Satriwitthaya 2 School

Diabetes poses a significant global health challenge due to its rising prevalence and the high number of undiagnosed cases. Early detection is crucial, and machine learning presents promising solutions for enhancing diagnostic accuracy. This study compares binary-class (supervised learning) and one-class classification (unsupervised learning) approaches for diabetes prediction using clinical data from the publicly available Kaggle Diabetes Dataset, which includes eight features: age, gender, hypertension, heart disease, BMI, HbA1c level, blood glucose level, and smoking history. The data is strongly biased towards diabetic cases, with 91500 cases compared to 8500 non-diabetic cases. Data preprocessing, feature selection, and model training were conducted in Python using Jupyter Notebook. For binary classification, several supervised machine learning algorithms are employed, including logistic regression, decision trees, random forests, gradient boosting, adaptive boosting, support vector machines, K-nearest neighbors, and Naïve Bayes. These models are trained and evaluated using accuracy, precision, recall, and F1-score, with 5-fold cross-validation to ensure model robustness. For one-class classification, 91,500 diabetic cases were used to train an unsupervised machine learning support vector machine model. The trained one-class model was then evaluated using both diabetic and non-diabetic cases, and it was found that the one-class model offers better and more consistent performance compared to the binary class, with overall performance metrics above 95%. The results highlight key performance differences between classification strategies, offering insights into the optimal modeling approach for clinical screening and biomedical applications.

Lung cancer is a prevalent disease, with nearly 238,000 new cases diagnosed in 2023. This study utilizes clinical predictors from a Kaggle dataset containing 309 observations across 15 variables to aid in lung cancer diagnosis. The variables include swallowing difficulty, peer pressure, gender, allergy, yellow fingers, anxiety, wheezing, alcohol consumption, chronic disease, chest pain, coughing, fatigue, smoking, age, and shortness of breath. The research aims to develop and compare various supervised machine learning models for classifying and predicting lung cancer, while also identifying key clinical tests and parameters using unsupervised statistical models. The dataset was divided into training and test sets, balanced, and preprocessed for unbiased training. Feature selection and machine learning models were applied to identify crucial predictors. The study explored tree models, logistic regression, Naïve Bayes, support vector machine (SVM), ensemble, neural network, and kernel models. Among these, the linear SVM achieved the highest accuracy of 93.75% with 5-fold cross-validation. However, it showed overfitting, with a lower test accuracy of 82.55%. The Gaussian Naïve Bayes model emerged as the optimal choice, providing consistent performance between validation and test cases. It achieved the highest cross-validation classification accuracy of 82.81% using only 9 variables: swallowing difficulty, peer pressure, gender, allergy, yellow fingers, anxiety, wheezing, alcohol consumption, and chronic disease. This model allows for effective training with fewer predictors without compromising classification

Breast cancer (BC) is now identified as a disease with a significant impact on morbidity and mortality that is growing and widespread worldwide. This study uses a publicly available clinical dataset of 699 patients from the University of Wisconsin with 9 variables: (1) clump thickness, (2) uniformity of cell size, (3) uniformity of cell shape, (4) marginal adhesion, (5) single epithelial cell size, (6) bare nuclei, (7) bland chromatin, (8) normal nucleoli, and (9) mitoses. This dataset has been used for many studies in the past to pinpoint critical factors in patient diagnosis. Here, we use this data to ensure its unbiasedness and accuracy. We then apply principal component analysis and machine learning models to identify factors in diagnosing a malignant or benign tumor. We investigate and compare the classification accuracy of different machine learning models, including tree, linear discriminant, quadratic discriminant, logistic regression, naive Bayes, support vector machine (SVM), K-nearest neighbor (KNN), ensemble, neural network, and kernel. The best models that can achieve the highest accuracy are medium Gaussian SVM, coarse Gaussian SVM, and cosine KNN, with an accuracy of 96.5%. The principal component analysis method is then performed to identify crucial components and build an accurate model with fewer parameters. The medium Gaussian SVM has the highest cross-validation classification accuracy of 96.98% and requires only three predictors: normal nucleoli, bare nuclei, and cell size uniformity.

Most of the respondents are female, aged 17–22 years, they are students/college students and are single. From the study, it was found that most of the samples had sleeping behavior. In terms of the sleeping duration which is between 5-8 hours, followed by less than 5 hours and more than 8 hours, respectively. In terms of the sleeping time, most of them had during 22.01-00.00, followed by 00.01-02.00, after 02.00 and 20.00 - 22.00, respectively. As for the study of symptoms and mental state, it was found that it was at a moderate level. When considering one by one, it was found that the symptoms of irritability and mood swings were the most, which were at a moderate level, followed by the anxiety of people being around them and their surroundings, feeling depressed and unhappy in life, respectively which is at a low level of symptoms. Therefore, from the results of the study, it can be concluded that sleep behavior affects the incidence of mental health conditions because most of the samples had a sleep duration in the normal period of 5-8 hours, and most of them slept during a reasonable time, not too late, which is during 22.01-00.00 hrs. This causes the overall symptoms to be at a moderate level. However, there are some behaviors of staying up late and sleeping less which may affect the risk of various mental health conditions in the future.

Background: Irrational antibiotic uses in livestock resulting in antibiotic residues in pork, chicken, meat and other products from animals. Objective: to examine antibiotic residues in pork, chicken, meat, and ready-to-drink cow milk Methods: The samples were tested by antibiotic residue detection kits from the Department of Medical Sciences, Thailand. These detection kits have 93% accuracy, 78.9% sensitivity, and 96.7% specificity. Convenience sampling was conducted. A total of 263 samples which consisted of 115 samples of fresh pork, 21 samples of chicken and 12 samples of fresh beef sold in the fresh markets, 43 samples of ready-to-eat cow's milk, 36 samples which advertised as organic pork, and 36 samples which advertised as hygienic chicken were tested for antibiotic residues; Tetracycline, Macrolide, Aminoglycoside, Sulfonamide, Penicillin. Result: From a total of 263 samples, the results showed that 148 sample of fresh pork, chicken and meat bought from fresh market were found antibiotic residues in 103 samples (69.59%); fresh meat (n=12, 100%), fresh chicken (n=18, 85.71%) and fresh pork (n=73, 63.49%). Results of ready-to-drink cow milk showed that from a total of 43 samples, 6 samples (13.95%) were found to contain Tetracycline residues. 72 samples of fresh pork and chicken, 36 each, which advertised as hygienic were examined, no sample was detected of Tetracycline residue Conclusion: 69.59% (103/148)of fresh pork, chicken and meat samples and 13.95% (6/43) of ready-to-drink cow milk samples were detected antibiotic residues. No antibiotic residues found in 72 samples consisted of 63 samples of fresh pork and 36 samples of chicken which advertised as hygienic.

<strong>ABSTRACT: </strong>Coronavirus in 2019, also known as COVID-19, is SARS-CoV-2, is spreading across the globe. Most of our work focuses on situation and statistics of coronavirus cases 2019 in Thailand. This article focuses on beginning of disease and spreading around the world and in Thailand. As many as 11 strains of the coronavirus 2019 mutation, causing the cumulative number of infections to increase and even with the invention and development of vaccines. To prevent disease comes out a variety of vaccines. But the number of infections and deaths continues to rise. Therefore, government disease prevention measures should be followed and self-protection should be appropriate. To prevent the number of infections and deaths from increasing again.

Logistics and supply chain play a very important role in business and industry these decades. Track and Traceability is one of the key components in making supply and chain more efficient. Furthermore, in Healthcare supply chain, Track and Traceability must be in place to ensure the safety of patients at the downstream. While all sectors in the world have the massive impacts from the COVID-19 pandemic, the world is starting to realize the importance of vaccine and it eventually becomes the only hope of the humanity. Hence, the vaccine supply chain becomes the major concerns in the Healthcare sectors. Temperature control throughout the supply chain activities e.g. storage, transportation and distribution are vital. Thus, not only tracking location and activity, temperature must also be monitored. Each of every vaccine has its own storage temperature in order to remain its quality and efficiency. One of the examples is our expectation COVID-19 vaccine. The sources reveal that the temperature storage range can be varied from -70 to 25 degree Celsius. From the authors' previous research, we identified problems about the supply chain and the certain requirement for the storage temperature of vaccine. Then, we invented the substitution of traditional ice pack used in nowadays' transportation to the liquid nitrogen cooling system. The research was concluded that liquid nitrogen has better performance in both terms of temperature stabilization and the period of time keeping temperature within desired range. However, our previous Vaccine Cold Box by Liquid Nitrogen did not have the ability to track and trace the location nor monitoring the temperature real time. Thus, in this study, an effort is made to develop the COVID-19 Vaccine Track and Traceability System. Firstly, the IOT system will be implemented. RFID tag with temperature sensor will be applied in the cold box. Then, the reader will collect the data and send to cloud server. At this point, the temperature data will be forwarded into two directions. One is to control the solenoid valve which is located in the cold box for releasing liquid nitrogen to the right amount wanted. Another is to display and collect the real time temperature at the Dash board for the temperature monitoring. Moreover, the previous study's calculation process has shown that there is another factor related to the length of time vaccine cold box could maintain temperature within range. It is the Thermal conductivity rate of the material used for the exterior of the cold box. We can easily increase the length of time by using the material with lower Thermal conductivity rate. After the cold box is built, we will set experiments to test the efficiency of the system, collect and analyze the data before the conclusion is reached.