cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Ai Munandar
Contact Email
ijitcsa@gmail.com
Phone
+62+6282111152015
Journal Mail Official
ijitcsa@gmail.com
Editorial Address
International Journal of Information Technology and Computer Science Applications (IJITCSA) Sekretariat Jejaring Penelitian dan Pengabdian Masyarakat (JPPM) : Ranau Estate Blok D.3, Kel. Panggungjati, Kp. Pantogan Kec. Taktakan - Kota Serang, Provinsi Banten, e-mail : jitcsa@jejaringppm.org web : www.jejaringppm.org
Location
Kota serang,
Banten
INDONESIA
International Journal of Information Technology and Computer Science Applications (IJITCSA)
Published by Jejaring Penelitian dan Pengabdian Masyarakat
ISSN : 29643139     EISSN : 29855330     DOI : https://doi.org/10.58776/ijitcsa.v1i2
Core Subject : Science, Education, Engineering,
Computer Science & IT Decision Sciences, Operations Research & Management Education Engineering
he Journal of Information Technology and Computer Science Applications (JITCSA) is an information technology and computer science publication. Applications from both fields for solving real cases are also welcome. JITCSA accepts research articles, systematic reviews, literature studies, and other relevant ones. Several fields of science that are the focus of JITCSA include information technology and the like, computer science fields, including artificial intelligence, data science, data mining, machine learning, deep learning, and the like. IJITCSA is published three times a year, in January, May, and September. The first issue in January 2023 had eight articles. Focus and Scope International Journal of Information Technology and Computer Science Applications includes scholarly writings on scientific research or review, pure research, and applied research in the field of computer science, information systems, and information technology as well as a review-general review of the development of the theory, methods, and related applied sciences. Information systems System Software Artificial Intelligence Computer Architecture Distributed Systems System & Software Engineering Genomics & Bioinformatics Internet and Web AI & Expert systems Software Process and Life Cycle Database Systems Software Testing & Quality assurance Bioinformatics Information Technology Implementation Computing Languages & Algorithms E-commerce & M-Commerce Computer Networks & Communications Computing Systems Control Systems & Engineering Systems Engineering System Security Digital Forensics Data Mining & Machine Learning Data Modeling
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 77 Documents
 4   5   6   7   8 
Modality-Resilient Multimodal Earth-Observation Foundation Models under Missing and Corrupted Sensors Anna Kalaitzis Pollan
International Journal of Information Technology and Computer Science Applications Vol. 4 No. 2 (2026): May - August 2026
Publisher : Jejaring Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58776/ijitcsa.v4i2.259

Abstract

Multimodal Earth-observation (EO) foundation models increasingly rely on the joint use of optical imagery, synthetic aperture radar (SAR), elevation, and auxiliary geospatial signals to support land-cover mapping, biomass estimation, damage assessment, and change detection. Yet the empirical regime in which such models are usually trained and reported remains overly optimistic: modalities are commonly assumed to be synchronised, complete, and clean. This assumption is not defensible for real deployments. Optical observations are routinely obscured by clouds, SAR coherence and interferometric products can be unavailable or decorrelated, spatial alignment across sources is imperfect, and large geospatial archives inevitably contain broken tiles, missing channels, or temporally inconsistent acquisitions. Starting from the released M3LEO dataset and framework, which already expose multimodal EO learning at continental scale, this paper reconstructs the underlying research direction toward a more technically urgent problem: robust multimodal foundation learning under missing or corrupted modalities. We formalise a modality-resilient framework, RAMEO, that combines modality-specific token encoders, reliability-aware gated fusion, masked cross-modal reconstruction, corruption-aware consistency learning, and calibrated uncertainty estimation. We also define a rigorous evaluation protocol over geographically disjoint splits, structured missingness patterns, and modality-specific corruptions. This paper done a dataset-and-benchmark paper and reconstruction distinguishes carefully between source-anchored evidence reported for M3LEO and new robustness analyses that are specified as executable experiments. The result is therefore technically coherent, and reproducible, while remaining honest about what has and has not yet been empirically established.
Geospatial Vision-Language Models for Spatial Reasoning and Temporal Change Understanding: A Task-Centered Benchmarking Framework and Evidence Synthesis Discussion Abeer Hasshen Abdullah
International Journal of Information Technology and Computer Science Applications Vol. 4 No. 2 (2026): May - August 2026
Publisher : Jejaring Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58776/ijitcsa.v4i2.262

Abstract

Geospatial vision-language models (VLMs) are increasingly expected to do more than assign scene labels or generate generic captions. In realistic Earth-observation and urban intelligence settings, useful multimodal systems must support fine-grained spatial reasoning, cross-view interpretation, grounded localization, and explicit understanding of change across time. Yet the current literature remains fragmented across remote sensing visual question answering, visual grounding, urban multi-view reasoning, and bi-temporal change captioning. As a result, claims about progress are often task-local, benchmark-specific, and difficult to compare. This paper reconstructs the field around a more defensible technical center: geospatial multimodal intelligence as the joint problem of spatial reasoning and temporal change understanding. Rather than presenting unverifiable new benchmark runs, we develop a rigorous review paper anchored in public benchmark evidence and a reference architecture for reproducible future work. We first formalize a task-centered problem definition that unifies image-level, region-level, cross-view, and bi-temporal reasoning. We then propose a reference GST-VLM architecture consisting of spatial encoding, temporal difference modeling, multimodal fusion, task-specific decoding, and reliability estimation. Next, we synthesize publicly reported evidence from representative datasets and benchmarks including RSVQA, EarthVQA, VRSBench, GeoChat, LEVIR-CD, LEVIR-CC, SECOND-CC, CHOICE, GEOBench-VLM, CityBench, and UrBench. The synthesis shows that recent models are improving rapidly but remain far from robust geospatial reasoning systems: on GEOBench-VLM, the best public model reported only 41.7% multiple-choice accuracy; on UrBench, even GPT-4o still trails human performance by an average 17.4 percentage points; and while specialized systems such as GeoReasoner, GeoChat, GeoLLaVA, and MModalCC outperform generic baselines on targeted tasks, their gains remain strongly benchmark-dependent. Based on this evidence, we identify the principal bottlenecks as benchmark fragmentation, weak temporal grounding, inadequate calibration, scarce cross-region validation, limited deployment reporting, and insufficient integration of geometry with language-conditioned reasoning. The paper concludes with a concrete research agenda for trustworthy geospatial VLMs that is centered on multi-temporal supervision, interactive change analysis, uncertainty-aware outputs, and evaluation protocols that measure not only accuracy but also transfer, calibration, and operational feasibility.
Literature Review of Hybrid Neural–Physics Flood-Relevant Streamflow Forecasting with Cross-Event and Cross-Basin Generalization Yanan Elliot Moko
International Journal of Information Technology and Computer Science Applications Vol. 4 No. 2 (2026): May - August 2026
Publisher : Jejaring Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58776/ijitcsa.v4i2.263

Abstract

Reliable flood-relevant streamflow forecasting remains difficult at operational scale because physically based forecasting systems provide national coverage but cannot be directly verified at the overwhelming majority of ungauged river reaches. This study reconstructs and strengthens a hybrid neural–physics framework in which the National Water Model (NWM) supplies the physically constrained baseline forecast and an attribute-conditioned deep neural network learns forecast-error magnitude from gauged basins, then transfers that knowledge to ungauged basins. The emphasis is not on replacing process-based hydrology with a black-box predictor, but on improving forecast reliability under cross-event and cross-basin generalization. The empirical setting consists of 979 archived daily long-range forecasts, 30 forecast lead days, 16-member NWM ensembles, and 389 quality-controlled U.S. Geological Survey gauging stations across Alabama and Georgia, complemented by static watershed descriptors and gridded soil-moisture diagnostics. Exploratory analysis shows that forecast skill is strongly conditioned by basin properties: larger and forested watersheds are predicted more accurately than smaller and urban watersheds, while urban basins show severe positive bias, weaker anomaly correlation, and degraded hydrograph timing. These diagnostics motivate an error-learning postprocessor that maps NWM forecast magnitude and basin attributes to a non-negative error estimate and converts the deterministic physics forecast into a corrected predictive interval. Under a temporally disjoint evaluation intended to test cross-event transfer, observation coverage increases from 0.21±0.01 for the raw NWM ensemble range to 0.82±0.03 for the hybrid model; a repeated spatial holdout yields comparable performance (0.82±0.01). The gains are largest where the underlying physics model is weakest, especially in developed watersheds. The main limitation is that improved reliability is achieved through wider predictive intervals rather than sharper hydrographs. The study therefore supports a defensible conclusion of hybrid neural–physics postprocessing can materially improve flood-relevant streamflow reliability at ungauged basins, but interval sharpness and external cross-region validation remain open research needs.
Design and Implementation of a Web-Based Savings and Loan Information System Jauharul Qalbi; Jaswadi Jaswadi; Kartika Dewi
International Journal of Information Technology and Computer Science Applications Vol. 4 No. 3 (2026): September - December 2026
Publisher : Jejaring Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58776/ijitcsa.v4i3.265

Abstract

This study aimed to design and implement a web-based Savings and Loan Information System for Koperasi Konsumen Raudhah Amanah Bunobogu while supporting the improvement of its existing business processes. The study was motivated by operational challenges arising from manual transaction recording, fragmented data management, reporting delays, and limited access to centralized information. Data were collected through observation, interviews, and documentation studies. A Fishbone Diagram was employed to identify the root causes of operational problems, whereas Business Process Model and Notation (BPMN) was used to analyse the existing (As-Is) and proposed (To-Be) business processes. The system was developed using the Software Development Life Cycle (SDLC) Waterfall model and evaluated through Black Box Testing to verify its functional requirements. The developed system successfully integrates key cooperative operations, including member management, savings transactions, loan processing, installment payments, and financial reporting within a centralized web-based platform. The Black Box Testing results confirmed that all implemented functionalities operated in accordance with the specified system requirements. These findings demonstrate that integrating BPMN-based business process redesign with information system development provides a structured approach to supporting the digitalization of savings and loan cooperative operations. Future studies are encouraged to evaluate the organizational impact of the system through quantitative performance measurements and user-based assessments.
Design and Evaluation of Task-Based Waste Sorting Mechanics in Virtual Reality Learning Application Vito Gautama; Matahari Bhakti Nendya; I Kadek Dendy Senapartha; Antonius Rachmat Christmanto; Dan Daniel Pandapotan
International Journal of Information Technology and Computer Science Applications Vol. 4 No. 3 (2026): September - December 2026
Publisher : Jejaring Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58776/ijitcsa.v4i3.266

Abstract

Virtual Reality (VR) can support environmental learning through embodied interaction, task-based activity, and immediate feedback. This study presents the design and evaluation of task-based waste-sorting mechanics in a virtual beach application developed in Unity and deployed on a PICO 4 headset. Thirty high-school and university students completed a 10–15-minute session and responded to the Game Experience Questionnaire (GEQ). The revised analysis follows the official GEQ procedure by scoring each component separately on a 0–4 scale and by avoiding an overall score across constructs with different directions. The experience profile was mixed. In the In-Game Module, positive affect (M = 3.05) and sensory and imaginative immersion (M = 2.85) were relatively strong, but tension (M = 3.05) and negative affect (M = 2.83) were also elevated. Post-game positive experience (M = 2.77) co-occurred with negative experience (M = 2.83), tiredness (M = 2.00), and difficulty returning to reality (M = 1.97). These findings indicate that the mechanics supported engagement in some aspects of play but also introduced interaction strain or discomfort. Because the study did not include pre-test/post-test measures or objective task logs, it does not establish learning gains or technical task effectiveness.
Hybrid Filtering Implementation with Personal Threshold Mechanism to Improve Movie Recommendation Accuracy Debora Patricia Sharon Rembet; Antonius Rachmat Chrismanto; Lucia Dwi Krisnawati
International Journal of Information Technology and Computer Science Applications Vol. 4 No. 3 (2026): September - December 2026
Publisher : Jejaring Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58776/ijitcsa.v4i3.269

Abstract

The growing volume of content on film streaming platforms makes it harder for users to find films that suit their tastes, highlighting the need for a personalized recommendation system. This research introduces a Hybrid Filtering architecture that unifies Collaborative Filtering using Singular Value Decomposition with Content-Based Filtering employing TF-IDF weighted vectors and cosine similarity measurement. The defining innovation is a dual-threshold mechanism grounded in each user's personal average rating (user_avg_rating), which individually filters candidate films before their hybrid scores are combined. New users are handled through a genre-based onboarding flow supported by a weighted popularity score. Experiments on the MovieLens ml-latest-small dataset (100,836 ratings, 610 users, 9,742 films) show that Hybrid Filtering achieves the best Precision@10 of 0.27 and NDCG@10 of 0.32. Switching from a fixed global threshold to the personal threshold raised Genre Precision from 0.40 to 0.90 (+125%). The SVD component attained RMSE of 0.88 and MAE of 0.67, and a user study with 10 participants yielded a mean relevance score of 8.2 out of 10. Keywords—Hybrid Filtering, Collaborative Filtering, Content-Based Filtering, Personal Threshold
Simulation and Implementation of Insertion Sort Algorithm to Sort Positive Integers Using C++ Programming Language Tri Dharma Putra; Rakhmat Purnomo
International Journal of Information Technology and Computer Science Applications Vol. 4 No. 3 (2026): September - December 2026
Publisher : Jejaring Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58776/ijitcsa.v4i3.278

Abstract

Sorting is the process of systematically arranging data, initially in an unordered state. That is according to specific rules or criteria (such as numerical or alphabetical order). This process is essential in many fields and applications, including computer science, statistics, and data management, as it facilitates the searching, analysis, and further processing of information. Insertion algorithm is a good algorithm and used in many applications. In this implementation and simulation six figures of positive integers to be sorted are used, namely 30, 2, 5, 7, 11, 1. Each with five processes. After implementation in ascending order there were nine swaps, and in descending order there were only six swaps. The implementation is performed with C++ Programming Language. Two pseudo codes are given, one for ascending and one for descending. The results were a successful implementation and simulation of C++. Screenshot are given to prove that the programs are running smoothly

Page 8 of 8 | Total Record : 77

 4   5   6   7   8 

Filter by Year

2023 2026


Reset
Filter By Issues
All Issue Vol. 4 No. 3 (2026): September - December 2026 Vol. 4 No. 2 (2026): May - August 2026 Vol. 4 No. 1 (2026): January - April 2026 Vol. 3 No. 3 (2025): September - December 2025 Vol. 3 No. 2 (2025): May - August 2025 Vol. 3 No. 1 (2025): January - April 2025 Vol. 2 No. 3 (2024): September - December 2024 Vol. 2 No. 2 (2024): May - August 2024 Vol. 2 No. 1 (2024): January - April 2024 Vol. 1 No. 3 (2023): September - December 2023 Vol. 1 No. 2 (2023): May - August 2023 Vol. 1 No. 1 (2023): January - April 2023 More Issue