Journal of Science & Technology (JST)
Not a member yet
967 research outputs found
Sort by
DNN based fake news identification and analysis
Get PDFIn this project we show an approach for detecting fake statements made by public figures by means of artificial intelligence. Several approaches were implemented as a software system and tested against a data set of statements. The best achieved result in binary classification problem (true or false statement) is 86%. The results may be improved in several ways that are described in the article as well. The progress in modern informational technologies brings us to the era where information is as accessible as ever. It is possible to find the answers to the questions we are interested in a matter of seconds. Availability of mobile devices makes it even more convenient for the users. This factor changed the way of how people get the news information a lot. Every mainstream mass media has its own online portal, Facebook account, Twitter account etc., so people can access news information really quickly
IDENTIFYING HEALTH INSURANCE CLAIM FRAUDS USING MACHINE LEARNING CONCEPT
Get PDF— Patients depend on health insurance provided by the governmentsystems, private systems, or both to utilizethe high-priced healthcare expenses. Thisdependency on health insurance draws some healthcare service providers to commit insurance frauds. In this paper, we perform a comparative analysis on various classification algorithms, namely Support Vector Machine (SVM), Decision-Tree (DT), K-Nearest Neighbor (KNN), Logistic Regression (LR), to detect the health insurance fraud. The effectiveness of the algorithms are observed on the basis of performance metrics: Precision, Recall and F1-Scor
DROPSTORE - A SECURE BACKUP SYSTEM USING MULTI CLOUD AND FOG COMPUTING
Get PDFData backup is essential for disaster recovery. Current cloud-based solutions offer a secure infrastructure. However, there is no guarantee of data privacy while hosting the data on a single cloud. Another solution is using multi-Cloud technologies. Although using multiple clouds to save smaller pieces of the data can enhance data privacy, it comes at the cost of the need for the edge device to manage different accounts and manage communication with different clouds. These drawbacks made this technology rare to use technology. In this paper, we propose DropStore to provide an easy-to-use, highly secure, and reliable backup system using state-of-the-art multi-Cloud and encryption techniques. DropStore adds an abstraction layer for the end-user to hide all system complexities using a locally hosted device, „„the Droplet‟‟, that is fully managed by the user. Hence, the user does not rely on any untrusted third party. This was achieved using Fog Computing technology. The uniqueness of DropStore comes from the convergence of MultiCloud and Fog Computing principles. The system implementation is open-source and available online. Performance results show that the proposed system improves data protection in terms of reliability, security, and privacy preservation while maintaining a simple and easy interface with edge devices
A Machine Learning Framework For Data Poisoning Attacks
Get PDFFederated models are built by collecting model changes from participants. To maintain the secrecy of the training data, the aggregator has no visibility into how these updates are made by design.. This paper aims to explore the vulnerability of federated machine learning, focusing on attacking a federated multitasking learning framework. The framework enables resource-constrained node devices, such as mobile phones and IOT devices, to learn a shared model while keeping the training However, the communication protocol among attackers may take advantage of various nodes to conduct data poisoning assaults, which has been shown to pose a serious danger to the majority of machine learning models. The paper formulates the problem of computing optimal poisoning attacks on federated multitask learning as a bi-level program that is adaptive to arbitrary choice of target nodes and source attacking nodes.The authors propose a novel systems-aware optimization method, Attack confederated Learning(AT2FL), which is efficiency to derive the implicit gradients for poisoned data and further compute optimal attack strategies in the federated machine learning
Simple Thermal decompose method of CdS nanoferriteparticles for Enhanced Biological Applications
Get PDFIn this work, cadmium sulfide nanoferriteparticles by using a new Cd-octanoate complex via a simple and fast method like thermal decompose method. The synthesized nanoferriteparticles were characterized by using X-ray diffraction pattern, Scanning Electron Microscopy, Fourier Transform Infrared Spectroscopy and Spectroscopic Techniques. These techniques were used to investigate the CdS surface purity. CdS nanoferriteparticles were dispersed in the solution as single entities. It showed very good resistance against oxidation for months according to their polymer shell. Finally, the optical properties of the product were obtained from photoluminescence (PL) spectroscopy
Water net:A Network For Monitoring And Assessing Water Quality
Get PDFWater is a fundamental requirement for human, animal, and plant survival. Despite its importance, quality water is not always fit for drinking, domestic and/or industrial use. Numerous factors such as industrialization, mining, pollution, and natural occurrences impact the quality of water, as they introduce or alter various parameters present therein, thus, affecting its suitability for human consumption or general use. The World Health Organization has guidelines which stipulate the threshold levels of various parameters present in water samples intended for consumption or irrigation. The Water Quality Index (WQI) and Irrigation WQI (IWQI) are metrics used to express the level of these parameters to determine the overall water quality. Collecting water samples from different sources, measuring the various parameters present, and bench-marking these measurements against pre-set standards, while adhering to various guidelines during transportation and measurement can be extremely dauntin
A Method for Vibration Testing Decision Tree-Based Classification Systems.
Get PDF"Without any intervention from a person, computers are capable of "learning" new things by analyzing data in various ways (training and testing) and making conclusions. One application of ML is decision trees. Many diverse disciplines make use of decision tree techniques. These algorithms have a wide variety of potential applications, including search engines, text extraction, and companies that provide medical certifications. Decision tree algorithms that are both accurate and affordable are now at our fingertips. Whenever a choice is necessary, it is critical to know what the best choice is. We present three decision tree algorithms in this study: ID3, C4.5, and CART. We use tools like WEKA, ML, and DT.
 
STUDY ON STRENGTHENING OF DAMAGED REINFORCED CONCRETE COLUMNS WITH GEOPOLYMER JACKETS
Get PDFThe objective of this investigation is to experimentally study the behaviour of reinforced concrete (RC) columns strengthened using RC and geopolymer concrete (GPC) jacketing by subjecting them to axial loading. The experimental results were analytically validated by the finite element model (FEM). For this investigation, six columns of M25- grade conventional concrete were subjected to more than 75% of the ultimate load. Then three columns were jacketed by using M40-grade RC and another three columns were jacketed by using M40-grade GPC. The interfacial behaviour of the conventional RC column and jacketed GPC columns was studied and compared. The 3D linear and FEM was employed to measure the effect of conventional RC and GPC-jacketed columns under increasing load by considering the concrete damage plasticity (CDP) and elastoplastic models with isotropic hardening. The validation against the experimental results confirmed 90% accuracy of the analytical mode
FACE MASK DETECTION USING MACHINE LEARNING
Get PDFCOVID-19 pandemic has rapidly affected ourday-to-day life disrupting the world trade and movements. Wearing a protective face mask hasbecome a new normal. In the near future, many public service providers will ask the customers to wear masks correctly to avail of their services. Therefore, face maskdetection has become a crucial task to help global society. This paper presents a simplified approach to achieve this purpose using some basic Machine Learning packages like TensorFlow, Keras and OpenCV. The application of ―machine learning‖ and ―artificial intelligence‖ has become popular within the last decade. Both terms are frequently used in science and media, sometimes interchangeably, sometimes with different meanings. In this work, we specify the contribution of machine learning to artificial intelligence. We review relevant literature and present a conceptual framework which clarifies the role of machine learning to build (artificial) intelligent agents.The proposed method detects the face from the image correctly and then identifies if it has a mask on it or not. As a surveillance task performer, it can also detect a face along with a mask in motion. The method attains accuracy up to 95.77% and 94.58% respectively on two different datasets. We explore optimized values of parameters using the mobileNetV2 which is a Convolutional Neural Network architecture to detect the presence of masks correctly without causing overfitting
PROTECTION FOR YOUR PURCHASE PREFERENCES WITH DIFFERENTIAL PRIVACY
Get PDFInternet banking can be done to uncover customers' buying habits as the conclusion to various attempts. Before actually transferring it on-line, monetary institutions with contrasting statutes of darkness. Every buyer can disrupt their local business connection before transferring it to online banks, due to divergent security. However, the adoption of differential security in web-based foundations will be problematic because popular differential protection plans do not involve the issue of the concussion limit. Similarly, we manage an academic test above and below to show that our projects are able to meet the standard of differentialprotection. Finally, in order to decide on sustainability, we place our diets on trial in the mobile initiation trial. The importance of aggregate usage and online banking. Total amount decreased significantly, and the protection errors for common data are less than 0.5, which is consistent with the test finding