exchange rates, etc., experience significant volatility. Instability in commodity prices is bad for economic development, financial reserves, and income distribution, and it may exacerbate poverty rather than alleviate it. Exports from various countries, including India, are dominated by commodities. The volatility of currency exchange rates has a ripple effect on commodity prices. Economic growth and stability require constant attention to these socioeconomic factors and an awareness of their inherent instability. Decades of research haven't shed any light on the reasons for a socioeconomic index's anticipated time and place fluctuations or the relationships between several indices. Economists can understand and foresee the volatility of social and economic indices with the use of predefined economic models. Traditionally, computational modelling has been the primary method of analysis for computer scientists when dealing with structured time series data. A rare opportunity to examine socioeconomic fluctuations has arisen because to the rapid expansion of unstructured data streams on the web and the development of cutting-edge computational linguistics algorithms during the past decade.

International Journal of Advanced Research in Science, Communication and Technology, Jan 12, 2023

Analytical methods and machine learning are progressively being incorporated into all kinds of in... more Analytical methods and machine learning are progressively being incorporated into all kinds of information systems. Despite the excitement around these technologies, contemporary firms nonetheless have trouble utilizing them to fully use their data and solve the company's challenges. Businesses must deal with a variety of challenges while developing business analytics and machine learning solutions, including requirements elicitation, design, development, and implementation. Although conceptual modelling and requirements engineering approaches to the process are important and relevant, little study has been done in this area. In this paper a conceptual modelling framework for business analytics and machine learning solutions that is shown and evaluated. The framework consists of instantiations, meta-models, techniques, design patterns and catalogues, rules, and recommendations. It is made up of three modelling perspectives that each reflect a distinct aspect of a solution or the perspective of a different role in the creation of such systems. Through the capture of stakeholders, strategic goals, choices, questions, and necessary insights, the Business View aids in the elicitation of business analytical needs. The Analytics Design View, which largely focuses on machine learning solutions, aids in the design of the solution by collecting algorithms, metrics, and quality criteria.

International Journal of Advanced Research in Science, Communication and Technology, Dec 11, 2022

The purpose of this article is to introduce price analytics as a tool for business. Improving out... more The purpose of this article is to introduce price analytics as a tool for business. Improving outcomes using supervised machine learning for find solutions to the challenges of determining appropriate pricing for a variety of goods and shopping for goods at the best possible price. Important and necessary important to do research on business analytics many factors, dimensions, and methods for enhancing productivity of business processes, managerial effectiveness, and decision making to get an edge in the market. The use of Machine Learning in the workplace can improve results in allowing us to make prompt, informed judgments based on the data we've stored knowledge. Methods such as supervised learning are used to achievement in business, both qualitatively and quantitatively, by the entrepreneur. In this step, we accomplish this after determining the optimal pricing and distributing it. Instantly update the costs of anything in stock. Because of this, it's possible that the operational effectiveness and efficiency by the highest possible profit, the rate of all of the bookkeeping work and determining the best possible pricing to reach the goal set by the business owners. To summarize, it may be argued that Because of the incredibly competitive corporate environment, cutting-edge scientific research is needed. In particular machine learning technologies with the rise of supervised learning, data mining methods, and corporate optimization of prices in a corporate setting using analytics essential, number one, must-have, etc. Machine learning with an instructor is called supervised learning. By entering the system's recommendations on what to do and what not to do the right values for the variables to get the expected outcome. Some of the many facets of in the corporate world, including domains, orientations, and methodologies..