Browse Articles
Discover research articles across all indexed journals
Early Prediction of Cardiac Arrest Using Data Mining Algorithms
Cardiac arrest is a sudden and unexpected loss of heart function that can lead to death. Early prediction of cardiac arrest could help to improve survival rates by allowing for early intervention. Datamining is a field of computer science that involves the extraction of knowledge from large datasets. Data mining algorithms can be used to identify patterns in data that may be indicative of cardiac arrest. For example, data mining algorithms can be used to identify patients who are at increased risk of cardiac arrest based on their medical history, lifestyle factors, and other characteristics. This paper reviews the use of data mining algorithms for early prediction of cardiac arrest. The paper discusses the different data mining algorithms that have been used for this purpose, as well as the results of studies that have evaluated the effectiveness of these algorithms. The paper also discusses the challenges of using data mining for early prediction of cardiac arrest, and the future directions of research in this area. The paper concludes that data mining algorithms have the potential to improve early prediction of cardiac arrest. However, more research is needed to develop more accurate and reliable data mining algorithms. Additionally, more research is needed to develop methods for integrating data mining algorithms into clinical practice.
Range Extension of Drones Using 5G Communication
Fire Accidents can cause serious injury and damages to the personnel and personal property. General Fire accidents occur often unexpectedly and sudden. Times of India published that, with 27,027 deaths, every fifth Fire related deaths in the world in 2017 took place in India. Around 9 million Fire incidents and 1.2 Lakh deaths were recorded across the globe that year. Thirty-five Indians die in Fire accident daily, says the National Crime Records Bureau (NCRB) based on the 12,748 lives in 2018.When the Fire service responders arrive on a Fire Scene, it is very difficult for them to predict the situation inside the building or any closed area subjected to Fire, so Drone can be a solution for the Firefighters to take decisions about where to concentrate resources and how to approach and enter the scene. Keywords—Drone, 5G Communication, Mobile, Fire extinguisher
Virtual Mouse – Hand Gesture Recognition System
The purpose of this research is to enhance the identification of hand gestures in a Human-Computer Interaction scenario, while also minimizing the computational time required and enhancing user comfort. To achieve this goal, the authors created a computer mouse control application that employs an algorithm and selected hand features, resulting in efficient performance. The integration of voice assistant with the recommended hand postures further improves user experience and facilitates system operation.
Digital Watermarking
The paper introduces the digital watermarking technology which is a data hiding technique that embeds a message into a multimedia work such as an image or text or other digital object. The proposed technique has several important applications; the majorly important is the digital copyrights protection. The digital watermarking system as any other data hiding technique has its own requirements that make the digital watermark strong as possible. Technologies of digital watermarking are mainly classified depending on their domain to spatial domain watermarks, Watermarks belonging to frequency (transform) domain and wavelet domain watermarks. The digital watermarks suffer from different types of attacks that include either state-of-the-art watermarking attacks or watermark estimation attacks. The recovery from these attacks requires strong detection techniques; the digital watermark agent provides a professional solution for these attacks.
Smart Remainder SoS And Emergency Detection Device
The lack of a dedicated device to remind chronic patients when to take their medications, the difficulty in quickly pressing an SOS button, and most importantly the delay in communication between the time of an accident and contact with care takers or hospitals were the three factors that served as the inspiration for the project. A study found that prompt treatment could preventable most 85% of deaths brought on by minor and major heart attacks, strokes, and shortness of breath. Therefore, a visible SOS button would be adequate A side from that, data demonstrate that it is detrimental to one's health to take prescriptions as prescribed and to take the incorrect medication at the incorrect time. In addition, News18 reports that each year 36,579 persons pass away in motor vehicle collisions, 36,213 in two-wheeler collisions, 31,997 in truck and lorry collisions, and nearly 45,000 in incidents involving other modes of transportation. A delay in bringing the patient to the hospital accounts for over 76percent of deaths in each vehicle. Guardians were unable to reach the injured in half of the cases, or the victim was not helped to get to the hospital in time. In such a scenario, a device or technology that detect
Under Ground Fault Monitoring system Using Cloud Computing and IoT
An underground fault monitoring system project's major objective is to develop and put into use a system that can quickly identify and pinpoint faults in subterranean power cables. The system uses a network of sensors put along the cable's length to monitor and communicated at a on a variety of characteristics, including temperature, vibration, and current. For analysis to a central control unit. Advanced algorithms are used by the control unit to process the data and find any anomalies or potential problems. The system alerts the maintenance crew in real time when a fault is found, allowing them to swiftly find and fix the issue. Reducing the possibility of failure is the project's main objective in order to increase the availability and dependability of the electricity system.
Analysing ML Models for AQI Prediction using Meteorological Data
Air is essential for every living being to survive. The modernization and industrialization have led to the rise of pollutants which affect the quality of air directly. Predicting changes in air pollutant concentrations due to human and nature drivers is critical and challenging, particularly in areas with scant data inputs and high variability of parameters. The air quality index (AQI) is an index for reporting air quality on a daily basis. It is a measure of how air pollution affects one's health within a short time period. The purpose of the AQI is to help people know how the local air quality impacts their health. The Environmental Protection Agency (EPA) calculates the AQI for five major air pollutants, for which national air quality standards have been established to safeguard public health. Every country has its own method of calculating the Air Quality Index and the rules for Air Quality Buckets. According to the Central pollution control board, Ministry of Environment, Forests, and climate change of India, the AQI is divided into 6 buckets with the minimum and maximum AQI being 0 and 500 respectively. The buckets are Good, Satisfactory, Moderate, Poor, Very Poor and Severe.
Implementation of Artificial Intelligence in Education
Artificial intelligence in education (AIED) applications have been made easier to implement largely to the quick development of computing technologies. In order to improve teaching, learning, or decision-making, AIED refers to the employment of AI technology or application programmes in educational contexts. This study analyses every facet of the education sector's use of AI tools and technologies in great detail. The findings show how we may integrate AI development into these teaching, learning, student assistance, and management technologies. This study attempts to show how AI is being used in learning and teaching in the digital age.
Accident Detection and Alert System Using IoT
Accidents have recently emerged as a major source of concern for humans. Due to a lack of information about the location, magnitude of the accident (or) other issues, some victims cannot be rescued by the response team, which may be an ambulance or police. Many technologies were developed, however they were unable to overcome the problem. However, this project will provide clarification on how to overcome this hurdle. A central system is employed in this project, to which a vibrator sensor, GSM (Global System for Mobile Communications), and GPS modules are attached. To prevent detecting errors, numerous sensors are strategically distributed throughout the vehicle. After an accident takes place the vibrator sensor becomes active, and GPS (Global Positioning System) is engaged with the assistance of the central system GSM ( Global System for Mobiles ). Immediately, alert messages will be handed down to the response teams, outlining the live location and severity of the accident
Authenticity of Online Publications via IPFS Blockchain
The world of the internet and the advent of technology have altered the digital era and how we access the stuff we publish or post on the Internet, such as books, music, and movies. Make it available on the internet. This was accomplished by integrating two technologies: the Interplanetary File System (IPFS) and blockchain smart contracts. We use IPFS to securely store digital stuff and make it available to anyone. We create a unified framework for creating and editing material using Ethereum smart contracts, enabling oversight and visibility of all content from creation to final publication. In an accessible world, this strategy promotes justice, efficiency, and openness. We offer all of the smart contract code, detail its implementation and testing, and demonstrate its significance.
Automated Brain Segmentation and Classification of Tumor through Robotics and Machine Learning
The process of neurosurgery is delicate and time consuming, often resulting in lower patient outcomes and survival rates. Therefore, we are implementing computer algorithms for the classification and segmentation of brain tumors. This aims to improve the accuracy of identifying tumor and segmentation of the brain. The automatic segmentation of the brain is based on CT (Computed tomography) data using the Desktop Image Processing System (DISOS). The DISOS system integrates modules such as preoperative planning and user guidance. Automated segmentation algorithms, including fuzzy c means clustering method, intensity thresholding, region growing, level set methods, and machine learning approaches, are employed to segment the brain structures. This system demonstrates improved accuracy, robustness, and efficiency, although a final check by a medical expert is still necessary. Additionally, our paper highlights the use of advanced algorithms and machine learning techniques to differentiate between cancerous and non-cancerous tumors using various medical imaging data. The incorporation of genetic, molecular, and clinical data further enhances the accuracy of tumor classification models. Challenges in real time robot path planning and navigation for neurosurgery are addressed, including the use of A-mode ultrasound and augmented reality systems to provide enhanced guidance during procedures. This study concludes by emphasizing the collaboration between medical professionals and computer scientists in advancing the field of computer-assisted brain tumor diagnosis and robot-assisted surgery. Our goal is not to replace humans with robots, but the collaboration between them for incredible outcomes.
Real Estate Price Prediction Using Artificial Intelligence
The sales of houses are influenced by various factors such as location, area, population, and other relevant information. Predicting individual housing prices can be instrumental in estimating future real estate prices. This study employs the Random Forest algorithm, a machine learning technique, as the primary methodology for developing a housing price prediction model. By focusing on the Random Forest algorithm, this project aims to optimize prediction accuracy and consistency, considering it as the best model for price prediction. The implementation of this project involves using Python (AI/ML) for coding the Random Forest algorithm, while HTML, CSS, and JS are employed for designing the system's frontend. Ultimately, the House Price Prediction system proves to be a valuable tool for accurately assessing property prices and maintaining a record of price fluctuations, promoting transparency and discouraging fraudulent activities.
Arduino-Based IoT System for Monitoring Air Pollution
Air pollution is a major global health concern, and there is a growing need for effective monitoring systems. This abstract presents an Arduino-based Internet of Things (IoT) system that can be used to monitor air pollution in real time. The system is low-cost, easy to deploy, and scalable, making it a valuable tool for environmental monitoring. The system incorporates low-cost Arduino microcontrollers, sensors, and wireless communication modules to enable remote data collection, analysis, and visualization. The system can be used to monitor air quality in a variety of settings, including schools, workplaces, and homes. The data collected by the system can be used to identify areas with poor or good air quality. The open-source nature of the Arduino platform facilitates community-driven development and customization, encouraging collaboration and innovation in air pollution monitoring. This paper outlines the procedure for constructing a prototype model for air contamination detection. It also emphasizes of alerting system when pollution levels exceed the threshold, enabling timely action and mitigation of the situation.
Paper on Smart Irrigation
Agriculture holds immense significance in India as it is the main source of livelihood for a majority of the population. Over the past few decades, farming has undergone significant technological advancements, becoming more industrialized and technology-driven. Smart agriculture gadgets have empowered farmers to have better control over livestock rearing and crop cultivation, enhancing predictability and efficiency. Technology plays a crucial role in the development of this agricultural nation, and water is a vital resource for farming. While water irrigation is a common method to supply water to farms, it can sometimes lead to wastage. The conventional water irrigation system faces challenges due to water scarcity caused by population growth and climate changes. The Internet of Things (IoT) has emerged as a new approach to modernize agriculture. By leveraging automation, IoT can optimize various farming processes and reduce the need for human intervention, making agriculture more efficient. Therefore, a novel method called "automation of water irrigation system using IoT" is proposed to conserve water and save time. This approach involves the use of sensors such as temperature, humidity, and soil moisture sensors to measure different soil parameters. Based on the soil moisture value, the motor controlling the water flow will automatically switch on or off. The status of the motor and the sensed parameters will be displayed on a mobile device. By monitoring and collecting data on soil moisture, temperature, humidity, and sunlight intensity across multiple fields, water usage efficiency and crop yield can be improved for both large and small farms. Additionally, when the soil in agricultural land becomes dry, this method triggers the automatic flow of water for irrigation. Sensors are deployed on farms to monitor crop status, taking into account climate changes and factors like light, humidity, temperature, shape, and size. If any deviations are detected by the sensors, the crop status will be displayed on the farmer's smartphone.
A Food Recognition System for Diabetic Patients Based on an Optimized Bag-of-Features Model
Healthcare delivery might be completely changed by computer vision technologies. It might be used, in instance, to assess the carbohydrate content of meals for 1 diabetes patients. Based on the bag-of-features (BoF) paradigm, this paper suggests a way for automated food recognition. A thorough technical analysis was carried out to identify and optimize the components that make up the BoF architecture in order to guarantee the best outcomes. Also estimated were the associated parameters. A visual dataset with about 5000 food photos that was divided into 11 groups was developed in order to construct and test the prototype system. Using the scale-invariant 3 feature transform on the HSV colour space, the optimised method calculates dense local features. After that, it utilizes a visual dictionary with 10,000 visual words to create a linear support vector machine classifier is then used to categorize the food photos. The system demonstrated the viability of the suggested strategy in a very difficult picture dataset by achieving a classification accuracy of about 88%. By giving diabetes patients a more precise and effective means to control their carbohydrate consumption, this cutting-edge technology might have a profound effect on their quality of life.
Cotton Crop Disease Prediction Using Deep Learning
Cotton was found in 3000 B.C and was first used as a fabric in the Indus Valley. The first mill of cotton in India was established in 1818’s near Kolkata. Cotton is a drought-resistant crop and is best grown in soils with excellent water holding capacity it creates reliable income for the cultivators who cultivate the crop under climate threat. In this study, we have worked on disease detection and crop recommendation system. For disease detection, we have implemented the Deep Convolutional Neural Network(CNN) models i.e., Sequential and VGG-16. In the proposed model we detect whether the cotton crops are infected or not, and if they are further particular disease is identified according to the crop. The highest Accuracy achieved is for VGG16 i.e., 97.53%. The proposed system also recommends medicine with the dosage which can be used to cure the plants. Which can help the farmers in increasing the production and quality of the cotton crop.
Building a Smart City Infrastructure Using Long Range Technology
Smart cities are urban areas that leverage fourth industrial revolution technologies and stakeholder governance to address urban challenges and enhance the well-being of citizens. Despite the evolving concept of smart cities, there is a lack of comprehensive studies on the overall trajectory of smart city research and key issues. Thus, this investigation examines smart city literature published from 2011 to 2020 to identify trends, characteristics, and propose future research directions. A systematic review of smart city studies conducted over the past decade was performed, dividing the research into methodology and content. The analysis framework encompassed research year, two research methodologies employed, research objectives, data collection methods, utilization of research outcomes, relevant keywords, analysis units, and classification criteria for smart city security. The findings of this study are anticipated to offer valuable insights for forthcoming smart city development initiatives.
Swarm Robotics and Intelligence
It's fascinating to observe how the concept of Swarm Intelligence in natural systems may be applied to human groupings, specifically in the realm of finance. According to the study you referenced, groups of financial traders were able to improve their accuracy in predicting weekly market indices by constructing online systems modeled after natural swarms. The increase in accuracy from 61% to 77% when predicting jointly as a real-times warm is a considerable improvement and demonstrates that the adoption of SI algorithms has the potential to considerably improve financial forecasting accuracy. It is also worth noting that the results' statistical significance (p=0.001) shows that the findings are reputable. Overall, the findings indicate that employing SI algorithms to allow groups of traders to construct real-time systems online could be a beneficial tool in the field of finance, potentially leading to more accurate financial predictions. More research is needed, however, to validate these findings and to investigate the possible applications and limitations of this approach.
Spam Detection on Social Media Platform
Social Media has become an essential platform for communication and information sharing. With its widespread popularity, the problem of spam has also become increasingly common. In this paper, we propose an effective machine learning- based approach for spam detection on social media. Our approach uses various features and classifiers to distinguish spam messages from legitimate ones. The features used include lexical, syntactic, and semantic features, while the classifiers used include decision trees, naive Bayes, and support vector machines. Our experimental results demonstrate that the proposed approach outperforms existing spam detection methods on social media.
The Comparative Study of Noise Removal Techniques in Compound Images
In an ever-evolving world, countless fresh methods for reflecting data are being developed. An image is used to illustrate. Compound images and data are widely used. Numerous photos that have been acquired contain noise, which impairs the image's qualities and produces visual disruption. Noise should be eliminated in order to preserve good image quality, as this helps the image restore its quality. Applying filters like the Median, Wiener, Gaussian, etc. can be used to remove noise from an image. This essay discusses Gaussian noise, salt-and-pepper noise, speckle noise, and filters including Mean, Median, and Gaussianfilters.