Background: Rice is the primary staple food crop in Indonesia, yet leaf diseases—including bacterial blight, blast, and brown spot—cause annual yield losses of 10–30%, disproportionately affecting smallholder farmers who lack timely access to plant-pathology expertise; unreliable rural connectivity further limits cloud-based diagnostic tools. High-capacity convolutional neural networks deliver strong accuracy but are too large and slow for low-cost devices, and their opaque predictions undermine farmer trust. Objective: This study designs and evaluates RiceLeaf-Edge, an explainable and lightweight convolutional neural network for on-device rice-leaf disease detection that operates fully offline. Methods: Following Design Science Research methodology, a compact depthwise-separable student network was trained with knowledge distillation from a high-capacity teacher and compressed via INT8 post-training quantization; a Grad-CAM visual explanation module was integrated and evaluated on a rice-leaf dataset comprising five classes (healthy and four disease categories, n = 3,355 images). Results: RiceLeaf-Edge achieved 97.3% accuracy and 97.0% macro-F1—within 0.8 percentage points of the heavy baseline (98.1%) at only 8.9 MB and 34 ms on-device latency versus 92.4 MB and 164 ms for the heavy baseline. Explanations were faithful (insertion score 0.87; deletion score 0.18) with 92.6% symptom agreement. Conclusion: The framework demonstrates that trustworthy, deployable agricultural diagnosis is achievable at the edge on commodity hardware, offering a transferable recipe for edge AI in low-connectivity settings.
Rafi Farizki, R. Santika, Cuong Hung Vo· Jurnal Ekonomi Teknologi dan...· 0 citations
Artificial intelligence (AI) tools are increasingly used in English as a foreign or second language (EFL/ESL) academic writing classrooms, yet evidence on their instructional use and effects remains fragmented across tools, contexts, and study designs. This systematic literature review synthesized primary empirical studies published between 2019 and 2025 and retrieved from Scopus, Web of Science, ERIC, and Google Scholar, following the PRISMA 2020 guidelines, and appraised the methodological quality of the included studies. Three research questions were addressed, concerning the AI tools used in EFL/ESL writing instruction, their effects on writing quality and skills, and the associated challenges and ethical considerations. The findings indicate that three categories of tools, automated writing evaluation and grammar-checking tools, paraphrasing tools, and generative AI are used across all stages of the writing process, frequently in combination. Their reported effects reveal a tension between consistently documented gains at the surface level of grammar, mechanics, and vocabulary and less certain gains in higher-order aspects such as content, organization, and coherence, which appear mainly in studies with stronger designs or newer generative models. Recurring concerns include student overreliance, academic integrity, and the uneven distribution of benefits across learners of differing proficiency. The review contributes an EFL-specific synthesis spanning multiple tool types and educational levels, and argues that the value of AI tools depends less on the technology itself than on how it is pedagogically mediated. Implications for teacher-guided, critically evaluated use and directions for future research are discussed.
R. Santika, Rafi Farizki· International Multidisciplin...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
