Volume 06 Issue 02
AN INTELLIGENT SYSTEM FOR IDENTIFYING THE RISK OF COVID-19 USING LOGISTIC REGRESSION
RAMYA VENKATESAN, UDAYA ALLANI, NIMMAGADDA DEEPA, ASHOK KUMAR K | pp: 68-74 | Purchase PDF
Abstract: SARS-CoV-2, also known as Covid-19 Corona Virus, caused damage worldwide, and the situation is getting worse. Every day, it is an epidemic disease from one person to another. Therefore, it is important to keep track of the number of patients involved. The current system provides computer data in an integrated way that is very difficult to analyze and predict the growth of disease locally and globally. To overcome this difficulty, Machine learning algorithms can be used effectively to map out the disease as well as continue to solve this problem. By analyzing X-ray images of the patient’s chest, machine learning, which is part of computer science, is important in classifying patients appropriately about illness. Supervised machine learning models with support algorithms (e.g. LR, SVR, and Time-series algorithms) for data analysis to back up classification helps model training to predict total global value confirmed cases or who will be at risk of contracting the disease in the coming days. Total Global data collection is being processed, pre-processed, and the number of verified cases has arrived at a specific date is issued, which is used as a model-set training in this regard proposed work. Supervised machine learning algorithms are used for training a model for predicting the growth of cases in the coming days. In this paper, we have proposed a method to identify whether a patient has a risk of covid-19 using a machine learning framework-logistic regression model, considering multiple symptoms and, also developed a web page that displays the attributes, and sample records, graphs related to the at risk-patients of covid-19.
OCR Word to Text Converter
Rohini R. Mergu, Vaishnavi Yemul, Vaishali Alli, Manjushri Talwar | pp: 75-79 | Purchase PDF
Abstract: Word recognition is an intelligent activity of a pattern recognition system. Sometimes the human brain is also confused to identify handwritten characters in a certain language. In an image of handwritten Marathi, Hindi compound characters, feature extraction techniques are playing a significant role to extract special features of the image. For handwritten characters, zoning is the most popular method to extract the features. The main aim of feature extraction is to extract the relevant information of an object or image. In this system, the zoning feature extraction technique is used to extract features. Besides this, the statistical feature extraction method is also proposed.
Design and Development of Smart Dustbin using IOT
Arindam Ghosh, Debajyoti Sarkar, Aditya Kumar Jha, Sayan Das, Tapas Kumar Nandi, Sandip Bhattacharya | pp: 80-87 | Purchase PDF
Abstract: A Smartbin for waste management is presented in this work, as an attempt to maintain clean and hygienic environment. The concept of the Internet of Things (IoT) has been implemented through GSM module integrated with Arduino UNO to design this bin along with Bluetooth connectivity. The Bluetooth Controller App is employed for establishing connection with the Bluetooth module. The module is therefore leveraged to detect distance between the user and the bin, and the information enables the planning of an optimal route for the bin to move towards the user. As it detects the object, the lid of the bin opens automatically and allows the object to dispose the waste into it. The waste is then segregated into dry or wet particles and then the lid will get close automatically. Level indicators allow estimation of remaining capacity of the bin to store further waste. On exhaustion of the capacity of the bin, SMS-based notification is provided to the user via a GSM module. In this work, a low cost, user-friendly, economically viable waste management solution to control pollution is demonstrated.
Thermohydraulic Transport Characteristics in Obstructed Microchannel with / without Pulsating Flow Condition at Inlet
Tapas Kumar Nandi, Gourav Kumar Chowdhury | pp: 88-94 | Purchase PDF
Abstract: The present work investigates the effect of pulsation on the transport process in a 2D microchannel. The inlet velocity varies sinusoidally in time at a constant dimensionless frequency (St=10) and amplitude of 0.8. The working fluid is considered as water which is made to flow in the obstructed microchannel whiles the microchannel walls were kept at a uniform temperature. The solution of two-dimensional Navier-Stokes equation was performed using the SIMPLE algorithm with the momentum interpolation technique. The simulations were performed in the laminar regime within the Reynolds number range between 100- 500 for the microchannel. The results of pulsating flow simulations had been analysed and compared with non-pulsating flow simulations. It is observed that the effect of pulsation in flow obstructed microchannel is significant and more enhancement of heat transfer is observed at higher Reynolds number while keeping the friction factor within tolerable limits.
Kerf analysis and Material Removal Rate during Abrasive water jet Machining of GFRP Laminates
Chetan, N. Rajesh Mathivanan | pp: 95-100 | Purchase PDF
Abstract: Non-conventional machining technique like Abrasive Water Jet (AWJ) machining is a good replacement for traditional methods to achieve higher tolerances and machining capabilities. With a fine jet of ultra-high-pressure water and abrasive slurry, AWJ uses erosion to cut the target material. This study investigates the material removal rate during abrasive water jet machining of Glass fiber reinforced polymer. Pressure, stand-off distance, and abrasive mass flow rate were the three process parameters considered in this study. Experiment was performed according to Taguchi’s experimental design. The data was analyzed using analysis of variance (ANOVA) to identify the most important process parameters that statistically influence the Material removal rate (MRR). Bottom kerf width and Top kerf width are considered to find the taper angle from the AWJ machining. Kerf analysis is carried out to judge the optimum values of parameters. The experimental studies reveal that the jet pressure is the most influencing variable for MRR.
Comparative analysis of Machine Learning and Deep Learning Algorithms using Fault diagnosis in Bevel gearbox
S. Ravikumar, Sharik N, C. Chandraprakash, V. Muralidharan, Syed Shaul Hameed | pp: 101-113 | Purchase PDF
Abstract: The bevel gearbox is one of the most common types of gearbox or gearhead used in automation and energy transmission applications. The term refers to the gearbox’s tools, such as bevel gears, which are a single-stage unit that interlocks the beveled edges of gears and transfers rotation, much like interlocking fingers. The use of vibration measurement analysis for diagnosing gearbox failure has been proven to be efficient. This study compares several time-frequency signal processing methods for extracting diagnostic information from transient vibration signals. Accelerometer vibration measurements were used in experiments conducted on a bevel gearbox test rig. The discrete wavelet transform was originally used in vibration signal scrutiny to extract the frequency content of a signal from the appropriate frequency region. Then, to extract statistical features from vibration signals, several time-frequency signal processing methods were used, and their characteristic performance was compared. Due to the difficulties in selecting a suitable window length to capture the impulse signal, it was found that the Short Time Fourier Transform (STFT) could not give a good time resolution to detect the periodicity of the broken gear tooth. As a result, statistical features were used as inputs for a variety of deep and machine learning algorithms, yielding results such as a confusion matrix and a high-accuracy comparison. The algorithms used in this study were Random Forest, Decision Tree, K-Star, ANN, Naïve Bayes, and SVM. Of all the algorithms used in this study, LSTM yielded the highest accuracy of 98.65 percent.
Performance Analysis of Global Exchange Traded Funds in India
Nindu Priya Laxmi S B N, Asok Kumar N | pp: 114-123 | Purchase PDF
Abstract: Exchange Traded Funds (ETFs) are basket of securities which can be bought and sold in the stock market, just like any other stocks or shares. Most of the ETFs track an index or a commodity or a sector. ETFs are attractive as an investment because of their low costs, tax efficiency, and stock like features. In Indian markets ETFs just started to become popular. Over the last few years Indian ETFs have seen a volume growth, most of it going towards Nifty50 ETFs.
Global Exchange traded funds are simple investment products that allow the domestic investors to take an exposure to international indices. Nowadays, investors approaching the global market for better returns. Indian ETF market is still evolving, there are only a few international ETFs available. This study aims to examine the performance of selected Global Exchange Traded Funds compared to other ETFs in the market. In our analysis, the Sharpe, Treynor and Jenson ratios are used as risk-adjusted performance measures also evaluates their performance using Data Envelopment Analysis (DEA).
FASTEST DATA TRANSMISSION USING PSO ALGORITHM
P. Sathiyamurthi, P.Sendhuvarthani, J.Jeyapratha, C.Kavi Arasan | pp: 124-135 | Purchase PDF
Abstract: Network inserting allots hubs in an organization to low dimensional portrayals and successfully protects the organization structure. In this paper, data transmission takes place with easy and high speed by transferring the data to the nearest data packets with low latency in a secured way. Using PSO algorithm and IAAS as a base we have built this project. Network frameworks, node creation, data queue, energy diagram, data packet all the process are carried out in a structural manner for the data to transmit in a fast and efficient way. Keywords— Network inserting, PSO, network framework, data queue.