Turkish Journal of Computer and Mathematics Education (TURCOMAT)
Not a member yet
9094 research outputs found
Sort by
ADVANCED WILD ANIMAL DETECTION AND ALERT SYSTEM USING THE YOLO V5 MODEL POWERED BY AI
No full textAn advanced wild animal detection and alert system using you only look once version5 (YOLO V5) model. The system utilizes you only look once version5 (YOLO V5) object detection algorithm to identify wild animals and alert users to their presence in real-time. The system employs a camera to capture real-time video, which is then sent to a computer running you only look once version5 (YOLO V5) algorithm. When the system detects a wild animal, it sends an alert to the wild animal by playing any sounds like bullets firing. The system is expected to have a significant impact on the safety of people in areas with high wildlife populations. This advanced wild animal detection and alert system using you only look once version5 (YOLO V5) model has the potential to improve the safety of people in areas with high wildlife populations. Future work will focus on improving the accuracy of the system and implementing it in real-world scenarios
ENHANCING ARITHMETIC OPERATIONS IN C++ THROUGH VEDIC MATHEMATICS PRINCIPLES
No full textVedic mathematics is a relatively recent subject of study that requires integration with other areas of study. It is a collection of formulas taken from ancient Vedic scriptures. Here, we have combined Vedic mathematics with computer science. Specifically, we have created C++ programmes utilising two Vedic mathematics sutras:
URDHVA TIRYAGBHYAM (Sutra-3)
SQUARE BY DUPLEX (4-DIGITS).
These two techniques speed up computations compared to more conventional techniques. We can discover the product and square of huge numbers with ease and with fewer errors when we use these two sutras
Botnet Attack Identification and Mitigation condition Software-Defined Networks Utilizing CNN Algorithm
No full textOne new design that makes managing and communicating across large-scale networks easier and more flexible is software-defined networking, or SDN. It allows for the smooth and dynamic execution of complicated network choices via programmable and centralized interfaces. But SDN opens doors for people and companies to tailor network apps to their needs, allowing them to enhance services. On the other hand, it began to encounter a host of new privacy and security issues and brought the dangers of one point of failure all at once. In most cases, hackers use OpenFlow switches to conduct botnets or distributed Denial of Service (DDoS) assaults against the controller. Popular security apps that use deep learning (DL) to quickly identify and counteract attacks are on the rise. Here, we examine botnet-based DDoS attack detection using DL approaches in an SDN-supported context and demonstrate their performance. For the assessment, we utilize a dataset that we just created ourselves. In order to choose the most useful subset of characteristics, we used weighting of features and tuning techniques. Using both a synthetic dataset and actual testbed conditions, we validate the measurements or simulation results. The primary objective of this research is to identify botnet-based DDoS assaults using easily-obtained characteristics and data using a lightweight DL approach with baseline hyper-parameters. We found that the DL technique\u27s performance is affected by the optimal subset of features, and that the accuracy of predictions of the same approach may be varied with a different collection of features. Lastly, our empirical findings show that the CNN approach works better than both the dataset and the actual testbed environments. With CNN, the detection rate for typical flows is 99% and for malicious flows it drops to 97%
An Innovative Hybrid Approach to Forecasting Soluble Oxygen for Optimal Water Purification in Highly Concentrated Aquaculture
No full textAn important measure of the water\u27s quality in an aquaculture setting is the concentration of dissolved oxygen. Disintegrating oxygen content prediction using conventional techniques is slow and inaccurate due to the complexity, nonlinearity, and dynamics of the process. This research develops a hybrid model that addresses these problems by combining the radiation gradient enhancement machine (LightGBM) with this simple rechargeable unit (Biru). The first step was to find the important parameters by using linear interpolation and smoothing. After removing superfluous variables, the LightGBM algorithm predicts dissolved oxygen in highly intensive aquaculture and establishes its relevance. Lastly, the attention approach was used to map the learning parameter matrices and weighting matrices, allowing various weights to be applied to the Biru\u27s hidden states. The results show that the given prediction model can capture the upward trend of oxygen dissolution fluctuations over a 10-day period with a rate of accuracy reaching 96.28% in only 122 seconds. It takes the least amount of time to compare the model impacts of Biru-AAttention, LightGBM-GGRU, LightGBM-LSTM, as well as LightGBM-BBiru. The improved accuracy of its predictions makes it a valuable tool for controlling the water quality in intensive aquaculture
This article has been retracted due to a serious plagiarism issue
No full textThis article has been retracted due to a serious plagiarism issu
PREDICTION OF AIR POLLUTION BY USING MACHINE LEARNING
No full textDefensive and in charge Nowadays, in many developing and urban areas, the greater air quality has become one of the most important factors in everything. The magnificence of the air is negatively affecting collectibles due to the many tainting methods caused by power consumption, transportation, and other factors. Population growth is a major issue in our nation as it is happening at a rapid pace. This, along with economic expansion, is causing environmental issues in cities, such as water and air pollution. in a portion of the air.
Air pollution and pollutants have a direct effect on human health. As is well known, the main sources of pollution include carbon monoxide, nitrogen oxide, particulate matter (PM), so2; etc. A propellant such as gasoline, petroleum, etc. that has not been properly oxidized is producing carbon monoxide. The burning of thermal fuel releases nitrogen oxide (NO), but sulfur dioxide (So2), one of the main air pollutants, is more prevalent and has a greater impact on human health. Multidimensional collisions with location, time, and imprecise boundaries augment the air\u27s dominance. To examine AI-based approaches for air quality prediction is the aim of this enhancement. In this research, we will use a machine learning system to forecast air pollution
AI in Cybersecurity: Transformative Approaches to Safeguarding Information Technology Systems
No full textAI in cybersecurity has significantly changed how businesses secure their IT systems against increasingly sophisticated and ever-evolving cyberattacks. AI solutions that leverage machine learning, deep learning, and data analytics analyze patterns in threat behavior to identify and predict threats, enabling immediate responses that help organizations stay ahead of emerging threats. However, this revolutionary approach also introduces several challenges related to ethics and technology, including security vulnerabilities, data quality issues, bias in AI models, and questions of responsibility and privacy. As AI continues to progress, innovations such as behavioral biometrics, quantum computing, and autonomous security systems could become viable means of strengthening future cyber defenses. This paper discusses the current application of artificial intelligence in cybersecurity, reports on the challenges faced by AI systems, and outlines potential future developments that could revolutionize cybersecurity policies. It aims to raise awareness among practitioners and scholars about the importance of AI technologies in cybersecurity, providing a comprehensive analysis of AI-driven cybersecurity solutions
LIVE EVENT DETECTION FOR PEOPLE’S SAFETY USING NLP AND DEEP LEARNING
No full textIn recent years, ensuring public safety during live events has become a critical challenge due to the increasing scale of gatherings and potential risks. This study proposes a novel approach to Live Event Detection for People’s Safety using audio data and the LightGBM classifier. The system leverages real-time audio streams to identify anomalies, such as loud disturbances, explosions, or unusual crowd behavior, which could indicate potential safety threats. Audio features are extracted using advanced signal processing techniques, including Mel-frequency cepstral coefficients (MFCCs), spectral contrast, and chroma features. These features are fed into a LightGBM classifier, which provides efficient and robust performance for real-time classification of event categories and potential risks. The proposed methodology is evaluated using diverse datasets comprising audio samples from live events, including concerts, sports, and emergency situations, to ensure a comprehensive understanding of normal and abnormal patterns. The LightGBM model demonstrates high accuracy, low latency, and scalability, making it suitable for deployment in real-time applications. Additionally, the system integrates a feedback loop for continuous model improvement based on new audio data. The results highlight the system\u27s ability to enhance situational awareness and proactively alert authorities to potential risks, ensuring timely interventions. This approach demonstrates a significant step toward leveraging machine learning and audio analytics to improve public safety at live events
The Keyframe based Face in Video Recognition using Multi-Artificial Neural Network
No full textFace in video recognition has several challenges. Although deep learning approaches have achieved performance that surpasses people for still image- face recognition, video- face recognition remains a challenging task due to the large volume of data to be processed and intra / intervideo variations in pose, lighting, occlusion, scene, blur, video quality, etc. In this paper, deep convolutional neural network is used for feature extraction and artificial neural network is used for face recognition. The computation overhead of these deep learning approaches is reduced by introducing keyframe based face recognition in video. The low-quality frames are removed by extracting keyframes. The proposed method is tested on YTF dataset and the results are compared with recent methods. The experimental results substantially proved that the proposed method achieves a higher accuracy rate of 98.36% when compared with other recent methods
On nearly C-compact space
No full textIn this paper we have introduced a new type of convex topological space [5]called nearly C-compact space where a convex topological space is a topological space with a convexity [16]. Some fundamental characterizations and various basic properties have been obtained. Its relationship with other types of compact spaces is also investigate