Scientific Publications Directory

Full Author List

Darwis, Herdianti; Adnan, Adam; Purnawansyah; Manga, Abdul Rachman, Faculty of Computer Science, Universitas Muslim Indonesia, Makassar, Indonesia; Wibawa, Aji Prasetya; Irawati, Department of Electrical and Informatics Engineering, Universitas Negeri Malang, Malang, Indonesia

Abstract

The proliferation of online learning platforms has necessitated automated systems for monitoring students' emotional states, given that variations in facial expressions significantly influence engagement and learning outcomes. This study proposes a spatio-temporal classification framework for recognizing emotion intensity levels in the DAiSEE dataset, utilizing Vision Transformer as a spatial feature extractor alongside various temporal models, including LSTM, BiLSTM, TimeSformer, and their hybrid variants. Embeddings are extracted via ViT, after which temporal dependencies are captured by each classifier, incorporating feature-level oversampling to mitigate severe class imbalance. Experimental findings reveal that, despite ViT's ability to generate robust spatial representations, all temporal models struggle to identify minority classes, resulting in predictions biased toward the majority class as evidenced by low balanced accuracy scores and overlapping clusters in t-SNE visualizations. Among all configurations, the ViT + LSTM model delivered the most reliable performance, attaining 59 % accuracy and a 0.59 weighted F1-score on engagement labels, while remaining competitive with prior methods. In essence, integrating spatial and temporal features enhances classification efficacy, yet its effectiveness is substantially constrained by imbalanced data distributions. These results offer a thorough examination of representational challenges in imbalanced affective datasets, along with recommendations for mitigation techniques, crossdataset assessments, and multimodal integrations.

Related SDGs Targets

Full Author List

Hayati, Lilis Nur; Indra Dolly, Universitas Muslim Indonesia; Handayani, Anik Nur; Irianti, Wahyu Sakti Gunawan, Universitas Negeri Malang; Damanhuri Nor Salwa, Universiti Teknologi MARA (UiTM);

Abstract

Indonesian Sign Language (Bahasa Isyarat Indonesia/BISINDO) enables communication for deaf individuals through hand gestures, yet limited public awareness creates significant barriers between deaf and hearing communities. Existing recognition systems often fail to generalize across diverse skin tones, reducing their effectiveness in inclusive real-world deployment. The contribution of this research is a BISINDO alphabet recognition system that integrates skin color features - extracted via HSV-based skin segmentation - as an additional preprocessing layer within the Faster R-CNN framework, explicitly improving detection robustness across varied skin tones. The dataset consists of 8,000 images from ten adult actors representing light, medium-brown, and dark skin tones, augmented through flipping and brightness variation, with a 90:10 training-to-testing ratio. The model was trained over 15,000 steps with a batch size of 24, selected through empirical validation to balance convergence stability and dataset size. Experimental results show that indoor conditions outperform outdoor settings due to controlled lighting. Light-skinned and dark-skinned participants achieved the highest accuracy of 87.5% and F1-score of 85.71%, while medium-brown-skinned participants showed slightly lower performance, likely attributed to greater variability in reflectance under mixed lighting. The system achieves 24 frames per second, demonstrating potential for real-time communication support. These findings confirm that Faster R-CNN with skin color feature integration is effective for BISINDO alphabet recognition, with skin tone diversity being a critical performance factor. Future work will explore larger participant pools and dynamic gesture recognition under varied real-world lighting scenarios.

Related SDGs Targets

Full Author List

Manga, Abdul Rachman; Nanda, As'syahrin, Department of Computer Science, Universitas Muslim Indonesia, Makassar, Indonesia; Handayani, Anik Nur; Herwanto, Heru Wahyu, Department of Electrical Engineering, Universitas Negeri Malang, Malang, Indonesia; Asmara, Rosa Andrie, Information Technology Department, State Polytechnic of Malang, Malang, Indonesia; Lantara, Dirgahayu, Faculty of Industrial Engineering, Universitas Muslim Indonesia, Makassar, Indonesia

Abstract

Data classification plays a crucial role in artificial intelligence, particularly in enhancing model accuracy. This study focuses on classifying Toraja buffalo, a livestock breed with significant cultural importance in South Sulawesi, Indonesia. While the Single Input Approach is commonly used for classification, it often fails to capture all the necessary attributes to effectively distinguish between racial traits. Therefore, this research aims to evaluate the effectiveness of a multi-input approach, which integrates multiple data inputs to improve classification performance compared to the Single Input method. We employed four classification techniques: K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Naïve Bayes, and Decision Tree, using both Single Input and Multi Input configurations. Model performance was assessed through Precision, Recall, F1 Score, and Accuracy metrics. The findings indicate that the Multi Input approach consistently outperformed the Single Input method. Notably, KNN achieved its best performance with Multi Input, recording an F1 Score of 0.7263 and an Accuracy of 0.7333, significantly surpassing the results obtained from Single Input. Similarly, SVM also demonstrated substantial performance enhancements with Multi Input. Overall, the study highlights the importance of incorporating a wider array of informative data to enhance the model's capability in accurately classifying specific categories, with KNN showing the most pronounced improvements

Related SDGs Targets

Full Author List

Purnawansyah; Adnan, Adam; Darwis, Herdianti, Faculty of Computer Science, Universitas Muslim Indonesia, Jl. Urip Sumoharjo KM 5, Makassar, 90231, Indonesia; Wibawa, Aji Prasetya, Universitas Negeri Malang, Jl. Semarang No. 5, Malang, 65145, Indonesia; Widyaningtyas, Triyanna; Haviluddin, Universitas Mulawarman, Jl. Kuaro, Samarinda, 75119, Indonesia

Abstract

Facial Expression Recognition (FER) plays a crucial role in humancomputer interaction, yet improving its accuracy remains a significant challenge. This study aims to enhance the robustness and effectiveness of FER systems by integrating multiple machine learning techniques within a semi-supervised learning framework. The primary objective is to develop a more effective ensemble model that combines Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), Support Vector Classifier (SVC), and Random Forest classifiers, utilizing both labeled and unlabeled data. The research implements data augmentation and feature extraction techniques, utilizing advanced architectures such as VGG19, ResNet50, and InceptionV3 to improve the quality and representation of facial expression data. Evaluations were conducted across three dataset scenarios: original, feature-extracted, and augmented, using various labelto- unlabeled ratios. The results indicate that the ensemble model achieved a notable accuracy improvement of 87% on the augmented dataset compared to individual classifiers and other ensemble methods, demonstrating superior performance in handling occlusions and diverse data conditions. However, several limitations exist. The study's reliance on the JAFFE dataset may restrict its generalizability, as it may not cover the full range of facial expressions encountered in real-world scenarios. Additionally, the effect of label-to-unlabeled ratios on the model's performance requires further exploration. Computational efficiency and training time were also not evaluated, which are critical considerations for practical implementation. For future research, it is recommended to employ cross-validation methods for more robust performance evaluation, explore additional data augmentation techniques, optimize ensemble configurations, and address the computational efficiency of the model to better advance FER technologies.

Related SDGs Targets

Full Author List

Syafie, Lukman, Universiti Kuala Lumpur, 50250 Kuala Lumpur, Malaysia; Rismayanti, Universitas Negeri Malang, Kota Malang, Jawa Timur 65145, Indonesia

Abstract

Benign Prostatic Hyperplasia (BPH) is a prevalent non-cancerous enlargement of the prostate gland in aging men, often requiring early diagnosis to prevent urinary complications and improve patient outcomes. Traditional diagnostic procedures are limited by subjectivity and accessibility, especially in under-resourced regions. This study proposes an automated diagnostic approach using a deep learning model based on DenseNet121 to classify RGB prostate images into BPH and normal categories. A region-specific dataset consisting of 176 labeled RGB images, collected from a clinical facility in Bangladesh, was used to train and evaluate the model. Pre-processingincluded image resizing, normalization, and data augmentation to enhance generalization. Transfer learning was employed to fine-tune the model, which was trained over 10 epochs using the Adam optimizer and cross-entropy loss. The model achieved a best validation accuracy of 94.12%, with a recall of 72.2% for BPH detection, demonstrating its ability to identify pathological patterns in simple imaging modalities. Despite challenges such as dataset size and imbalance, the findings indicate that RGB image-based deep learning models can support clinical diagnosis of BPH in low-resource settings. This work contributes a lightweight, accessible solution for prostate disease screening and provides a foundation for future research on scalable AI-assisted diagnostics

Related SDGs Targets

Full Author List

Belluano, Poetri Lestari Lokapitasari, Department of Electrical Engineering and Informatics, Universitas Negeri Malang, Indonesia; Department of Informatics Engineering, Universitas Muslim Indonesia, Makassar, Indonesia; Patmanthara, Syaad; Ashar, Muhammad, Department of Electrical Engineering and Informatics, Universitas Negeri Malang, Indonesia; Kurniawan, Fachrul, Department of Informatics Engineering, Universitas Islam Negeri Maulana Malik Ibrahim, Malang, Indonesia; Kurubacak, Gulsun, Department of Distance Education, Anadolu University, College of Open Education, Eskisehir 26470, Turkey

Abstract

This study introduces a clustering-driven adaptive User Experience (UX) architecture for e-learning systems, aligning machine learning segmentation with the 21st-century 4C educational framework (critical thinking, communication, collaboration, creativity). The objective is to dynamically personalize digital learning interactions through a microservices architecture responsive to users' UX profiles. A quantitative survey was conducted involving 50 active users of Shopee and Tokopedia, whose interaction feedback was mapped using the User Experience Questionnaire (UEQ). Three unsupervised clustering techniques—KMeans, Agglomerative, and DBSCAN—were compared. KMeans outperformed the others with a silhouette score of 0.157, compared to 0.146 for Agglomerative and −0.017 for DBSCAN, identifying three meaningful clusters representing high, medium, and low UX proficiency. A one-way ANOVA test confirmed statistically significant differences (p < 0.01) among the clusters in dimensions such as error clarity, support responsiveness, and user confidence. These UX profiles were then mapped to individualized microservices: Cluster 0 received autonomous content with minimal support, Cluster 1 was offered guided prompts, and Cluster 2 was provided with simplified interfaces and proactive assistance. Each cluster was aligned with specific 4C competencies to ensure pedagogical relevance. The proposed architecture, built with gRPC-based microservices, enabled asynchronous, low-latency personalization based on user cluster membership. The novelty of this research lies in its dual alignment—technological (microservices + machine learning) and educational (4C competency mapping)—to construct a scalable and responsive e-learning environment. The system design, although validated through simulation, demonstrates a practical foundation for future deployment in platforms like Moodle or OpenEdX. By linking behavioral UX clustering to pedagogical intervention strategies, this study offers a model for adaptive, data-informed instructional systems that are both scalable and learner-centered.

Related SDGs Targets

Full Author List

B, Poetri Lestari Lokapitasari; Patmanthara, Syaad, Department of Electrical Engineering and Informatics, Faculty of Engineering, State University of Malang, Malang, Indonesia; Ashar, Muhammad, Department of Informatics Engineering, Faculty of Science and Technology, Maulana Malik Ibrahim State Islamic University, Malang, Indonesia; Kurniawan, Fachrul, Department of Informatics Engineering, Faculty of Computer Science, Universitas Muslim Indonesia, Makassar, Indonesia.

Abstract

This paper evaluates the user experience of a microservices-based e-learning platform created for technopreneurship education using the User Experience Questionnaire (UEQ). Microservices present new chances to improve system performance, dependability, and learner involvement when educational systems choose modular and scalable designs. The study presents a benchmarking strategy by contrasting the newly created platform with two extensively utilized commercial platforms, Shopee and Tokopedia, which both use scale microservices. Fifty undergraduates participated in the study and evaluated six fundamental UX dimensions: attractiveness, perspicuity, efficiency, dependability, stimulus, and novelty. Quantitative research shows that the e-learning system works well in terms of pragmatic quality (clarity, efficiency, and reliability) and hedonic quality (stimulus and creativity). Comparatively, in perspicuity and efficiency, T-test comparisons reveal statistically significant benefits of the e-learning platform over Tokopedia; similarly, in stimulation and novelty, over Shopee. These findings imply that the microservices-based design improves emotional involvement and perceived innovation in the learning environment and supports functional performance. The study indicates that tools usually used in commercial environments allow one to assess user experience in education effectively. It also emphasizes how the design of learner-centred digital platforms can be guided by benchmarking against industry systems. The results provide helpful information for teachers trying to match educational technologies with user expectations moulded by actual digital experiences and for e-learning developers.

Related SDGs Targets

Full Author List

Purnawansyah, Department of Electrical Engineering and Informatics, Universitas Negeri Malang, Jl. Semarang, Malang, 65145, Indonesia; Department of Computer Science, Universitas Muslim Indonesia, Jl. Urip Sumoharjo, Makassar, 90231, Indonesia; Darwis, Herdianti; Azis, Huzain, Department of Computer Science, Universitas Muslim Indonesia, Jl. Urip Sumoharjo, Makassar, 90231, Indonesia; Wibawa, Aji Prasetya; Widiyaningtyas, Triyanna, Department of Electrical Engineering and Informatics, Universitas Negeri Malang, Jl. Semarang, Malang, 65145, Indonesia; Haviluddin, Department of Computer Science, Universitas Mulawarman Jl. Kuaro Gunung Kelua, Samarinda, 75119, Indonesia

Abstract

This study aims to assess the effectiveness of various algorithms in the realms of supervised and semi-supervised learning applied to three multiclass facial image datasets: JAFFE, Georgia tech, and Yale. The datasets were partitioned into proportions of 80:20, 75:25, and 50:50 for supervised learning, while semi-supervised learning was conducted with labelled and unlabeled data ratios of 20:80, 25:75, and 50:50. The evaluated algorithms include convolutional neural networks (CNNs), decision tree, long short-term memory, K-nearest neighbors (K-NNs), multilayer perceptron, and support vector classifier (SVC), each with varying parameters. Experimental outcomes reveal that the performance of models depends on the dataset partitioning strategies and the type of algorithms used. Specifically, linear and polynomial SVC consistently yield favorable results in supervised learning, particularly demonstrating efficacy on the Georgia tech dataset. Conversely, on the JAFFE and Yale dataset, linear SVC and K-NN emerge as optimal choices. The inclusion of semi-supervised learning enhances insights, particularly evident in the Georgia tech dataset, where the combination of labeled and unlabeled data significantly improves accuracy, especially when leveraging linear SVC algorithm. Although there are some instances of sub-optimal performance in certain algorithms like CNN on specific datasets, this research provides comprehensive insights into the effectiveness of various models in contexts of limited-label learning. The implications of these findings are crucial in advancing the development of adaptive and robust facial recognition systems, especially in navigating datasets characterized by diverse variations and complexities.

Related SDGs Targets

Full Author List

Rifaat, Muhammad Taufik; Faradibah, Amaliah, Program Studi Teknik Informatika, Fakultas Ilmu Komputer, Universitas Muslim Indonesia, Jl.Urip Sumoharjo km.05, Makassar dan 90231, Indonesia; Fauzi, Achmad Nuri, Program Studi Teknik Elektro, Fakultas Teknik, Universitas Negeri Malang, Malang dan 65145, Indonesia

Abstract

This study aims to analyze and identify vulnerabilities to Distributed Denial of Service (DDoS) and phishing attacks on FIKOM UMI’s Wi-Fi with the access point SSID “UMI Connect,” and to provide recommendations to FIKOM UMI. The method employed is Vulnerability Assessment using the Fluxion tool and a TP-Link wireless adapter. The findings reveal two types of vulnerabilities—packet injection and wireless hijacking—each with medium risk and medium confidence. These weaknesses reside at the SSID layer. Attackers can exploit them to disconnect clients from the network and subsequently perform phishing to obtain the access-point password of the targeted SSID. While some security components on the target access point are functioning properly, several areas still require improvement—specifically, unlimited packet rates per second passing through TCP/UDP data transmissions between users and the access point, which should be rate-limited.

Related SDGs Targets

Full Author List

Hayati; Lilis Nur, Department of Electrical Engineering and Informatics, Universitas Negeri Malang, Malang, Indonesia; Department of Computer Science, Universitas Muslim Indonesia, Makassar, Indonesia; Handayani, Anik Nur; Irianto, Wahyu Sakti Gunawan, Department of Electrical Engineering and Informatics, Universitas Negeri Malang, Malang, Indonesia; Asmara, Rosa Andrie, Information Technology Department, Politeknik Negeri Malang, Malang, Indonesia; Indra, Dolly, Department of Computer Science, Universitas Muslim Indonesia, Makassar, Indonesia; Damanhuri, Nor Salwa, Electrical Engineering Studies, Universiti Teknologi MARA (UiTM),Cawangan Pulau Pinang, Malaysia

Abstract

Sign language recognition plays a critical role in promoting inclusive education, particularly for deaf children in Indonesia. However, many existing systems struggle with real-time performance and sensitivity to lighting variations, limiting their applicability in real-world settings. This study addresses these issues by optimizing a BISINDO (Bahasa Isyarat Indonesia) alphabet recognition system using the SSD MobileNetV2 architecture, enhanced with gamma correction as a luminance normalization technique. The research contribution is the integration of gamma correction preprocessing with SSD MobileNetV2, tailored for BISINDO and implemented on a low-cost assistive robot platform. This approach aims to improve robustness under diverse lighting conditions while maintaining real-time capability without the use of specialized sensors or wearables. The proposed method involves data collection, image augmentation, gamma correction (γ = 1.2, 1.5, and 2.0), and training using the SSD MobileNetV2 FPNLite 320x320 model. The dataset consists of 1,820 original images expanded to 5,096 via augmentation, with 26 BISINDO alphabet classes. The system was evaluated under indoor and outdoor conditions. Experimental results showed significant improvements with gamma correction. Indoor accuracy increased from 94.47% to 97.33%, precision from 91.30% to 95.23%, and recall from 97.87% to 99.57%. Outdoor accuracy improved from 93.80% to 97.30%, with precision rising from 90.33% to 94.73%, and recall reaching 100%. In conclusion, the proposed system offers a reliable, real-time solution for BISINDO recognition in low-resource educational environments. Future work includes the recognition of two-handed gestures and integration with natural language processing for enhanced contextual understanding.

Related SDGs Targets

Full Author List

Satra,Ramdan, Faculty of Computer Science, Universitas Muslim Indonesia, Indonesia; Hadi, Mokh. Sholihul; Sujito, Department of Electrical and Informatics Engineering, Universitas Negeri Malang, Indonesia; Febryan,Faculty of Computer Science, Universitas Muslim Indonesia, Indonesia; Fattah, Muhammad Hattah, Faculty of Fisheries and Marine Sciences, Universitas Muslim Indonesia, Indonesia; Busaeri, Siti Rahbiah, Faculty of Agriculture, Universitas Muslim Indonesia, Indonesia

Abstract

Cultivation of tiger prawns stands as a crucial sector in Indonesia's fisheries industry, significantly contributing to the country's foreign exchange. However, challenges persist in the cultivation process, particularly concerning suboptimal harvest outcomes. A critical factor in tiger prawn cultivation is the water temperature within shrimp ponds, a parameter directly influencing shrimp growth. The recommended normal temperature range is 28-31°C. Deviations from this range can adversely impact the shrimp's metabolic system and appetite, resulting in stress and potential mortality. Temperature fluctuations can lead to severe issues such as hindered growth, reduced productivity, and increased shrimp mortality. Real-time monitoring of air temperature emerges as a pivotal element in ensuring the success of shrimp farming. This research aims to provide a practical solution for shrimp cultivation by presenting a system that enables farmers to adjust air temperature in ponds in real-time through a user-friendly website application. The ability to promptly respond to abnormal temperature fluctuations empowers farmers to optimize cultivation conditions, thereby reducing shrimp mortality rates. The research focuses on creating a water temperature monitoring system for tiger prawn ponds using cloud storage through the Firebase platform. By implementing real-time temperature monitoring, financial risks for shrimp farmers can be mitigated, preventing losses attributed to temperature-induced shrimp mortality. The research utilizes the DS18B20 temperature sensor and WeMos D1 R2 as the control center. The website displays air temperature measurements, showcasing a high accuracy of 99% with a minimal error of 1.2%. This underscores the system's effectiveness in measuring air temperature both above and below the pond. The incorporation of IoT technology for monitoring water quality in ponds offers a practical and innovative approach to tiger prawn cultivation, with the potential to enhance production outcomes in each harvest.

Related SDGs Targets

Full Author List

Purnawansyah, Department of Information Systems, Universitas Muslim Indonesia, Indonesia; Wibawa, Aji Prasetya; Widiyaningtyas, Triyanna Department of Electrical Engineering and Informatics, Universitas Negeri Malang, Indonesia; Haviluddin, Department of Informatics, Universitas Mulawarman, Indonesia; Raja, Roesman Ridwan; Darwis, Herdianti, Department of Informatics, Universitas Muslim Indonesia, Indonesia; Nafalski, Andrew, UniSA Education Futures, School of Engineering, University of South Australia, Australia

Abstract

Network congestion arises from factors like bandwidth misallocation and increased node density leading to issues such as reduced packet delivery ratios and energy efficiency, increased packet loss and delay, and diminished Quality of Service and Quality of Experience. This study highlights the potential of deep learning and ensemble learning for network congestion analysis, which has been less explored compared to packet-loss based, delay-based, hybrid-based, and machine learning approaches, offering opportunities for advancement through parameter tuning, data labeling, architecture simulation, and activation function experiments, despite challenges posed by the scarcity of labeled data due to the high costs, time, computational resources, and human effort required for labeling. In this paper, we investigate network congestion prediction using deep learning and observe the results individually, as well as analyze ensemble learning outcomes using majority voting, from data that we recorded and clustered using K-Means. We leverage deep learning models including BPNN, CNN, LSTM, and hybrid LSTM-CNN architectures on 12 scenarios formed out of the combination of level datasets, normalization techniques, and number of recommended clusters and the results reveal that ensemble methods, particularly those integrating LSTM and CNN models (LSTM-CNN), consistently outperform individual deep learning models, demonstrating higher accuracy and stability across diverse datasets. Besides that, it is preferably recommended to use the QoS level dataset and the combinations of 3 clusters due to the most consistent evaluation results across different configurations and normalization strategies. The ensemble learning evaluation results show consistently high performance across various metrics, with accuracy, Matthews Correlation Coefficient, and Cohen's Kappa values nearing 100%, indicates excellent predictive capability and agreement. Hamming Loss remains minimal highlighting the low misclassification rates. Notably, this study advances predictive modeling in network management, offering strategies to enhance network efficiency and reliability amidst escalating traffic demands for more sustainable network operations.

Related SDGs Targets

Full Author List

Ilmawan, Lutfi Budi, Department of Informatics Engineering, Universitas Muslim Indonesia, Makassar, Indonesia; Muladi; Prasetya, Didik Dwi, Department of Electrical and Informatics Engineering, Universitas Negeri Malang, Malang, Indonesia

Abstract

Negation plays an essential role in sentiment analysis within natural language processing (NLP). Its integration involves two key aspects: identifying the scope of negation and incorporating this information into the sentiment model. Before delving into scope detection, the specific negation cue must be identified, with explicit and implicit negation cues being the two main types. Various methodologies, such as rule-based, machine learning, and hybrid approaches, address the negation scope detection challenge. Strategies for leveraging negation information in sentiment models encompass heuristic polarity modification, feature space augmentation, end-to-end approach, and hierarchical multi-task learning. Notably, there is a need for more studies addressing implicit negation cue detection, even within the state-of-the-art bidirectional encoder representation for transformers (BERT) approach. Some studies have employed reinforcement learning and hybrid techniques to address the implicit negation problem. Further exploration, particularly through a hybrid and multi-task learning approach, is warranted to make potential contributions to the nuanced challenges of handling negation in sentiment analysis, especially in complex sentence structures.

Related SDGs Targets

Full Author List

Hasanuddin, Tasrif, Department of Computer Science, Universitas Muslim Indonesia, Makassar, Indonesia; Hadi, Mokh Sholihul; Sujito, Department of Electrical Engineering and Informatics, Universitas Negeri Malang, Malang, Indonesia; Rosnani, Department of Information System, STMIK Professional Makassar, Makassar, Indonesia

Abstract

In the context of rapidly advancing smart education systems, the effective management and optimization of modern classroom remain critical challenges. This research presents a novel methodology leveraging cloud and fog computing-based simulations, with a specific focus on the implementation of iFogSim. Empirical findings validate the efficacy of fog computing in monitoring classrooms, demonstrating significant improvements in performance metrics compared to traditional cloud computing architectures. Specifically, fog computing ensures remarkably low latency, with a mere 7 milliseconds, even with scalable integration across multiple classrooms. In contrast, cloud computing infrastructures exhibit considerably higher initial latencies, starting at 210 milliseconds, which further escalate with the increasing number of monitored classrooms. Furthermore, our analysis reveals substantially lower network overhead associated with fog computing, measuring at 5,231.8 kilobytes, in sharp contrast to the significantly higher network usage of 80,808 kilobytes observed with cloud computing solutions. These findings underscore the potential of fog computing as a promising solution for efficient and real-time management classroom in smart education environments.

Related SDGs Targets

Full Author List

Astuti, Wistiani, Univeristas Muslim Indonesia; Wibawa, Aji Prasetya, Universitas Negeri Malang; Haviluddin, Universitas Mulawarman; Darwis, Herdianti, Univeristas Muslim Indonesia

Abstract

One prevalent conversational system within the realm of natural language processing (NLP) is chatbots, designed to facilitate interactions between humans and machines. This study focuses on predicting frequently asked questions by students using the Duel Intent and Entity Transformer (DIET) Classifier method and assessing the performance of this method. The research involves employing 300 epochs with an 80% training data and 20% testing data split. In this study, the DIET Classifier adopts a multi-task transformer architecture to simultaneously handle classification and entity recognition tasks. Notably, it possesses the capability to integrate diverse word embeddings, such as BERT and GloVe, or pre-trained words from language models, and blend them with sparse words and n-gram character-level features in a plug-and-play manner. Throughout the training process of the DIET Classifier model, data loss and accuracy from both training and testing datasets are monitored at each epoch. The evaluation of the text classification model utilizes a confusion matrix. The accuracy results for testing the DIET Classifier method are presented through four case studies, each comprising 25 text messages and 15 corresponding chatbot responses. The obtained accuracy values range from 0.488 to 0.551, F1-Score values range from 0.427 to 0.463, and precision range from 0.417 to 0.457.

Related SDGs Targets

Full Author List

Manga, Abdul Rachman; Sulistya, Yudha Islami; Kasmira, Universitas Muslim Indonesia; Handayani, Ani Nur; Herwanto, Heru Wahyu; Asmara, Rosa Andrie, Universitas Negeri Malang

Abstract

Dalam Buku ini penulis dengan jelas dan ringkas menguraikan konsep dan teknik yang digunakan dalam pemrosesan citra dan video, sehingga pembaca dapat dengan mudah memahami topik yang kompleks. Buku ini juga dilengkapi dengan ilustrasi dan contoh kasus yang membantu pembaca memahami konsep yang dijelaskan. Selain itu, penulis juga membahas teknologi terbaru dalam bidang komputer visi, seperti deep learning dan augmented reality, sehingga pembaca akan terus memperbarui pengetahuan mereka tentang topik ini. Buku ini dapat dijadikan referensi penting bagi mahasiswa dan peneliti di bidang komputer visi, serta praktisi yang ingin memperluas pengetahuan mereka dalam bidang ini

Related SDGs Targets

Full Author List

Ilmawan, Lutfi Budi, Universitas Muslim Indonesia; Muladi; Prasetya, Didik Dwi, Universitas Negeri Malang

Abstract

One crucial issue affecting the performance of sentiment analysis tasks is negation. Handling negation involves determining the negation scope and negation cue. Feature space augmentation is one approach used to address negation. Feature space augmentation has been carried out by some previous researchers using a negation flag with the rule that the negation scope includes all words from the explicit negation cue to the punctuation mark. This study aimed to analyze the classifier's performance when negation handling was applied by adding a new rule for the negation scope. The new rule for determining the negation scope no longer took all words from the negation cue to the punctuation mark, but only considered or ignored words with certain POS tags. The results of this study showed that using the new rule for negation scope contributed to improving the performance of the classifier in sentiment analysis tasks. The proposed approach for negation handling was better than the previous approach in terms of accuracy, precision, recall, and f1-score.

Related SDGs Targets

Full Author List

Hayati, Lilis Nur; Indra, Dolly; Fahmi, Universitas Muslim Indonesia; Handayani, Anik Nur; Irianto, Wahyu Sakti Gunawan, Universitas Negeri Malang; Asmara, Rosa Andrie, Politeknik Negeri Malang

Abstract

Indonesian Sign Language (BISINDO) is one of the sign languages used in Indonesia. The process of classifying BISINDO can be done by utilizing advances in computer technology such as deep learning. The use of the BISINDO letter classification system with the application of the MobileNet V2 FPNLite SSD model using the TensorFlow object detection API. The purpose of this study is to classify BISINDO letters A-Z and measure the accuracy, precision, recall, and cross-validation performance of the model. The dataset used was 4054 images with a size of consisting of 26 letter classes, which were taken by researchers by applying several research scenarios and limitations. The steps carried out are: dividing the ratio of the simulation dataset 80:20, and applying cross-validation (k-fold = 5). In this study, a real time testing using 2 scenarios was conducted, namely testing with bright light conditions of 500 lux and dim light of 50 lux with an average processing time of 30 frames per second (fps). With a simulation data set ratio of 80:20, 5 iterations were performed, the first iteration yielded a precision result of 0.758 and a recall result of 0.790, and the second iteration yielded a precision result of 0.635 and a recall result of 0.77, then obtained an accuracy score of 0.712, the third iteration provides a recall score of 0.746, the fourth iteration obtains a precision score of 0.713 and a recall score of 0.751, the fifth iteration gives a precision score of 0.742 for a fit score case and the recall score is 0.773. So, the overall average precision score is 0.712 and the overall average recall score is 0.747, indicating that the model built performs very well

Related SDGs Targets

Full Author List

Purnawansyah, Purnawansyah; Darwis, Herdianti; Universitas Muslim Indonesia, Indonesia; Wibawa, Aji; Yulinda, Nurul; Universitas Negeri Malang, Indonesia

Abstract

AFDAL adalah sistem manajemen pembelajaran yang diterapkan di SMAIT Al-Fityan School Gowa Sulawesi Selatan selama pandemic COVID-19. Penting bagi pihak SMAIT Al-Fityan School Gowa untuk mengetahui bagaimana kepuasan pengguna terkait LMS AFDAL. Penelitian ini menggunakan model End User Computing Satisfaction (EUCS) untuk mengetahui kepuasan pengguna LMS AFDAL dengan mempertimbangkan lima variabel utama yaitu content, accuracy, format, ease of use dan timeliness. Kuisioner dalam bentuk skala likert disebarkan kepada 162 responden yaitu 142 peserta didik dan 20 guru SMAIT Al-Fityan School yang diambil secara acak dan bertingkat. Analisis deskriptif dilakukan sebagai tahap awal dan dilanjutkan dengan uji validitas dan realibilitas yang menyatakan bahwa data valid dan reliabel untuk analisis selanjutnya. Berdasarkan hasil dari uji F diperoleh bahwa variabel input berpengaruh signifikan secara simultan dengan memberikan sumbangsih 98 persen terhadap kepuasan pengguna. Adapun dari uji T diperoleh hasil bahwa setiap variabel memberikan pengaruh signifikan secara parsial terhadap kepuasan pengguna dengan urutan variabel yang paling signifikan yaitu content, timeliness, ease of use, format, dan accuracy yang secara deskriptif juga diperkuat bahwa 76 persen pengguna merasa puas dari segi content dan tingkat ketidakpuasan tertinggi terdapat pada variabel format. Dengan demikian, berdasarkan EUCS diperoleh bahwa peserta didik dan guru sebagai pengguna merasa puas dengan sistem dan pengembangan LMS AFDAL direkomendasikan pada sisi format LMS, yaitu fitur, warna, dan desain.

Related SDGs Targets