https://vjol.info.vn/index.php/DHM-TPHCM <p><strong>Tạp chí của Trường Đại học Mở Thành phố Hồ Chí Minh</strong></p> vi-VN Wed, 15 Oct 2025 00:00:00 +0700 OJS 3.1.2.4 http://blogs.law.harvard.edu/tech/rss 60 https://vjol.info.vn/index.php/DHM-TPHCM/article/view/125366 Intelligent irrigation systems play a crucial role in addressing the global issues of water scarcity, climate variability, and sustainable agricultural production. These systems can help identify the efficient time and the exact quantity of irrigation through the use of data-driven ideas, which ensures maximum crop yield with minimal use of water. This paper provides a thorough comparative analysis of the four most commonly used Machine Learning (ML) models: Support Vector Machines (SVM), Gradient Boosting (GB), K-Nearest Neighbors (KNN), and Logistic Regression (LR), to predict the need of irrigation based on critical environmental and agronomic variables. The dataset features include soil moisture, air temperature, relative humidity, solar radiation, and crop types, among other features, obtained using sensor networks installed on farmland. We trained and tested each model before comparing its performance using standard evaluation metrics, which include accuracy, precision, recall, F1 Score, and the Area Under the Curve. These findings indicate that GB and KNN models performed better than SVM and LR. For instance, GB and KNN achieved precisions of 95.6% and 92.4%, respectively, compared to SVM and LR, which achieved precisions of 86.2% and 72.8%, respectively. In both accuracy and generalization, the GB model performs overall best. This study contributes a fair investigation of the suitability of well-known ML models in irrigation forecasting for smart farming in the south-western region of Nigeria. This study makes use of a region-specific dataset that is gathered by sensor networks, involving 100,000 records in two farming seasons. Yusuf Owolabi Olatunde, Oluwafolake Esther Ojo, Oluwatobi Adedamola Ayilara-Adewale, Glorious Omokunmi Anjorin-Adeboye, Taiwo Samson Olutoberu Bản quyền (c) https://vjol.info.vn/index.php/DHM-TPHCM/article/view/125366 Sun, 07 Sep 2025 00:00:00 +0700 https://vjol.info.vn/index.php/DHM-TPHCM/article/view/125370 Accurate soil classification is imperative for determining land suitability for various construction projects in construction and geotechnical engineering. The physical and mechanical properties of soil significantly influence the design of foundations, the assessment of landslide risks, and the overall stability of structures. Recognizing the limitations of traditional soil classification methods, which are often labor-intensive and time-consuming, this research introduces machine learning as a transformative tool for enhancing soil classification processes. Utilizing K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) algorithms, this study analyzes 5,869 soil samples collected from 39 construction projects in Ho Chi Minh City, Vietnam, to evaluate the efficacy of machine learning techniques in classifying construction soils. The study identifies optimal strategies that significantly improve classification accuracy through a methodical investigation that includes varying training set sizes and integrating directly obtained and indirectly derived soil features. The findings underscore the importance of incorporating liquid and plastic limits and their derived indices, with the KNN model demonstrating superior performance in specific scenarios. This research highlights the potential of machine learning to revolutionize traditional soil classification methods. It provides foundational insights for future advancements in geotechnical engineering, aiming to achieve safer, more efficient, and sustainable construction practices. Danh Thanh Tran, Dinh Xuan Tran, Vinh Hoang Truong Bản quyền (c) https://vjol.info.vn/index.php/DHM-TPHCM/article/view/125370 Mon, 13 Jan 2025 00:00:00 +0700 https://vjol.info.vn/index.php/DHM-TPHCM/article/view/125367 Automated customer consulting is a form of automated customer care and consulting that utilizes texting and chat functions to replace human interaction. This research improves the Bi-LSTM language model. We aim to enhance the accuracy and applicability of an automated customer consultation system, which may impact enterprises and traders. Our question-answer system uses querying the entity and model textual similarity to match models. Automated customer care systems utilize computers or other technologies to assist customers. It empowers clients to address problems without human assistance in customer care. Human resources can address complex requests or high-value consumers, as automation handles many repetitive and straightforward activities. Many firms utilize it, especially fast-growing ones that need to arrange support. Trung Quoc Nguyen Bản quyền (c) https://vjol.info.vn/index.php/DHM-TPHCM/article/view/125367 Fri, 05 Sep 2025 00:00:00 +0700 https://vjol.info.vn/index.php/DHM-TPHCM/article/view/125371 The rapidly increasing volume of textual data has made manual labeling extremely costly and time-consuming. To address this limitation, researchers have gradually focused on unsupervised learning techniques that enable models to classify text without relying on labeled data. Among these, deep clustering has garnered significant interest. However, most existing deep clustering methods are primarily designed for computer vision tasks. In this paper, we propose modifications to two of the most powerful deep clustering methods, including DEKM and DeepCluster, by integrating transformer algorithms in the Natural Language Processing (NLP) domain, enabling these methods to handle textual data. With the proposed methods, we achieved the best results on the test set of the Financial Phrase Bank (FPB) dataset with an accuracy of 57.71% and on the test set of the Twitter Financial News (TFN) dataset with an accuracy of 65.58%. Although these results are still lower than those of traditional supervised deep learning methods, we have demonstrated that the performance of our proposed methods can be further improved when trained with more data. This highlights the promising potential of deep clustering methods for natural language processing tasks. Especially when addressing tasks where the data is either unlabeled or lacks sufficient labeling. Cong Chi Pham, Bay Van Nguyen, Huy Quoc Nguyen Bản quyền (c) https://vjol.info.vn/index.php/DHM-TPHCM/article/view/125371 Mon, 13 Jan 2025 00:00:00 +0700 https://vjol.info.vn/index.php/DHM-TPHCM/article/view/125368 Breast cancer remains a leading cause of mortality among women worldwide. In Vietnam, the rising incidence underscores the urgent need for early diagnostic markers. Genetic factors, particularly Single Nucleotide Polymorphisms (SNPs), play a critical role in breast cancer susceptibility. The SNP rs34678647, located downstream of the miR-221/222 cluster targeting Estrogen Receptor alpha (ERα), is hypothesized to influence breast cancer risk by modulating cancer-related pathways. This study investigates the association between rs34678647 and breast cancer risk in the Vietnamese population. A total of 234 DNA samples, comprising 131 breast cancer cases and 103 healthy controls, were genotyped using the Polymerase Chain Reaction-High Resolution Melting (PCR-HRM) technique, which is selected for its high sensitivity and specificity in SNP detection. Genotype frequencies were determined, and statistical analyses were conducted to evaluate associations. The PCR-HRM method successfully genotyped rs34678647 with high accuracy. The T allele was observed in 23% of cases and 19% of controls; however, no significant association with breast cancer risk was identified (OR = 1.19, 95% CI: 0.77-1.85, p = 0.43). Genotype distributions conformed to the Hardy-Weinberg equilibrium in both groups, supporting the representativeness of the sample. In conclusion, while the T allele of rs34678647 showed a nonsignificant trend toward increased breast cancer risk among Vietnamese women, the results were not statistically conclusive. These findings highlight the need for larger-scale studies to further explore the potential role of rs34678647 as a genetic risk factor and its applicability as an early diagnostic biomarker. Nga Thi Nguyen, Thanh Thi Ngoc Nguyen, Hue Thi Nguyen Bản quyền (c) https://vjol.info.vn/index.php/DHM-TPHCM/article/view/125368 Sun, 07 Sep 2025 00:00:00 +0700 https://vjol.info.vn/index.php/DHM-TPHCM/article/view/125365 Distichochlamys citrea, an endemic plant native to central Vietnam, holds significant ethnomedicinal value in Vietnamese herbal medicine. Although the essential oil derived from the rhizome of D. citrea is known for its bioactivities, including antibacterial and antioxidant properties, its anti-inflammatory potential has not been extensively explored yet. In this study, the anti-inflammatory effect of the essential oil has been comprehensively evaluated from in silico to in vivo studies. A molecular docking study revealed that cineole, neral, and geranial, three main components of the essential oil, were capable of forming promising interactions with 5-lipoxygenase and inducible nitric oxide synthase (ranging from -4.7 to -6.3 kcal/mol). Furthermore, the essential oil exhibited a strong inhibitory effect against protein denaturation (86.67%, 100 µg/mL). In the carrageenan-induced paw edema model, the essential oil (4%) could inhibit 32.83% of paw edema as compared to the NaCl-treated group. Collectively, these findings position the essential oil extracted from rhizomes of D. citrea as a novel candidate for the development of anti-inflammatory medicine. Buu Gia Tran, Hang Bich Do, Huong Ngoc Quynh Dinh, Phu Hoang Nguyen, Khanh Kim Dao, Ty Viet Pham Bản quyền (c) https://vjol.info.vn/index.php/DHM-TPHCM/article/view/125365 Fri, 05 Sep 2025 00:00:00 +0700 https://vjol.info.vn/index.php/DHM-TPHCM/article/view/125369 Indole-3-Acetic Acid (IAA) is a crucial plant growth-promoting hormone produced as a secondary metabolite by various microorganisms. The present study aims to isolate and screen IAA-producing endospore-forming bacteria from soil samples collected in Vietnam. A total of ten bacteria were isolated, and they were shown to have the ability to produce IAA, with strain IA3 exhibiting the highest production. Strain IA3 was identified as Bacillus subtilis based on the 16S rRNA sequencing and subsequently used to optimize conditions for IAA production. To maximize IAA yield, key factors influencing production were analyzed using Box-Behnken design. The optimized conditions led to a maximum IAA production of 47.67 ± 0.78 g/mL under the following conditions: 15.65 g/L molasses, 1.06 g/L (NH4)2SO4, and 0.52 g/L tryptophan. Therefore, Bacillus subtilis IA3 has potential applications for stimulating and enhancing plant growth or crop production. Tuan Ngoc Nguyen, Linh Huynh Yen Luu Bản quyền (c) https://vjol.info.vn/index.php/DHM-TPHCM/article/view/125369 Wed, 07 May 2025 00:00:00 +0700