Publications
Survey of Multiple Destination Route Discovery Protocols
Jul 16, 2024Journal International Journal of Computational and Experimental Science and Engineering
Publisher Prof.Dr. İskender AKKURT
DOI 10.22399/ijcesen.385
Issue 3
Volume 10
Route discovery protocols for multiple destinations are one of the most interesting research topics since it is applied for real-world applications and is needed in smart city services such as delivery services. The inclusion of artificial intelligence can improve the performance of multiple destination route discovery protocols. In this paper, we studied and analyzed multiple destination route discovery protocols based on different search strategies, especially artificial intelligence methods. The survey compares multiple destination route discovery protocols related to their applications and implementation tools. Important parameters are considered regarding route planning such as the mapping models of multiple destinations and different artificial intelligence search strategies. In this survey route discovery protocols for multiple destinations consider their different goals related to travel time and cost deadlines, moving obstacles, real-time traffic conditions in the city, customer satisfaction, and optimal route. In conclusion, using artificial intelligence can enhance route discovery protocols for multiple destinations compared to traditional search methods.
An Enhancement for Wireless Body Area Network Using Adaptive Algorithms
Jul 16, 2024Journal International Journal of Computational and Experimental Science and Engineering
Publisher Prof.Dr. İskender AKKURT
DOI 10.22399/ijcesen.409
Issue 3
Volume 10
Wireless Body Area Networks (WBANs) are one of the most critical technologies for maintaining constant monitoring of patient’s health and diagnosing diseases. They consist of small, wearable wireless sensors transmitting signals. Within this vision, WBANs are not without unique difficulties, for instance, high energy consumption, heat from the sensor, and impaired data accuracy. This paper introduces adaptive algorithms combining Convolutional Neural Networks (CNNs) and dynamic threshold mechanisms to enhance the performance and energy efficiency of Wireless Body Area Networks. The study utilizes the MIB-BIH Arrhythmias dataset to improve the detection of arrhythmias. The results show a 10.53% improvement in battery life and a 5.62-fold enhancement in temperature management when sleep mode technology is applied. As a result, the model reached the average accuracy of ECG classification of 98% and a high level of selectivity and sensitivity to a normal type of heartbeat and quite satisfactory results in the classification of arrhythmia type of heartbeat
Traffic Accident Prediction Using Historical Accident Data and Machine Learning
Feb 19, 2025Traffic accidents continue to pose a significant public safety challenge, resulting in substantial human and economic losses around the globe. The primary goal of this study is to investigate the role of machine learning methodologies in predicting road traffic accidents through the examination of previous accident reports. The plan is to craft a predictive model by analyzing past accident occurrence trends and patterns that will flag potentially high-risk regions and periods for road traffic accidents. The data will come from various sources including police documents, traffic camera footage, and climate models, ensuring that it is not affected during this stage of the project. Different methods of machine learning like the decision tree model, random forests, and neural networks will be put through their paces in order to ascertain which among them gives the best prediction results. The outcomes show that the models we examined can be efficient traffic safety mechanisms linking decision-makers and the public as well as enabling timely targeted interventions. Finally, the research emphasizes the need to make good use of the historical data in developing advanced predictive systems, thus serving as an effective way of regulating road safety through forecasting.
Analyzing Credit Risk with Machine Learning for Financial Institutions
Feb 19, 2025Journal Conference
In recent years, the financial industry has increasingly adopted machine learning models to enhance traditional credit risk assessment methods. This paper explores the application of machine learning techniques in analyzing credit risk for financial institutions, emphasizing predictive accuracy and model interpretability. The study evaluates various algorithms, including logistic regression, decision trees, and ensemble methods such as random forests and boosting algorithms like gradient boosting, using a dataset of historical credit data. Key performance metrics are discussed to assess the effectiveness of these models in predicting default probabilities and managing risk. The paper also tackles the challenges posed by model complexity, regulatory compliance, and ethical considerations regarding the use of machine learning models. The research results indicate that while machine learning models are more effective in risk prediction, proper implementation and continuous checking are necessary to ensure fair credit decision-making while preventing model biases. Thus, this paper adds to the existing literature that supports the inclusion of advanced analytics in financial risk management practices.
Predicting Judicial Decisions Using Machine Learning on Historical Court Case Data
Feb 19, 2025Journal Conference
The judicial system plays a crucial role in the functioning of society, however, the process of predicting judicial decisions continues to be a difficult and critical task. This paper looks at how machine learning techniques can be applied to predict judicial outcomes based on historical court case data. The analysis utilizes datasets containing case summaries, legal arguments, and previous verdicts, which can be also outfitted with sophisticated analytical models to enable the identification of patterns and critical factors which most likely impacted verdicts. The approach comprehensively includes data preprocessing, feature extraction, and the leveraging of advanced machine learning methods like natural language processing for text analysis. The findings show that the models can achieve a maximum precision rate in predicting the outcomes of cases, thus, giving legal practitioners, policymakers, and researchers remarkable knowledge. In addition, this study includes the discussions of ethical issues, limitations, and how to improve the level of legal transparency and efficiency. The project aspires to contribute to the rising area of research on the integration of law and artificial intelligence which also includes the development of predictive analytics for justice and the judicial process with the employment of this research methodology of data mining.