cover
Contact Name
Prananda Anugrah
Contact Email
jitet.journal@um.ac.id
Phone
-
Journal Mail Official
jitet.journal@um.ac.id
Editorial Address
Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LP2M) Alamat: Graha Rektorat Lantai 6, Jl. Semarang No.5, Sumbersari, Kec. Lowokwaru, Kota Malang, Jawa Timur 65145, Indonesia
Location
Kota malang,
Jawa timur
INDONESIA
Jurnal Inovasi Teknologi dan Edukasi Teknik
ISSN : -     EISSN : 27977196     DOI : 10.17977
Core Subject : Engineering,
Jurnal Inovasi Teknologi dan Edukasi Teknik menerbitkan naskah terkait Teknik Sipil, Teknologi Industri, Teknik Mesin, Teknik Elektro, dan Pendidikan Kejuruan. Fokus dan lingkup jurnal meliputi Teknik Sipil, Teknologi Industri, Teknik Mesin, Teknik Elektro, dan Pendidikan Kejuruan
Articles 291 Documents
DEEP LEARNING FOR COLORECTAL CANCER TISSUE CLASSIFICATION FROM HISTOPATHOLOGY IMAGES: CONTROLLED EVALUATION OF EFFICIENTNET-B0, RESNET50, AND DENSENET121 WITH PATIENT-INDEPENDENT EXTERNAL VALIDATION Mohammed S. H. Al-Tamimi
Jurnal Inovasi Teknologi dan Edukasi Teknik Vol. 6 No. 7 (2026)
Publisher : Universitas Ngeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17977/um068.v6.i7.2026.1

Abstract

Histopathological examination of Haematoxylin and Eosin (H&E) stained tissues is the foundation of diagnosing colorectal cancer (CRC). The increasing digitization of pathology has resulted in a surfeit of images. Currently, computational methods to automatically classify histopathological tissues are in their infancy. In this paper, nine-class colorectal tissue classification was evaluated using EfficientNet-B0, ResNet50, and DenseNet121. The classification problem was standardized with respect to data pre-processing, data augmentation, model optimization and evaluation. The classification models were developed using the NCT-CRC-HE-100K dataset (100,000 histopathology image patches) and validated on the independent CRC-VAL-HE-7K dataset (7,180 image patches). The validation was performed using accuracy, macro-average precision, macro-average recall, macro-F1 score, weighted-F1, and class-wise average precision, average recall, average F1 score and average specificity. Class-level analysis revealed that MUS and STR were challenging classes for the studied architectures with DEB resulting in confusion. A qualitative Grad-CAM analysis was performed on representative images to understand the reason for the predicted class. The study revealed that the three CNN architectures were able to generalize well for colorectal histopathology classification. Controlled external evaluation of deep learning models is essential to understand the class-specific reasons for the errors.
HEART DISEASE PREDICTION USING MULTI-OBJECTIVE META-HEURISTICS-BASED FEATURE SELECTION AND ENSEMBLE CLASSIFICATION Amel Nashat Shakir
Jurnal Inovasi Teknologi dan Edukasi Teknik Vol. 6 No. 8 (2026)
Publisher : Universitas Ngeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Heart disease is a serious medical issue, and detecting it correctly can make a difference between life and death. Recently, machine learning techniques have begun to be used to help doctors in making a diagnosis, however, there is a problem: medical databases are full of unnecessary, excess, or noisy features. These unnecessary features complicate the prediction of newly arrived patients as they slow down the system and confuse it, which results in over-learning; thus, the system may perform well in predicting the disease based on the data it was trained on but will fail while predicting sick patients. In this paper, we present one of the simplest solutions to that problem. The proposed approach utilizes optimization techniques of multi-objective meta-heuristics for ongoing feature selection integrated with ensemble classification algorithms. In short, the proposed method employs four optimization techniques: Multi-Objective Genetic Algorithm (MOGA), Multi-Objective Grey Wolf Optimizer (MOGWO), Multi-Objective Particle Swarm Optimization (MOPSO), and Multi-Objective Artificial Bee Colony Optimization (MOABC). These algorithms work in parallel to reduce both the number of features selected and the classification error. After acquiring the desired best features subsets, these are forwarded to four different classifiers: K nearest neighbors (KNN), artificial neural networks (ANN), support vector machines (SVM), and naive Bayesian (NB). In the experiments on a standard dataset for heart disease, the best results were reported for the combination of MOPSO with KNN since it achieved an accuracy of 96.66%, precision of 98.24%, and F-measure of 98.15%. The values presented are much better than the ones achieved with the help of other existing approaches. Therefore, the proposed approach is very efficient as it enables elimination of any useless features and focus on the most useful ones for the effective prediction of heart diseases
WORKLOAD-AWARE BENCHMARKING OF MODBUS TCP, OPC UA PUBSUB OVER TSN, AND ETHERCAT: A LITERATURE-CALIBRATED MONTE CARLO STUDY OF LATENCY, JITTER, AND DETERMINISM FOR MIXED INDUSTRIAL NETWORKS Yahya Tareq Hussein; Sayf Waleed Majeed
Jurnal Inovasi Teknologi dan Edukasi Teknik Vol. 6 No. 9 (2026)
Publisher : Universitas Ngeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Selecting an industrial communication protocol is usually treated as a single, plant-wide decision, although factory networks host traffic classes whose timing requirements differ by more than three orders of magnitude. This paper presents a reproducible, workload-aware benchmark of three widely deployed protocols—Modbus TCP, OPC UA PubSub over Time-Sensitive Networking (TSN), and EtherCAT-across five representative workloads ranging from 250 µs synchronized servo control to 1 s condition monitoring. Stochastic latency models for each protocol were calibrated to published measurement studies and specifications and evaluated through a Monte Carlo experiment of 30 independent replications × 4,000 cycles per protocol-workload pair (1.8 million simulated cycles in total). Performance is quantified by on-time reliability, jitter, tail latency, and a composite score combining reliability, determinism, and deadline headroom. EtherCAT delivered 100% on-time reliability with sub-microsecond jitter on every workload. OPC UA PubSub achieved ≥99.87% reliability for deadlines of 1 ms or longer but only 75.3% at 250 µs. Modbus TCP was unusable below 2 ms yet reached ≥99.8% at 10 ms and above (average 34.5). The ranking is statistically significant (Kruskal–Wallis, p < 10⁻¹⁵ for every workload) and robust to changes in composite-score weights. Sensitivity analyses quantify the degradation of OPC UA PubSub with TSN hop count and of Modbus TCP with background load. The results support a segmented architecture-EtherCAT for motion control, OPC UA PubSub/TSN as the cell-to-enterprise backbone, and Modbus TCP for legacy, slow telemetry-and provide an open, recalibratable methodology for site-specific protocol selection.
HYBRID CONTROL OF MOBILE ROBOTS USING COMPUTED TORQUE AND PID CONTROLLERS FOR ENHANCED TRAJECTORY TRACKING Rafeaf J.Salman
Jurnal Inovasi Teknologi dan Edukasi Teknik Vol. 6 No. 10 (2026)
Publisher : Universitas Ngeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

In this research, a hybrid control system is designed and implemented to achieve high performance a Four-Mecanum Wheeled Mobile Robot's (4-MWMR) trajectory tracking using Computed Torque Control (CTC) and Proportional–Integral–Derivative (PID) controller. The FMWMRs are characterized as omnidirectional mobile robots, which suffer from nonlinear dynamics, wheel slippage and parameter uncertainties, resulting in difficulties in achieving accurate motion control. A dynamic model is derived from the study using the Euler-Lagrange formulation and this results in a CTC that linearizes the system. The PID controller is used to improve trajectory accuracy and steady state performance. The hybrid approach takes into account several reference trajectories, calculates the tracking errors and calculates steering commands to modify the wheel velocities. System is robust against disturbances and modelling errors, due to real-time wheel encoder and Inertial Measurement Unit (IMU) feedback.The simulation results show that the hybrid controller has better performance than the traditional PID controllers with regard to the errors it reduces, stability and response time. It combines the dynamic compensation capabilities of the Computed Torque Controller, with the simplicity of the PID controller, thus creating a powerful solution for dealing with the nonlinear dynamics of Four-Mecanum Wheeled Mobile Robots. The hybrid method is a promising concept for use in high-precision autonomous navigation systems, which are found in industrial automation, intelligent transportation and warehouse logistics.
EVALUATION OF USER EXPERIENCE IN WEB QUEST GAMIFICATION USING A USER EXPERIENCE QUESTIONNAIRE Muhammad Wildan Ramadhana; Dimas Wahyu Wibowo; Eka Larasati Amalia; Achmad Zakki Falani
Jurnal Inovasi Teknologi dan Edukasi Teknik Vol. 6 No. 1 (2026)
Publisher : Universitas Ngeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17977/um068.v6.i1.2026.3

Abstract

Advances in information technology have encouraged more interactive learning media, particularly in Web Programming courses. However, instruction still often relies on static media that are less effective in enhancing student engagement and learning motivation. To address this, a gamified Web Quest was developed using a guided discovery learning approach. This study measures user experience with the Web Quest system for learning basic web programming, using the User Experience Questionnaire (UEQ), focusing on Pragmatic Quality and Hedonic Quality, supported by Microsoft Reaction Cards (MRC). Respondents consisted of 34 students who had used the system. Results show Pragmatic Quality scored 1.48 and Hedonic Quality scored 1.43, indicating a positive user experience overall. The system was rated easy to understand, effective in supporting completion of learning tasks, and able to make learning engaging and motivating through gamification elements. MRC results showed the most frequently selected words were "Clean," "Creative," "Useful," "Attractive," and "Motivating," reflecting a positive perception of the system. These results indicate that gamification in Web Quest provides a good user experience from both pragmatic and hedonic perspectives. However, several aspects still require improvement, including interface refinement, clearer task flows, and further development of gamification features for a more engaging learning experience.
OPTIMIZATION OF WI-FI ACCESS POINT PLACEMENT USING GENETIC ALGORITHM: A CASE STUDY OF WIFI.ID PT TELKOM INDONESIA, TBK Khairil Anam
Jurnal Inovasi Teknologi dan Edukasi Teknik Vol. 6 No. 1 (2026)
Publisher : Universitas Ngeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17977/um068.v6.i1.2026.4

Abstract

The need for WiFi use in the era of the Covid-19 pandemic increased sharply. PT. Telkom Indonesia is one of the state-owned enterprises that provide super-fast internet services. One of its flagship products is WiFi.Id service up to 100 Mbps. But there is often an Access Point Crisis for installing new WiFi.Id. Because it is less than optimal in installing Access Point WiFi.Id, this research aims to optimize the location of WiFi.Id. The study used a Geographic Information System (GIS)-based genetics algorithm application to map out which locations were not potential. The Genetic Algorithm results are in population and generation in location coordinates with the best fitness costs. This research can be used to potentially secure asset access points, overcome access point crises and can be used to increase revenue PT. Telkom Indonesia, Tbk. The accuracy rate of application systems using genetic algorithms to map productive locations with an average accuracy rate of 84%.
DISCOUNT PRICING SYSTEM USING FUZZY SUGENO METHOD Dinda Amanda Mutia; Kartika Candra Kirana
Jurnal Inovasi Teknologi dan Edukasi Teknik Vol. 6 No. 1 (2026)
Publisher : Universitas Ngeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17977/um068.v6.i1.2026.5

Abstract

In an online shop, some items do not sell optimally, so a price cut or discount is applied to them to maximize sales. Determining the discount price in the Tokotadia online shop is based on three pieces of data: price, stock, and the item’s rating. The data is obtained from Shopee’s online shop. Using the Fuzzy method because of its easy-to-understand logic and mathematical concept. The output of this method will be displayed as a statement indicating whether a discount is applied, using the Mape method. Therefore, a Discount Price Determination System Using the Sugeno Fuzzy Method is proposed. Based on MAPE calculations, the average price prediction error is approximately 4.17%, so the prediction model is classified as very accurate and follows the original price trend well.
ANALISIS PENGARUH VARIASI DAYA FREKUENSI FEED RATE LASER DAN MATERIAL TERHADAP HASIL POTONG PADA MESIN LASER ENGRAVING Mochammad Dimas Awalludin; Fatkhur Rohman
Jurnal Inovasi Teknologi dan Edukasi Teknik Vol. 6 No. 2 (2026)
Publisher : Universitas Ngeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17977/um068.v6.i2.2026.2

Abstract

Penggunaan mesin laser engraver konvensional sering terkendala oleh rumitnya interaksi termal dengan material uji. Penelitian ini mengevaluasi dampak daya laser (5 Watt dan 10 Watt), feed-rate, serta jenis material (busa, kulit sintetis, karton, dan karton duplex) terhadap mutu fisik produk akhir. Analisis statistik menunjukkan korelasi signifikan (p < 0,001) antara penyetelan daya dan presisi dimensi. Peningkatan daya secara konsisten memperbesar persentase penyusutan akibat penumpukan panas. Pada daya 5 Watt, penyusutan terendah terjadi pada busa (6,02%–8,55%) dan tertinggi pada duplex (22,50%–30,98%). Pada 10 Watt, kerusakan memburuk dengan penyusutan busa mencapai 22,81% dan duplex menembus 46,08%. Reaksi degradasi material juga berbeda: spesimen organik berserat menyusut akibat karbonisasi berlebih, sedangkan polimer berongga hancur murni karena pelelehan instan. Karena setiap material memiliki ambang toleransi panas yang kaku, kesalahan injeksi daya akan memicu penyimpangan ukuran hingga kegagalan pemotongan mutlak. Penelitian ini berhasil merumuskan acuan parameter untuk meminimalkan risiko kegagalan dimensi dan meningkatkan efisiensi produksi.
MULTI-TOOL APPROACH FOR SOFTWARE QUALITY EVALUATION BASED ON ISO/IEC 25010:2011 ON THE BAJAPRO APPLICATION Zulfa Ulinnuha Azazi; Pramana Yoga Saputra; Yuri Ariyanto
Jurnal Inovasi Teknologi dan Edukasi Teknik Vol. 6 No. 2 (2026)
Publisher : Universitas Ngeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17977/um068.v6.i2.2026.3

Abstract

Evaluating the software quality of web-based learning applications requires testing methods tailored to the specific quality characteristics under assessment. This study evaluates Bajapro, a programming learning application, based on the eight characteristics of the ISO/IEC 25010:2011 standard using a multi-tool approach. Testing was conducted using black-box testing following the Software Testing Life Cycle (STLC) stages, leveraging Cypress, Playwright, OWASP ZAP, the System Usability Scale (SUS), and supporting manual tests. The results indicate that Functional Suitability, Reliability, Compatibility, and Portability achieved a 100% success rate. Performance Efficiency yielded response times ranging from 0.008 to 1.20 seconds, with maximum CPU usage of 6.5% and maximum server memory usage of 4.42 GB out of 15.6 GB. Usability evaluation involving 50 respondents produced a SUS score of 60.15, placing it in the "OK" (Fair) category. Security testing identified one High-Risk vulnerability, specifically SQL Injection in the Run Code feature. For Maintainability, all regression testing scenarios executed successfully, while the maintainability checklist achieved a score of 60%. These findings demonstrate that functional success does not guarantee high quality across other quality characteristics. The multi-tool approach enables comprehensive evaluation using techniques and tools customized to each characteristic's unique requirements, providing an accurate representation of software quality from both technical and user perspectives.
ANALISIS SENTIMEN PENGGUNA X TERHADAP LAYANAN CHATBOT SHOPEE DAN TOKOPEDIA MENGGUNAKAN METODE LEXICON-BASED Luthfi Indana; Kevin Sawadil Azham Syachwani
Jurnal Inovasi Teknologi dan Edukasi Teknik Vol. 6 No. 2 (2026)
Publisher : Universitas Ngeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17977/um068.v6.i2.2026.4

Abstract

Layanan pelanggan otomatis berupa chatbot banyak digunakan oleh platform e-commerce di Indonesia, namun kemampuannya dalam memenuhi kebutuhan pelanggan masih diperdebatkan. Penelitian ini menganalisis sentimen pengguna X terhadap layanan chatbot Shopee dan Tokopedia berdasarkan unggahan di media sosial X. Sebanyak 1.013 post berbahasa Indonesia dikumpulkan melalui web scraping menggunakan delapan kata kunci terkait chatbot. Data diproses melalui tahap cleaning, case folding, tokenizing, stopword removal, dan stemming, kemudian dilabeli menggunakan pendekatan berbasis leksikon dengan kamus Indonesian Sentiment Lexicon (InSet). Secara keseluruhan, diperoleh 402 post (39,7%) bersentimen positif, 341 (33,7%) negatif, dan 270 (26,7%) netral. Dari 636 post tentang Shopee, 35,7% positif, 28,0% negatif, dan 36,3% netral, sedangkan dari 688 post tentang Tokopedia, 47,7% positif, 34,6% negatif, dan 17,7% netral. Analisis word cloud menunjukkan bahwa sentimen positif berkaitan dengan respons yang cepat dan kemudahan transaksi, sedangkan sentimen negatif berkaitan dengan ketidakmampuan chatbot memahami konteks dan menyelesaikan masalah yang kompleks. Model layanan hibrida, yaitu chatbot menangani pertanyaan rutin dan meneruskan kasus kompleks kepada agen manusia, direkomendasikan.