Journal of Science & Technology (JST)
Not a member yet
967 research outputs found
Sort by
Flow Chemistry: Recent Developments in the Synthesis of Pharmaceutical Products
Get PDFThe tiny size makes it simple to apply and remove a heating source, allowing for highly accurate temperature control along the microreactor and preventing uncontrolled dangerous exothermic reactions. This not only promotes transfer but also allows for exact monitoring of the heat exchange. Compared to a batch process, a continuous flow system makes it easier to set up and monitor reaction parameters like temperature, pressure, and flow rate, leading to a more consistent and repeatable process.7 The minimal volume needed for flow processes allows for quick screening of reaction conditions; once optimised, the reaction may be ramped up
ENHANCED MALICIOUS URL DETECTION SYSTEM WITH MACHINE LEARNING ALGORITHMS
Get PDFCurrently, the risk of network information insecurity is increasing rapidly in number and level of danger. The methods mostly used by hackers today is to attack end-to end technology and exploit human vulnerabilities. These techniques include social engineering, phishing, pharming, etc. One of the steps in conducting these attacks is to deceive users with malicious Uniform Resource Locators (URLs). As a results, Malicious URL detection is of great interest nowadays. There have been several scientific studies showing several methods to detect malicious URLs based on machine learning and deep learning techniques. In this paper, we propose a malicious URL detection method using machine learning techniques based on our proposed URL behaviors and attributes. Moreover, bigdata technology is also exploited to improve the capability of detection malicious URLs based on abnormal behaviors. In short, the proposed detection system consists of a new set of URLs features and behaviors, a machine learning algorithm, and a big data technology. The experimental results show that the proposed URL attributes and behavior can help improve the ability to detect malicious URL significantly. This is suggested that the proposed system may be considered as anoptimized and friendly used solution for malicious URL detection
CRYPTOCURRENCY PRICE ANALYSIS WITH ARTIFICIAL INTELLIGENCE
Get PDFCryptocurrency is playing an increasingly important role in reshaping the financial system due to its growing popular appeal and merchant acceptance. While many people are making investments in Cryptocurrency, the dynamical features, uncertainty, the predictability of Cryptocurrency are still mostly unknown, which dramatically risk the investments. It is a matter to try to understand the factors that influence the value formation. In this study, we use advanced artificial intelligence frameworks of fully connected Artificial Neural Network (ANN) and Long ShortTerm Memory (LSTM) Recurrent Neural Network to analyze the price dynamics of Bitcoin, Ethereum, and Ripple. We find that ANN tends to rely more on long-term history while LSTM tends to rely more on short-term dynamics, which indicate the efficiency of LSTM to utilize useful information hidden in historical memory is stronger than ANN. However, given enough historical information ANN can achieve a similar accuracy, compared with LSTM. This project provides a unique demonstration that Cryptocurrency market price is predictable. However, the explanation of the predictability could vary depending on the nature of the involved machine-learning model
MODEL PREDICTIVE CONTROL OF SMART GREENHOUSES AS THE PATH TOWARDS NEAR ZERO ENERGY CONSUMPTION
Get PDFAs we know the fact that, India is the second largest population country in the world and majority of people in India have agriculture as their occupation. Farmers are growing same crops repeatedly without trying new verity of crops and they are applying fertilizers in random quantity without knowing the deficient content and quantity. So, this is directly affecting on crop yield and also causes the soil acidification and damages the top layer. So, we have designed the system using machine learning algorithms for betterment of farmers. Our system will suggest the best suitable crop for particular land based on content and weather parameters. And also, the system provides information about the required content and quantity of fertilizers, required seeds for cultivation. Hence by utilizing our system farmers can cultivate a new variety of crop, may increase in profit margin and can avoid soil pollution
Deep Learning-based Traffic Sign Recognition for Autonomous Driverless Vehicles
Get PDFTraffic sign detection and recognition play a crucial part in driver assistance systems and autonomous vehicle technology. One of the major prerequisites of safe and widespread implementation of this technology is a TSDR algorithm that is not only accurate but also robust and reliable in a variety of real-world scenarios. However, in addition to the large variation among the traffic signs to detect, the traffic images that are captured in the wild are not ideal and often obscured by different adverse weather conditions and motion artifacts that substantially increase the difficulty level of this task. Robust traffic sign detection and recognition (TSDR) is of paramount importance for the successful realization of autonomous vehicle technology. The importance of this task has led to a vast amount of research efforts and many promising methods have been proposed in the existing literature. However, the machine learning methods have been evaluated on clean and challenge-free datasets and overlooked the performance deterioration associated with different challenging conditions (CCs) that obscure the traffic images captured in the wild. In this paper, we look at the TSDR problem under CCs and focus on the performance degradation associated with them. To overcome this, we propose a Convolutional Neural Network (CNN) based TSDR framework with prior enhancement
Integrating Blockchain with Database Management Systems for Secure Accounting in the Financial and Banking Sectors
Get PDFThe research aims to improve financial security in the national health insurance market by integrating blockchain technology with cloud-based technologies. The research goals are to provide financial transparency in health insurance schemes, minimise fraud, and improve data privacy. The suggested method offers a solid response to the present problems with financial management in the healthcare industry by utilising the benefits of blockchain technology, such as tamper-proof data storage and decentralised transaction confirmation. The study also looks at how the Nudge theory might help consumers make wise privacy choices while upholding high standards of security and confidence in open banking systems. In-depth reviews of previous research, case studies, and assessments of the functionality of current systems are all part of the methodology. The results show that integrating blockchain with cloud computing can greatly increase the security and efficiency of financial transactions related to health insurance. However, issues remain to be resolved, including blockchain connection with current systems, regulatory compliance, and technological adoption. Recommendations for further research and real-world applications are included in the study's conclusion to maximise blockchain's utility in the financial industry, especially concerning national health insurance
A Hybrid Framework For Travel Advice System Using Big Data And AI
Get PDFIn recent years, with the development of the internet and technology, the tourism industry has seen a significant increase in tourist numbers. The growing demand for personalized travel experiences has led to the development of travel advice systems for tourism. This helps travel agents find suitable travel destinations for clients, especially those unfamiliar with the location. Advisory systems are becoming more common in everyday activities like social networking and online buying. A hybrid framework for a travel advice system is proposed based on big data and artificial intelligence. The main aim of the system is to provide tourists with personalized travel planning based on user preferences and historical data. This allows the user to quickly locate what they are seeking for without wasting time or effort. It combines the strength of a content-based and collaborative filtering approach. To improve user affinity relationships and the quality of recommendations in the travel industry, a common recommendation filtering algorithm based on designations and user preferences has been proposed. Context-aware advice systems combine software computing and data mining to incorporate user profiles, social media history, and POI (points of interest) data. Suggestion system for a list of tourist attractions adapted to the preferences of tourists. Also acts as a travel planner by developing a detailed program that includes a multi-level framework for the travel advice system. Based on the traveler's experiences, the ratings (reviews) were also collected and analyzed to make better decisions for new travelers that advise tourist travel locations based on their previously rated venues. The algorithm searches the database for travel opportunities and uses text-mining techniques to find places of interest. the application of intelligent e-tourism consultation in tourism, focusing on interfaces, consultation algorithms, characteristics, and techniques of artificial intelligence. The goal aims to develop a hybrid travel advisory system that leverages intelligent e-tourism advice in the travel industry, focusing on interfaces and recommendations based on big data and artificial intelligence techniques
Estimation of blood lipid profile to study dyslipidemia in patients with hypertension, diabetes, liver and kidney disease
Get PDFIntroduction: Lipotoxicity is a result of hyperlipidemia. Lipid and cholesterol buildup in the arteries causes atherosclerosis, which damages key organs including the heart and kidneys and causes cardiovascular disorders. Methods: Fasting blood samples were collected and tested using an automated biochemistry analyzer for dyslipidemia screening. Five participant groups—those with hypertension, diabetes, kidney disease, or liver disease—as well as a control group of people without these conditions—were used to collect the data. There were 101 patients in the study, with at least 20 volunteers in each group ranging in age from 18 to 70. The data were statistically compared using the independent two-sample t-test. Results: Hypertension and diabetes associated participants had an increased mean of low-density lipoprotein, very low-density lipoprotein, total cholesterol, and triglycerides levels than control (p<0.05). These were likewise higher in kidney disease patients compared to the control group (p<0.05). High-density lipoprotein levels did not change significantly in these groups. In liver disease patients mean triglycerides and very lowdensity lipoprotein levels were found significantly higher when compared to the control group (p<0.05). Mean high density lipoprotein levels in individuals with liver disease reveal a significant drop when compared to the control group, with a 90% confidence level. Conclusion: A link between hyperlipidemia and patients with hypertension, diabetes, liver disease, and renal disease was observed. Diabetes and high blood pressure were present in the majority of patients with renal and hepatic dysfunction
IDENTIFYING HEALTH INSURANCE CLAIM FRAUDS USING MACHINE LEARNING CONCEPT
Get PDFPatients depend on health insurance provided by the governmentsystems, private systems, or both to utilizethe high-priced healthcare expenses. This dependency 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-Score
 
AN STRATEGY OF POWER AND AREA COMPETENT APPROXIMATE MULTIPLIERS
Get PDFIn this paper, the area of efficiency multiplier put a sign suggests a fixed width through a replica redundancy through adoption My tolerance for noise (ANT) architecture with a multiplier of fixed width to build a redundancy version precision cutting Masa (RPR). ANT proposed architecture can meet the demand for high precision, low power consumption, and region Efficiency. RPR fixed-width design with error compensation through the circles of the possibilities and statistical analysis. use the When a partial product of the correct input vectors and vectors fixed in the palace and put in place to reduce truncation errors, hardware Failure holding circuit can be simplified compensation. The multiplier ANT 16 × 16 bits, the circuit area in our RPR fixed width It may be less, energy consumption in the design of ants can be saved as compared with the ANT state of the art design