cover
Contact Name
Edo Yonatan Koentjoro
Contact Email
edo@dinamika.ac.id
Phone
+6281252457234
Journal Mail Official
joti@dinamika.ac.id
Editorial Address
Jalan Raya Kedung Baruk No. 98, Surabaya 60298
Location
Kota surabaya,
Jawa timur
INDONESIA
Journal of Technology and Informatics (JoTI)
Published by Universitas Dinamika
ISSN : 27214842     EISSN : 26866102     DOI : https://doi.org/10.37802/joti
1. Teknologi Informasi : Rekayasaperangkat lunak, Pengetahuan data maining, Mobile Computing, Parallel/Distributed Computing, Kecerdasan Buatan, Tata Kelola dan Manajemen Sistem Informasi, User Interface/ User Experience, Process Management, IT Security, IS Adoption and Evaluation. 2. Sistem Komunikasi : Jaringan Protokol dan Manajemen, Sistem Telekomunikasi, Komunikasi Nirkabel, Jaringan Sensor.
Articles 120 Documents
Cloud-Based Mobile Application for Skin Lesion Screening Using InceptionV3 Habibullah Akbar; Raynaldi Sandy
Journal of Technology and Informatics (JoTI) Vol. 8 No. 2 (2026): Vol. 8 N. 2 (2026)
Publisher : Universitas Dinamika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37802/joti.v8i2.1346

Abstract

Skin-lesion studies have achieved promising classification accuracy; however, their implementation in mobile–cloud environments remains limited. This study presents Skin Alert, a cloud-based prototype for classifying seven skin-lesion categories in the HAM10000 dataset using an ImageNet-pretrained InceptionV3 model. Hyperparameters, including learning rate, dropout rate, batch size, and number of epochs, were optimized using grid search. The original class distribution was retained, while data augmentation and class-weighted learning were applied during training. The final model achieved an internal validation accuracy of 85.32%, weighted precision of 85.79%, weighted recall of 85.32%, weighted F1-score of 85.38%, macro F1-score of 72.93%, and macro-average one-vs-rest AUC of 96.84%. The model was deployed through a Flask API on Google Cloud Platform and integrated with a Flutter application, Firebase Authentication, Realtime Database, and Storage. Black-box and backend integration testing confirmed that predefined workflows operated as intended. The locally hosted API achieved approximately 250–300 ms response time per image, while cloud deployment required approximately 1.10 s per image. These findings demonstrate the technical feasibility of the proposed mobile–cloud prototype.
Comparative Evaluation of Deep Learning Architectures for Early Skin Cancer Detection Using Dermatoscopic Images  Aurel Elviolita Putri; Agung Mulyo Widodo; Nizirwan Anwar; Binastya Anggara Sekti
Journal of Technology and Informatics (JoTI) Vol. 8 No. 2 (2026): Vol. 8 N. 2 (2026)
Publisher : Universitas Dinamika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37802/

Abstract

Early identification of skin cancer is essential for improving diagnostic reliability and patient outcomes. Although convolutional neural networks (CNNs) have demonstrated promising performance in dermoscopic image classification, comparative evaluations on imbalanced multiclass datasets remain challenging. This study compares three transfer learning-based CNN architectures—VGG16, ResNet50, and MobileNetV2—for seven-class skin lesion classification using the imbalanced HAM10000 dataset. All models were evaluated using the same dataset partitions, image resolution, and performance metrics, while architecture-specific augmentation and loss-function strategies were retained. In particular, VGG16 used MixUp, ResNet50 used CutMix, VGG16 and ResNet50 employed Focal Loss, and MobileNetV2 used label smoothing. Performance was assessed using accuracy, precision, recall, F1-score, confusion matrices, and ROC–AUC. ResNet50 achieved the best overall performance, with 85.71% accuracy and a weighted F1-score of 0.8502, ahead of VGG16 (82.52%, 0.8172) and MobileNetV2 (79.32%, 0.7739). ResNet50 also showed the highest recall for melanoma and dermatofibroma among the three tested configurations, although minority-class sensitivity remained limited. These results favor ResNet50 under the evaluated training configurations; however, differences in augmentation and loss functions prevent attributing performance gaps solely to network architecture.
Data Integrated K-Means Clustering And Random Forest Classification For Crop Recommendation Based On Environmental Parameters Aryanti Aryanti; M. Dimas Putra Ramadhan; Muhammad Arcy Alfaathir; Ghefira Fariah; Putri Arum Sari
Journal of Technology and Informatics (JoTI) Vol. 8 No. 2 (2026): Vol. 8 N. 2 (2026)
Publisher : Universitas Dinamika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37802/

Abstract

The agricultural sector plays a strategic role in Indonesia’s economy, yet inappropriate crop selection under specific environmental conditions can reduce yields and cause economic losses. Existing studies commonly apply individual classifiers to environmental data, while clustering is often used only for descriptive analysis. This study proposes an integrated two-stage pipeline combining K-Means clustering and Random Forest classification for crop recommendation. First, K-Means groups 22 crop types based on four environmental parameters: temperature, humidity, soil pH, and rainfall. The resulting cluster membership is then encoded as an additional categorical feature and combined with normalized environmental features for Random Forest classification. Experiments using 2,200 samples from Kaggle identified four clusters, achieving a Davies–Bouldin Index of 0.84 and a Silhouette Score of 0.61. The integrated model achieved 97.7% test accuracy, with precision, recall, and F1-score of 0.99, outperforming the Random Forest baseline accuracy of 96.9%. These findings demonstrate the potential benefits of incorporating unsupervised cluster information into supervised classification. This approach offers a reusable feature-augmentation framework for agricultural intelligent decision support systems.
Relational Database Model Design for Logistics and Shipment Tracking Systems Erza Hanif Pramudita Hanggara; Ezekiel Besarianta Prabaswara Sitorus; Aditya Wahyu Wiranatha; Fathan Rafif Ryansyah; Raditya Ramadhan Eka Widhianto; Diva Kurnianingtyas
Journal of Technology and Informatics (JoTI) Vol. 8 No. 2 (2026): Vol. 8 N. 2 (2026)
Publisher : Universitas Dinamika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37802/

Abstract

Efficient and reliable shipment tracking is essential for modern logistics, where managing large volumes of real-time transportation data remains a significant challenge. This study proposes a normalized relational database model to support structured logistics data management and shipment tracking using Entity Relationship Diagrams (ERDs) and Structured Query Language (SQL). The methodology involved analyzing a Transportation and Logistics dataset comprising 6,880 records and 32 attributes, identifying entity relationships, and applying normalization up to the Third Normal Form (3NF). The resulting database was implemented in Microsoft SQL Server and evaluated using simulated datasets containing 10,000, 100,000, and 1 million records. Experimental results demonstrated that complex queries could be executed in approximately 6 seconds for 1 million records. Furthermore, integrating a dedicated GPS_Ping table provides a structured mechanism for storing time-stamped shipment location observations, supporting location-based tracking data management. The proposed model reduces data redundancy, strengthens relational data integrity, and supports scalable query processing. These findings demonstrate the potential of a normalized relational database architecture as a foundation for developing scalable logistics information systems and reliable shipment tracking applications
Securing IoT Data in Power Consumption Anomaly Detection Systems Using the Rivest–Shamir–Adleman Cryptographic Algorithm Ardian Banuarta Frizi; Arief Arfriandi; Djuniadi
Journal of Technology and Informatics (JoTI) Vol. 8 No. 2 (2026): Vol. 8 N. 2 (2026)
Publisher : Universitas Dinamika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37802/

Abstract

The Internet of Things (IoT) enables real-time monitoring and transmission of power consumption data but introduces security risks, including unauthorized access, data interception, and manipulation. This study proposes an asymmetric cryptographic mechanism based on the Rivest–Shamir–Adleman (RSA) algorithm to secure sensor data in a power consumption anomaly detection system. RSA public-key encryption and private-key decryption were integrated into a power monitoring device to protect voltage, current, power, and energy measurements during data transmission. The security and computational performance of the proposed mechanism were evaluated using encryption and decryption time, Shannon entropy, and avalanche effect. Experimental results showed an average encryption time of 114.322 ms and decryption time of 7.893 ms, resulting in a total processing time of 122.215 ms, which remained below the defined system evaluation threshold. The resulting ciphertext achieved an average Shannon entropy of 7.173 bits, approaching the theoretical maximum of 8 bits, while the average avalanche effect reached 49.993%, closely matching the ideal value of 50%. These findings demonstrate that RSA can provide practical protection for periodically transmitted IoT sensor data while producing ciphertext with desirable randomness characteristics for power consumption anomaly detection applications
COLLISION AVOIDANCE MOBILE ROBOT USING VECTOR FIELD HISTOGRAM ON POINT CLOUD KINECT Devan Yusfa Sukmadya; Muhammad Fuad
Journal of Technology and Informatics (JoTI) Vol. 8 No. 2 (2026): Vol. 8 N. 2 (2026)
Publisher : Universitas Dinamika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37802/

Abstract

Autonomous mobile robots operating in indoor environments must be capable of avoiding humans as dynamic obstacles while maintaining reliable navigation performance. Although the Vector Field Histogram (VFH) algorithm has been widely applied for obstacle avoidance, most previous studies rely on two-dimensional sensors or do not directly integrate three-dimensional point cloud perception with real-time navigation on differential drive mobile robots. This limitation motivates the development of a more robust human-aware navigation system. Therefore, this study proposes a Differential Drive Mobile Robot (DDMR) that integrates Microsoft Kinect V1 point cloud sensing with the Vector Field Histogram (VFH) algorithm for real-time collision avoidance. Environmental depth information is converted into a three-dimensional point cloud, processed into a VFH polar histogram, and used to determine safe navigation directions during robot motion. Experimental evaluation was conducted in dynamic indoor environments involving human obstacles. The proposed system processes point cloud data at approximately 22 FPS, detects humans within a range of 0.8–3.5 m with a measurement error of 0.042 m, achieves an average VFH computation time of 0.05 s, and produces an average avoidance response time of 0.73 s with a collision-free success rate of 93.3%. These results demonstrate that integrating Kinect-based point cloud perception with VFH provides an effective and practical solution for real-time human-aware obstacle avoidance in indoor autonomous mobile robot navigation
Condition-Aware Cross-Scale Transformers for Object Detection under Compound Adverse Environments Fiston Oshasha Oshasha; Saint Jean Djungu; Franklin Mwamba Kande
Journal of Technology and Informatics (JoTI) Vol. 8 No. 2 (2026): Vol. 8 N. 2 (2026)
Publisher : Universitas Dinamika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37802/

Abstract

Object detection under adverse environmental conditions remains a critical challenge for autonomous driving systems, with performance degrading by over 40% under dense fog, heavy precipitation, or nighttime scenarios. Existing approaches either specialize for single degradation types or remain fundamentally condition-agnostic, failing to address the compound nature of real-world adverse conditions. We present a Condition-Aware Cross-Scale Transformer (CACST), a unified framework integrating explicit environmental condition estimation, adaptive image preprocessing, and cross-scale feature interaction. Our approach introduces: (1) a condition estimation module quantifying degradation parameters via supervised and contrastive learning; (2) a gated image adaptation mechanism with learnable ISP operations dynamically modulated by estimated conditions; and (3) an Enhanced Density-aware Cross-Scale Transformer (EDST) performing global attention across feature pyramid scales with spatial reliability weighting. Comprehensive experiments across five benchmarks demonstrate state-of-the-art performance: CACST achieves +4.1% mAP on ACDC (47.8% vs. 43.7%), +3.2% on Foggy Cityscapes (49.7% vs. 46.5%), and +6.7% on ExDark (74.9% vs. 68.2%) compared to the strongest specialized baseline, maintaining balanced accuracy across all conditions
Systematic Literature Review: Modern Data Stack Architecture Layers and Technologies for Data Warehousing Nanang Fajar Untoro; Farisa Aulia Safira; Natia Seanesya Kencana; Rizky Muflih; Vitri Tundjungsari
Journal of Technology and Informatics (JoTI) Vol. 8 No. 2 (2026): Vol. 8 N. 2 (2026)
Publisher : Universitas Dinamika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37802/

Abstract

This systematic literature review (SLR) examines modern data stack architectures for data warehousing, focusing on their architectural layers and the tools used within each layer. Following SLR procedures, scholarly articles published between 2020 and 2025 were retrieved from IEEE Xplore and Google Scholar and screened using predefined inclusion and exclusion criteria, resulting in 35 primary studies. The review addresses three research questions: (1) which architectural layers predominate in modern data stack frameworks, (2) which tools and technologies are commonly applied within each layer, and (3) which trends shape the evolution of these architectures. The findings show a clear convergence toward modular, cloud-native architectures consisting of six layers: data ingestion, storage, transformation, orchestration, serving, and governance. Four major trends were identified: the shift from Extract, Transform, Load (ETL) to Extract, Load, Transform (ELT), the emergence of lakehouse architectures, the growing adoption of managed and serverless services, and the expansion of real-time analytics. This study contributes a layer-by-layer technology mapping that offers a structured reference for practitioners, researchers, and organizations in evaluating and designing cloud-based data warehouse platforms.
RespiScan: Tuberculosis Triage Support from Cough Acoustics Using Continuous Wavelet Transform Scalograms and MobileNetV2 Gibran El Fahmi; Heri Pratikno; Pauladie Susanto; Weny Indah Kusumawati
Journal of Technology and Informatics (JoTI) Vol. 8 No. 2 (2026): Vol. 8 N. 2 (2026)
Publisher : Universitas Dinamika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37802/

Abstract

Tuberculosis (TB) requires accessible pre-screening approaches for referral prioritization in resource-limited settings. Cough-acoustic studies have not always reported subject-level partitioning, patient-level evaluation, operating-point selection, and performance uncertainty consistently. This study presents RespiScan, a patient-level triage-support framework using complex Morlet Continuous Wavelet Transform scalograms and ImageNet-pretrained MobileNetV2 with corrected weighted focal loss. We curated a secondary cohort of 198 subjects (87 TB and 111 Non-TB) from TBscreen and Coswara. Audio was standardized to 16-kHz mono, one-second segments, capped at 10 clean recordings per subject, and partitioned strictly by subject into 137 training, 30 validation, and 31 internal-holdout subjects. Training-only augmentation used 10-dB environmental noise for both classes and speed perturbation for Non-TB. We selected the Non-TB: TB weight of 1.5:1.0 from three validation-only settings, then averaged patient scores before applying a validation-derived Youden threshold of 0.424084. On the internal holdout, RespiScan achieved an AUROC of 0.8866 (95% CI: 0.7479-0.9832), 77.42% accuracy, 71.43% sensitivity, and 82.35% specificity. Wide uncertainty, source-label confounding, and exploratory calibration preclude clinical-readiness claims; larger source-balanced prospective validation is required.
Investigating the Benefits and Challenges of Mobile-Based Learning Among Students at Kabul Education University Mohammad Asif Dawlatnazar; Qurban Ali Frugh; Ali Shah Saber
Journal of Technology and Informatics (JoTI) Vol. 8 No. 2 (2026): Vol. 8 N. 2 (2026)
Publisher : Universitas Dinamika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37802/

Abstract

The increasing integration of smartphones into education has highlighted the potential of Mobile-Based Learning (MBL) to enhance learning accessibility and engagement. This study investigated students’ perceptions of the benefits and challenges of MBL at Kabul Education University. A quantitative, descriptive survey design was employed, using an expert-reviewed questionnaire distributed randomly to 351 students across nine faculties. Instrument reliability was confirmed with a Cronbach’s alpha coefficient of 0.79. Descriptive statistical analysis revealed that mean scores for the perceived benefits of MBL ranged from 3 to 4, whereas mean scores for its challenges ranged from 2 to 3, indicating generally favorable perceptions of its educational value. Students recognized the potential of mobile learning to improve access to educational resources and support learning motivation. However, concerns regarding distraction, headaches, and eye strain highlighted potential barriers to effective implementation. These findings suggest that students perceive MBL as a promising educational approach, although the results reflect subjective perceptions rather than objectively measured improvements in learning outcomes. To maximize its educational potential, the study recommends strengthening digital infrastructure and promoting awareness of responsible, pedagogically appropriate mobile device use. This research provides insights for educators and policymakers seeking to integrate mobile technology more effectively into higher education

Page 12 of 12 | Total Record : 120