Claim Missing Document
Check
Articles

KLASTERISASI KONDISI TANAH PADA URBAN FARMING DI SURABAYA DENGAN METODE K-MEANS CLUSTERING BERDASARKAN DATA SENSOR TANAH Fuady, Ahmad Ihsan; Widyantara, Helmy; Lidiawaty, Berlian Rahmy
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 4 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i4.6483

Abstract

Tahun 2045 sekitar 70% populasi Indonesia akan tinggal di area perkotaan, sehingga isu ketersediaan lahan pertanian dan pangan menjadi semakin krusial. Tahun 2021, Kota Surabaya menunjukkan 81% lahan pertanian adalah lahan non-sawah. Untuk menghadapi dampak urbanisasi dan memastikan keberlanjutan pasokan pangan diperlukan solusi potensial dengan urban atau urban farming. Salah satu implementasi urban farming di Surabaya adalah rooftop Telkom University Surabaya, yang dilengkapi sensor pemantau kondisi tanah secara real-time. Namun sensor ini belum diproses sistematis untuk menentukan jenis tanaman yang sesuai untuk ditanam. Penelitian ini bertujuan untuk mengelompokkan data kondisi tanah menggunakan metode kmeans clustering yang berdasarkan kesamaan karakteristik. Data yang digunakan mencakup tujuh variabel kondisi tanah, yaitu nitrogen, fosfor, kalium, pH, suhu, konduktivitas, dan kelembaban. Klasterisasi dilakukan pada data rata-rata harian selama 74 hari pengukuran. Evaluasi model dilakukan menggunakan dua metode utama: Elbow method dan Silhouette Score. Hasil evaluasi menunjukkan terdapat enam cluster optimal. Penurunan nilai WCSS (Within-Cluster Sum of Squares) tidak signifikan setelah enam cluster, sementara nilai silhouette score menurun setelah titik enam cluster. Setiap cluster yang terbentuk menunjukkan kondisi tanah yang serupa, yaitu suhu tinggi dan kelembaban rendah, dengan pH yang agak masam. Selain itu, terdapat variasi kandungan nitrogen, fosfor, kalium, dan konduktivitas antar cluster. Cluster dengan jumlah data terbanyak adalah C2, yang terdiri dari 23 data, sementara cluster dengan jumlah data paling sedikit adalah C4, yang hanya memiliki satu data. Hasil penelitian memberikan wawasan tentang kondisi tanah urban farming dan menawarkan rekomendasi tanaman untuk kebutuhan pangan di lingkungan perkotaan.
Double direction optimization: a new metaheuristic that performs exploitation and exploration simultaneously Purba Daru Kusuma; Helmy Widyantara
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 3: June 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v15.i3.pp2874-2884

Abstract

This research constructs a novel method called double direction optimization (DDO). DDO is constructed based on swarm intelligence (SI) approach and it does not use any metaphor. As its name suggests, it employs a novel algorithm by performing exploitation and exploration simultaneously which is transformed into two sequential searches. In the 1st search, the motion toward the highest quality agent is combined with the motion toward a randomly taken higher quality agent. In the 2nd search, the motion toward the finest entity is combined with the motion relative to a randomly taken agent. In this work, the efficacy of the DDO is assessed using three use cases: 23 functions, four engineering problems, and an economic emission dispatch (EED) problem. In this assessment, there are five metaheuristics that become the benchmark: crayfish optimization algorithm (COA), hiking optimization (HO), osprey optimization algorithm (OOA), carpet weaver optimization (CWO), and dollmaker optimization algorithm (DOA). The result indicates the supremacy of DDO in high dimension functions and competitiveness of DDO in fixed dimension multimodal functions, four engineering problems, and the EED problem.
Conditional toggle algorithm: an adaptive metaheuristic and its implementation on handling engineering problems Purba Daru Kusuma; Helmy Widyantara
Bulletin of Electrical Engineering and Informatics Vol 15, No 2: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i2.10048

Abstract

There have been numerous new metaheuristic algorithms in this decade. Unfortunately, the attention on taking stagnation is still less considered so that it is difficult to find new metaheuristic algorithms that are enriched with stagnation taking mechanism. This work introduces a new method called conditional toggle algorithm (CTA). CTA is designed to be adaptive on facing enhancement and stagnation during iteration as its novelty. When enhancement occurs, the exploitation-focused look is applied. Meanwhile, the exploration-focused look is applied when stagnation occurs. The efficacy of CTA is then measured by implementing to solve three cases: 23 functions, 4 engineering design problems, and economic emission dispatch (EED) problem in Java-Bali power system in Indonesia. CTA is compared with five new metaheuristic algorithms. The evidence provides that CTA is supreme in taking high dimension functions and competing in taking fixed dimension functions. CTA is also supreme in taking pressure vessel and speed reducer design problems and the EED problem. But its performance is average in taking welded beam and spring design problems. In the future, CTA can be modified with other metaheuristic algorithms to enhance its performance and challenged to take broader problems, especially in electrical engineering fields.
Static Sign Language Classification Using RGB, Skeleton Image, and Fusion Representations: A Cross-Dataset Evaluation Moch. Iskandar Riansyah; Mohamad Yani; Ubaidillah Umar; Helmy Widyantara
Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI Vol. 15 No. 2 (2026)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v15i2.114587

Abstract

This study investigates static sign language classification by examining three image-based input representations, namely RGB images, skeleton images, and RGB+skeleton fusion, using two datasets with different visual characteristics. The first dataset reflects a relatively controlled acquisition setting, whereas the second dataset contains more complex background and visual variations. As an initial baseline, eight pretrained convolutional neural network (CNN) architectures were evaluated, and two representative models were subsequently selected for more detailed analysis. The baseline evaluation indicates that ResNet50 and EfficientNetB0 achieve the most competitive performance when RGB images are used as input. Further analysis of input representations shows that skeleton images are highly effective, particularly on the more challenging dataset, while RGB+skeleton fusion does not consistently improve classification performance. The cross-dataset evaluation further reveals a considerable performance drop across all configurations, suggesting the presence of a strong domain shift between the two datasets. In the A-B scenario, EfficientNetB0 with RGB input yields the best results, while in the B-A scenario, EfficientNetB0 with skeleton input shows the most stable performance. These findings indicate that the most effective input representation depends on the direction of domain transfer and that high intra-dataset performance does not necessarily reflect good generalization capability.
Co-Authors Achmad Yanu Aliffianto Adiputra, Dimas Aditya Prima Suparno, Aditya Prima Afandi, Mas Aly Ahmad Wali Satria Bahari Johan Andi Divangga Pratama , Moch. Andrew Brian Osmond Anifatul Faricha Aufa Ulinuha, Panji Aulia Rahma Annisa Axel Danu Pramudita Basuki Rahmat Bayu Dadang Pribadi Berlian Rahmy Lidiawaty Bernadus Anggo Seno AjiAji Chokoh Setyo Utomo Dewa Nusantara Murdoko Putra Djoko Purwanto Dominggo Bayu Baskara Dwi Edi Setyawan DWI SURYANTO Dwi Wahyu Saputra FADHLAN, FATHURROZAQ Farah Zakiyah Rahmanti Fuady, Ahmad Ihsan Galih Kusuma Wardana Harianto Harianto Hariyanto Hariyanto Hariyanto, Muhammad Dwi Hendra Kusuma Hendy Briantoro Ignatia Indreswari Ira Puspasari Isa Hafidz Khodijah Amiroh Ma'ruf Firmansyah, Muhammad Madha Christian Wibowo Madha Christrian W. Minto Waluyo Moch. Iskandar Riansyah Moh. Yani Mohamad Irwan Afandi Mohamad Yani Mohammad Yanuar Hariyawan Montolalu, Billy Muhammad Adib Kamali Muhammad Iqbal Maulana Muhammad Rafi Irzam Muhammad Rivai Muhammad Rivai Oktavia Ayu Permata Pambudi, Sandhi Yuda Pauladie Susanto Philip Tobianto Daely Purba Daru Kusuma Purnama Anaking Rachmawati Oktaria Mardiyanto, Rachmawati Oktaria Ratih Kesuma Dewi Reynanda Shaquille Purwanto Reza Alauddin Albanna Ristanti Akseptori Rizaldy Febry Nugraha Rochmanto, Raditya Artha Seno Adi Putra Shochibah Yatimatul Asmak, Shochibah Yatimatul Sukamto, Ika Sumiyarsi Sukma Ardihantoko, Irdani Therzian Richard Perkasa Tjahyadi, Nathanael Toto Alfian Wahyuono, Toto Alfian Tri Arief Sardjono Tuhu Agung Rachmanto Ubaidilah Umar Ubaidillah Umar Ubaidillah Umar, Ubaidillah Wahyu Andy Prastyabudi Yanuhar Prabowo Yupit Sudianto