Browse Articles
Discover research articles across all indexed journals
Smart Energy Meter Using IOT
The efficient use of energy plays a very vital role in the development of smart grid. So, the chief priority of the smart grid id the monitoring and controlling of the energy consumption. The present energy meter has few problems. The proposed system is an add on module that controls and calculates the energy consumption using ESP 8266 12E, a Wi-Fi module and it will upload the data to the cloud from where the consumers can view their reading. Our system is slightly modified from the original module to get the current reading. The energy consumption and computation become easier and controllable by the consumer. Smart Energy Module enables the vision of a smart grid it ensures more accurate energy measurement and lower power consumption.
Object Identification Using Deep Learning
Human visual system is very fast that he can easily detect and identify the objects using this visual system it can easily identify multiple objects and detect the obstacle. This time there is a very large amount of data, a faster CPU and good algorithm that can easily train computers to detect and classify multiple objects with high accuracy. It uses an algorithm to detect and identify the objects that is “You Only Look Once” (YOLO) algorithm. This project is based on a deep learning approach to solve the problem of object detection and recognition. This network is trained on the most challenging dataset known as (PASCAL VOC), in which object detection is conducted annually manner. The resulting system is very fast and accurate. Object recognition is a collection of related tasks for identifying objects in digital photograph. R-CNN is a family of techniques for addressing object localization and recognition tasks. Propose a new object detection method which improves the existing model at every stage of object detection and identification, use COCO dataset model in this lot of categories of images are stored.
IoT Based Smart Chair Using Raspberry PI
The Internet of Things (IoT) is a network of physical objects "things" embedded with sensors, software, and other technologies for the purpose of connecting and exchanging data with other devices and systems via the internet. This project enables us to assess a seated person's posture in real time and improve sitting posture. Long-term sitting harms the spine and causes chronic problems that require long-term therapy. People who are sick have a significant impact on office productivity. Long periods of sitting while studying cause major postural and spinal problems in young people. Our motivation is to assist people in paying attention to their health and proper sitting .Maintaining good posture by sitting with a straight back and shoulders not only enhances physical well-being but also enhances confidence and productivity through the development of healthy habits and frequent breaks. To make the chair smart, we use an IoT system with sensors, processing power, and software, with the goal of eventually assisting humans in maintaining good posture and healthy habits. Making a regular chair into a smart chair using Raspberry Pi, which will continuously detect your sitting posture and send a notification if it is incorrect. Two FSR sensors will be fitted onto the backrest of the chair to detect the inclination of the chair. The backrest sensor will detect if the person is sitting straight or not. The humidity and temperature sensor module inside the cushion of the seat will detect the temperature and pressure of the user. The goal of this project is to maintain proper posture for improved health and longevity.
Identification of Medicinal Plants by Visual Characteristics of Leaves
Plants Leaf play a vital role in human life, they provide oxygen, food, shelter, medicine, fuel, gums and environmental protection. Many plants are rich in medicinal values and contain active ingredients for medicinal use. Because of factor such as global warming, increasing population, professional secrecy, lack of Government support for research activities and lack of awareness about medicinal plants, many useful plants species are now becoming extinct and are getting destroyed. Manual identification of medicinal plants leaf is a time-consuming process and need the help of experts for plants identification. To overcome this problem automatic identification and classification of medicinal plants is needed for greater benefit to humankind. In today’s era, the automatic identification and classification of medicinal plants leaf is an active research area in the field of image processing. Feature extraction and classification are the main steps in identification of medicinal plants and classification process which affect the overall accuracy of the classification system. This paper presents literature on image processing techniques used in identification and classification of medicinal plants and also the importance and benefits of medicinal plants in recent years.
Real-Time Parking Using AI & ML
Real time parking systems have a potential to reduce the congestion in crowded areas by providing real time indications of occupancy of parking spaces. To date, search systems are mostly implemented for indoor environments using costly sensor based techniques. Consequently, with the increasing demand for parking systems in outdoor environments, inexpensive image based detection methods have become a focus of research and development recently. Motivated by the remarkable performance of Convolutional Neural Networks (CNNs) in various image category recognition tasks, this study presents a robust parking occupancy detection framework by using a deep CNN and a binary Support Vector Machine (SVM) classifier to detect the occupancy of outdoor parking spaces images. The classifier was trained and tested why the features learned by the deep CNN (convolutional neural network) from public datasets (PKlot) having different illuminance and weather conditions. The indicates the great potential of this method to provide a low- cost and reliable solution to the parking systems in outdoor environments.
Age and Gender Detection Using Deep Learning
Age and gender detection using deep learning with Convolutional Neural Networks (CNNs) is a popular computer vision task that involves predicting the age and gender of a person from their image. CNNs are powerful deep learning algorithms that are well-suited for image classification tasks. In this task, a CNN model is trained on a large dataset of labeled images, where each image is annotated with the corresponding age and gender of the person. The CNN model learns to extract features from the input image and uses these features to predict the age and gender. Age and gender detection using deep learning with CNNs has various applications in different domains, including surveillance, security, healthcare, and entertainment.
Heart Disease Prediction Using ML
Machine Learning is used across many ranges around the world. The healthcare industry is no exclusion. Machine Learning can play an essential role in predicting presence/absence of locomotors disorders, Heart diseases and more. Such information, if predicted well in advance, can provide important intuitions to doctors who can then adapt their diagnosis and dealing per patient basis. We work on predicting possible Heart Diseases in people using Machine Learning algorithms. In this project we perform the comparative analysis of classifiers like decision tree, Naïve Bayes, Logistic Regression, SVM and Random Forest and we propose an ensemble classifier which perform hybrid classification by taking strong and weak classifiers since it can have multiple number of samples for training and validating the data so we perform the analysis of existing classifier and proposed classifier like Ada-boost and XG-boost which can give the better accuracy and predictive analysis.
Smart Online Exam Proctoring System
The Covid-19 pandemic has been one of the defining events in recent history. Education and company hiring processes has been impacted most adversely due to the pandemic. Disrupting the age-old class-room setup, the pandemic has forced educational institutions like schools and universities to implement online classes and online examinations. This paper proposes a smart online proctoring system which is the most effective method to reduce the percentage of cheating in online examinations. One can easily take an online proctored exam at any quiet environment. The system uses real time video from the webcam which is then passed onto the ML models to detect any malpractice performed by the examinee. The online proctoring system can be used by the educational institutes for conducting online examinations in a supervised manner. It can also be used by the companies for initial hiring processes through which the candidates can be filtered. This approach is cost effective and less time consuming.
An Efficient Spam Detection Technique for IOT Devices using Machine Learning
Internet of Things (IoT) devices is becoming increasingly popular, and as their usage grows, so does the risk of spam and malicious attacks on these devices. Spam detection is one of the primary concerns for securing IoT devices, and machine learning has shown great potential in addressing this issue. In this abstract, we will discuss the use of machine learning algorithms for spam detection in IoT devices. The proposed solution involves collecting data from IoT devices, such as sensor readings, network traffic, and user behavior, and then training a machine learning model on this data. The model can be trained on both known and unknown spam patterns, allowing it to identify and classify potential spam messages with a high level of accuracy. Several machine learning algorithms can be used for spam detection, including decision trees, support vector machines (SVMs), and neural networks. These algorithms can be trained on different features of the data, such as the frequency of certain keywords or the source of the message, to identify patterns that are indicative of spam. To ensure the effectiveness of the spam detection system, it is essential to continuously update the machine learning model as new types of spam are discovered. This can be achieved by deploying the model in the cloud, allowing it to learn from new data and improve its accuracy over time. Using machine learning algorithms for spam detection in IoT devices can greatly enhance the security of these devices. By training a model on data collected from IoT devices, we can accurately detect and classify potential spam, allowing us to take appropriate action to protect these devices from malicious attacks.
Smart Agriculture
Agriculture is the primary main stay of the economy in our country. In recent years, because of uncertain trends in climate and policy making this has attributed to the price of crops becoming highly volatile. Farmers remain oblivious of these uncertainties, which attribute a degradation of the farmers’ mental and financial wellbeing. The excessive use of chemicals in the soil have caused the soil to lose its organic properties ultimately causing the soil to be exothermic in nature, hence requiring large amounts of water for maintenance of the farm land with an unhealthy quality of production causing wide spread devastation to the overall economy and health of a country. This inspired us to create a system which is handy, easy-to-use and breaks the farmers from the shackles of the large chemical fertilizer corporations, to detect the plant disease early and the harvest optimal crop for better productivity. This system provides accurate results in predicting the optimum crop according to the location and soil conditions. The system frame work in corporate disease detection and fertilizer recommendation all with a custom dataset of organic remedies for the relevant diseases detected
Eye Ball Based Cursor Movement Control
Eye tracking technology has been widely used in the field of human-computer interaction as an assistive technology for individuals with motor disabilities. This study presents a novel approach for controlling the movement of a computer cursor using eye tracking techniques. The proposed method relies on the user's eye movement patterns to accurately and intuitively move the cursor on the screen. The system is designed to be simple, easy to use, and accessible to a wide range of users. Results from a preliminary user study show that the proposed method can achieve high accuracy and efficiency in cursor control. This research has potential applications in various fields, such as gaming, virtual reality, and accessibility.
Smart Traffic Light Control System with Automatic Vehicle Speed Breaker
The aim of the project is to design a smart traffic light control system interfaced with a barrier gate and an LDR based traffic light control system. When the signal timing changes a delay is provided with the help of a microcontroller, pop up barrier before the zebra crossing will open or close to allow vehicles to pass. When the signal is red the interfaced barrier gate closes and a buzzer notifies the closing of gate, thereby blocking the traffic but when the signal is green the same barrier opens and allows a proper flow of vehicles to avoid traffic congestion. We provide a time delay for all signals to change and buzzer action by using ESP32 microcontroller. ESP32 microcontroller is used for signal timing change as well as street light control according to LDR. Smart Street light which operates with the help of sensors Microcontrollers are programmed in such a way to adjust their timing and phasing to meet changing traffic conditions. The circuit, besides being reliable and compact, is also cost effective. This project presents the way of conservation of energy by reducing electricity wastage as well as to reduce the man power. The project uses light emitting diodes (LED) that do not consume an enormous amount of electricity. LDR is used as a sensor for the functioning of street lights effectively.
AI Cricket Score Board
Gesture Recognition pertains to recognizing meaningful expressions of motion by a human, involving the hands, arms, face, head, and/or body. It is of utmost important in designing an intelligent and efficient human–computer interface. The applications of gesture recognition are manifold, ranging from sign language through medical rehabilitation, monitoring patients or elder people, surveillance systems, sports gesture analysis, human behavior analysis etc., to virtual reality. In recent years, there has been increased interest in video summarization and automatic sports highlights generation in the game of Cricket. In Cricket, the Umpire has the authority to make important decisions about events on the field. The Umpire signals important events using unique hand on signals and gestures. The primary intention of our work is to design and develop a new robust method for Umpire Action and Non-Action Gesture Identification and Recognition based on the Umpire Segmentation and the proposed Histogram Oriented Gradient (HOG) feature Extraction oriented of Deep Features. Primarily the 80% of Umpire action and non-action images in a cricket match, about 1, 93,000 frames, the Histogram of Oriented Gradient Deep Features are calculated and trained the system having six gestures of Umpire pose using Densenet121.
Anti Theft Security System
The Anti-theft security system designed to detect intruders and alert the user. The proposed system is built with a piezo sensor installed under the floor and a Raspberry Pi Pico W microcontroller. The piezo sensor detects the presence of an intruder and triggers an alarm, which is sent to the Raspberry Pi Pico W microcontroller. Microcontroller then sends a notification to the user, notifying them of the potential threat. The device includes a servo motor to control the camera angle. Piezo sensor detects the pressure and passes the signal to the Pi Pico W. The Raspberry Pi Pico W sends the instruction to the servo motor to move where the pressure was detected. Later, with the help of ESP32 CAM the photo is captured. The application was designed to control the actions such Buzzer, lights, Hidden door and along with live stream of the captured photo where the user can control the actions with the help of switch in the application. The proposed system is cost-effective, efficient, and easy to install and operate.
Multiple Disease Prediction System
In recent years, the rise of chronic diseases and health problems has created a pressing need for accurate and efficient disease prediction. The Corona virus pandemic further highlighted the importance of early disease detection and giving importance to early signs of symptoms. Further, many people experience symptoms of illnesses but are unsure about what disease or condition they might have. This uncertainty can lead to anxiety and stress, and sometimes people may delay seeking medical help until their symptoms worsen. Additionally, some people may not have easy access to health care services and facilities or may not want to visit a healthcare facility for various reasons. Taking all these factors into consideration, this paper proposes a multiple disease prediction system that allows users to enter their symptoms and get an indication of what they might be experiencing. The system facilitates early disease detection. Machine learning algorithms are utilized to analyze a symptom dataset which has hundreds of symptoms combinations for each disease. After training and development of machine learning models, they have been in corporate into a Stream lit application.
Malpractice Detection Using Machine Learning
Cheating during exam is unfair behaviour of the students. This becomes disadvantage for other students who do not cheat and work hard to study. This project is meant to detect the suspicious activities of the students who intend to cheat during exams. This project is useful in educational institutions where in invigilators are not able to detect the cheating done by students in the exam hall. This project has two phases namely, training phase and the testing phase. The dataset is a pre-recorded video of students which is captured in real time. This system works well with live web camera input also. The algorithm used is DenseNet121.This system predicts three kinds of activities such as turning around, passing of paper and a normal activity differentiated by RGB colours.
Analysing the Performance of Support Vector Machine Algorithm in Predicting Parkinson’s Disease
Parkinson’s disease (PD) is a neurodegenerative measure disease where the symptoms steadily develop start with an insignificant a slight shaking movement in one hand and a feeling of stiffness in the body and it became worse over time. Dopamine is most notably involved in helping us feel preference as part of the brain's reward system. It acts as a message between the parts of the brain and nervous system that support control and co-ordinate body movements. As dopamine generally neurons in the parts begin to experience difficulty in speaking, writing, walking or completing another simple task. Virtually, 90% pretentious people with Parkinson have tongue disorders. It affects over 6 million people worldwide. At present there is no conclusive result for this disease by non-specialist clinicians, particularly in the early stage of the disease where identification of the symptoms is very difficult in its earlier stages. The future predictive analytics outline is a combination of K-means clustering and Decision Tree which is used to improvement visions from patients. By using machine learning methods, the problem can be explained with negligible error rate. The investigated approach serves as a guide in determining the diagnosis and in planning the appropriate by a loss of nerve cells in the part of the brain
Online Attendance System Using CCTV
The online attendance system is a project that aims to create a more efficient and secure method for recording attendance at educational institutions, offices, and other organizations. The main objective of the project is to develop a system that can accurately identify individuals based on their facial features, and record their attendance automatically. One of the main problems that the face recognition attendance system aims to solve is the issue of manual attendance recording, which is often time-consuming and prone to errors. By automating the attendance process, we eliminate the need for annual attendance registers and reduce the burden on staff. The online attendance system uses advanced algorithms to analyze and compare facial features, and can accurately identify individuals even if they are wearing masks or have changed their appearance. The system can also be integrated with other software, such as payroll systems, to provide a more streamlined and efficient process for managing attendance and payroll. Overall, the face recognition attendance system is a valuable tool for improving attendance management and security at educational institutions, offices, and other organizations. It offers a more accurate and efficient method for recording attendance, and can significantly reduce the workload and costs associated with manual attendance recording.
Gas Leakage Detection and Booking Using IoT
There is a rapid development in technology which influencing the human life in several aspects due to rapid development in different fields but we still need to adopt that technology such that we can make human life easier to live. In our Country it is not possible to supply LPG through Pipes to each and every home as production of LPG is too short. At present we are having a system Advance LPG cylinder booking through IVRS or online which is most difficult for the illiterate and busy schedule people to book the LPG cylinder in advance. Another Major problem LPG cylinder users facing is “They don’t know exactly the status of LPG gas completion” makes even more delay in booking the cylinder which is uncomfortable most of the times. Now a day we are having a IVRS system in which customer needs to go through few steps in accordance with the Automatic voice which also includes selecting options. Most of the illiterate people can’t even complete the booking due to this reason and also most of the times these landline phones are either busy due to congested calls or phones not working due to some technical issues. This paper proposes a system that will make entire LPG cylinder booking procedure automated without human intervention. This system continuously measures the weight of the cylinder and once it reaches minimum threshold it will automatically sends message to the authorized LPG Agent so that they can deliver the LPG cylinder in time. Along with the Automated cylinder booking we also designed feature related to the safety of the user in which it continuously monitor the leakage of LPG gas and alerts the user regarding leakage to avoid major accidents which costs human lives mostly.
Fingerprint Image Identification for Crime Detection
The identification of a person has become, crucial part in this physical world (fast growing) identification features of a person can be included iris, Fingerprints etc. The fingerprint plays an important role in crime investigation, to identify the criminals which makes easy to solve the crime. The fingerprint is collected from the crime scene. These images are stored in digital format saved in database. The image is pre-processed using techniques acquisition, Enhancement, Thinning fingerprint image features are extracted from the pre-processed image. These pre-processed data is tested and trained by CNN model using random forest and decision trees these algorithms, Algorithm identifies the criminals based on matching accuracy.