https://elib.vku.udn.vn/handle/123456789/1431 2026-09-09T21:45:29Z 2026-09-09T21:45:29Z Le, Dinh Phuc Nguyen, Tran Chi Khang Duong, Cong Cuong Doan, Quang Thang Pham, Van Ngoc Vinh Nguyen, Huu Nhat Minh Nguyen, Thanh Binh https://elib.vku.udn.vn/handle/123456789/7694 2026-09-08T08:54:28Z 2026-03-01T00:00:00Z

Title: A Two-Stage Learning Framework for Coffee Disease Detection Authors: Le, Dinh Phuc; Nguyen, Tran Chi Khang; Duong, Cong Cuong; Doan, Quang Thang; Pham, Van Ngoc Vinh; Nguyen, Huu Nhat Minh; Nguyen, Thanh Binh Abstract: Coffee production is a key component of the agri-cultural economy of the Central Highlands, with considerable commercial value derived from the Robusta and Arabica varieties grown in a variety of ecological zones. However, coffee production is hampered by geographically distributed disease outbreaks that require sophisticated, real-time monitoring capabilities, and has not benefited from modern technological advances in digitization and artificial intelligence. The recent climate changes cause geographically distributed disease out-breaks - require more sophisticated monitoring mechanisms. Existing disease detection and response systems are severely constrained by the lack of data analytics tools to provide timely, location-aware information. To fill the critical gap, this paper will create an integrated deep learning framework to detect coffee diseases with computer vision techniques and support real-time disease surveillance and management decisions. The proposed two-stage learning framework could classify diseases into seven categories: rust, pink disease, maly-bug infestation, nematode damage, Phoma leaf spot, leaf miner damage and healthy foliage. YOLO is used to precisely locate the symptom areas. By integrating the automated detection module into the digital mapping platform, the prevalence of the disease can be monitored spatiotemporal manner, enabling early warning systems and targeted intervention strategies for sustainable coffee production in the region. Description: Proceedings of The FISU Joint Conference on Artificial Intelligence 2026 (FJCAI); pp: 131-135

2026-03-01T00:00:00Z Tran, Minh Quan Huynh, Xuan Hau Thai, Thi Hong Phuc Nguyen, Ket Doan Le, Thi Thu Nga https://elib.vku.udn.vn/handle/123456789/7693 2026-09-08T08:31:56Z 2026-03-01T00:00:00Z

Title: A Two-stage Architecture for Phishing Email Detection via Domain Analysis with Inverse Transformer Fine-Tuning Authors: Tran, Minh Quan; Huynh, Xuan Hau; Thai, Thi Hong Phuc; Nguyen, Ket Doan; Le, Thi Thu Nga Abstract: In the digital era, email has become the primary attack vector exploited by cybercriminals through increasingly sophisticated phishing campaigns. In Vietnam, unique linguistic characteristics, combined with the widespread use of domain obfuscation techniques, have significantly reduced the effectiveness of traditional detection systems that rely on blacklists or hand-crafted lexical features. To address these challenges, this paper proposes a comprehensive two-stage architecture for phishing email detection that efficiently eliminates obvious threats in the first stage and accurately classifies ambiguous “gray-zone” cases in the second stage. The proposed architecture rapidly detects overt attack indicators by integrating an in-depth rule-based filtering mechanism with a classification module based on modern Transformer architectures. Experiments were conducted on a large scale dataset collected from reputable Vietnamese sources, consisting of 48,866 phishing email samples. The experimental results show that the first stage achieves an accuracy of 87%, while the second stage reaches an accuracy of 97.0% accuracy for legitimate emails and 88.0% for phishing emails by using the URLBERT-Tiny model enhanced with an inverse layer-wise fine-tuning strategy. The proposed Two-stage strategy demonstrates the best overall performance, achieving an accuracy of 99.8%. These results validate the effectiveness of combining rule based domain analysis with intelligent parameter optimization techniques on specialized compact language models for real-time cybersecurity tasks. Description: Proceedings of The FISU Joint Conference on Artificial Intelligence 2026 (FJCAI); pp: 219-226

2026-03-01T00:00:00Z Dang, Vinh Phan, Thi Yen https://elib.vku.udn.vn/handle/123456789/7692 2026-09-08T08:25:28Z 2026-03-01T00:00:00Z

Title: Measuring Research Competence of University Students using a Multisource Assessment Model Authors: Dang, Vinh; Phan, Thi Yen Abstract: Research has become an essential of higher edueation as universities increasingly emphasizæ inquiry-based learning and student engagement in research activities. However, measuring students' research competence remains challenging many existing studies rely primarily on self-assessment, which may lead to subjective bias and limited reliability. To address this limitation, the present study proposes a multi-source assessment model for measuring research competence among university students. The study aims to develop and validate a multidimensional framework for assessing students' research competence by integrating multiple perspectives, including student self-assessment, lecturer evaluation, and assessment. A survey instrument consisting Of 36 items was developed based on eight dimensions of research competence: research cognition, research methodology, data analysis, academic communication, research ethics, collatR)ration, research management, and research technology. Data were collected from 627 undergraduate students at a Vietnamese university using a five-m)int rating scale ranging from 1 (very low) to 5 (very high). Reliability analysis and exploratory factor analysis were conducted to examine the internal consistency and construct validity of the measurement model. The results supl%m the multidimensional structure of research competence and demonstrate the usefulness of a multi-source assessment approach in improving the robustness of competence measurement. The study contributes to the development of a practical assessment framework that can supFXyrt universities in evaluating and enhancing students' research competence in higher education contexts. Description: International Congress on Interdisciplinary Science and Technology; pp: 778-785

2026-03-01T00:00:00Z Nguyễn, Thị Khánh Hà https://elib.vku.udn.vn/handle/123456789/7691 2026-09-08T08:13:51Z 2026-03-01T00:00:00Z

Title: Marketing số hướng tới phát triển bền vững trong doanh nghiệp du lịch và khách sạn Việt Nam: Phân tích nội dung số và chiến lược triển khai qua các trường hợp điển hình Authors: Nguyễn, Thị Khánh Hà Abstract: Tóm tắt Trong bối cảnh chuyển đổi số và yêu cầu phát triển bền vững của ngành du lịch, marketing số ngày càng trở thành công cụ quan trọng trong việc xây dựng thương hiệu và định hướng hành vi du khách. Nghiên cứu này phân tích thực tiễn triển khai marketing số trong lĩnh vực du lịch - khách sạn tại Việt Nam dưới góc độ phát triển bền vững, dựa trên dữ liệu số công khai. Phương pháp nghiên cứu kết hợp phân tích định tính và khai thác dữ liệu thứ cấp từ website, mạng xã hội, thảo luận xã hội và xu hướng tìm kiếm trực tuyến của một số mô hình doanh nghiệp và điểm đến tiêu biểu. Kết quả cho thấy mức độ tích hợp yếu tố bền vững trong marketing số có sự khác biệt rõ rệt giữa các mô hình. Các doanh nghiệp du lịch trải nghiệm và nghỉ dưỡng sinh thái thể hiện chiến lược kênh và nội dung gắn với giá trị môi trường - cộng đồng rõ ràng hơn, trong khi các khách sạn đô thị và truyền thông điểm đến vẫn thiên về mục tiêu thông tin và bán hàng ngắn hạn. Nghiên cứu góp phần làm rõ vai trò chiến lược của marketing số trong thúc đẩy phát triển du lịch bền vững tại Việt Nam. Description: Kỷ yếu Hội thảo khoa học quốc gia “Du lịch Việt Nam trong bối cảnh chuyển đổi số và chuyển đổi xanh: Định hướng phát triển bền vững và giải pháp thực tiễn”; trang 321- 345.

2026-03-01T00:00:00Z