Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : International Journal of Technology and Modeling

A Review Learning Media Development Model Saluky; Marine, Yoni
International Journal of Technology and Modeling Vol. 1 No. 2 (2022)
Publisher : Etunas Sukses Sistem

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63876/ijtm.v1i2.7

Abstract

This study aims to review various models of ICT-based learning media development. This study covers several development models such as ADDIE, SAM, RADD, Agile Development Model, Spiral Model, and DADD. The purpose of this research is to evaluate the advantages and disadvantages of each model and provide the best recommendations for the development of effective and efficient learning media. The results of this study are expected to contribute to the development of ICT-based learning media in the future.
Revolutionizing Natural Language Processing (NLP): Cutting-edge Deep Learning Models for Chatbots and Machine Translation Arif, Muhamad; Saefurohman, Asep; Saluky
International Journal of Technology and Modeling Vol. 3 No. 1 (2024)
Publisher : Etunas Sukses Sistem

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63876/ijtm.v3i1.111

Abstract

Natural Language Processing (NLP) has undergone a transformative evolution with the advent of deep learning, enabling significant advancements in chatbots and machine translation. This article explores state-of-the-art deep learning models, including Transformer-based architectures such as GPT, BERT, and T5, which have revolutionized the way machines understand and generate human language. We analyze how these models enhance chatbot interactions by improving contextual understanding, coherence, and response generation. Additionally, we examine their impact on machine translation, where neural models have surpassed traditional statistical approaches in accuracy and fluency. Despite these advancements, challenges remain, including computational costs, bias mitigation, and real-world deployment constraints. This article provides a comprehensive overview of recent breakthroughs, discusses their implications, and highlights future research directions in NLP-driven AI applications.
Unmanned Aerial Vehicles (UAVs) for Pest and Disease Detection in Rice Cultivation: A Systematic Review Saluky, Saluky; Marine, Yoni; Fatimah, Aisya
International Journal of Technology and Modeling Vol. 4 No. 3 (2025)
Publisher : Etunas Sukses Sistem

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63876/ijtm.v4i3.158

Abstract

This paper presents a systematic review of the use of Unmanned Aerial Vehicles (UAVs) for pest and disease detection in rice cultivation, a critical challenge in maintaining yield stability and reducing chemical overuse in global food systems. The study aims to synthesize current approaches, technologies, and algorithms employed in UAV-based monitoring of rice pests and diseases, while identifying research gaps and future directions for precision rice farming. Following PRISMA-inspired guidelines, a Systematic Literature Review (SLR) was conducted across major scientific databases (Scopus, Web of Science, IEEE Xplore, and ScienceDirect) using predefined keyword combinations related to UAVs, rice, pest/disease detection, and remote sensing. Inclusion criteria focused on peer-reviewed studies that explicitly employed aerial platforms for detecting biotic stress in rice, while review papers, non-rice crops, and purely simulation-based works were excluded. The findings highlight three dominant technology dimensions: sensing modalities, with RGB and multispectral imagery being most prevalent, followed by hyperspectral and thermal sensors; analytical methods, ranging from traditional vegetation indices and thresholding to advanced machine learning and deep learning models; and operational considerations, including flight altitude, spatial resolution, and temporal frequency of data acquisition. The review contributes by proposing a conceptual framework linking sensor choice, image processing pipelines, and pest/disease symptom characteristics in rice, and by outlining open challenges regarding data standardization, smallholder adoption, and model transferability across regions.