TULTECH Journals
Not a member yet
235 research outputs found
Sort by
Performance Evaluation of Logistic Regression, Random Forest, and SVM Models in Heart Disease Prediction
No full textEarly identification of high-risk patients for cardiovascular disease is critical for reducing morbidity and improving treatment outcomes. This study applies supervised machine learning techniques to predict heart disease using the publicly available Kaggle heart failure dataset, which comprises 918 observations with demographic, clinical, and laboratory attributes, including age, resting blood pressure, cholesterol level, fasting blood sugar, maximum heart rate achieved, ST depression induced by exercise (Oldpeak), and electrocardiographic and chest pain characteristics. The dataset was pre-processed using a unified pipeline that standardized numerical features and encoded categorical variables via one-hot encoding. The data were split into training and testing sets using an 80/20 stratified approach. Three classification algorithms like Logistic Regression, Random Forest, and Support Vector Machine (SVM) with a radial basis function kernel were evaluated using accuracy, precision, recall, F1-score, and ROC–AUC metrics, complemented by confusion matrices and ROC curves. All models demonstrated strong predictive performance, achieving test accuracies of approximately 0.88. The SVM model exhibited the highest discriminative capability, with a ROC–AUC of approximately 0.95, while Logistic Regression achieved the highest recall (≈ 0.93), making it particularly suitable for applications where minimizing false negatives is critical. Correlation analysis identified Oldpeak, maximum heart rate, age, and fasting blood sugar as key factors associated with heart disease. These findings suggest that relatively simple machine learning models, when combined with appropriate preprocessing, can serve as effective decision-support tools for heart disease risk stratification in clinical settings
SCP-IoT: Enhancing IoT Communication Security Against Routing Attacks
Full text linkThe Internet of Things (IoT) needs to be protected while in transmission. Insecure Internet of Things equipment connectivity can direct to security breaches. As a result, third parties can get access and make changes in order to cause problems for things connected in the system. In order to address these difficulties, the IoT communication security needs to be addressed. A new strategy named "secure communication utilising cryptographic approaches for IoT" was presented in this research to deal with this problem. There are three parts to the model, which is called the "safe communication protocol for IoT." First, the initiator sends a connection request to the respondent with the source identification and a true cryptography nonce to initiate the communication. Secondly, the responder examines the nonce\u27s freshness and the source\u27s identity when it receives a request. After that, the responder uses KDH to compute and deliver the MAC result for the SRC ID as part of the Finish message to the initiator. Few current strategies, including developing constrain fuzzy routing principles, were evaluated and compared to the proposed model. Prior to this study, the most important metrics were the MLR and MDR ratios, the spectrum utilisation rate, the network lifetime, and the utilisation rate
Assessing Creativity in Text-to-Image Generation: A Quantitative Analysis using Structured Human Rating Metrics
Full text linkThis research examines the creativity of text-to-image (T2I) generation models using a systematic human rating framework to evaluate four important dimensions of creativity: originality, relevance, aesthetic appeal, and imaginativeness. The advanced development of generative AI tools DALL•E 2, Mid journey, and Stable Diffusion creates subjective barriers to measuring their creative output. This evaluation analyses 100 pictures generated by DALL•E 2 versus Midjourney versus Stable Diffusion through testing a wide spectrum of commands from various artistic domains. The evaluation demonstrates that Mid journey offers better artistic results than DALL•E 2 and Stable Diffusion when comparing artistic achievements between the models. DALL•E 2 stands out for its relevance because it produces prompts with extremely strong semantic alignment to the provided instructions. The total creativity score for Stable Diffusion falls below its rivals but the model presents occasional improvements in originality. The framework quality shows itself through high agreement among evaluators. The evaluation needs multiple assessment methods to identify distinctive creative abilities of T2I models while providing important guidance for AI development in creative domains in the future. The research has established comprehensive evaluation standards that future investigations in creative AI must follow because of the essential need for methodological rigor
Developing a Conceptual Framework for Soil Property Analysis and Crop Yield Prediction Using Machine Learning Techniques
Full text linkThe most important single factor is soil fertility which influence crop sustainability and agricultural productivity. The necessity to use data-driven approaches to assess the health of the soil and propose the crops that should be grown in it has become a crucial issue because the accuracy of agriculture is required increasingly frequently. Based on the dataset of the Soil Health Card (SHC) of the Government of India, the presented study provides a conceptual framework that involves the application of the machine learning approaches to analyse soil characteristics and predict its agricultural productivity. The framework is based on twelve important soil parameters: sulphur (S), nitrogen (N), zinc (Zn), phosphorus (P), electrical conductivity (EC), potassium (K), manganese (Mn), copper (Cu), boron (B), iron (Fe), organic carbon (OC), and pH to cluster soil samples into the categories of low, medium, and high soil fertility by using the K-means algorithm. To suggest the correct crops that must be grown in each of the fertility categories, the Random Forest Classifier is then trained after the clustering. The model is checked by K-Fold cross-validation (k=5) and Holdout (80/20 split) to make sure that in unseen data strong generalization will be achieved. An average performance of 91 percent in K-Fold, and zero in holdout validation showing no inaccuracies in dividing the test set and an RMSE and MAE also zero, results indicate high performance and no mistakes in classification. Also, the proposed methodology enhances the agronomic decision-making with the help of AI-based crop proposals targeting each of the fertility classes. This study is an indication of the efficiency of the integration of supervised and unsupervised methods in agricultural informatics. It attracts interest in how intelligent models can high-grade the use of resources, encourage sustainable agriculture and endow growers with useful information based on real-life DO data
Utilizing Gamification in Smart Waste Management: A Participatory Approach Integrating Green Schools, the Internet of Things (IoT), and Social Marketing
No full textUrban and rural life heavily depends on the movement and collection of waste. A weak and inefficient waste collection system increases costs and poses significant risks to public health. Conventional waste collection methods are neither the most effective nor the most efficient. Enabling smart, sufficient, and self-sustaining Internet of Things (IoT) solutions is crucial for enhancing human welfare. In recent years, many countries have faced increasing pressure to meet legally binding targets related to recycling and waste management, with a growing focus on sustainability from policymakers and consumers alike. From this perspective, recycling plays a crucial role in reducing the amount of waste disposed of while simultaneously decreasing the demand for raw materials. The waste management process consists of six main stages: waste generation; handling, segregation, storage, and processing at the source; collection; sorting, processing, transformation, and conversion; transportation; and disposal. In this proposal, we first explore foundational studies on creating incentive systems to attract public participation. The next phase focuses on the implementation of participatory systems. The third step involves the development and construction of waste management applications, followed by the fourth step, which is dedicated to educating all stakeholders involved
Predicting Vitamin D Levels Using Ordinal Logistic Regression, Gaussian Process Regression and ARIMA: A Comparative Study
No full textVitamin D deficiency is a common health condition that increases the risk of metabolic, cardiovascular, and musculoskeletal disorders. Many individuals are unaware of their vitamin D deficiency. In this work, we develop and present three complementary machine learning models to explore Vitamin D levels based on regular healthcare data. The dataset consists of anonymized patient records with demographic features, clinical indicators, and laboratory measurements of serum 25(OH)D. It is taken from a healthcare setting and pre-processed to eliminate absent or inconsistent results. Vitamin D level variables were transformed into ordered, clinical categories: severe deficiency, deficiency, insufficiency, and sufficiency. However, for regression and time-series forecasting, the original continuous concentration, measured in ng/mL, was preserved together with monthly averages. A proportional odds Ordinal Logistic Regression model was used to figure out Vitamin D status. The best overall performance was an accuracy of 0.77, a macro recall of 0.76, and an F2-score of 0.78. Most of the mistakes were made between categories that were next to each other. We utilized Gaussian Process Regression to predict continuous Vitamin D concentration. The results were R² = 0.79, MAE = 2.3 ng/mL, and RMSE = 3.4 ng/mL, which means that the model can get close to laboratory values with clinically acceptable error. To capture temporal dynamics, an ARIMA model was fitted to monthly mean Vitamin D levels and showed the best performance with R² = 0.82, MAE = 2.0 ng/mL and RMSE = 3.1 ng/mL, accurately recreating the observed seasonal pattern
Assessment of Seasonal Fluctuations in Heavy Metal and Bacterial Pollution in the Euphrates River near Najaf, Iraq
Full text linkThis research work assessed seasonal variations in physicochemical parameters, heavy metals, and bacterial contamination in the Euphrates River near Najaf, Iraq, from December 2023 to November 2024. Results revealed marked seasonal fluctuations in water temperature, ranging from 14.80 ± 2.04 °C in winter to 30.31 ± 1.01 °C in summer. Total dissolved solids (TDS) were highest in winter (924.19 ± 44.26 mg/L) and lowest in summer (652.74 ± 37.50 mg/L). While pH, dissolved oxygen (DO), and biochemical oxygen demand (BOD5) remained within international standards, TDS exceeded the World Health Organization (WHO) aesthetic guideline, and concentrations of lead and cadmium surpassed both WHO and U.S. Environmental Protection Agency (USEPA) limits. Lead concentrations increased substantially from spring (0.05 ± 0.02 mg/L) to autumn (1.47 ± 0.31 mg/L). Total coliform bacteria (TCB), indicative of faecal contamination, were present in all samples. Correlation analyses suggested that industrial effluents and untreated sewage represent common sources of heavy metals and bacterial pollutants. The findings indicate that the Euphrates River water in this region is unsuitable for direct consumption without advanced treatment and presents significant risks to human health and the aquatic ecosystem
The Effect of Temperature-Induced Stress at Different Developmental Periods on Short-Term Memory of C. elegans
No full textAs the incidence of neurodegenerative diseases continues to increase, it is essential to evaluate the causal factors that lead to neurodegeneration and resultant memory loss. In this study, Caenorhabditis elegans were used as a model organism to explore the effects of developmental stress on learning and short-term memory. Half of the population were placed into elevated temperatures, to invoke heat stress, while the other half was kept at their optimal functioning temperature of 22°C. The worms were then taught a simple chemosensory learning task. Results show that 25°C produced a small reduction in learning, while 28°C produced a substantial reduction. In a follow-up study, C. elegans were exposed to 28°C at different life stages Day 0 (embryo), Day 1, Day 2, and Day 3 stress each reduced learning when compared to controls, with the greatest deficit being stress experienced during Day 2. Insights into neurodevelopmental time periods of vulnerability to stress and the potential mechanisms affected by early-life stress can help in the prevention of neurodegenerative diseases and their associated cognitive decline
Enhancing Human Activity Recognition through Machine Learning Models: A Comparative Study
No full textThis study explores Human Activity Recognition (HAR), a machine learning technique utilized in health monitoring and human-computer interaction. HAR identifies human actions through sensor data from accelerometers and gyroscopes in smartphones and wearables. Key components of this technique include model selection, feature extraction, preprocessing, and data collection to classify activities such as standing, lying, sitting, and walking. Despite its potential, privacy concerns warrant further research for effective deployment. A comprehensive analysis of HAR techniques has been described in this research work
Spatiotemporal Assessment of Physicochemical Properties and Anthropogenic Impacts on Seawater Quality in the Gulf of Durrës, Albania
No full textThe coastal zone of Durrës, Albania, represents one of the most anthropogenically influenced marine areas along the eastern Adriatic Sea, where intensive tourism, industrial activities, and agricultural runoff exert increasing pressure on coastal ecosystems. This study presents a year-long assessment of seawater quality based on physicochemical parameters measured across seven sampling stations in the Gulf of Durrës from January to December 2024. In situ analyses were conducted using a Horiba “U-50” multiparameter analyzer to evaluate temperature, pH, oxidation–reduction potential (ORP), conductivity, turbidity, dissolved oxygen (DO), total dissolved solids (TDS), salinity, and specific gravity. Overall, the recorded parameters indicated stable water quality within acceptable ecological limits, with limited spatial and temporal variation among most sites. However, localized deviations in ORP and turbidity were observed near the Pista Koka, Fishing Port, and Old Port stations during the summer months, corresponding to periods of intensified human activity and wastewater discharge. These findings emphasize the influence of seasonal anthropogenic inputs on nearshore water quality and underscore the need for continuous monitoring and targeted management strategies to mitigate human-induced degradation and ensure sustainable marine and tourism development in the Durrës coastal region