International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control EngineeringA monthly Peer-reviewed & Refereed journal
IJIREEICE meets the suggestive parameters outlined in the latest University Grants Commission (UGC) for peer-reviewed journals, ensuring high standards of research integrity, publication ethics, and academic excellence.
Miss. MAYURI D. NAITAM, Miss. CHAITANYA P. POFLEY, Miss. NEHA H. DARUNDE,Mr. MANOJA.TIKHAT, Mr. ANIKET S. BELEKAR, Prof. R. C. Rajurkar, Prof. A. V. REKKAWAR
Stability Robustness Bounds for State-Space Models with Dependent Uncertainty: Application to a Microgrid System
Sri R. Kolla, Md Samiul Mohsin
DOI: 10.17148/IJIREEICE.2022.10701
Abstract: In this paper stability robustness bounds for linear state space models with dependent uncertainty based on the Lyapunov stability method and time-invariant perturbation method are applied to a microgrid system. In contrast to previous observations, it is shown that the Lyapunov stability bound gives better result than the time-invariant perturbation bound for a dependent uncertainty for the open-loop microgrid system. It is also shown that the Lyapunov stability bound gives larger value for the closed-loop microgrid system with the linear quadratic regulator control.
Shivaramu H T, Mohammed Yaseen, Loyal Aaron Noronha, Mahammed Javid, Rithvik S Shetty, Chinmay N Naik
DOI: 10.17148/IJIREEICE.2022.10702
Abstract: Farmers suffer losses as a result of crop damage caused by animals and birds during the stages of sowing, seeding, ripening, and harvesting. Traditional methods of controlling bird and animal attacks, such as beating drums, screaming, lighting fireworks, and using reflective materials, are less effective when used on daytime attacks by birds and animals. Surveillance, as is well known, is widely used in a variety of settings, including homes, hospitals, schools, public spaces, farms, and so on. It allows us to keep an eye on a specific area, prevent theft, and provide proof of evidence. Monitoring is critical in the case of farmlands or agricultural grounds to both protect the environment and prevent unauthorized individuals from entering the region area from animals. Image processing techniques, night vision cameras, and IoT technologies will undoubtedly solve these problems. This system is capable of repelling animals from agricultural fields when they attempt to intrude; the system is outfitted with different triggering systems based on animal type. It has a loud noise generator for larger animals like elephants and a rotten egg sprayer for smaller animals like deer and boar. At first, these animal movements will be detected by passive infrared and microwave sensors, which will turn on the camera for image processing following successful animal detection. The primary goal of this work is to increase food production rates, prevent economic losses for farmers due to animal intrusions, and bring a smile to the farmer community.
Miss. MAYURI D. NAITAM, Miss. CHAITANYA P. POFLEY, Miss. NEHA H. DARUNDE,Mr. MANOJA.TIKHAT, Mr. ANIKET S. BELEKAR, Prof. R. C. Rajurkar, Prof. A. V. REKKAWAR
DOI: 10.17148/IJIREEICE.2022.10703
Abstract: This paper presents an idea or a concept for home automation using ESP32 with Blynk, IR remote and manual switch to control 8relays with internet and monitor the real time feedback in the Blynk app. Automation of device has a wide scope for this generation as well as in forthcoming generation. In this mobile communication technology is playing a major role in the world of automation. This articles is fully based on low cost and reliable home control monitoring system for accessing and controlling devices and appliances remotely using Android based smart phone application. while using this technology the system improves the living standard at home, reduce human effort, energy efficient and time saving and thus make a smart home. And also it is very helpful for providing support to disable people and fulfill their needs in home and thus they leads a normal life. This propose system consists of Android mobile in using ESP32 with Blynk app, IR remote & Manual control relays. We are a using Wi-Fi technology to monitor the device because of its accuracy, high range and instant connectivity. This module controls the home appliances with a very ease of installation and it is user friendly.
Keywords: Smarthome, IoT, Home automation, Sensors, IOT.
DETECTION OF STANDARD DIMENSION OF NUT AND BOLT AND THEIR SEGREGATION
Mrs . B VijayaNirmala, Mrs. Gonuguntla Kousalya, Mr. Manohar Y S, Mr. Adarsh C S, Mr. T S Varun
DOI: 10.17148/IJIREEICE.2022.10704
Abstract: Most of the Industries are growing faster these days and they need most accuracy results in every product they develop. Especially in the automotive mechanical industries which manufacture nuts and bolts. There is need to design a system that is recognises the nuts and bolts and it’s dimensions. For these type of segregation and detection the most prominent technology that is “ CONVOLUTION NEURAL NETWOK” algorithms are used by the most of the industries. When coming to CNN it is a type of artificial neural network used for image recognition , image processing and specifically designed to process pixel data.
Descriptive study to assess knowledge regarding the management of patients with psychosomatic disorders among Nurses in selected Hospitals of Gwalior
Jyoti Walia, Prof. Vishnupriya Knnan, Mr. Ram Prasad
DOI: 10.17148/IJIREEICE.2022.10705
Abstract: BACKGROUND: The general hospital psychiatric care is most important since 30-50% of the patients attending primary care levels or general hospitals suffer from various forms of psychosomatic disorders, but they complain only vague symptoms which cannot be diagnosed medically. So, nurses working in general hospitals setting can help these clients by assessing and proper psychosocial care should be given for a permanent relief.
Abstract: Wind energy is the most available form of renewable energy among all the energy sources. Wind energy can be extracted by a wind turbine and can be converted into electrical energy using proper electricity generating apparatus. This paper is focused on a technique that can be used effectively for the purpose of converting the kinetic energy of wind into electrical energy. This process is completely friendly to environment and the cost associated with the fabrication is very little. In this research a vertical axis wind turbine has been designed and fabricated to perform the job of extracting energy from wind. The turbine is of Darrieus type with three twisted blades. For the conversion of mechanical energy from the turbine into electric current an alternator also fabricated and coupled with the turbine. This paper describes the whole procedure to build up a simple wind power system with vertical axis wind turbine and shows performance of such power system under various wind speed. The specialty of this system is its extremely simple arrangement and absence of any motion transmission
TRAVEL HANDS FREE and ACCESS AUTHENTIC TOURIST PLACE INFO USING QR CODE
Sindhu.R, Chandan.M.N
DOI: 10.17148/IJIREEICE.2022.10707
Abstract: Cultural heritage comes to life if it can effectively spread knowledge and foster societal cultural development. Therefore, communication is essential for giving visitors—especially tourists—information. Connecting with clients in the heritage business requires the use of information technology, which offers a variety of channels via which information can be provided. The quality and quantity of visitors' interactions with heritage can be improved thanks to technological developments like QR Code that have increased in recent years. On signs and advertisements, there are squares with a black-and-white pattern known as quick response (QR) codes that link to more information. Numerous uses for QR codes have been developed throughout time. They were initially created in the middle of the 1990s as a more practical alternative to traditional barcodes for usage in the automotive industry.
Abitkar Suraj M, Dange Akash S, Desai Shambhuraje B, Warke Prathamesh D, Ghatage Abhishek B, Prof. S. J. Bardeskar
DOI: 10.17148/IJIREEICE.2022.10708
Abstract: Automatic tiles cleaner is a system that enables cleaning of the tiles by the help of highly stabilized and rapidly functionalized electronic and mechanical control system. Current project work targets to use automatic tiles cleaner for large tiles in house-hold purposes and office tiles. The cleaning purpose is specifically carried out by continuous relative motion between a scrubber and the tiles surface. During the cleaning and moving operation of vehicle a propulsion mechanism such as driven wheels and guide wheels for the dry tracking on the floor surface to be cleaned, suction of water is carried out by vacuum pump, scrubbing action is done by the scrubber directing water towards rear end. Preferably, a sweeper mechanism is mounted on the body forwarded by propulsion mechanism and operated with such control system for advance sweeping of a debris-laden floor surface. A PID controller is used to govern the motion of system which takes the input from sensor circuit and feeds it back to microcontroller which gives rise to the simulation of wheel in a synchronized manner. The new automatic floor cleaner will save huge cost of labor in future. The basic advantage of this product is that it will be cost effective and no human control is needed. Once put in on mode it will clean the whole room without any omission of surface.
Abstract: Electrical discharge machining (EDM), also known as spark machining, spark eroding and die sinking machining process, is a metal removal process where desired shape can be obtained by using electrical discharges (sparks). Material is removed from the work piece by a series of rapidly recurring current discharges between two electrodes, which is separated by a dielectric liquid and subject to an electric voltage. EDM is one of the efficient machining processes for manufacturing geometrically complex or hard material parts that are extremely difficult-to- machine by conventional machining processes. Inconel 825 is a family of austenite Nickel-Chromium based super alloys and having wide application in numerous engineering fields. The presented study provides a valuable insight for the selection of the process parameters setting in Electrical Discharge Machine (EDM) in order to minimize electrode wear ratio (EWR) by using copper electrode materials. It is found that optimal process parameters setting is Ton1Toff1Vg2Sg1 for minimizing EWR. The results clearly depict that the combination of independent process parameters i.e. Ton, Toff, Vg and Sg is found as 100, 20, 60 and 005 for optimizing EWR
PACKET INSPECTION TO IDENTIFY NETWORK LAYER ATTACKS
Sarvesh Ganesh Hegde, H.P.Mohan Kumar
DOI: 10.17148/IJIREEICE.2022.10710
Abstract: In the recent years, the usage of internet is at its peak. As the usage of internet increases the number of people who will try to make money in an easy way through the growing internet also increases. In order to do achieve this the attacks on the user’s computer system happens so that the hackers can collect the user’s data and can be used for various purposes. Such attacks take place just by inserting the spoofed packets into the user’s line of communication in the network. To prevent this type of attacks bifurcation of the incoming and outgoing packets from a system’s network can be an accurate solution. To achieve such bifurcation between the normal packets and spoofed packets the model is developed using Deep Learning algorithm. By using the Deep Learning algorithm Long Short-Term Memory the user can obtain a comparatively higher accuracy.
Keywords: Deep Learning, Long Short-Term Memory, LSTM, Packets, Attack, Network
A Patient Health Information Exchange Using Aws S3 Service
Madhu Sudhan K N, B M Bhavya
DOI: 10.17148/IJIREEICE.2022.10711
Abstract: Health information exchange (HIE) has several impressive advantages for patient care, including raising the standard of medical treatment and accelerating the coordination of care. In order to transfer data ownership from providers to patients, the Office of the National Coordinator (ONC) for Health Information Technology is looking for patient- focused HIE ideas. The existing system faces several obstacles to patient-centric HIE, including worries about security and privacy, inconsistent data, and slow access to the appropriate information across numerous healthcare facilities. This project uses the distinctive property of the AWS technology, which is regarded as "extremely secure," to propose a workable solution to these problems. We created an AWS architecture to safeguard patient privacy and data security, maintain data provenance, and give patients complete access to their medical information. This design achieves patient- centric HIE by personalizing data segmentation and creating an "allowed list" for clinicians to access their data. This patient-centered HIE method assessed the model's viability, stability, security, and robustness statistically.
Keywords: AWS S3 Service, Electronic Health records (EHR), Health Information Exchange (HIE), Medical Prescription.
ATTRIBUTABILITY OF SPURIOUS MEDICINE SUPPLY CHAIN THROUGH BLOCKCHAIN
Vismaya S M, Chandan M N
DOI: 10.17148/IJIREEICE.2022.10712
Abstract: Healthcare supply chains are complex networks that span organizational and geographic boundaries and act as the structural foundation for a variety of services that are necessary for daily life. Due to the inherent complexity of such systems, it is possible to introduce impurities like false data, a lack of transparency, and a shoddy data provenance. The creation of spurious pharmaceuticals, which not only has a significant detrimental effect on people's health but also costs the healthcare industry a lot of money, is one effect of these limits within the present supply chains. The need for a robust, end-to-end track and trace system for pharmaceutical supply chains has thus been highlighted by a recent study. To assure product safety and eliminate fakes, the pharmaceutical supply chain needs a comprehensive product recall procedure. Healthcare supply chains encounter difficulties with concerns relating to data privacy, openness, and authenticity because the majority of track and trace systems now in use are centralized. In this study, we suggest a block chain-based strategy for effective product tracing in the healthcare supply chain that makes use of smart contracts and decentralized off-chain storage. To ascertain how successfully the system can enhance attributability inside pharmaceutical supply chains, we test and confirm it before providing a cost and security analysis.
Mrs B VijayaNirmala, Deepika Singh J, G Harshita Reddy, Dimple Chowdri M, Dhanyatha V
DOI: 10.17148/IJIREEICE.2022.10713
Abstract: The aim of image processing is to help the computer to understand the content of an image. OpenCV is a library of programming functions mainly used for image processing. It provides de-facto standard API for computer vision applications. We can solve many real time problems using image processing applications. In this paper, sample real time image processing applications of OpenCV are discussed along with steps.
An additional web-camera extension can also be used, for multiple usage such as to operate and record the operation. A inverted mask has been created to save the content written in air as .PNG file using screenshot. In Gesture Based Visual Writing System, we have implemented gesture controlled real time application [ex: .ppt] , including various gestures to operate namely thumb finger open for previous slide, little finger open for forward slide, fore finger open to write/doodle, fore-middle-ring fingers open to erase doodle, thumb and little finger open for screenshot , thumb-fore-little fingers open for pseudo screen.
Abstract: A method for authenticating drivers and identifying vehicles as part of the development of smart cities. It contains a centralized database where all of the approved cars are kept, as well as Unique Id vehicle tags. A vehicle is given the Unique Id tag. Identification of vehicles is simple to perform. The monitoring of the driving license system is a major duty of the government. While the traffic cops are inspecting the paperwork, there are numerous illicit operations. Both sides will commit the crime (people and police). To solve this issue, the traffic police are given access to a further Smart-No module that is coupled with a centralized database that houses the data from person licenses (DLs). If the user selected Smart-No, the software would inform you if they held a valid license or not. This may be accomplished by connecting the centralized database and the vehicle information.
Keywords: AWS S3 Service, Smart No, Unique VehicleID tag
Review on Enhancement of Power Quality in the Grid Connected Wind Energy System using STATCOM
Sanyukta J. Awaghate, Mr. V.M. Harne
DOI: 10.17148/IJIREEICE.2022.10715
Abstract: This paper discusses how to improve power quality for effective power transfer in a grid-integrated wind energy system. The system is a wind energy conversion system based on a renewable energy farm. The system is subjected to frequent disruptions in AC loads and renewable farm power output. As a result, there is a reactive power mismatch, which causes voltage instability and power quality issues. This gap can be closed by using a variable reactive power source, such as a static synchronous compensator. Three case scenarios of the system are tested to compare their dynamic and transient performances: (A) standalone mode, (B) grid-integrated without STATCOM mode, and (C) grid- integrated with STATCOM mode. The result will be based on the fault created on the wind system, which will be classified and controlled by STATCOM.
Keywords: Grid, Power Quality, STATCOM, Wind Turbine.
Abstract: The Smart Placement Co-Ordinator Android application is available for portable devices.The Android program is simple and user-friendly and it aids college students in planning their placement activities. The application is made up of three essential components: Student, Company,and Placement Cell. This application can be used to handle data about students and employers for placement by the college placement cell. The application also makes it possible for the placement cell to view comments made by companies that come to the college to recruit students, including input on the institution's hospitality, the plans for placements, the students' skills and employability, etc. The application gives students access to details about the business visiting college for placements. Because the student can only see the list of positions for which he/she is eligible to apply, there is less clutter. The application enables the learner to submit an application for the job as well. Every time a visiting company advertises its job requirements, the qualified students will be contacted by SMS. The application allows organizations that come to the university to recruit to post details about their business, job descriptions, and requirements. Employers have the ability to offer feedback on the college hiring process.
Keywords: Android, mobile, placement, business, Short Message Service.
Autonomous Driving Vehicle Using IOT And Artificial Intelligence
Shivaprasad G, M N Chandan
DOI: 10.17148/IJIREEICE.2022.10717
Abstract: This work we are automated the vehicle using the IOT components like Raspberry Pi 3B+, Arduino Uno, pi Camera, Motor driver and other sensors. Whole idea of this work is to Build the new generation smart vehicle which works without any human intervention and Vehicle traveled on the road. In our Work vehicle will run in two modes Automated mode and Manual mode, when we have the proper road witch suites for self-driving like clear lane, clear Traffic signals and other requirement’s, we use Automated mode otherwise we can change into Manual mode and Drive the vehicle.
Abstract: The agricultural industry is increasingly in peril from climate change and other environmental issues. Machine learning is a key tactic for identifying practical and effective solutions to this problem (ML). The technique of predicting crop involves making projections about the crop's output based on historical information such as weather, soil, and prior crop yields. Due to the agriculture industry's rapid innovation and liberalised market economy, accuracy in crop prediction is necessary (CP). For accurate prediction, machine learning (ML) techniques and the selected attributes are crucial. The performance of any ML algorithm may be improved by employing a special set of features from the same training dataset. This study evaluates the crucial elements of a precise CP.
Predicting the Price of Bit Coin using Machine Learning
Indu B T, Dr. H R Divakar
DOI: 10.17148/IJIREEICE.2022.10719
Abstract: The price of cryptocurrencies, particularly Bitcoins, has increased significantly in recent years, reaching a high of $19,783 USD in 2017 and a more recent high of about $4,000 USD. $40,001 USD in January 2021. Due to the extremely volatile Having a propensity towards manipulation, there have discussions on whether it is worthwhile to invest in the bitcoin market. This undertaking is what we aim to accurately forecast changes in the price of bitcoin creating investment strategies that can be traded on Binance utilising convolutional and recurrent neural networks superior to the standard strategy of holding inactively assets. The inputs to our algorithms are at the nanoscale level. the volume traded, the high, low, open, and close prices, all displayed as exchange rates in US dollars. The quantity of Bitcoin exchanged on the Binance platform an open market. Our system will then forecast the direction. putting the new understanding of Bitcoin price turbulence to use in the next minute algorithms.
Keywords: Cryptocurrency, Bitcoin, Recurrent neural network, Long short term memory.
Abstract: Cultural heritage comes to life if it can effectively spread knowledge and foster societal cultural development. Therefore, communication is essential for giving visitors—especially tourists—information. Connecting with clients in the heritage business requires the use of information technology, which offers a variety of channels via which information can be provided. The quality and quantity of visitors' interactions with heritage can be improved thanks to technological developments like QR Code that have increased in recent years. On signs and advertisements, there are squares with a black-and-white pattern known as quick response (QR) codes that link to more information. Numerous uses for QR codes have been developed throughout time. They were initially created in the middle of the 1990s as a more practical alternative to traditional barcodes for usage in the automotive industry.
SURVEY ON - BRAIN TUMOUR DETECTION USING CONVOLUTIONAL NEURAL NETWORK
Dr. Syed Salim, Sahana S, Yashaswini M S, Sanjana H K, Sneha C
DOI: 10.17148/IJIREEICE.2022.10721
Abstract: Clinical professionals still find detecting a brain tumor to be a very difficult and time-consuming process, despite substantial advances in medical technology. Early and correct diagnosis of brain tumors may help with their successful and efficient treatment. Higher levels of predictability might improve the efficiency and precision of the automatic identification and therapy of brain tumors. Although it is generally acknowledged that the accuracy performance using automatic identification and tracking systems varies from methodology to technology and frequently depends on the computer vision applications, this is not always the case. This paper examines the advantages and disadvantages of contemporary detection methods.
Company Reputation using Sentiment Analysis using Twitter Data
Soham Kolhe, Ankur Konwar, Anand Saxena, Aditya P. Kamble
DOI: 10.17148/IJIREEICE.2022.10722
Abstract: The data from the Twitter sentimental analysis experiment has gained much renown as a topic of research. The potential to obtain information about public opinion by breaking down Twitter data and automatically classifying its sentimental polarity has consistently attracted researchers due to the concise language commonly used in tweets. The aim of this study was to use the Valence Aware Dictionary for sEntiment Reasoner (VADER), to classify the sentiments expressed in Twitter data. In this study, we developed a generic tool for analyzing tweets. We used VADER to categorize tweets on a particular keyword to predict recent trends about it. We successfully used the generated tool to classify multilingual tweets on any keyword to analyse public opinion.
Keywords: Natural Language Processing, NLP, Twitter, sentiment analysis, VADER.
Abstract: Vehicle theft has increased significantly in several nations as a result of the growth of vehicles. The safety of the car may thus depend heavily on a vehicle theft monitoring equipment. Theft of vehicles has been a major issue in recent years, and it needs to be tracked, recognized, and regulated. Safety and defense of the vehicle are essential. The GSM is the component that connects the DC motor. Using a GPS app and the wireless module, it was possible to locate a vehicle. As a satellite-based navigation system, a GPS system can precisely locate a car in any weather. A GPS device provides the position's latitude and longitude. With the aid of a GSM module that is connected to the vehicle, the owner may now manage the ignition of the vehicle and start or stop it with the simple click of a message.
Keywords: GSM Technology, Vehicle Tracking, GPS, Internet of things (IoT), SMS, Motor, GSM modem, Ignition key.
Abstract: Individual security is under real danger from suspicious exercises in open areas. Many different video surveillance systems are used in open areas, like as streets, jails, blessed places, airports, and grocery stores. Even during ongoing operations, video reconnaissance cameras lack the intelligence to detect irregular exercises. Screening for suspicious exercises and verifying the reliability of reconnaissance video are crucial. For rapid and efficient administration, it is necessary to constantly recognize a rush situation from video surveillance. Current innovation is making individual’s life simpler; however the security of life is additionally the major Problem. Swarmed places like public occasions, arenas, celebration grounds, rally influences the solace level of people, however it too builds the gamble of security of people on foot and different regular citizens. Weighty groups might prompt significant mishaps, swarm smash and causing a general control misfortune. To diminish the gamble of regular folks in weighty groups, we have worked with innovation to make due the group. The uses of group the executives are complex, going from swarm building up to human PC connection. Research verbalized this is centered around the way to distinguish any strange occasion in swarms at the beginning phase utilizing current innovation like Deep realizing with the goal that it very well may be taken care of and oversaw convenient and hurts least regular folks. The idea of Convolutional Neural Network is used for handling of pictures and recordings.
Keywords: Crowd Detection, Deep Learning, CNN, YOLO, Image Processing.
Abstract: The talent is the most complex organ in the human body. Brain Stroke is a long-term disability that occurs global and is a leading reason of death. A stroke happens when the blood of the intelligence is reduce off and stops working. There are two major causes of cerebral stroke: ischemic stroke or hemorrhagic stroke. Early brain predictions divulge the best possible quantity for the first time. Brain stroke is largely a result of lifestyle choices, in particular in a variety of prerequisites such as excessive blood sugar, heart rate, obesity, diabetes and high blood pressure. This research find out about used more than a few in-depth learning algorithms (ML) such as CNN, Dense net and VGG-16. This research undertaking is designing a mannequin that makes use of one of the following techniques to be greater correct to predict the have an impact on of new inputs.
Smart Online Voting System through Facial Recognition Using Haar Casecade Algorithm
Hemanth Kumar T, Sowmya B P
DOI: 10.17148/IJIREEICE.2022.10726
Abstract: The biometric software category known as facial recognition operates by comparing the face features. We will research how different algorithms are implemented in the field of secure voting procedures. Three layers of verification were applied for the voters under the system we propose. UID verification comes first,and voter cards come second. usage of several algorithms for number, and the third level of verification includes face identification utilising the algorithm of Haar cascade. This technique can reduce the amount of money the government spends on elections. Overall, the goal of this project is to assist electoral commission of India employees while also minimizing intensive tasks.
Abstract: Plant infections are one of the issues in the agricultural industry. Disease on plant leads to the substantial drop in both the quality and output of agricultural goods. Early identification and detection of plant diseases are therefore crucial. Plant illnesses frequently manifest on the leaves, and the diseased leaves' characteristics might vary and make them difficult to identify. Automatic disease identification is therefore challenging. It is possible to employ image processing techniques. Typically, illness symptoms can be noticed on the leaves. In this work Convolution neural networks and ensemble classifiers are employed in this study to categorise tomato disease into 7 groups (six disease and one healthy class), each with 100 photos. This study has effectively identified tomato plant disease using an automatic leaf image detection method with an accuracy of 96% and 92%.
CALL DETAIL RECORD ANALYSIS AND REPORT GENERATION USING DATA MINING TECHNIQUE
Subhash R,, K M Sowmyashree
DOI: 10.17148/IJIREEICE.2022.10728
Abstract: This system is an attempt to develop and advanced and clear understanding of the call record report. Call Detail Record (CDR) is a detailed record of all calls through the telephone exchange or any other means of communication. The record is kept by the telephone exchange involved and contains call details such as call time, call duration, source number and destination, call completion status, etc. CDRs are created by telephone billing systems. CDRs are saved by rotating the transmitter until the end of the call. CDRs can be used to support the operation of a telephone company by providing information about incorrect calls. Route traffic value estimates can also be obtained.
Abstract: The development of aberrant brain cells, some of which may turn cancerous, is known as a brain tumor. Magnetic Resonance Imaging (MRI) scans are the most common technique for finding brain tumors. Information about the aberrant tissue growth in the brain is discernible from the MRI scans. In numerous research papers, machine learning and deep learning algorithms are used to detect brain tumors. It takes extremely little time to forecast a brain tumor when these algorithms are applied to MRI pictures, and the better accuracy makes it easier to treat patients. The radiologist can make speedy decisions thanks to these predictions. A self-defined KNN and Naive Bayes is used in the proposed study to identify brain tumors and related
Abstract: There is undoubtedly room for improvement in the realm of recruiting given modern technological breakthroughs in this electronic age. Today, hands-free enrollment is well known for monitoring the requirements for quadriplegics. The Human PC Cooperation (HCI) system is presented in this study as a fundamental tool for people with disabilities and those who abhor using their hands. The created system is an eye-based interface that functions maybe as a computer mouse to decipher eye enhancements like flashing, staring, and squinting toward mouse cursor activities. The system under discussion makes use of a necessary webcam, and its item requirements include Python (3.6), OpenCv, numpy, and two or three different packs that are crucial for face verification. The HOG (Histogram of organised Gradients) include near to a straight classifier, or substantial learning estimates (cnn) and the sliding window process, can be used to create the face finder. There are no hands needed, and no additional equipment or sensors are needed.
Keywords: Human Computer Interaction [HCI], Convolutional Neural Networks [CNN], Histogram Of Oriented Gradients [HOG].
Detection of Child Predators Cyber Harassers on Social Media
Sandhya.V, Prof. B P Soumya
DOI: 10.17148/IJIREEICE.2022.10731
Abstract: Professional psychologists must comprehend the risks of cyberbullying and how to shield children from it. The possibility for online sexual conduct is one of the most dangerous aspects of the internet, despite the fact that it does have some pleasant aspects. The internet has made it possible for offenders to obtain entry to lots of kids while remaining silent. The major goal of our project is to identify the social media accounts used by predators and transmit a predator record to the cyber cell administrator (Wolak, 2000; Mitchell, Finkelhor, & Wolak, 2001). This study report provides an overview of our most recent efforts to create a system. As a result, with an upgraded system, the supervisor can keep taking action after providing any report to the sexual assault victim.
Predicting the Impact of Disruptions to Urban Rail Transit Systems
Suhasini M, Dr. H R Divakar
DOI: 10.17148/IJIREEICE.2022.10732
Abstract: Over the past few decades, service disruptions of rail transportation systems have increased in major cities for a number of reasons, such as power outages, signal issues, etc. The impacts of disruptions on users and transit networks are studied and projected. This makes it easier for service providers to set both short- and long-term goals to enhance their offerings. We precisely establish two metrics—stay ratio and journey delay—to assess the impact. In order to overcome the main challenge of unusual data scarcity—namely, the fact that there were only 6 documented disruptions in our one-year data sets—we propose structuring the issue as a training problem on a feature space relevant to alternate commuter route choices. We demonstrate that the new feature space correlates to more comparable data distribution across different disruptions, which is helpful for creating disruptor predictors that can be used more widely. We test and evaluate our approach using a dataset from real transit cards. The result clearly shows that our strategy performs better than a variety of benchmark techniques.
Keyword: Service disruption, impact prediction, data scarcity
Emotion based smart music player using Deep Learning
Bharath K.V, Chandan M.N
DOI: 10.17148/IJIREEICE.2022.10733
Abstract: Songs have long been a common choice as a means of expression to describe and comprehend human feelings. We can greatly benefit from trustworthy emotion-based classification systems when it comes to interpreting their significance. The outcomes of study into the classification of music based on emotions, however, have not been the best. We provide an affective cross-platform music player in this project that makes music suggestions based on the user's current mood. By merging the capabilities of emotion context reasoning within our adaptive music recommendation engine, EMP offers intelligent mood-based music recommendations.
Keywords: Deep Learning, CNN Algorithm, Face Expression, Music Classification.
Recognition of fish categories using deep learning
Nirikshitha M S, Prof. Shilpa H.L
DOI: 10.17148/IJIREEICE.2022.10734
Abstract: The two most critical components of fisheries nowadays are fish classification and fish location. Due to problems with segmentation, noise, and shifting environmental circumstances, it is challenging to categorise the images accurately. However, there is a big market for more precise object recognition. Neural Convolutional Network,VGG16, It enhances the accuracy of classifying and locating the photos of 97 percent, is utilised in order to tackle this challenge. The dataset was used to train a fish classification algorithm, and many activation functions have improved accuracy. Finally, after numerous comparisons, a better strategy has been discovered. The accuracy has improved. The successful creation of class labels and region recommendations is aided by localization.. Lastly, localisation and classification of images with better accuracy.
Keywords: Image processing, Fish Category detection, CNN, VGG16.
Abstract: People's lives are greatly impacted by music. Like-minded people come together via music, and it serves as the community's binding agent. The genres of music that different communities write or even just listen to can be used to identify them. Our research aims to develop a machine learning system that can predict music genres more accurately than the current approaches.We constructed many categorization models for this project and trained them using the Free Music Archive GTZAN dataset. All of these models' performances have been compared, and the results have been recorded in terms of prediction accuracy. A select few of these models are trained using both the mel-spectrograms and the audio characteristics of the songs, while a select few others are trained exclusively using the spectrograms of the songs. One of the models, a convolutional neural network, was shown to have the highest accuracy of all the models when only given the spectrograms as the dataset.
Customer Churn Prediction Using Artificial Neural Network
Dhanush N, Dr. M N Veena
DOI: 10.17148/IJIREEICE.2022.10736
Abstract: Churn research had been used for years to acquire possibility and to set up a sustainable patron-organization relationship. Deep learning knowledge of is one of the cutting-edge techniques utilized in churn evaluation because of its capacity to technique massive quantities of patron data. In this study, a deep learning knowledge of version is proposed to expect whether or not clients withinside the retail enterprise will churn withinside the future. The version advanced is synthetic neural community version, that are additionally regularly used withinside the churn prediction research. You can be acquainted with deep learning knowledge of, a sort of system learning knowledge of that employs a multilayer structure called neural networks, from which the word neural community derives. In the shape of a pc community, we create a community of synthetic neurons this is much like mind neurons. The synthetic neural community is primarily based totally on the gathering nodes we can name the synthetic neurons, which similarly version the neurons in a organic mind. The outcomes of the fashions had been in comparison with accuracy type tools, that are precision, keep in mind etc. The outcomes confirmed that the deep learning knowledge of version finished higher type and prediction achievement than different in comparison fashions.
“ORDRED OR ORDERLESS A REVIST FOR VIDEO BASED PERSON RE-IDENTIFICATION”
Akshaya Ramya, Dr. H R Divakar
DOI: 10.17148/IJIREEICE.2022.10737
Abstract: Convolutional network really necessary for learning a good visual representation for videobased person re- identification (VPRe-id)? In this paper, we first show that the common practice of employing convolutional neural networks (CNNs) to aggregate temporal spatial features may not be optimal. Specifically, with a diagnostic analysis, we show that the recurrent structure may not be effective learn temporal dependencies than what we expected and implicitly yields an order less representation. Based on this observation, we then present a simple yet surprisingly powerful approach for VPRe-id, where we treat VPRe-id as an efficient order less ensemble of image-based person re- identification problem. More specifically, we divide videos into individual images and re-identify person with ensemble of image-based rankers. Under the i.e. assumption, we provide an error bound that sheds light upon how could we improve VPRe-id. Our work also presents a promising way to bridge the gap between video and image-based person re- identification. Comprehensive experimental evaluations demonstrate that the proposed solution achieves state-of-the-art performances on multiple widely used various datasets.
Keyword: video, person re-identification, convolutional neural network.
“A CONVOLUTIONAL NEURAL NETWORK MODEL FOR EARLY STAGE DETECTION OF AUTISM SPECTRUM DISORDER USING DEEP LEARNING”
Theja G, Prof. Shilpa H L
DOI: 10.17148/IJIREEICE.2022.10738
Abstract: Autism spectrum disorder (ASD) is a neurological disorder that begins in childhood and lasts the rest of person’s life. It has an influence on how a person communicates and learns, as well as how they act and connect with others. There are number of techniques that can be used to help the child to grow and acquire new abilities. Behavioural and communication therapy, skill training, and symptom-controlling medications are all options available for treatment which are time consuming and subjective. Therefore, early and accurate detection of ASD is required which will help in treatment planning. With the patient’s history and different medical tests, the brain MR scans can proceed towards the distinguish between the Typical controls (TC) and ASD controls. The work is towards the development of Computer Aided Diagnosis for ASD detection and its classification into Typical Control (TC) and ASD. This project is about the selection of CNN deep learning techniques for accuracy improvement. In this project we have used total 10878 image belongings to typical control and autism. The collected datasets are pre-processed and applied convolution neural network with four layers which is giving 99% accuracy for training and validating data.
Abstract: The fall detection system has grown in importance within the homecare system in recent years. Among the elderly, accidental falls are a common source of damages, fatalities, and loss of control. Accident falls also significantly affect the costs of the national health system. Therefore, there is a need for in-depth research and the creation of fall detection technology to save elderly people. This article offers a thorough analysis of contemporary fall detection methods taking into account the most potent deep learning technique yolo algorithm which uses convolutional neural network (CNN) layers in recognizing persons and detects fall based on height and width dimension analysis of a person. This fall detection technique uses neural networks, open source human detection dataset, yolo v3 pre-trained model which make more reliable and accurate than the conventional fall detection methodology.
Abstract: Online video streaming platforms are heavily used nowadays. Websites such as YouTube offers content creators a great platform to share their knowledge, ideas and interesting information to their viewers. For a video to reach to maximum people, YouTube offers a trending page on website that shows videos which are trending at that particular time. Other than few viral videos that achieve high view count which are predictable to end up in trending section, rest of the videos cannot be predicted. Corporate companies are using social media for improving their businesses, the data mining and analysis are very important in these days. This paper deals with analysis of YouTube Data on Trending Videos. The analysis is done using user features such as Views, Comments, Likes, and Dislikes. Analysis can be performed using algorithms like Linear Regression, classification and navi bayes algorithm and python libraries like pandas, matplot library to classify the YouTube Data and obtain useful information.
DeepCross Model FaceNaming for People News Retrieval
Rashmi Ranjan Pradhan, Prof B P Sowmya
DOI: 10.17148/IJIREEICE.2022.10741
Abstract: A popular yet difficult subject is how can we incorporate multimodal data sources for face recognizing in news. This work develops a revolutionary deep crossmodal face naming technique to enable more efficient people news retrieval for widespread multi-modal news. The effective naming technique in this scheme intends to group the deep features of various modalities into a shared space to investigate their inter-related correlations, and a unique Web mining technique is proposed to optimize the face name matching for uncommon noncelebrity. This method incorporates deep multimodal analysis, crossmodal correlation learning, and multimodal information mining. A crossmodal face naming model can be modelled using a bi-media concept mapping issue with an inter-related correlation distribution across deep representations of multimodal news. This model's primary purpose is to improve crossmodal Name-face correlation and the degree to which they are associated
Keywords: CNN, Face Naming, caption Retrieval, News, modal
OBJECT RECOGNITION AND LOCALIZING For VISUALLY IMPAIRED PEOPLE
Vishwas B M, M N Chandan
DOI: 10.17148/IJIREEICE.2022.10742
Abstract: The number of people with visual impairments is considered to be in the hundreds of billions on a global scale. Integration into society is a crucial and continuing objective. Substantial work that has gone into ensuring a health care system. The creation of numerous guide system techniques has made it possible for people who are blind to live more regularly. These systems often only consider a limited set of functions. However, these solutions can greatly determine the movement and protection of such people.
Abstract: Air pollution is an important environmental risk factor in propagation diseases such as lung cancer, autism, asthma and low birth weight etc. Regulation of air quality is an important task of the government in developing countries for ensuring people’s health and welfare. Air pollution differs from place to place and depends on multiple pollutant sources such as industrial emissions, heavy traffic congestions, temperature, pressure, wind, humidity and burning of fossil fuels etc. Analyzing and protecting air quality has become one of the most required activities for the government in almost all the industrial and urban areas today. In this paper, machine learning algorithms are used to analyze the concentrations of air pollutants such as SO2, NO, PM2.5, O3 and PM10. This model analyses the air quality based on various pollutant concentrations through visualizations for effective feature extraction and decision making. A machine learning model is built using linear regression and SARIMA model to predict the air quality index based on past air quality data. The experimental results show that the proposed model can be efficiently used to detect the quality of air and predict the level of air quality in the future. The model has scored 71.69% for the train data.
Keywords: Air Pollution, air pollutants, air quality index.
Blockchain Based Milk Delivery Platform for Dairy Farmers
Darshan Varma K.R, H.L Shilpa
DOI: 10.17148/IJIREEICE.2022.10744
Abstract: The dairy industry, which encompasses the full dairy value chain, currently provides jobs and financial assistance to over 2 million people. The majority of dairy farmers are small-scale landowners, and they rely on local milk collection services, who manually record milk supply transactions in hardcopy inventory files held in their offices. These centres have been known to change and remove these documents in order to decrease their payments to farmers. The purpose of this work is to explore the potential application of blockchain technology in milk supply among smallholder farmers in rural parts of developing nations in order to establish transparency, dependability, and justice in the payment of these farmers. We seek to develop a farmer-centric blockchain-based platform to protect farmers from predatory intermediaries in the milk supply chain who tricks on ignorant and trusting farmers.
T. Sushmitha, Sahana N, Sabari Giri O.D, Tejaswini N
DOI: 10.17148/IJIREEICE.2022.10745
Abstract: In today’s world, people get too busy with their job and find less time for shopping. As we know during weekends shopping malls are much crowded and after shopping it’s a tedious process to stand in a long queue and wait for billing to happen. The bar-code-based billing process fails to be on par with the speed of the billing process when it has many products to be scanned. Thus, it is time-consuming and inefficient. So, for this reason, people nowadays undergo online shopping which has got huge drawbacks like quality issues. To overcome this issue, there are many technologies used. RFID technology is one of them. Instead of scanning laser light reflections from printed barcode labels, an RFID scanner recognizes the location and identification of tagged things. It leverages low-power radio frequencies to collect and store data. In this survey, we examine the use of different techniques such as Wireless Sensor Network (WSN), Global System for Mobile communication (GSM), Microcontroller, etc. for the smart trolley. This concept “Smart Trolley” aids us to save time and brings the billing process to be on par with the busy days of the customer. This unique smart trolley system can be easily implemented and tested on a commercial scale and can be made used as a real-time scenario in the future.