This research aims to examine the usefulness of integrating various feature selection methods with regression algorithms for sleep quality prediction. A publicly accessible sleep quality dataset is used to analyze the effect of different feature selection techniques on the performance of four regression algorithms - Linear regression, Ridge regression, Lasso Regression and Random Forest Regressor. The results are compared to determine the optimal combination of feature selection techniques and regression algorithms. The conclusion of the study enriches the current literature on using machine learning for sleep quality prediction and has practical significance for personalizing sleep recommendations for individuals.

One of the most important steps in the manufacturing of electronic goods is the creation of printed circuit boards (PCB). An electronic device's PCBs are the first stage in production, so even a small error there could cause serious flaws in the finished product. Finding and identifying flaws in PCBs is crucial given the size and demand of the PCB industry. In this paper, we propose a reference comparison method for PCB defect localization and classification that employs a template and a test picture and integrates machine learning and image processing techniques. We introduce a solution pipeline that works in three stages: Subtraction of Images where the test images are subtracted to generate a mask that highlights the regions of defect on the test image, Contour search to find the contour of the defects from the generated test image, and Model Inference where the contours found above are extracted from the images and fed into our machine learning model which then classifies those defects in the test image. We train the machine learning model, in our case, a Convolutional Neural Network (CNN) that forms the artificially intelligent (AI) part of our solution which can identify the type of defect present given the image of the defect as input. Our experimental findings demonstrate that, compared to other traditional methods utilized for this work, our model diagnoses the afflicted parts with 97% accuracy.

Before releasing an item, every news website or-ganizes it into categories so that users may quickly select the categories of news that interest them. For instance, I frequently visited news websites and click on the technology section because I want to read about the most recent technological developments. You might prefer to read about politics, business, entertainment, or even sports if you don ‘t enjoy reading about technology. The content administrators of news websites currently classify the news stories by hand. However, in order to save time, they can also incorporate a machine learning model on their websites that reads the news headline or the news’s content and categorizes it. Information from high-profile sources as well as inadvertent and unconscious mechanisms, people to apply to any news that is detrimental to their viewpoints. In this project, we ‘ll create an LSTM model to determine whether a particular news item is authentic or not. Based on information in the dataset. Data will be gathered using the ” pandas-datareader ” package with an API to ensure that the data is current and we are not left behind. The LSTM module is subsequently trained using the preprocessed data. The output of the test data will then be predicted and plotted. The authors main aim is to do a comparison between the LSTM method and the GRU method and find which performs better.

Liver illness is one of the worst diseases on the planet. It occurs in the human body, most notably in the liver. The liver's primary function is to eliminate waste created by organisms, to store key vitamins required by the body so that they do not go to waste, and to digest meals. This is a highly terrible disease, and the first thing that has to be done is to limit the risk explored by this lethal disease, and early detection can assist save the organism. The amount of people that are disease in the world is approx. 3.5 percent. The number of advancements that are happening in prediction of the disease done through the help of machine learning classification techniques like KNN, random forest SVM, and logistic regression. Other deep learning methods are also incorporated to solve this problem such as artificial neural network and convolution neural network. The methods would definitely increase the life expectancy of the patient suffering from this disease and avoid the chronic liver disease (CLD). The data may be gathered in enormous quantities as a result of the widespread use of bar codes for superior marketable items, the automation of many commercial and government transactions, and the advancement of data gathering systems. The proposed system that has been used ensemble methods such as random forest, xgboost and gradient boost and are combined to get a greater accuracy.

Health is the functional or metabolic regulation of a living body. In humans, health is an individual capability to conform and adjust to the challenges like socially, mental or physically. Mouth is the window to health of our body. Most of the nutritional deficiencies, systemic diseases, infections etc are manifested first as oral conditions. Good oral health is very important for overall wellbeing of an individual. Malocclusion is a misalignment or incorrect relation between the teeth of the two dental arches when the jaws are closed. Malocclusion is the highest public health problem in the world because of its high prevalence. Worldwide data on prevalence of malocclusion has shown that malocclusion is more prevalent in whites than in blacks, then more in females than males and more in developed countries than in developing countries, less in rural population than urban population. A definite geographical and racial variation is seen in southern and northern parts of India. In India class I malocclusion is more prevalent than class II and class III malocclusions. A prior recognition of malocclusion not only aids in intercepting its severity but it also helps in addressing the aesthetics and functional problems.

NLP is a computer-based software technology that used primarily to translate the natural human language into machine understandable format efficiently. The inputs for the machine could be text, audio, video, image, and speech. NLP is emerging globally and is being used in many applications. One popular application of NLP is Siri introduced in Apple Inc. This created a greater impact on iPhone community. Machines being trained with respect to voice search will facilitate the future generation in performing day-to-day activities. Machine learning (ML) algorithms have contributed extensively for building this popular framework. The paper aims to provide an NLP solution to a text classification problem and solve it using NLP and machine learning to get the best results and the best accuracy.

For large bandwidths and secure data transfer applications, FSO communication has gotten a lot of interest from academics. However, the local atmospheric conditions restrict its performance. The focus of this work is on an FSO system that uses a diversity strategy to compensate for signal loss caused by moderate to heavy air turbulence. Over the gamma-gamma distribution channel, we obtain a closed-form equation for two crucial parameters: average BER and outage probability. In this study, numerical results for several combining strategies are provided. With wavelength diversity, the reliability and performance of the FSO communication system are improved.

Heart disease causes a significant mortality rate around the world, and it has become a health threat for many people. Early prediction of heart disease may save many lives; detecting cardiovascular diseases like heart attacks, coronary artery diseases etc., is a critical challenge by the regular clinical data analysis. Machine learning (ML) can bring an effective solution for decision making and accurate predictions. The medical industry is showing enormous development in using machine learning techniques. In the proposed work, a novel machine learning approach is proposed to predict heart disease. The proposed study used the Cleveland heart disease dataset, and data mining techniques such as regression and classification are used. Machine learning techniques Random Forest and Decision Tree are applied. The novel technique of the machine learning model is designed. In implementation, 3 machine learning algorithms are used, they are 1. Random Forest, 2. Decision Tree and 3. Hybrid model (Hybrid of random forest and decision tree). Experimental results show an accuracy level of 88.7% through the heart disease prediction model with the hybrid model. The interface is designed to get the user's input parameter to predict the heart disease, for which we used a hybrid model of Decision Tree and Random Forest.

Heart sound analysis has been used as a tool for many cardiovascular disease diagnosis. In this study, wavelet packet energy based features have been proposed to detect the abnormal heart sound in phonocardiogram(PCG) signal. The heart sound dataset of 2016 PhysioNet/CinC challenge is utilized for developement of the model. The effectiveness of proposed features are assessed by the machine learning techniques: random forest(RF), support vector machine (SVM) and multilayer perceptron (MLP). The proposed wavelet packet cepstral coefficients (WPCC) features achieved an average accuracy of up to 84.88% on the unseen test dataset using SVM classifier. The proposed features have shown better performance compare to time and frequency domain features. Automated analysis of phonocardiogram signal will provide better clinical information to doctors to diagnose different heart abnormalities.

Data tampering and fraud in land records have increased drastically in the modern world. A data storage model using Blockchain and Interplanetary File System (IPFS) is proposed in this work. Land records and the farmer’s information are stored inside the Interplanetary file system. To avoid data faking, the hash address of the respective data generated by IPFS is stored in the blockchain. This proposed system when deployed on a large scale can outperform the existing methods of securing user data. One of the latest technological advancements in the software industry is the innovation of Blockchain Technology. This new technology has opened up a new business relationship platform that delivers feasibility, protection, and cheap rates. It provides a new foundation of trust for transactions that can facilitate a very streamlined workflow and a faster economy.

Detecting wine variety based on the country, year of origin and the review alone is a very difficult task. This problem is converted into a classification problem using the combination of Natural Language Processing (NLP) and machine learning. A public dataset that consisted of wine variety corresponding to its country, review, designation, province, winery and year was used for analysis of proposed approach. Natural Language Processing is used as a preprocessing step in our approach along with neural network to build a classifier. For more robust training k-fold cross validation technique was also looked and implemented for the same. The evaluation metric chosen to analyse the performance was accuracy. 98\% accuracy was attained on the evaluation set with our model. To our best knowledge, this is the first attempt to exploit NLP and neural networks to deal with prediction of wine variety.

Now a day's Robotics is a emerging technology which reduces the effort of humans. The concept of Mobile Robot is fast evolving and the number of mobile robots and their complexities are increasing with different applications.. There are many types of mobile robot navigation techniques like path planning, self -localization and map interpreting. The project is to build a mobile robot which avoid obstacle and to plan its moment. It has an infrared sensor which is used to sense the obstacles coming in between the path of ROBOT. It will move in a particular direction and avoid the obstacle which is coming in its path. AnInfrared ray sensor is used to detect the obstacle and send information to controller and after processing the input microcontroller redirects robots using motors which are controlled by motor drivers.

Steganography is the basis of information covering the puzzle in some other data (we call it the ship), leaving no obvious evidence of data change. Most conventional steganographic strategies is limited data that hide the limit. They can cover up just 10% (or less) of the information measures of the vessel. This is on the grounds that the standard of those procedures was either to supplant an uncommon piece of the recurrence parts of the vessel picture, or to supplant all the slightest critical image bits with a secret multi-valued data. Our new Steganography uses the image as vessel information, and we enter the data in the bit-plane mystery vessel. This strategy makes use of human attributes, through which people cannot see the structure of any form of data exclusively damned pair, for example. We can replace most of the «Commotion like" regions in the bit-planes of the puzzle vessel image data without deteriorating the quality of the photos. We called our steganography "BPCS-steganography," which remains a Bit-Plane Complexity Segmentation steganography.

A smart energy meter provides real time power consumption data. This helps the consumer to manage their power requirement efficiently and economically. In a developing country like India, there is a rapid growth in the power sector. This paper explains the development of an IoT enabled smart energy meter capable of real time load management. The real time energy monitoring is visualized using a mobile application. The application also serves as a smart home controller where the user is capable of controlling the electrical appliances remotely or controlled based on events set by the user.

This paper presents the concept of Auto roll punching machine mainly carried out for production based industries. Industries are basically meant for Production of useful goods and services at low production cost, machinery cost and low inventory cost. Today in this world every task have been made quicker and fast due to technology advancement but this advancement also demands huge investments and expenditure, every industry desires to make high productivity rate maintaining the quality and standard of the product at low average cost, but still we are using a separate machines for separate operations.this is a time and power consuming process, it need maintenance as well as more space. Our project is to overcome above listed problems.In our project two operation are builted as a one machine tool i.e.punching and feeding of work materials In auto roll punching machine consists of two sections. One is automatic feeding mechanism and the second section is punching section .The first section consists of geneva wheel disc keyed with a shaft at one end and the other end is connected with chain sprocket wheel.This sprocket wheel transmits the rotary motion from the geneva wheel to the metal sheet feeding rollers through a chain drive.Hence, when the geneva wheel is rotated. So, the metal sheet also moved for punching operation. Keywords—Geneva Mechanism, Gear Box, Punching Ram, Feeding Rollers.

The paper presents an efficient reconfigurable hardware implementation of Advance Encryption Standard (AES) algorithm on Field Programmable Gate Array (FPGA); using High Level Language (HLL) approach with lesser hardware resources. The mode of data transmission in the modified AES is 128-bit plaintext and keys which converted into four 32bit blocks and exclusion of shift row. Using this feature, not only area is optimized but also higher throughput is achieved. The proposed architecture can deliver higher throughput at both encryption and decryption operations.Design has been done using Verilog and simulated using ModelSim. The design has been synthesized using Xilinx 14.5 for target device Spartan6.