cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Johan Reimon Batmetan
Contact Email
garuda@apji.org
Phone
+6285885852706
Journal Mail Official
danang@stekom.ac.id
Editorial Address
Jl. Majapahit No.304, Pedurungan Kidul, Kec. Pedurungan, Semarang, Provinsi Jawa Tengah, 52361
Location
Kota semarang,
Jawa tengah
INDONESIA
Journal of Technology Informatics and Engineering
Published by Universitas Sains Dan Teknologi Komputer
ISSN : 29619068     EISSN : 29618215     DOI : 10.51903
Core Subject : Science,
Computer Science & IT
Power Engineering Telecommunication Engineering Computer Engineering Control and Computer Systems Electronics Information technology Informatics Data and Software engineering Biomedical Engineering
Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi
Articles 197 Documents
 16   17   18   19   20 
A Lightweight Medical Foundation Model for Cross-Modal Multi-Task Pretraining and Parameter-Efficient Few-Shot Transfer on MedMNIST Mi, Gaotian; Ye, Tong; Wood, Dan
Journal of Technology Informatics and Engineering Vol. 4 No. 3 (2025): DECEMBER | JTIE : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v4i3.492

Abstract

Medical imaging has rapidly adopted pre-trained backbones, yet many transfer-learning pipelines remain expensive to train and difficult to adapt when data, compute, or privacy constraints limit full fine-tuning. We present STMedFM, a lightweight medical multi-task backbone baseline designed for fast prototyping across 2D images and 3D volumes. STMedFM uses modality-specific convolutional stems (2D and 3D) and a shared low-depth encoder, and it supports parameter-efficient transfer via Low-Rank Adaptation (LoRA) and bottleneck adapters. We pretrain STMedFM with supervised multi-task learning on four MedMNIST tasks (PathMNIST, BloodMNIST, DermaMNIST, and OrganMNIST3D) using official train/validation/test splits. We then compare (i) training from scratch, (ii) full fine-tuning from the multi-task checkpoint, and (iii) parameter-efficient fine-tuning (LoRA or adapters) that updates only a small fraction of parameters. Under a fixed compute budget (200 pretraining steps; 120 fine-tuning steps for 2D tasks; 50 steps for the 3D task), multi-task pretraining improved performance on PathMNIST (test accuracy 0.568 → 0.634; macro AUROC 0.886 → 0.914) and preserved most gains under PEFT (LoRA AUROC 0.909; Adapter AUROC 0.913) while training only 4,041–5,225 parameters versus 160,105 for full fine-tuning. For DermaMNIST, pretraining increased macro AUROC from 0.746 (Scratch, weighted) to 0.756 (Pretrain+Full), with similar AUROC under LoRA (0.760) and Adapter (0.763). In contrast, BloodMNIST and OrganMNIST3D showed mixed behavior, including cases where Scratch outperformed pretrained variants, indicating that transfer in this compact shared encoder is task-dependent and budget-sensitive. Calibration results were similarly non-monotonic: methods with better AUROC did not always achieve lower ECE. Overall, our results show that a small cross-modal multi-task model can serve as a practical MedMNIST-scale transfer baseline and that LoRA/adapters offer substantial parameter savings when task alignment is favorable. STMedFM should therefore be viewed as a lightweight supervised multi-task backbone on benchmark-scale tasks rather than a broadly general medical foundation model.
Offline Counterfactual Evaluation for Advertising and Recommendation Slot Policies: A Reproducible Study on the Open Bandit Dataset (Small) Mu, Jinyi; Ye, Tong; Patel, Priya
Journal of Technology Informatics and Engineering Vol. 4 No. 3 (2025): DECEMBER | JTIE : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v4i3.500

Abstract

Offline or counterfactual evaluation is a critical capability for iterating advertising and recommender ranking strategies when online A/B testing is slow, expensive, or risky. Off-policy evaluation (OPE) estimates the expected reward of a candidate policy using logged interaction data from a different behavior policy. Still, it can suffer from high variance under poor overlap and can be misleading when the operational objective is choosing among candidate policies rather than minimizing point-estimation bias alone. This paper presents a fully reproducible empirical study of IPS, self-normalized IPS (SNIPS), doubly robust (DR), and Switch-DR estimators on the Open Bandit Dataset (OBD) small release. Using the Men and Women campaigns (10,000 logged item-impressions per campaign and behavior policy) collected by uniform random and Bernoulli Thompson Sampling (BTS), we construct a held-out oracle for stationary slot-wise policies from the random-traffic split and evaluate both value estimation and policy-ranking consistency on random-logged and BTS-logged test sets. Across 1,000 nonparametric bootstrap replications, IPS and SNIPS are accurate on randomly logged data, whereas BTS-logged data exhibit extreme importance weights and very small effective sample sizes (ESS), making IPS-based ranking unreliable under weak support. Switch-DR is most useful in moderate-overlap regimes, where it truncates high-variance corrections. Still, it introduces bias that depends on the switching threshold and must therefore be stress-tested rather than treated as a universally superior estimator. Finally, we provide a structured reporting template—based on oracle decomposition, overlap diagnostics, and estimator components—for explaining why a policy appears better and how reliable that conclusion is.
Calibration-Light Subject-Independent Motor Imagery BCI via Self-Supervised Pretraining and Conformer Qiyou Wu; Gaotian Mi; Dan Wood
Journal of Technology Informatics and Engineering Vol. 4 No. 1 (2025): APRIL | JTIE : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v5i1.493

Abstract

Motor imagery (MI) electroencephalography (EEG) is a foundational paradigm for non-invasive brain–computer interfaces (BCIs). However, its practical adoption is constrained by time-consuming per-user calibration and limited cross-subject generalization. This study evaluates a calibration-light MI-BCI framework that combines self-supervised masked EEG pretraining with a lightweight Conformer fine-tuning model. Experiments were conducted on BCI Competition IV Dataset 2b using only the labeled sessions 01T–03T, with artifact-annotated trials removed according to the official 1023 markers. Three deployment-relevant settings were examined: within-subject evaluation (01T–02T → 03T), strict leave-one-subject-out (LOSO) evaluation, and few-shot adaptation with k = 1/5/10 trials per class from the held-out subject’s screening sessions. Full within-subject benchmarking included CSP+LDA, EEGNet, DeepConvNet, ShallowFBCSPNet, supervised Conformer, and SSL+Conformer, while the subject-independent and few-shot analyses focused on CSP+LDA, EEGNet, supervised Conformer, and SSL+Conformer. In the fully calibrated setting, the best mean accuracy was obtained by ShallowFBCSPNet (62.23% ± 14.16%), whereas SSL+Conformer achieved 54.85% ± 11.15% and slightly outperformed the supervised Conformer (53.56% ± 8.81%). Under strict LOSO, EEGNet achieved the highest mean accuracy (52.92% ± 8.25%), while SSL+Conformer reached 51.56% ± 7.18%. In few-shot adaptation, SSL+Conformer achieved the highest mean accuracy at k = 10 (52.84% ± 7.64%) among the core calibration-light methods. The proposed model had a size of 0.1329 MB, a median CPU latency of 0.8777 ms/trial, and LOSO calibration values of ECE = 0.0630 and Brier = 0.4995. These results indicate that masked EEG pretraining provides a competitive lightweight baseline and is most useful when a modest amount of target-subject calibration data is available.
Ranking AODV Routing Characteristics in MANETs: Fuzzy Delphi Method Application Njoroge, Patrick; Ndia, John; Makupi, Daniel
Journal of Technology Informatics and Engineering Vol. 5 No. 1 (2026): APRIL | JTIE : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v5i1.494

Abstract

Optimization of Mobile Ad hoc Networks (MANET) routing has the potential to improve performance. Enhancing the Ad-hoc On-demand Distance Vector (AODV) protocol, which is predominantly used in MANET routing, would lead to performance improvements. This study sought to provide a structured approach to identifying which AODV protocol characteristics should be prioritized for modification to improve performance in MANETs. This would provide guidance for future research on AODV prioritization. Thirteen AODV characteristics were identified through a systematic review. The Fuzzy Delphi Method was employed to analyze and prioritize the study characteristics. Route discovery characteristics were prioritized and ranked as number one, with a threshold value of 0.097, 100% agreement among experts, and a fuzzy score of 0.72. The experts unanimously agreed that modifying the route discovery characteristic has the greatest potential to improve performance in MANET. This was because a large amount of control traffic in the network is generated during the route discovery process. The other characteristics were route selection, route maintenance, route table management, routing updates, number of routes discovered, hop count, time to live, and use of hello messages. However, some characteristics were perceived to be structurally critical for AODV operation but less responsive to performance-optimization modifications, namely hop-by-hop communication, identification of route request messages, sequence numbers, and neighbor lists. Future studies should complement the expert-based prioritization of AODV characteristics with experimental and simulation evaluations to quantify performance gains.
Multi-Horizon GPU Demand Forecasting with Workload Semantics and Operational Risk Curves: An Empirical Study on Alibaba Clusterdata GPU Trace Siming Zhao; Jingwen Bai; Drew Roberson
Journal of Technology Informatics and Engineering Vol. 4 No. 3 (2025): DECEMBER | JTIE : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v4i3.498

Abstract

This study addresses the operational challenge of multi-horizon GPU demand forecasting in large-scale computing clusters, where GPUs are costly resources and demand fluctuates under constraint-driven scheduling. The objective is to evaluate whether integrating workload semantics improves forecasting performance across horizons up to 72 hours. A reproducible empirical benchmark is developed using the Alibaba Clusterdata GPU trace (cluster-trace-gpu-v2023), comprising 8,152 pods over approximately 149 days with a total capacity of 6,212 GPUs. The study compares two statistical baselines, ARIMA(48,0,0) and a seasonal-trend additive model, with three lightweight deep learning models: Temporal Convolutional Network (TCN), Informer-lite, and TFT-lite. Workload semantics are approximated by converting hourly job metadata into textual summaries, embedding them with TF-IDF and truncated SVD (8 dimensions), and incorporating them as exogenous covariates. Evaluation uses SMAPE and MASE across multiple horizons (1–72 hours), along with peak-aware metrics and operational risk curves. Results show that the seasonal-trend model achieves the best overall accuracy (15.34% sMAPE), while TCN is the strongest deep model (17.20% sMAPE). Semantic embeddings do not improve short horizons (1–48 hours) but reduce 72-hour sMAPE by 11.1% and improve peak-window error. These findings indicate that autoregressive signals dominate short-term forecasting, whereas semantic context becomes beneficial at longer horizons. The study emphasizes that combining point accuracy with risk-based evaluation is essential for effective GPU capacity planning under dynamic and uncertain demand conditions.
Digital-Twin Dispatching for Urban Mobility via Spatio-Temporal Transformers and Offline Reinforcement Learning Long Zhang; Ruiyan Ma; Peter Greg
Journal of Technology Informatics and Engineering Vol. 4 No. 2 (2025): AUGUST | JTIE : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v4i2.501

Abstract

This study addresses the challenge of optimizing ride-hailing dispatch and repositioning under data limitations by proposing an end-to-end digital-twin dispatching framework that integrates spatio-temporal demand forecasting with offline reinforcement learning. Using publicly available NYC FOIL ride-hailing data aggregated at the dispatching-base level, the research aims to evaluate whether coarse-grained data can still support reliable, reproducible decision-making pipelines. The methodology consists of two main components: (i) multivariate time-series forecasting using baseline models, a temporal convolutional network (TCN), and a spatio-temporal transformer to predict next-day demand; and (ii) a digital-twin simulation combined with an action-constrained offline reinforcement learning approach, including behavior cloning (BC) and Conservative Q-Learning (CQL), to optimize fleet repositioning decisions. Experimental results show that the TCN achieves the best forecasting accuracy on the test period, although dominant demand regions largely drive performance gains. In the control phase, conservative policies such as CQL demonstrate stable performance with reduced repositioning costs, but do not significantly outperform behavior cloning due to limited training data. The findings indicate that, in coarse aggregate settings, operational improvements are more influenced by controlling policy sensitivity than by marginal forecasting gains. This study contributes a reproducible benchmark pipeline and highlights the importance of conservative control strategies, transparent assumptions, and sensitivity analysis when deploying AI-driven mobility systems based on limited or aggregated data.
Federated Topic-Preference Learning for Knowledge-Grounded Chat with Differential Privacy Meng-Ju Kuo; Daren Zheng; Julie Hires
Journal of Technology Informatics and Engineering Vol. 4 No. 2 (2025): AUGUST | JTIE : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v4i2.502

Abstract

Retrieval-augmented approaches have become central in knowledge-grounded dialogue systems, yet incorporating topical preferences remains difficult due to privacy constraints on user interaction data. This study introduces a lightweight federated topic-preference (FedTP) mechanism that models session-level preferences without centralizing raw data and uses client-level differential privacy (DP). Using the Topical-Chat dataset (8,628 conversations), each conversation is treated as a client, and evidence routing is framed as selecting relevant knowledge snippets based on dialogue context. The proposed method augments a TF-IDF relevance score with a small preference-based component derived from both local session distributions and a DP-aggregated global prior. Experimental results on 9,553 grounded test turns show a consistent but limited improvement in evidence hit rate, from 0.6167 to 0.6194. The small optimal preference weight (λ = 0.005) indicates that the preference signal mainly influences decisions when competing candidates have similar relevance scores, rather than substantially altering routing behavior. A privacy–utility analysis under Gaussian DP (ε ranging from 9.69 to 0.606, δ = 1e−5) shows negligible changes in performance, which is expected given the large number of clients in a one-shot aggregation setting. Additional metrics remain largely stable, suggesting that the method affects selection margins rather than overall alignment. These findings suggest that federated preference aggregation can provide a modest, privacy-preserving bias for evidence routing, but its practical impact remains incremental and context-dependent.
IoT-Enabled Multimodel Emotion Detection and Assistive Smartwatch for Special-Needs Children Samrin, A.; Saidharshini, S.; Shalima, S.; Moohambiga, B.
Journal of Technology Informatics and Engineering Vol. 5 No. 1 (2026): APRIL | JTIE : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v5i1.471

Abstract

Children with neurodevelopmental and communication challenges often find it difficult to express emotional discomfort, stress, or urgent needs, which can delay timely support and increase anxiety. To address this issue, this paper presents an IoT-enabled assistive smartwatch designed to support near real-time emotion inference and basic communication for children with special needs. The proposed system integrates physiological sensing, including heart rate variability, galvanic skin response, and skin temperature, with camera-based facial expression analysis using a multimodal data fusion approach. In addition to emotion-aware monitoring, the smartwatch provides a simple icon-based communication interface and a routine reminder module to support daily activities. The framework enables caregiver-side visualization of emotional trends, communication events, and adherence to routines through a cloud-based dashboard. The system is evaluated through a design-level feasibility assessment using simulated experiments and analysis of benchmark datasets. Overall, this work presents a technically feasible and ethically conscious assistive framework that highlights the potential of combining IoT and emotion-aware computing for supportive care applications.
Self-Supervised Representation Learning for Criminology: Detecting Anomalies, Classifying Reports, and Mapping Networks Hassan S., Noorul; S., Sivalakshmi; M., Janani; A., Fouziya; S., Thirisha
Journal of Technology Informatics and Engineering Vol. 5 No. 1 (2026): APRIL | JTIE : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v5i1.473

Abstract

Crime analysis using various types of data, such as video surveillance, crime reports, and criminal networks, has been widely investigated in digital criminology. Most of the available data are unlabelled. In this work, we introduce a self-supervised learning framework for multimodal criminology, which enables the fully automatic learning of effective features for unlabelled video, text, and graph datasets and the completion of crime analysis tasks, including anomaly detection, crime report classification, and high-risk node prediction via contrastive learning, masked prediction, and graph self-supervised learning. The experimental results show that our SSL model learns high-quality features and achieves better performance than its supervised counterpart and baseline models. Unlike traditional deep learning-based models that require large amounts of labeled data, our proposed SSL model is label-efficient, scalable, and robust to artificial or anonymous data. Our work aims to develop an AI-based multimodal self-supervised learning approach for efficient, accurate, reliable, and safe crime analysis
AI-Driven Multi- Modal Fake Content Detection System Using Audio-Text Fusion and Transformer Network Jeeva, S.; Trisha, J. S.; Keerthana, S.
Journal of Technology Informatics and Engineering Vol. 5 No. 1 (2026): APRIL | JTIE : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v5i1.475

Abstract

The rapid proliferation of AI-generated synthetic media has posed substantial threats to digital trust, particularly through audio deepfakes and manipulated text. Existing unimodal detection systems that analyze either audio or text in isolation remain insufficient to counter advanced generative attacks that exploit both modalities simultaneously. This paper proposes an AI-driven multimodal fake content detection framework that jointly leverages acoustic and linguistic signals to enable robust deepfake identification. Mel-Frequency Cepstral Coefficients (MFCCs) and Mel-Spectrograms are extracted from raw audio to capture spectral and temporal vocal patterns. At the same time, BERT-based transformer embeddings encode semantic and contextual information from transcripts generated via Automatic Speech Recognition (ASR). An attention-based fusion layer dynamically weights and integrates both feature streams, and a Random Forest–XGBoost ensemble classifier performs the final authenticity prediction. Experiments conducted on the ASVspoof 2019 benchmark demonstrate a classification accuracy of 95%, with precision of 93%, recall of 94%, and F1-score of 95%, outperforming standalone audio-only and text-only baselines by approximately 4–7%. These findings confirm that cross-modal feature fusion substantially reduces false-detection rates and improves generalization over single-modality approaches. The proposed system offers practical applicability in cybersecurity, voice biometrics, and digital forensics.

Page 18 of 20 | Total Record : 197

 16   17   18   19   20 

Filter by Year

2022 2026


Reset
Filter By Issues
All Issue Vol. 5 No. 2 (2026): AUGUST | JTIE : Journal of Technology Informatics and Engineering Vol. 5 No. 1 (2026): APRIL | JTIE : Journal of Technology Informatics and Engineering Vol. 4 No. 3 (2025): DECEMBER | JTIE : Journal of Technology Informatics and Engineering Vol. 4 No. 2 (2025): AUGUST | JTIE : Journal of Technology Informatics and Engineering Vol. 4 No. 1 (2025): APRIL | JTIE : Journal of Technology Informatics and Engineering Vol. 3 No. 3 (2024): December (Special Issue: Big Data Analytics) | JTIE: Journal of Technology Info Vol. 3 No. 2 (2024): Agustus : Journal of Technology Informatics and Engineering Vol 3 No 2 (2024): Agustus : Journal of Technology Informatics and Engineering Vol 3 No 1 (2024): April : Journal of Technology Informatics and Engineering Vol. 3 No. 1 (2024): April : Journal of Technology Informatics and Engineering Vol 2 No 3 (2023): December : Journal of Technology Informatics and Engineering Vol. 2 No. 3 (2023): December : Journal of Technology Informatics and Engineering Vol 2 No 2 (2023): August : Journal of Technology Informatics and Engineering Vol. 2 No. 2 (2023): August : Journal of Technology Informatics and Engineering Vol 2 No 1 (2023): April : Journal of Technology Informatics and Engineering Vol. 2 No. 1 (2023): April : Journal of Technology Informatics and Engineering Vol. 1 No. 3 (2022): December: Journal of Technology Informatics and Engineering Vol 1 No 3 (2022): Desember: Journal of Technology Informatics and Engineering Vol 1 No 3 (2022): December: Journal of Technology Informatics and Engineering Vol 1 No 2 (2022): August: Journal of Technology Informatics and Engineering Vol 1 No 2 (2022): Agustus: Journal of Technology Informatics and Engineering Vol. 1 No. 2 (2022): August: Journal of Technology Informatics and Engineering Vol. 1 No. 1 (2022): April: Journal of Technology Informatics and Engineering Vol 1 No 1 (2022): April: Journal of Technology Informatics and Engineering More Issue