Publication Search

This study develops a computational-based system to identify individual potential through the analysis of signature patterns using Artificial Neural Networks (ANN) and the Backpropagation algorithm. The research aims to explore and examine the effectiveness of applying ANN in recognizing and identifying signature patterns that are assumed to be related to an individual’s potential. In the data processing stage, Principal Component Analysis (PCA) is employed as a dimensionality reduction and feature extraction technique to optimally obtain the main characteristics of signature images. The system performance evaluation is conducted using a total of 80 signature images, consisting of 60 training data and 20 testing data. This study analyzes two network architecture configurations, namely a model with one hidden layer and a model with two hidden layers. The experimental results show that both network configurations achieve the same accuracy level of 92.5%. These findings indicate that the use of Artificial Neural Networks with the Backpropagation algorithm is effective in producing high accuracy in the signature pattern recognition process. Furthermore, the developed system has broad potential applications in the field of personal identification, such as employee evaluation, selection systems, and other applications across various organizational and industrial sectors.

The integration of Digital Signal Processing (DSP) algorithms in low power microcontroller based embedded systems has emerged as a promising solution to optimize energy efficiency without compromising signal accuracy and performance. This study focuses on the design and optimization of DSP algorithms specifically for microcontrollers, aimed at achieving real-time, reliable monitoring for applications such as healthcare, environmental sensing, and IoT devices. The research highlights the system's ability to handle complex signal processing tasks while maintaining low power consumption, ensuring long-term, continuous operation in remote or battery-powered environments. The system employs various techniques, including advanced power management strategies such as dynamic voltage scaling (DVS) and adaptive voltage scaling (AVS), along with lightweight AI algorithms and model pruning, to minimize energy use. The results show significant reductions in power consumption compared to traditional systems, particularly during continuous monitoring tasks. Despite this, the optimized DSP algorithms maintain or even enhance signal accuracy, ensuring that critical monitoring data remains reliable. Furthermore, the system demonstrates robust performance and reliability over extended periods, making it suitable for long-term deployment in critical applications such as wearable medical devices and industrial sensors. This research provides a foundation for the development of future low power embedded systems, emphasizing the importance of DSP-aware optimization in achieving energy-efficient and high-performance monitoring. Future improvements may include advanced AI-driven power optimization techniques, enhanced scalability, and cross-domain interoperability, ensuring that these systems can be effectively deployed across diverse applications, from healthcare to environmental monitoring.

Human–Robot Interaction (HRI) systems increasingly rely on data-driven approaches to interpret multimodal sensory inputs and support natural interaction. However, purely neural-based HRI models often suffer from limited interpretability and insufficient context-aware decision-making, which can reduce user trust and adaptability in dynamic interaction scenarios. To address these limitations, this study proposes a hybrid neural–symbolic HRI framework that integrates multimodal neural perception with explicit symbolic reasoning for adaptive and interpretable robot behavior. The proposed system combines deep neural networks for processing visual, speech, and gesture inputs with a rule-based symbolic reasoning layer that models interaction context, user states, and behavioral constraints. A loosely coupled integration strategy enables neural outputs to be transformed into symbolic representations, allowing logical inference to guide action selection while preserving perceptual accuracy. The framework was evaluated through controlled HRI experiments comparing a neural-only baseline with the proposed hybrid configuration across multiple interaction scenarios. Experimental results demonstrate that the hybrid neural–symbolic system significantly improves interaction accuracy, contextual responsiveness, and user satisfaction, while achieving substantial gains in interpretability. These findings indicate that symbolic reasoning effectively complements neural perception by enhancing transparency and context-aware adaptation without compromising performance. The study concludes that hybrid neural–symbolic architectures provide a promising foundation for developing trustworthy, adaptive, and human-centered HRI systems.

The increasing adoption of collaborative robots in modern manufacturing environments requires reliable perception systems that can ensure both safety and operational efficiency during human–robot collaboration. This study proposes a CNN-based real-time computer vision system for object and human detection in shared robotic workspaces. The research focuses on developing and evaluating a single-stage deep learning detection model optimized for real-time performance while maintaining high detection accuracy. The proposed methodology includes dataset preparation, model training using transfer learning, real-time system implementation, and comprehensive performance evaluation. Experimental results demonstrate that the developed system achieves high detection accuracy, as reflected by strong precision, recall, and mean Average Precision (mAP) values, while maintaining low inference latency suitable for real-time operation. The system consistently operates above real-time frame-rate thresholds, ensuring timely perception updates required for safety-related decision-making in collaborative robotic environments. Graphical and quantitative analyses further confirm the stability of inference performance under dynamic interaction scenarios involving human movement and multiple objects. Compared with existing approaches, the proposed system provides a balanced trade-off between accuracy and computational efficiency, making it practical for deployment in safety-aware human–robot collaboration scenarios. Overall, the findings indicate that CNN-based real-time object detection systems can effectively support perception and situational awareness in collaborative robotics, contributing to safer and more efficient industrial automation.

This research explores the role of human algorithm interaction mechanisms in enhancing trust, reliability, and user confidence in Decision Support Systems (DSS). Traditional DSS models often focus solely on algorithmic accuracy and performance, neglecting crucial factors such as transparency and user engagement, which are essential for building trust. By incorporating explainable AI (XAI) techniques like SHAP and LIME, real-time feedback mechanisms, and user-friendly interfaces, the study develops structured interaction models that improve the interpretability of AI-driven decisions. The results show that transparent decision-making processes and interactive features significantly enhance user trust, making DSS more reliable and easier to adopt. Users interacting with systems that provide clear, understandable explanations of decisions, along with real-time updates on the system’s confidence, reported higher levels of decision-making confidence, especially in high-stakes scenarios. These improvements lead to greater user engagement and adoption of the system in various domains, including healthcare and finance. The study also highlights the importance of balancing interpretability with efficiency in user interface design to ensure both trust and usability. The findings contribute to the design of more user-centric DSS that prioritize trust, interpretability, and cognitive factors, providing a framework for the successful integration of intelligent decision support systems in complex decision-making environments. Future research should focus on refining interaction models and exploring the broader applicability of these systems in different sectors.

Concept drift, the phenomenon where the statistical properties of data streams change over time, poses a significant challenge in machine learning, particularly for long term data streams. Traditional machine learning models, including batch learning and non-adaptive approaches, struggle to detect and adapt to these changes, leading to degraded performance and inaccurate predictions. This study proposes an adaptive computational model designed to detect and respond to concept drift using incremental learning techniques and statistical drift detection mechanisms. The model integrates an Adaptive Drift Detector (ADD) and Incremental Learning System, enabling real-time adjustments to data distribution changes. The model is evaluated across synthetic and real-world datasets, demonstrating its superior ability to detect abrupt, gradual, and recurring drifts compared to traditional models. Experimental results indicate that the adaptive model maintains high prediction accuracy, minimizes false positive rates, and reduces detection delays. Furthermore, the model performs well in resource-constrained environments, making it suitable for real-time applications such as healthcare prediction, fault detection, and IoT systems. Despite its promising performance, the study identifies challenges related to computational complexity and the model’s performance with imbalanced datasets and noisy data. Future research should focus on optimizing the model’s scalability, computational efficiency, and adaptability to more complex data types to ensure broader applicability in dynamic environments. This work contributes to advancing the detection and adaptation of concept drift, offering a robust solution for dynamic and evolving data streams.

User experience (UX) evaluation plays a crucial role in understanding how users interact with digital platforms and in improving product design. Traditional UX evaluation methods, such as surveys and interaction logs, often rely on a single data source, which limits the depth of analysis. This study explores the integration of multimodal data processing techniques in UX research, aiming to enhance the accuracy and comprehensiveness of UX evaluations. By combining interaction logs, visual attention data, and physiological measurements, this approach provides a more holistic understanding of user behavior, emotional responses, and satisfaction. Interaction logs offer objective data on user actions, while eye-tracking and physiological data capture users' emotional states, providing richer insights into usability and user experience. This study highlights the effectiveness of multimodal integration in identifying patterns that traditional methods overlook, such as emotional responses to interface elements and real-time feedback from users. The findings reveal that multimodal data processing improves the precision of UX assessment by combining objective behaviors with subjective emotional responses, offering a more complete view of user interactions. The study also discusses the challenges of data synchronization and the potential ethical concerns related to the use of physiological data. The integration of these data sources shows great potential for enhancing the design process, allowing designers to make informed decisions based on comprehensive insights. Finally, this research underscores the future potential of multimodal analytics in UX research, suggesting further exploration of additional data modalities and real-time applications in various digital environments.

This research aims to develop a multiclass flower image classification system using the Convolutional Neural Network (CNN) algorithm with the EfficientNet architecture. The main problem addressed is the difficulty of manual identification of flower species that share high visual similarity. The research stages include collecting 17,299 flower images across 19 classes, performing data preprocessing such as image resizing, pixel normalization, and augmentation, followed by model training using the EfficientNet transfer learning approach. The model was trained for 10 epochs with an 80:20 training-validation data split. The evaluation results show that the model achieved a validation accuracy of 98.05% with a loss value of 0.0968, and an average precision, recall, and F1-score of 0.98. The trained model was then implemented into a web-based application built using the Next.js framework, enabling users to upload flower images and obtain real-time classification results via the Hugging Face API. The system successfully identified flower species with a confidence level of 99.87%. These findings demonstrate that combining a modern CNN architecture with transfer learning provides efficient and highly accurate flower classification performance, which can be effectively implemented for educational and digital conservation purposes.

User reviews on the Shopee e-commerce platform represent an important source of information for understanding consumer perceptions of products and services. Sentiment analysis is commonly applied to classify user opinions into positive, neutral, and negative sentiment categories based on textual data. This study aims to analyze the performance of the Long Short-Term Memory (LSTM) method in sentiment classification of Shopee user reviews. The dataset used in this study consists of Indonesian-language user reviews that have undergone preprocessing stages, including case folding, text cleaning, tokenization, and stopword removal. The LSTM model was trained using preprocessed text represented as word sequences. Model performance was evaluated using overall accuracy and class-wise classification results. The experimental results indicate that the LSTM method achieved an overall accuracy of 87.62%. In addition, the classification performance for the positive sentiment class reached 95.27%, the neutral class achieved 4.96%, and the negative class reached 74.26%. These results demonstrate that the LSTM method performs well in classifying sentiment in Shopee user reviews, particularly for positive sentiment. This study is expected to provide insights and references for the application of deep learning methods in sentiment analysis of Indonesian e-commerce review data.

The increasing complexity and scale of modern cybersecurity threats necessitate the development of advanced systems capable of efficiently detecting, analyzing, and mitigating incidents in real time. This paper proposes an automated framework for digital forensics and incident response that leverages big data analytics and real time network traffic profiling. The framework integrates cutting-edge technologies, including Apache Spark for real time data processing and Hadoop for scalable data storage, combined with machine learning models like LSTM and Autoencoders to detect anomalies and threats in network traffic. By automating the process of incident detection and response, this framework significantly reduces the time required to identify threats and improves the accuracy of forensic evidence correlation across heterogeneous network environments. The study highlights the advantages of using machine learning models and big data tools to address the limitations of traditional manual and semi-automated systems, which often struggle to keep pace with large-scale data generation. Testing results demonstrate that the proposed framework can handle large data volumes efficiently, providing real time, actionable insights with significantly reduced response times. Additionally, the framework improves forensic analysis by enabling the correlation of evidence from different devices and protocols, making it more effective than traditional methods in identifying the root cause of security incidents. However, challenges related to data heterogeneity, scalability, and system integration were encountered during testing. The proposed framework holds promise for significantly enhancing the efficiency and effectiveness of cybersecurity operations, with future work focusing on further integration of advanced AI techniques and machine learning models for dynamic and adaptive incident response.

This research explores the integration of Enterprise Architecture (EA) and Artificial Intelligence (AI) to optimize strategic decision-making in digital service-oriented organizations. These organizations often face challenges such as fragmented decision-making due to disconnected IT systems and limited data-driven insights. The objective of the study is to develop an integrated framework that combines EA and AI to enhance decision-making accuracy, operational efficiency, and strategic alignment. The study employs design science research methodology, involving the development of the framework, expert validation, and testing in simulated organizational scenarios. The findings reveal that the integrated framework improves decision-making by providing real-time, data-driven insights, predictive analytics, and better alignment with organizational goals. AI's role in analyzing large datasets and generating actionable insights allows decision-makers to anticipate future trends and make more informed decisions. The framework significantly outperforms traditional EA approaches, particularly in terms of predictive decision support and adaptive intelligence. The study concludes that the integration of EA and AI provides a robust solution for organizations looking to improve strategic decision-making, enhance operational efficiency, and stay competitive in dynamic business environments.

Explainable Artificial Intelligence (XAI) has become a critical area of research within artificial intelligence, focusing on improving the transparency and interpretability of machine learning (ML) models, often referred to as "black-box" models. The need for XAI techniques arises from the inherent complexity of ML models, which can make their decision-making processes difficult for users to understand. This study investigates various XAI techniques, including LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive exPlanations), to assess their impact on model interpretability without significantly compromising predictive performance. A comparative experimental design was used, applying these XAI methods to different ML models, including deep neural networks and ensemble methods, within large-scale enterprise data analytics systems. The results indicate that XAI methods significantly enhance model transparency and decision traceability, allowing users to understand the influence of individual features on predictions. While a slight reduction in predictive accuracy was observed, especially with simpler models, the trade-off between interpretability and performance was deemed acceptable, particularly in fields requiring transparency, such as healthcare, finance, and autonomous systems. The use of XAI in enterprise data systems has practical implications for fostering trust and enabling informed decision-making among stakeholders. Furthermore, the study discusses the challenges and limitations of applying XAI techniques, such as complexity, scalability, and model-specific limitations. Future research is suggested to focus on developing more scalable and efficient XAI methods, enhancing their applicability across various model types, and addressing the challenges of real-time applications. This will be crucial in ensuring the widespread adoption of XAI in critical domains, promoting the ethical use of AI while maintaining predictive accuracy.

The use of Information Systems and Information Technology (IS/IT) is a crucial factor in improving the efficiency and accuracy of retail sector operations. PT XYZ, a retail-level staple goods provider, has implemented IS/IT to support sales recording, inventory management, security, and operational reporting. This study aims to assess the effectiveness, efficiency, security, and compliance of the information system used. The audit was conducted through observation, interviews, document review, and system testing, referring to the COBIT framework and the ISO/IEC 27001 standard. The audit results indicated that the system supported core operational functions, but weaknesses remained, including insufficient system documentation, limited access controls, and suboptimal data security and backup mechanisms. Furthermore, reliance on manual procedures has the potential to lead to errors and slow down service delivery. Therefore, system improvements, strengthening security controls, developing standard operating procedures, and enhancing the competency of human resources and IT infrastructure are needed. This audit is expected to support improved service quality and secure, effective, and sustainable IT governance at PT XYZ.

The rapid proliferation of Internet of Things (IoT) devices across diverse industries has significantly increased the vulnerability of IoT edge networks to sophisticated cyber threats. Traditional intrusion detection systems (IDS), such as signature-based and anomaly-based approaches, are often insufficient in addressing the dynamic and evolving nature of these threats. This study proposes a hybrid intrusion detection system (IDS) framework that combines supervised machine learning (ML) techniques with deep reinforcement learning (DRL) to enhance detection performance in real-time, resource-constrained IoT environments. The proposed framework utilizes supervised learning for initial traffic classification and DRL for adaptive decision-making, enabling the system to continuously learn and optimize its detection policies based on new attack patterns. The hybrid approach significantly improves detection accuracy and reduces false positives when compared to conventional signature-based and single-model ML systems. In addition to improved detection capabilities, the framework's computational efficiency allows it to operate effectively within the constraints of IoT devices, ensuring that it is suitable for large-scale deployments. Benchmark evaluations using publicly available datasets, such as NSL-KDD, IoT-23, and BoT-IoT, show that the hybrid IDS framework outperforms traditional methods, providing a more robust and adaptive solution to cybersecurity challenges in IoT edge networks. The findings of this study suggest that combining machine learning with deep reinforcement learning offers a promising approach to secure IoT environments and address the limitations of existing IDS techniques. Future work will explore enhancing real-time adaptability, scalability, and the detection of zero-day attacks in evolving IoT ecosystems.

This study aims to develop an effective predictive model for identifying students at risk of academic dropout using the Decision Tree and Linear Regression algorithms. The data used are sourced from the public Kaggle dataset Students Dropout and Academic Success, which includes demographic, socioeconomic, and academic performance variables for each semester. The research method includes data preprocessing stages, such as data cleaning, label encoding for categorical variables, numeric feature normalization, and target class adjustment to focus on binary classification, namely Dropout and Graduate. The modeling process is carried out by comparing the performance of the two algorithms using evaluation metrics of accuracy, precision, and recall. The results show that the Decision Tree algorithm has superior performance compared to Linear Regression in mapping non-linear patterns in student data. Feature importance analysis revealed that the number of curricular units in the second semester and tuition payment status are the main predictors of dropout risk. These findings are expected to assist educational institutions in implementing early interventions to improve student academic success.  

This study investigates the levels of asprosin and irisin in patients with type 2 diabetes mellitus (T2DM) and diabetic nephropathy (DN), and evaluates their relationships with insulin resistance, glycemic control, and renal function. Additionally, it explores their diagnostic performance as potential non-invasive biomarkers for the early detection of DN using ROC curve analysis. A controlled prospective study was conducted involving 130 participants, categorized into healthy controls, T2DM patients, and T2DM with DN. Serum asprosin, irisin, and insulin levels were measured using ELISA, while biochemical and renal parameters such as fasting blood glucose, HbA1c, creatinine, urea, and eGFR were assessed using standard spectrophotometric techniques. ROC analysis was employed to assess the diagnostic accuracy of asprosin and irisin. Asprosin levels were significantly elevated, while irisin levels were markedly reduced in DN patients compared to T2DM and control groups (p < 0.001). Moreover, DN patients exhibited higher levels of fasting glucose, HbA1c, HOMA-IR, creatinine, and urea, with lower eGFR, indicating substantial renal dysfunction. ROC analysis revealed that asprosin had an AUC of 0.910 (95% CI: 0.839–0.981), with 90.0% sensitivity and 88.9% specificity at a cutoff value of 11.27 ng/mL. Irisin showed an AUC of 0.886 (95% CI: 0.812–0.960), with 95.0% sensitivity and 71.1% specificity at a 158.25 ng/mL cutoff. Asprosin and irisin are strongly associated with insulin resistance and renal impairment in patients with T2DM and DN. Their high diagnostic performance supports their utility as promising non-invasive biomarkers for the early detection and monitoring of diabetic nephropathy progression.

The implementation of the zoning-based admission policy (PPDB) in Semarang City continues to face challenges related to the accuracy of distance measurement and the transparency of information provided to the public. This study aims to examine the application of Geographic Information Systems (GIS) in defining zoning boundaries for public junior high schools in Semarang City and integrating the results into a web-based information platform. A quantitative descriptive approach was employed, incorporating spatial analysis through a 3-kilometer buffer radius using QGIS software. The results indicate that buffer analysis is effective in delineating priority domicile zones based on school coordinate data. These findings are integrated into a GIS-based website that presents visual information on school locations, enrollment capacity, and final score calculation mechanisms in accordance with current regulations. The proposed system contributes to improving information transparency, enabling the public to better understand admission opportunities while supporting government decision-making in promoting equitable access to education. For future development, the use of road network analysis is recommended to obtain more realistic distance estimations.

This study aims to describe the implementation of multisensory strategies in improving the early reading skills and comprehension of dyslexic children in grade 2 of Bugel 2 Public Elementary School. The subject of the study was a student with dyslexia characteristics who had shown difficulties in phonological aspects, letter recognition, reading syllables, and reading comprehension. The method used was direct observation using an early reading test instrument, a comprehension test, and a learning behavior observation sheet. The results showed that the implementation of multisensory strategies (Visual-Auditory-Kinesthetic-Tactile) through letter tracing activities, reading with the help of sounds, arranging letter cards, and reading together exercises was able to improve reading accuracy, strengthen letter-sound relationships, and foster students' self-confidence. Thus, multisensory strategies were proven effective in helping dyslexic children master early reading skills and comprehend simple texts. This study provides an important contribution to the development of more inclusive and effective teaching methods, especially for students with dyslexia, who require a more holistic and comprehensive approach to improve their literacy skills. As a suggestion, the implementation of this strategy can be expanded by involving more students and considering variations in the types of texts and teaching materials used.

This study compares Grammarly and Paraphraser.io in supporting students’ academic writing and rewriting skills based on Flower and Hayes’s (1981) cognitive process theory, which includes the stages of planning, translating, and reviewing. Using a descriptive qualitative method supported by quantitative data, the research involved 32 English Education students who had used both tools in academic writing. Data were collected through questionnaires and analyzed descriptively to identify students’ perceptions of grammatical accuracy, rewriting ability, feedback quality, and overall writing improvement. The results of this study indicate that 54.4% of students use Grammarly and 45.6% use Paraphraser.io, showing that Grammarly is the slightly more dominant and trusted tool for improving grammatical accuracy and clarity, while Paraphraser.io functions as a complementary platform for paraphrasing and generating new sentence structures; together, both tools contribute effectively though through distinct roles to enhancing students’ academic writing performance. The comparative analysis revealed that Grammarly was most effective in enhancing analytical skills during the planning and reviewing stages, improving grammar, coherence, and clarity. In contrast, Paraphraser.io was most beneficial for generative skills in the translating stage, directly enhancing originality and sentence variation. Most respondents rated their writing improvement highly, confirming the positive impact of both tools on academic performance. In conclusion, the findings confirm that Grammarly and Paraphraser.io serve distinct, yet complementary roles: the former ensures linguistic precision, while the latter supports structural creativity, ultimately helping students produce highly accurate and original academic texts.

Detection and identification of plant diseases is critical to the success and efficiency of agricultural production. Plant disease outbreaks are becoming more frequent throughout the world, and the presence of these diseases in cultivated plants has a significant impact on productivity. Therefore, researchers are focusing on developing effective and reliable plant disease detection methods. Thus, farmers can take advantage of early detection of this disease to minimize future losses. This article discusses machine learning approaches as well as decision trees, K-nearest neighbors, naive Bayes, support vector machines (SVM), and random forests for detecting coffee leaf diseases using leaf images. The above-mentioned classifications were researched and compared to determine the most suitable plant disease prediction model with the highest accuracy. Compared with other classification algorithms, the SVM algorithm achieves the highest accuracy of 99.75%. All the models trained above will be used by farmers to quickly identify and classify new diseases in images as a prevention strategy. As a preventive measure, farmers can detect and classify new diseases in images early.