VOLUME 11, ISSUE 1, JANUARY 2022

Abstract: The primary aim of the present study was to compare the occurrences of Ligament injuries among three level of football player. The investigator has made an attempt to classify or define the groups of Football players based on the class of the games of the Football players. Accordingly three groups of Football players were targeted; International, National and State Football players aged between 14 to 30 years, information of occurrences of injuries was collected, Individually through a questionnaire from Football players. The International Football players was found to have got more suffered from Ligament injuries as compared to National and state level football Players. Key Words : Injuries , ANOVA, Football, Ligament

Abstract: One of the major problems of most developing towns and metropolises is the degeneration in the state of neatness of the surroundings with respect to waste control. This happens owing to the negligence of the model waste collection method. This negligence produces the spread of waste in communities which in turn generate unhealthy circumstances in the environment. It also stimulates several serious diseases amongst the people in proximity and destroys the beauty of the environment. To avoid negligence of the waste and to increase the neatness of the society, waste monitoring system is needed. In this system, the level of the waste is sensed with the help of ultrasonic sensor and the information is sent to the authorized agency via GSM module. PIR sensor is used to detect the motion of the people coming to the waste bin with refuse when the waste bin is full and stopped adding of more refuse to the bin through sound notification. The GSM and the sensors used are interfaced via the Arduino microcontroller. The receive sms will efficiently help to monitor the waste collection to make the surroundings smart, clean and safe.

Keywords: Waste, Arduino, Monitoring, Sensors, GSM Module

Abstract: The development of automatic fish counters had been driven by the need for accurate, long-term and cost-effective counting and recognition for the advancement of aquaculture in the Philippines. Non-invasive methods of fish counting are ultimately limited by the properties of the immerging technologies like when candidates for counting are transparent and or small (Bangus Fry). Image processing is one of the most modern approaches in automating the counting process. The main objective of the study is to evaluate three image segmentation algorithms namely (1) Watershed Algorithm, (2) Hough Transform, (3) Concavity Analysis, in 2D image, whether or not they are capable of segmenting two-weeks old bangus fry’s’ in an image. The basic steps involved in the conduct of this study are the following; Image acquisition, Image Pre-Processing, Image segmentation, and Object counting. Result shows that the first method of the Concavity Analysis which locates the contours or curve points edges of the objects in an image performs best with the other algorithm with an accuracy rate of 94.36% with 7 false positive detections, and 154 False Negative, in an experimental data of four sets of 2D image ranging from 100, 200, 300, and 400 bangus fry per test image.

Keywords: Aquaculture, Image Segmentation Algorithms, Watershed Algorithm, Hough Transform, Concavity Analysis, Evaluation

Abstract: Algorithm in general terms is set of rules to be followed for doing a calculation. In computer science, an algorithm is a finite set of steps of well-defined instructions to perform a particular task or to solve a well-defined problem. Various type of algorithm is developed and used in the field of networking. Some may be divide and conquer algorithm other may follows the standards of dynamic programming and some may follow the greedy approach. Dynamic programming is an algorithmic approach that solves a given problem by dividing or breaking it into subproblems and further dividing that subproblems into smaller subproblems until one reach to the smallest subproblem. It stores that result of the subproblem such that if in near future that same problems encounters then that previously saved output can be reused instead of solving that problem again and again. Hence it saves sand increase the time efficiency and uses the optimal solution approach.

Keywords: Bottom-up Approach, Optimal Dynamic Programming approach, Standard dynamic programming, Fibonacci Sequence, Optimal substructure programming, Tower of Hanoi Problem, Word Break Problem, All Pair shortest Path Algorithm.

Abstract: There are priority preemptive scheduling algorithm and priority non-preemptive scheduling algorithm in operating system. When the newly arrived process is compared its priority to the process that is running and if its priority is higher it will executed by the CPU. This is known as priority preemptive scheduling algorithm where when the recently arrived process is positioned at the head of the queue and cannot be interrupted, this is known as priority non-preemptive scheduling algorithm. This priority algorithm is based on execution of process over a priority value. The higher the value, the higher the priority. Every process has its own priority. The first process to be executed is the process with higher priority, then continue until all the processes finish. In this journal we discuss the priority preemptive scheduling algorithm. With the priority number from 0 until 10, where the 0 the the lowest priority and 10 is the highest priority. Two case studies are discussed here.

Keywords: Priority, Scheduling, Priority Preemptive Scheduling Algorithm, Priority Non-Preemptive Scheduling Algorithm

Abstract: All real-world computers perform some sort of computations like mathematical models to solve their problems in a systematic manner. The essence of the automata theory is to help and develop mathematical and logical models that run efficiently. Since all the machines that implement logic or follows and predefined algorithm apply TOC (Theory of Computation). Thus, studying TOC gives learners an insight view of both computer hardware and software, its working and limitations.

Keywords: Theory of computation, Automata, Finite Automata, Turning Machine, Grammar, Regular Expression.

Abstract: Cyber bullying has emerged as a serious problem among the various effects of Social Media. It is afflicting children, adolescents and young adults. Machine learning techniques make automatic detection of bullying messages in social media is possible, and this could help to construct a healthy and safe social media environment. Robust and discriminative numerical representation learning of text messages is the critical issue in the research area. In this paper, we propose a new representation of learning method to tackle this problem. Our method is developed via semantic extension of the popular deep learning model stacked denoising auto encoder which is named as Semantic-Enhanced Marginalized Denoising Auto-Encoder (smSDA). The semantic extension consists of semantic dropout noise and sparsely constraints. Where the semantic dropout noise is designed based on domain knowledge and the word embedding technique. Our proposed method is able to exploit the hidden feature i.e., structure of bullying information and learn a robust and discriminative representation of text.

Keywords: Social Media, Bullying, Machine Learning, Safe Environment.

Abstract: As the Technology changes testing of a integrated circuits should be simpler, easier and faster to complete the process, according to the Design For Testability (DFT) process, testing of the integrated circuit becomes complex depending upon the number of flip flops present in the design. To make the testing simpler we are going to compression up to 20x and 25x depending upon the input configuration. It will be simple to find the input/output test channels for test coverage. In this paper we have defined to make test time and test data volume very simple and easier for multi users at different input. Scan insertion and compression can be done easily but EDT Compression is a tool used to make for multi configuration depending on the multi-input and multi output configurations. In this process of testing the integrated circuits and ATPG (Automatic Test Pattern Generation) setup can be done for the multi configuration. Experiments are done based on the multi-channel configuration for multi users at different compression Ratios, Serial and parallel Patterns can be generated according to configuration level

Abstract: Electrician is an android and iOS-based application which helps peoples to find nearby electrician for their electrician related works in home or in office. Small and Moderate Works like changing Lights/Bulbs, boards, wiring, and repairing electrical instruments/appliances like TV, Refrigerator, ac, or even a bulb change and etc. The electrician app finds and provide nearby electrician according their work and their professional specialities and get electrician to customers at their doorstep's.

Keywords: Android, iOS, Application, Flutter, Problem Solving, Database, Maps.

Abstract: This research constructs a face emotion framework that can examine fundamental human facial expressions. The approach suggested was used by humans to classify the humans' mood and eventually to play the audio file that links to human emotion using this result. First of all, the device takes the face of the human being as a part of the process. It is carried out facial recognition. After this, the facial expressions can be recognized using attribute extraction techniques. This way the emotion of humans can be identified using the picture element. Those signature points are located by the extraction of tongue, mouth and eyebrows, eyebrows. Training with a small range of characteristics faces can gain recognition in varying environmental conditions. An easy, effective and reliable solution is proposed.

Keywords: Deep Learning, Music Player, face detection, feature extraction, and face emotion.

Abstract: Heart is the a huge part in living creatures. Analysis and detection of heart related illnesses requires more accuracy, flawlessness and rightness on the grounds that a little slip-up can cause exhaustion issue or demise of the individual, there are various demise cases identified with heart and their number is expanding dramatically.. Predicting of Heart disease illness saves many lives recognizing Symptoms namely Raising in the heartbeat, Slow heartbeat ,Chest pain or discomfort ,Shortness of breath ,Light headache., Dizziness and so forth, is a basic challenge by the customary clinical information investigation. In this paper , we analysed the Machine Learning algorithms like K-KNN, NB,Decision Tree And Random Forest .and proposed a hybrid model which can predict the heart disease based on the basic symptoms like age, sex, pulse Rate etc. by comparing the accuracy we proven hybrid algorithm is the most accurate and reliable algorithm compared to all algorithms.

Keywords: K-Nearest Algorithm,Logistic Algorithm,Naïve Bayes ,Multi-Layer Perceptron,Machine Learning Algorithms.

Abstract: - In the present work we tried to develop a Sorting Visualizer using the technologies like HTML, CSS and JScript. Sorting Visualizer will be displaying the working mechanism of various sorting algorithms like, Bubble Sort, Selection Sort, Insertion Sort, Quick Sort, Heap Sort and Merge Sort. The main objective of developing this Visualizer is to make a learner comfortable in learning these techniques quickly and easily. We know the sorting algorithms are the most widely used algorithms in many applications including Discrete event simulation, Operating Systems, real time systems and many other as well. In the general case the efficiency of an application depends on the efficiency of sorting algorithm used. The only limitation of the Sorting Visualizer is that we should have graphic cards in the general purpose computer. Key-words: - HTML, CSS, JS, Selection Sort, Bubble Sort, Insertion Sort, Quick Sort, Merge Sort, Heap Sort

Abstract: The rapid development and the progress of technology in and all around the earth, Automation technology has got an important position in different fields and the application of power system has increased widely. Electrical automation technology is primarily used to monitor, during the operation of electrical equipment, the equipment running status monitoring, and to quickly identify problems resulting from the operation of the equipment through data analysis and feedback operation, as well as warning Therefore the importance of automation technology in power system and other fields is of great significance because automation technology comprises of all different types of processes and system to run automatically which includes the machinery of different types and other devices So, in this paper we are going to see the what does automation means and the application of electrical automation technology.

Keywords: Electrical Automation, PLC Technology, Fault Detection, Fieldbus

Abstract: To increase the worth of software products, every Software organization wants to develop high-quality software. Quality of software means satisfaction of stakeholders (end-user, developer, organization).The quality of software depends on the attributes such as functionality, usability, reliability, testability, etc. Software quality models later on abbreviated as SQM help software organizations, software developers, software quality researchers, and managers to decide which software quality attributes should be incorporated while developing the software. SQM are used for the prediction of software quality. Software quality is the central concept of software quality engineering. To achieve software quality assurance, we need to develop a high-quality software product. Software reliability plays a key role in software where time is a critical factor like in satellite launching, aerospace engineering, health care system, etc. If a software error occurs, the mission will fail. After the study of various SQM, we have studied, tabulated, and depicted software quality attributes in the form of bar graphs and tables. For the development of any new SQM, a literature review is essential.

Keywords: SQ (Software quality), SQM (software quality models), QF (quality factor), Software quality assurance, CBSD (component-based software development).

Abstract: The purpose of the study was to effects of 12 weeks program in Plyometric exercise on Body Mass Index (BMI) in Women Volleyball players. The 25 volleyball players were selected for sample size of the study and their age ranged between 20 -25 years. Only training was given to the experimental groups. Exclusion criteria were the presence of chronic medical conditions such as asthma, heart disease or any other condition that would put the subjects at risk when performing the experimental tests. The Plyometric exercise training program was planned as 12 weeks 4 day a week and 30 minutes in a day. The Plyometric exercise includes Front Box Jump, Lateral Box Jump, Weighted Lateral Jumps, Broad Jumps,Skater Jumps, Scissor Jumps, Dot Drill,Lateral Box Shuffles, Abdominal muscular endurance was measured by performing the 1-minute bent knee sit-up test . The result reveals that there was significant effects of Plyometric exercise on BMI in female volleyball players. Key words: Plyometric exercise, Volleyball, Women, BMI

Abstract: Porosity and permeability is plays an important effect in the production of oil and gas in a reservoir. The accumulation of oil and gas plays a very important role in the formation of gas reservoir. In other to have a better flowrate in a reservoir, this paper presents a smart system that will be used in estimating the permeability and porosity in carbonate rocks. The methodology or technique used in this work is Random Forest Classifier. Random Forest Classifier was used in training a machine model for classifying the porosity and permeability in carbonate rocks. The model was trained using a reservoir data consist of a total of 14 columns which was reduced to just three columns. The reduction was done by selecting just the most important feature by means of feature extraction. The model was trained using just the selected features with an estimator function of 100, the model for evaluate based on accuracy and precision. The result generated shows that the model achieved an accuracy of about 100%. The model was saved and deployed to production using python flask. The result of the deployed model shows a correct classification of the porosity and permeability in carbonate rocks.

Keywords: Porosity, Permeability, Carbonate Rocks, Oil Reservoir, Random Forest Classifier.

Abstract: Computer Vision and deep learning techniques to recognize the hand gestures are among the trending domain of research now a days. The power of Artificial intelligence to improve the user interface and HCI is making human life much easier. Many researches are going on to develop systems that can understand hand gestures as input and perform several tasks. The communication through sign language is very ambiguous as it differs from person to person. This makes it very specific. Therefor, this project aims to build a system that can effectively determine a set of gestures, convert it to text and audio then perform certain task. At the same time it allows user to teach the system, their own gestures and associated messages to recognize.To accomplish this a CNN model is built to classify the gestures and Open CV is used for image capture and processing. After the model identifies the gesture it is converted to text/audio and associated task is performed.

Keywords: Computer Vision,Convolution Neural Network, Deep Learning,TensorFlow,Keras,Tkinter

Abstract: DBMS acronym of Database Management System comprises of a collection of inter related data. It is a set of program or software that help to access the stored data in a very easy and efficient manner.  Database are generally used to design and to manage large amount of data in a very systematic manner. The management of stored information includes both the definition of structures for the storage of information and provision mechanism for manipulation of this information. This information is stored permanently in various files. Various application software is written to fetch or extract the information from these files as and when required. DBMS removes the data redundancy and inconsistency among the data. DBMS also provides different levels of security to the data. It also retrieves the data form the database as per the criteria specified by the user.

Keywords: RDBMS, DBMS, Relational Algebra, Relational Calculus, Procedural Language, No-Procedural Language, Query Language

Abstract: Digital fabrication technology, also referred to as 3D printing or additive manufacturing, creates physical objects from a geometrical representation by successive addition of materials. 3D printing technology is a fast-emerging technology.

Keywords: 3-D Printer, Manufacturing, Rapid Prototyping, Application of 3D Printing

Abstract: This examination intends to plan and execute a home security framework with human location ability. Customary home security frameworks,i.e., Closed-Circuit Television (CCTV) can catch and record recordings without he capacity of giving notice input assumig there is any dubious object. Hence, an extra item discovery and cautioning technique is required. The proposed plan is executed utilizing Raspberry Pi 3 and Arduino, that is associated by USB link. The PIR sensor is introduced on Arduino and webcam is mounted on Raspberry Pi 3. The Raspberry Pi 3 is used to deal with inputs from sensors and interaction pictures for human identification. PIR sensor recognizes the development around the sensor to initiate the webcam to catch an image. Then, at that point, the item acknowledgment is performed utilizing Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) to distinguish the dubious item.Expecting that the questionable article is distinguished, then, the alert is ordered and sends an email to alert the house proprietor about the presence of the gatecrasher. The outcomes show that it takes onnormal 2 seconds for the proposed framework to distinguish an intruder and that the framework can really perceive the interloper

Keywords: Closed-Circuit Television ,Support Vector Machine ,Histogram of Oriented Gradient

Abstract: Nowadays biometric systems are useful in recognizing a person’s identity, but criminals change their appearance in behaviour and psychological to deceive recognition system. To overcome this problem we are using a new technique called Deep Texture Features extraction from images and then building train machine learning model using CNN (Convolution Neural Networks) algorithm. This technique refers as LBPNet or NLBPNet as this technique is heavily dependent on features extraction using LBP (Local Binary Pattern) algorithm. In this project, we are designing LBP Based machine learning Convolution Neural Network called LBPNET to detect fake face images. Here first we will extract LBP from images and then train LBP descriptor images with Convolution Neural Network to generate a training model. Whenever we upload a new test image then that test image will be applied to the training model to detect whether the test image contains a fake image or a non-fake image. Below we can see some details on LBP.

Keywords: Biometry, Identity, Recognition, Detection, Fake face.

Abstract: Air pollution is one of the biggest dangers to human health but even then the data related to it is usually limited and mostly not accurate or updated. Commonly, there are only 3-4 pollution monitoring stations in each city which means that the data that we get from these stations are accurate only to close proximity of the monitoring station and may vary considerably just a few kilometres away from the station. The purpose of the paper is to present the choice of architecture and the implementation of a mobile platform which by using connected sensors collects real-time air quality data. The data can then be provided to the general public where primarily people suffering from diseases related to respiration like asthma can benefit from real-time information about air quality.

Keywords: Air quality, Sensors, Location Based Services, Android application, Raspberry Pi, Arduino, Air Pollution.

Abstract: In the past, batik artists to create a batik motif required special skills and a long time because motif is the main element in batik, and the uniqueness of batik is from the motif itself. Recently computers were able to produce many ordinary images turned into works of art even producing a new motif variant product. The method used is neural transfer style based on CNN architecture. It has performed feature extraction on batik motifs and has produced variations of batik motifs from collaborations of existing batik motifs such as the kawung batik motif and Asian Games 2018 mascot image. Neural transfer style empowers people around the world to experiment with their own creativity seeing the importance of style transfer in the commercial arts world and how art exists in the real world Index Terms.

Keywords: CNN, Batik, Mascot, Silhouette.

Keywords: Image Processing, Magnetic Resonant Image, Deep Learning, MATLAB etc.

Abstract: In Nigeria, the dominance of English as a medium of communication is worrying as minor indigenous languages are heading towards extinction. The main objective of this study is to develop a language framework that could take English input and translate it into Nupe. The theoretical framework was first considered. Due to the differences between the systems between English and Nupe and the lack of similar arrangements in English and Nupe languages, Transfer Rule-Based Machine Translation was used in the development of the system. It is used because it allows manual speech tagging, design and modelled of language translation systems. This process was designed using Unified Modeling Language (UML). UML is used to design the system flowchart, sequence diagram, use case diagram and class diagrams. A bilingual (dictionary) database is designed to store source language (English) and target language (Nupe) words with the Python programming language interpreter and test the translation grammar using a natural language application(NLTK). The results show that the system can provide translation of acceptable quality. The system can benefit many kinds of people as it allows them to process their translations quickly and easily.

Keywords: English, Nupe, Rule-based Approach, Machine Translation, Bilingual, tagging, Unified Modeling Language.

Abstract: The conventional security protective cap wearing acknowledgment is just founded on the shading, shape, surface and different attributes of the picture, which is extraordinarily impacted by the outer climate, and has the issue of temperamental acknowledgment precision. Considering the above issues, this paper concentrates on the acknowledgment strategy for power development labourer’s security head protector dependent on man-made brainpower innovation. Subsequent to pre-processing the development checking picture, for example, turning Gray and denoising, the development work force in the identification picture are found, that is, based on recognizing the development staff region, the head position of the development faculty is found, lastly the wellbeing protective cap wearing acknowledgment is acknowledged by utilizing YOLO calculation. The re-enactment results show that the normal acknowledgment exactness is 95.2%, the acknowledgment impact is steady and has great heartiness.

Keywords: Helmet detection, Construction sites, Deep learning, Accidents

Abstract: The Inability to determine better patterns in a group of events that will lead to particular deviations in customers’ behaviour and difficulty in detection of a repetitive approach to a particular sales company or a group of companies in order to identify regularities in the business or in a particular sector of a business as regards to purchasing item at different seasons. which have become a problem in data mining. However, periodic mining patterns from transactional database require an exponential mining space to produce a huge number of patterns, the first priority for a mining algorithm is the efficient discovery of user-interest-based periodic patterns. It is often necessary to mine a limited, interesting representative subset of frequent trends in many real-world scenario. This paperpresents a model for efficient exploration of periodic pattern in big data. Suffix and prefix trees have been used to capture the contents of the database in a very compact way to generate the full set of periodic-frequent patterns in a database for frequency and support thresholds provided by the user. A periodic pattern algorithm was developed to efficiently list all periodic item-sets. Themodel was implemented in Jupyter notebook using python programming language. The results show that some of the patterns discovered in this database are appearing not only frequently within the database but also appearing at regular intervals within the database at minSup 0.1% and maxPrd 10%.

Keywords: Data mining, Support Vector Machine, Logistic Regression, Recognition

Abstract: Our project aimed to detect fire by using the image processing technology that will alert people by early detection of fire. As there are many automatic fire alarm systems already existed like the sensor method, that has some limitations and designed to sense fire with the smoke, limited areas. To reduce limitations and to optimize with new technology, the project is proposed. The project is implemented by using Raspberry Pi3 Model B as a central processing unit and to connect the webcam as hardware. Webcam is taken as an input source, which cap-tures the video feed from the surrounding and feeds into the Raspberry Pi. The entire codeis written in pure python language using the open CV library for image processing. The the-oretical parts emphasize more in computer vision, machine learning, image processing, color model, and the working algorithm of the project to detect the fire. The project gives a better understanding of object detection with the computer and the useof these technologies in different forms and uses.

Abstract: Electric Load Forecasting (ELF) is an indispensable interaction in the preparation of the power business and assumes a significant part in electric limit booking and power frameworks the board, subsequently, it has drawn in expanding scholarly interest. Consequently, the exactness of electric burden anticipating has extraordinary significance for energy creating limit planning and power framework the board. This paper presents an audit of determining techniques and models for power load. Around 45 scholarly papers have been utilized for the correlation in view of indicated models, for example, time period, inputs, yields, the size of the venture, and worth. The audit uncovers that notwithstanding the overall straightforwardness of all evaluated models, relapse examination is still broadly utilized and effective for long haul determining. With respect to transient forecasts, AI or man-made consciousness-based models like Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Fuzzy rationale are leaning toward. Watchwords - Electric Load Forecasting; Modeling power loads; Methods and models of anticipating.

Abstract: Nowadays shopping malls and D Marts keep the track of their sales data of each and every individual item for predicting future demand of the customer and update the inventory management as well. These data stores basically contain a large number of customer data and individual item attributes in a data warehouse. Further, anomalies and frequent patterns are detected by mining the data store from the data warehouse. The resultant data can be used for predicting future sales volume with the help of different machine learning techniques for the retailers like D Mart. In this paper, we propose a predictive model using Xgboost technique for predicting the sales of a company like D Mart and found that the model produces better performance as compared to existing models. A comparative analysis of the model with others in terms performance metrics is also explained in details.The aim is to build a predictive model and find out the sales of each product at a particular store.Using this model, D Mart will try to understand the properties of products and stores which play a key role in increasing sales.

Keywords: D Mart Sales Prediction.

Abstract: Matlab’s rich and powerful functions have made it a fundamental teaching tool in the course of linear algebra, signals and systems, control theory, digital signals processing, image processing. Matlab has provided many main signal and system processing functions such as convolution, Fourier transform, Laplace transform, z-transform, etc, which simplify the calculation process greatly. This paper describes the applications of Matlab in signals and systems and digital signal processing DSP. Matlab provides various methods to analyze the signals and systems, including both continuous and discrete situations. Some methods can simplify the complicated calculation: some finish the same functions in accordance with the mathematical processing: and some can save operation time via efficient algorithms. Matlab can be used at different levels to solve problems quickly and efficiently, to understand the signal processing procedures deeply and to develop new algorithms.

Keywords: Convolution, DSP, Fourier, Matlab, Optimize, Signal, System, Simulation

Abstract: online social networks are growing rapidly in various directions. A number of industries are using these platforms to promote their products and communicate with end clients. On the other hand, some communities are misusing such platforms to promote hate, violence and negative or bully contents. All these happening misbalance the social environment online and offline too. The proposed work offers a research proposal on online hate and bullies content detection by analyzing the text contents of the social media post, message, and blogs. In this context, machine learning techniques and sentiment features are involved as essential tools to deal with bulk amounts of data. This paper first introduces the complexities and needs of cyberhate and bully content problem then a survey is performed over recently available research contents. Further, basic design and functional aspects are provided for proposing a final data model. Finally the conclusion of the proposal offered with the next step of the proposed research work.

Keywords: sentiment analysis, text mining, natural language processing, cyber bulling, hate speech.

Abstract: This research paper gives us the information about ‘Regula-Falsi Method’. This method helps us to find the roots of transcendental and polynomial equations. It is closed bracket method and closely resembles the bisection method. The method of false position provides an exact solutions for linear functions.

Abstract: Monte Carlo methods, or Monte Carlo experiments, are a broad class of computational algorithms that rely on repeated random sampling to obtain numerical results. The Underlying concept is to use randomness to solve problems that might be deterministic in principle. A Monte Carlo simulation can be used to tackle a range of problems in virtually every field such as finance, engineering, supply chain, and science. It is also referred to as a multiple probability simulation.

Keywords: random, probability, simulation, statistics, distribution.

Abstract: Our proposed system is an online food ordering system that enables ease for the customers. It overcomes the disadvantages of the traditional queueing system. Our proposed system is a medium to order online food hassle free from restaurants as well as mess service. This system improves the method of taking the order from customer. The online food ordering system sets up a food menu online and customers can easily place the order as per their wish. Also with a food menu, customers can easily track the orders. This system also provides a feedback system in which user can rate the food items. Also, the proposed system can recommend hotels, food, based on the ratings given by the user, the hotel staff will be informed for the improvements along with the quality. The payment can be made online or pay-on-delivery system. For more secured ordering separate accounts are maintained for each user by providing them an ID and a password. General Terms Cloud Computing, Wi-Fi

Keywords: Automated Food Ordering System, Dynamic Database Management, Internet of Things, Smart

Abstract: In our financial framework, banks have numerous items to sell yet fundamental kind of revenue of any banks is on its credit line. So they can procure from revenue of those advances which they credits. Past research in this period has shown that there are such countless techniques to examine the issue of controlling advance default. A vital methodology in prescient investigation is utilized to examine the issue of anticipating defaulters: The information is gathered from the Kaggle for examining and expectation. The advancement of innovation and execution of Data Science in banking, changes the substance of banking industry. The vast majority of the banking, monetary areas and social loaning stages are effectively contributing on loaning. Be that as it may, monetary foundations may confront enormous capital misfortune on the off chance that they affirmed the credit without having any earlier appraisal of default hazard. Monetary organizations consistently need a more exact prescient framework for different purposes. Foreseeing credit defaulters is a urgent assignment for the financial business. Banks have massively enormous measure of information like client's information, exchange conduct, and so on Information Science is a promising zone to handle the information and concentrate the secret examples utilizing AI strategies. Considering the magnitude of risk and financial loss involved, it is essential for banks to give loans to credible applicants who are highly likely to pay back the loan amount.

Keywords: Classification, Pre-processing, Prediction, Features selection, Generic algorithm, PSO algorithm, Naïve Bayes, decision tree, SVM, Random Forest.

Abstract: Physical games, both indoor and outdoor, play a major role in the formation of friendships amongst children and adolescents. But today, this form of play has been replaced by video games, where the relationships are often built through the computer/mobile screens, and this is especially true in the case of multiplayer video games. They have become a means for gamers to meet new and like-minded people. For instance, since the pandemic, the number of hours that gamers have spent gaming has increased considerably and the number of people who have played video games for the first time has also gone up. One of the reasons for this could be the very fact that these games help us build new relationships that could go on to be lasting, particularly due to the shared interests and the sense of belonging and community that they offer. This study was done with the goal of better understanding the impacts of video games' growing influence on younger generations. The focus of this paper is to study the effect that video games can have on social interactions, exclusively amongst students belonging to the age group of 16-21 years. Its goal is to raise awareness of the beneficial aspects of video games that are often overlooked, as well as to examine if they influence player behavior and, if so, to study these changes in behavior, with a focus on social interaction. A survey has been conducted to determine the same. We have also suggested measures to help and prevent people from crossing the line between recreation and addiction because, an innovation made for boredom could turn into an addiction, if not controlled. The null hypothesis is that there is no substantial difference in social interaction between gamers and non-gamers. Key words: Video Games, Social Interaction, Students

Abstract: The Indian dairy business has witnessed major changes. The country's transformation from a milk shortage state in the 1950s to the world's largest milk producer is remarkable. With a compound Annual Growth Rate of 4.7 percent, milk production has increased significantly and contributes 22% to the world's milk production. The dairy industry continues to be one of the most important sources of income for 80 million rural people. India has been the world's largest producer of milk since the White Revolution in the 1970s, with annual production of 198.4 million MT (2019-20). Digitalisation will have a profound impact on the ‘Milk Production’ segment in the value chain. In India, dairy farming is unorganized, so technology penetration is relatively less; however, in the last five years, a few start-ups have mushroomed in this space. These firms aim to increase farmer productivity and reduce wastage. Supply chain of the Indian dairy industry is quite complex owing to its dependency on various factors such as ambient temperature, availability of cold chains and shorter shelf life. The fragmented Indian dairy industry further adds to the complexity. Digitalisation solutions such as the IoT and advanced analytics can help by sharing real-time data with different stakeholders, and detecting any deviations in the quality and quantity of milk during phases of transportation in the value chain. Thus, digitalization of the dairy sector could help the farmers and the industrialists for efficient management at each stage of processing

Abstract: The security of PC systems assumes a vital part in current PC frameworks. With a specific end goal to uphold high assurance levels against noxious assault, various programming apparatuses have been as of now created. Interruption Detection System has as of late turned into a warmed research subject because of its capacity of recognizing and keeping the assaults from noxious system clients. An example coordinating IDS for system security has been proposed in this paper. Numerous system security applications depend on example coordinating to separate the danger from system activity. The expansion in system speed and activity may make existing calculations to end up an execution bottleneck. In this way it is extremely important to grow quicker and more proficient example coordinating calculation so as to defeat the inconveniences on execution.

Keywords: Enemies, Effect of adversaries, Security.

Abstract: Edge detection is a technique of image processing used to identify points in a digital image with discontinuities, simply to say, sharp changes in the image brightness. Edge detection algorithm finds numerous applications in image segmentation and data extraction in areas such as image processing, computer vision, and machine vision In This paper, certain important methods on edge detection generally applied in image preprocessing has been presented. A detailed analysis of various edge detection algorithm has been covered with suitable illustration were ever necessary. The paper also serves as aid for researchers working in this direction. Key Words: Edge, Image Processing, Edge Detection.

Abstract: Gender identification is considered to be one of the major problems in the field ofsignal processing. Formerly, this problem has been solved using various image classification techniques which typically includes information extraction from aset of images. However, gender classification using vocal features has recently been a topic of interest to a lot of researchers across the globe.

Keywords: Voice, Gender identification,etc.

Abstract: Now-a-days, deep learning plays a vital role in the field of machine learning. Deep learning is derived from the concept of artificial intelligence. The major advantages of using deep learning is effective, supervised, reduced cost and time efficient machine. Deep learning allows various procedures and topographies for the input data to be sent into an algorithm for processing to produce required output. Deep learning is used in various applications and mainly for security purposes. Domains which are running by using deep learning are education, science and technology, medical science in the job of cancer detection, stock market analysis, natural language processing, face recognition and many more. The most complicate process in deep learning is training deep neural networks, because, each and every input layer has to be trained in the manner of using parameters to produce required output. This process may slow the entire process, in the form learning rates and initialization of parameters. By using an appropriate algorithm like Multilayer perceptron neural network (MLPNN) which is forward technique of Artificial Neural Network (ANN) that can be used for back propagation training, convolutional neural network (CNN) which is used for analyzing visual image based on shared-weights architecture and translation invariance characteristics, recurrent neural network (RNN) which develops a connection between the nodes in the directed graph, generative adversarial network (GAN) which acts as a two neural network and used for gaming process, deep belief network (DBN) which helps to develop a graphical model of an input data under several layers of perceptron and many more. Deep learning mechanism allows user to intercept an input to many layers of perception until the required output is obtained. This paper is designed in the process of deriving the super concept of normalization in deep learning architecture for training the input data sets. Normalization is a new technique for training data seta and also activating hidden data sets in the neural network. It uses the unbiased technique in gradient variations for input data sets. Gradient variation helps to develop the model in various layered perceptron. This normalization can also be implemented for statistical data analysis. Normalization is also helps to identify the minimum and maximum values among the data sets. If huge number of data sets is processed, then normalization allows batch process to train the data sets.

Keywords: Artificial Intelligence, Machine Learning, Neural Networks, Generative Adversarial Network, Normalization, Gradient Variations.

Abstract: Cardio Vascular Disease (CVD) is a leading cause of death worldwide. It is also called heart disease. As per the WHO report, around 17.9 million people die every year from Cardio Vascular Diseases, an estimated 31% of all deaths globally, and patients die mainly because of non-appropriate and un-affordable treatment. Heart related diseases are a worldwide major health crisis in the present scenario. This disease can be curable with early diagnosis and proper treatment[1][2]. The purpose of this paper is to establish some predictive analytical models using Machine Learning algorithms by taking a real time CVD dataset. In this paper, we have shown some experimental observations with the help of some Machine Learning classification algorithms, and also shown a clear vision on the predictive analysis on medical diagnosis of the Cardio Vascular Disease(CVD) using Machine Learning algorithms using which patients may get benefited by the accurate result for the better diagnose in their early treatment.

Keywords: Algorithm, Cardio Vascular Disease, Classifier, Machine Learning, Predictive Analysis.

Abstract: Data mining for healthcare is an interdisciplinary subject of research that has its roots in database statistics and may be used to assess the efficacy of medical treatments.. Diabetes is a chronic disease in which the pancreas fails to make adequate insulin or body fails to utilize the insulin that is produced appropriately. In the health-care business, data analysis plays a critical role in illness identification. The proposed research is being carried out to compare the performance of various classifiers in the Ada-Boost learning environment. We employed three distinct algorithms in this regard: BPN (back propagation neural network), SVM (support vector machine), C4.5 decision tree, and classifier. The ada-boost learning approach is used to train all of the algorithms. The diabetic disease type dataset from the UCI machine learning data repository is utilized in CSV format for training and testing developed classifiers. Hence, we implemented proposed hybrid classification system using the JAVA WEKA machine learning library. The performance of the system for all the classifiers is calculated and compared in terms of Accuracy, Error Rate, Time and Memory usages based on various experiments and datasets. Furthermore we also compared our system to the traditional base Decision Stump method.

Keywords: Data Mining, Machine Learning, Classification, Dataset, ensemble learning, boosting, Ada-Boost, diabetes disease, Prediction.

Abstract: To answer the research questions, it is always doubtful that researcher should be ready to collect data from the cases happening around. Thus, there is a desire to pick out a sample for correct checking. Here this paper presents the steps to go through to conduct sampling. Furthermore, as there are differing kinds of sampling techniques/methods, here the right understanding of researcher is needed to opt the right sampling method for the research. In regards, this paper also presents the various forms of sampling techniques and methods that helps us to make a transparent vision. Key words: Non-Probability Sampling, Sampling Method, Sampling Technique, Research Methodology and Probability Sampling.

Abstract: Agriculture is the backbone of countries like India. Water crisis also arises often depending on the season and the locality especially tropical states like TamilNadu. In order to use the resources wisely and also make the farmer use technology to make work simple the IoT concepts are implemented. Also some crops are not in need of lot of water but the water is sent through pathways throughout the field. This can be replaced by spraying technique by implementing IoT technology using a wireless network. A system is proposed which uses the water wisely and checks the temperature, humidity, capture using a camera and then data aggregation takes place and is sent to the peasant mobile as a SMS/MMS. The system can be implemented using a Arduino board. The data can be transferred using a wireless medium. The agriculturist may be made smart by learning and utilizing these modern concepts. The water usage can be reduced to a larger extent and the Mother Nature can be preserved from exploiting the natural resources.

Keywords: Agriculture, IoT, water, wireless networks, Arduino, water

Abstract: Uncontrolled medicine administration can always show unpropitious effects on the health of the patients. The proposed system is designed to help the patients to take the required medicine in the right quantity at the right time. The basic ideology is, integrating the principle of LCD, messaging system, buzzer along with motor driver circuit on a normal pill box. To make it more state-of-the-art, it is inbuilt with a GSM module for alerting the patient at the needed instant. This project presents a Smart Medicine Reminder Box (SMR) prototype. The main purpose of this system is to help the patients, primarily seniors, take their medications on time in an easy way without the possibility of missing pills, also reduce the risk of over or under dosing accidentally. Not taking medications correctly can have serious consequences such as delayed recovery, illness and even death. The smart medicine Reminder Box (SMR) could solve such problems by informing and alerting the patients to take the appropriate dose at the right time. Also, it provides direct communication between the patients and the care givers as it will immediately notify the care giver in case the patient missed his/her pill. In addition, SMR provides the user with a touch interface available as an application on their smartphone which will allow them to remotely manage and control pill schedules and usage data.

Keywords: SMR. GSM, medication adherence, pill box, motor driver circuit, medication

Abstract: Result varies from student to student, institution to institution, year over year, due to various reasons. This system is developed for prediction & analysis of the upcoming university results by considering certain dependent parameters. This project is based on data mining and analysis of the extracted data from the result sheets. The project outputs a prediction value which is near to the expected value with variance.

Keywords: Regression, Multiple Linear Regression(MLR), Data Mining, Hypothesis, Exam Result Analysis.

Abstract: Routing in delay tolerant networks is a challenging problem due to the intermittent connectivity between nodes resulting in the frequent absence of end-to-end path for any source-destination pair at any given time. Recently, this problem has attracted a great deal of interest and several approaches have been proposed. Since Mobile Social Networks (MSNs) are increasingly popular type of Delay Tolerant Networks (DTNs), making accurate analysis of social network properties of these networks is essential for designing efficient routing protocols. In this work, a new metric that detects the quality of friendship relations between nodes accurately is introduced. Utilizing this metric, each node defines the community of nodes having close friendship relations with it either directly or indirectly. Later Friendship-Based Routing algorithm is introduced which uses this community information in forwarding of messages. Extensive simulations show that the introduced algorithm works efficiently.

Keywords: Social Network, MSN, DTN, Routing protocols, Metrix

Abstract: COVID-19, a deadly disease originated in 2019 is still affecting millions across the globe and has become a global pandemic. The virus is continuously mutating and Omicron being the latest mutated variant (2022). Most nations had to take measures to react to the sudden and rapid outbreak of COVID-19 within a relatively short period of time. Because radiographs such as X-rays and computed tomography (CT) scans are cost-effective and widely available at public health facilities, hospital emergency rooms (ERs), and even at rural clinics, they could be used for rapid detection of possible COVID-19-induced lung infections. Therefore, toward automating the COVID-19 detection, in this paper, we propose a viable and efficient deep learning-based chest radiograph classification (DL-CRC) framework to distinguish the COVID-19 cases with high accuracy from other abnormal (e.g., pneumonia) and normal cases. A unique dataset is prepared from four publicly available sources containing the posteroanterior (PA) chest view of X-ray data for COVID-19, pneumonia, and normal cases. Our proposed DL-CRC framework leverages a data augmentation of radiograph images (DARI) algorithm for the COVID-19 data by adaptively employing the generative adversarial network (GAN) and generic data augmentation methods to generate synthetic COVID-19 infected chest X-ray images to train a robust model. The training data consisting of actual and synthetic chest X-ray images are fed into our customized convolutional neural network (CNN) model in DL-CRC, which achieves COVID-19 detection accuracy of 98.94% compared to 54.55% for the scenario without data augmentation (i.e., when only a few actual COVID-19 chest X-ray image samples are available in the original dataset). Furthermore, we justify our customized CNN model by extensively comparing it with widely adopted CNN architectures in the literature, namely ResNet, Inception-ResNet v2, and DenseNet that represent depth-based, multi-path-based, and hybrid CNN paradigms. The encouragingly high classification accuracy of our proposal implies that it can efficiently automate COVID-19 detection from radiograph images to provide a fast and reliable evidence of COVID-19 infection in the lung that can complement existing COVID-19 diagnostics modalities. H5 model in Convolutional Neural Networks (CNN) is a new innovation done by us. CNN (Convolutional Neural Network) is a popular NN algorithm and it clearly outperforms Artificial Neural Networks (ANN) and Recurrent Neural Networks (RNN) in this project. Inception V3, ResNet50, MobileNet and Xception [1] are the existing CNN models but are found to be less accurate and more time consuming. In our R&D lab we have developed a new CNN model called the H5 model. It is the best fit after the output is obtained from Haar Cascade Classifiers. A model which was developed for facial detection and distinction is now used for all objects detection with more accuracy focusing on five regions with different pixel Intensity scheme. The encouragingly high classification accuracy of our proposal implies that it can efficiently automate COVID-19 detection from radiograph images to provide a fast and reliable evidence of COVID-19 infection in the lung that can complement existing COVID-19 diagnostics modalities. In our previous paper on CNN we had exhibited one channel output. In this paper we will deploy the designed model onto heroku cloud. We prefer our model to be deployed in the cloud platform, for global access of our AI application.

Abstract: The design and simulation of a rectangular pyramidal horn antenna at 2GHz are described in this work, which may be utilized in electromagnetic sensing, antenna calibration, microwave heating and different wireless communication systems. Pyramidal horn antennas have many merits such as simple in manufacturing low fabrication cost, moderate bandwidth; because of these merits, they find more applications in electromagnetic compatibility measurements and radars. To design the desired horn antenna a maximum gain of 15 dB at 2 GHz is considered and the range of frequency chosen is 1.6 to 2.4GHz, which is often L-band or S-band. The horn antenna design and its simulation are explained in this study. ANSYS HFSS software was used for the simulation. A gain of 12.94 dB was attained at 1.96 GHz, according to the simulation results.

Keywords: ANSYS HFSS, Horn antenna, Radiation pattern, Gain

Abstract: The massive growth of energy consumption by buildings and release of huge amount of carbon footprints by resources such as air conditioners motivated to develop eco friendly solutions for room temperature monitoring. As a result task scheduling has drawn attention in which limited resources can be efficiently utilized to consume less energy. In this paper, we compare different scheduling policies in terms of energy efficiency for room temperature monitoring. Finally a solution is provided to efficiently reduce the energy consumption.

Keywords: Scheduling, Cyber Physical Systems, Energy Consumption, Makespan

Abstract: In sporting out a hit E-Commerce , the maximum critical matters are innovation and information what client wants. Now-a-days the benefit of the usage of ecommerce encourages the clients to shop for the usage of ecommerce. It runs on the idea of innovation having the capacity to enthral the clients with the merchandise, however with any such big raft of merchandise go away the clients pressured of what to shop for and what now no longer to. According to enterprise , a organization may also create 3 segments like High ( Group who buys often , spends greater and visited the platform lately ) , Medium ( Group which spends much less than excessive organization and isn’t always that lots common to go to the platform) and Low (Group that’s at the verge of churning out ). This is wherein Machine Learning presents a critical answer, numerous algorithms are implemented for revealing the hidden styles in statistics for higher selection making. In this paper we proposed a client segmentation idea wherein the consumer bases of an established order is split into segments primarily based totally at the clients’ traits and attributes. This concept may be utilized by the B2C businesses to outperform the opposition through growing uniquely attractive services and products and make it attain to cappotential clients. This method is carried out the usage of “K-Means”, an unmanaged clustering device mastering set of rules.

Keywords: Innovation, B2C, Machine Learning, E-Commerce, K-means Clustering, Client segmentation, Innovation, RFM Analysis, Loyalty Level, Cluster Creation, Business segments, Market Basket Analysis.

Abstract: CNN classification is a big name in the field of image classification, segmentation of images and Natural Language Processing (NLP). The processing of medical images can be done by CNN to diagnose diseases. We will study the working of CNN and every individual component’s working. Along with that, we will analyze other researchers' work in this field and review their work in this paper. We will work on the solution to the real-life problem of the lack of healthcare professionals and the high cost of healthcare facilities. We will discuss how a multilayer perceptron approach can solve this real-life problem with computational ability.

Keywords: CNN, Convolution Neural Network, medical e-Diagnosis, computer vision, deep learning

Abstract: Air pollution is a very serious problem facing urban the dwellers where various types of dangerous and poisonous air pollutants are discharged directly into the atmosphere on daily basis as a result of increased industrial and human activities due to increase in population and urbanization. These pollutants have serious and adverse impact on health and well-being of human beings and the environment. Air pollution prediction or forecasting can be adopted to predict or forecast the air quality index (AQI) of a city or area in advance before pollution occurs. This is helpful where air pollution monitors or stations are not installed or deployed. Awka Metropolis, the focus of this research, is a rapidly growing city due to the rising influx of people into it within the last ten years. The rapid population growth in Awka is as a result of it several important factors such as infrastructural, industrial and economic developments. Awka as a growing city has its own fair share of urbanization and environmental challenges. In this paper, ensemble technique of machine learning was used to develop a prediction model for air pollution one hour before time for PM2.5 (particulate matters) pollutant emissions within Awka Metropolis. A historical dataset consisting of about 12,958 one-minute of sensor readings for several air and noise pollutants such as PM1, PM2.5, PM10, TVOC (volatile organic compound), carbon dioxide, noise as well as historical weather or meteorological data comprising air temperature, humidity, pressure, light intensity were also used as input predictors to the model. Seven machine learning algorithms comprising about three traditional machine learning algorithms such as Linear Regression, Multi Layer Perceptron (MLP) Artificial Neural Network (ANN), Decision Tree, and four ensemble learning algorithms - Random Forest, XGBoost, AdaBoost, Extra Tree were used in the simulation modeling. Experimental results showed that the ensemble algorithms performed best in prediction accuracy having highest R2 values and lower RMSE (Root Mean Square Error) and MAE (Mean Absolute Error) scores. Random Forest and Extra Trees ensemble algorithms came first with the highest accuracy score (R2=0.9886), followed by XGBoost R2=0.9870, AdaBoost came fourth with R2=0.9854. Equally the ensemble learning algorithms have the lowest prediction residual errors when compared to the traditional machine learning algorithms. The experimental test-bed and programming was carried out in Anaconda, Python 3 and Python machine learning module Scikit-learn. Jupyter Notebook IDE was used as programming development and simulation environment.

Keywords: Air Pollution, Regression, PM2.5, Ensemble, Ensemble Algorithm, Machine Learning.