Delayed study completion among undergraduate students is a complex issue associated with the interplay of internal and external factors. This study aims to identify and examine the dimensions of risk factors associated with delayed study completion among Information Systems students using Principal Component Analysis (PCA) with Varimax rotation. Primary data were collected through a structured questionnaire administered to 299 undergraduate students of the Information Systems Study Program, semesters 3 to 8, at UNPAM Viktor Campus, covering 17 operational indicators. The analysis reduced the 17 indicators into 4 major risk factor dimensions, explaining 50.15% of the total variance: (1) Mobilization & Work Factor (14.02%), (2) Lecturer Mentorship Factor (14.28%), (3) Academic Competence Factor (13.07%), and (4) Assistance & Integrity Factor (8.78%). Factor 4 (Assistance & Integrity) was characterized by indicators related to dependence on external resources, including the use of third-party/joki services (0.717), peer assistance (0.598), and AI tools (0.592). Factor loading evaluation also identified two weak indicators (trap items) with loadings below 0.40: P1 (Employment Status; 0.363) and P4 (Primary Transportation Mode; 0.194). These findings highlight the importance of hybrid thesis mentoring, assignment load management, and academic integrity oversight to support timely study completion.
AI shopping assistants increasingly employ agent-based retrieval, combining lexical search, structured filtering, and LLM-mediated selection. However, effective retrieval often requires knowledge beyond textual matching. This exploratory single-case study of an Indonesian grocery e-commerce assistant triangulates 279 observations, 52 failure traces, 74 practitioner-reported defects, a schema audit, and four practitioner interviews. The analysis identifies six retrieval-critical knowledge dimensions and reveals that externalization fails at two distinct layers. At the product data-model layer, essential fields (allergens, dietary constraints, age suitability) were absent and persisted despite architectural changes. At the retrieval-schema layer, existing knowledge failed to reach candidates: structured filters appeared in only 29% of calls, and correctly invoked filters often returned empty sets from non-empty pools. Addressing these layer-specific failures, the study proposes a structured knowledge framework based on the knowledge management process cycle, positioning GraphRAG as a future direction.
Hotel booking cancellations are a major challenge in revenue management because they may cause operational inefficiencies and financial losses. This study develops a cancellation prediction model using CatBoost based on real-world Property Management System (PMS) data from a budget hotel in Central Java. The dataset covers 67 months, from October 2020 to April 2026. After preprocessing and data cleaning, 74,826 independent reservation records were obtained from 80,110 raw records. To address the extreme class imbalance, with a cancellation ratio of 1.56%, this study applied cost-sensitive learning through the scale_pos_weight parameter, which was set based on the class ratio without synthetic oversampling. SHAP was used to improve model interpretability. The proposed CatBoost model achieved an F1-score of 72.04%, precision of 87.20% for the cancellation class, and an AUC-ROC of 0.86, outperforming the baseline models. SHAP analysis indicates that lead time, deposit type, and arrival month were the main features contributing to cancellation predictions.
Ganoderma disease is one of the most destructive diseases affecting oil palm plants, causing basal stem rot, reduced productivity, plant mortality, and financial losses. This study applies Gamma Correction and CNN-Based Enhancement to improve the quality of oil palm images for Ganoderma disease identification. Gamma Correction improves image illumination and intensity, while CNN-Based Enhancement enhances structural details through a deep learning approach. The model achieved a test accuracy of 0.7714 and a test loss of 0.4165. The Healthy, Infected, and Initial Infection classes achieved F1-scores of 0.8571, 0.7500, and 0.7200, respectively. The results indicate that image transformation techniques can support Ganoderma disease identification in oil palm plants. The proposed enhancement process, which combines intensity correction with CNN-based enhancement, provides a potential approach for improving image quality and supporting the development of automated detection systems that are more accurate, adaptive, and suitable for field deployment.
The increasing administrative workload of teachers makes manual preparation of assessment questions time-consuming and may lead to the reuse of questions from previous years. This study examines the application of the transformer-based Generative Pre-trained Transformer 2 (GPT-2) model for automatic question-and-answer generation in elementary school Natural and Social Sciences (IPAS). The model was fine-tuned using 239 Indonesian context-question-answer triples, with 90% used for training and 10% for testing. Fine-tuning was conducted using four dataset sizes: 50, 100, 150, and 239 samples, to examine the relationship between training data volume and generation quality. Model performance was evaluated by examining parameter changes between the pre-trained and fine-tuned models and using the ROUGE metric to measure textual similarity between generated and reference questions and answers. The 239-sample dataset produced the most coherent and contextually appropriate questions, with ROUGE-1, ROUGE-2, and ROUGE-L scores of 1.0 for questions and 0.41, 0.24, and 0.36 for answers. These findings suggest that GPT-2 fine-tuning can support automatic question-generation tools when sufficient training data are available.
Item-loan administration in one subdivision still relies on physical handover forms and non-centralized records, making loan status and history difficult to trace. This study developed and evaluated an item-loan information system based on Google Apps Script. The study applied the Waterfall model, covering requirements analysis, design, implementation, testing, and maintenance. Evaluation involved six actual users through total sampling, comprising three officers and three administrators. Functional suitability was assessed using User Acceptance Testing (UAT), while usability was measured using the System Usability Scale (SUS). The UAT score reached 90.56%, with 88.89% for officers and 92.22% for administrators. The mean SUS score was 74.58, categorized as acceptable and good, although three respondents scored below the reference value of 68. Implementation reduced physical-document searches, improved record completeness and loan traceability, and centralized data. The system met functional needs but still requires improvements in initial guidance, activity notifications, stock checks, and handover reporting. The results are limited to six users in one subdivision.
This study analyzes sentiment in InDrive user reviews from the Google Play Store using IndoBERT, Genetic Algorithm (GA), and K-Nearest Neighbor (KNN). A total of 2,000 reviews were assigned to three sentiment classes: 1,695 negative, 235 positive, and 70 neutral reviews. The pretrained indobenchmark/indobert-base-p1 model was used as a feature extractor by taking the [CLS] representation to produce 768-dimensional embeddings. The dataset was divided using a stratified 80:20 split into 1,600 training and 400 testing samples. The optimal K value was determined through stratified five-fold cross-validation on the training data. GA was applied only to the training set using a population of 30 individuals, 25 generations, a crossover rate of 0.8, a mutation rate of 0.005, and a feature penalty of 0.002. GA selected 250 features, reducing the dimensionality by 67.45%. IndoBERT + KNN correctly classified 365 of 400 test samples, achieving 91.25% accuracy (95% CI: 88.07–93.64%) and a macro F1-score of 66.88%. IndoBERT + GA + KNN correctly classified 362 samples, achieving 90.50% accuracy (95% CI: 87.23–93.00%) and a macro F1-score of 62.71%. Both models exceeded the 84.75% majority-class baseline. However, only three and two of the 14 neutral samples were correctly classified, respectively. GA substantially reduced feature dimensionality but did not improve predictive performance, indicating a trade-off between representation compactness and minority-class classification performance.
Abstract Federated learning is a technology that is used to protect data privacy in machine learning. Nonetheless, in federated learning, updating the global model requires the use of gradient descent algorithm, which involves multiple rounds of interaction between entities to complete the iterative updates, inevitably incurring massive computational and communication overhead. In 2020, Wang et al. first proposed a non-interactive federated regression scheme, which effectively improves the training efficiency of regression models while protecting the privacy of local training data. However, like most current federated regressions, it involves a third authority (TA) to generate keys for each entity, which poses a significant privacy risk and results in considerable communication overhead. From the view of security and practicality, this paper first proposes a multi-party homomorphic encryption algorithm named MPaillier. Furthermore, we have designed PNFR, a privacy-preserving federated learning scheme for regressions training built on the MPaillier algorithm. The participating entities of PNFR are the data owners and a cloud server, eliminating the need for a TA, thus enhancing the practicality and efficiency of the scheme. Experimental results demonstrate that our scheme is $\sim 10^{3}$ times faster than interactive federated regressions PrivFL and about 80% faster than non-interactive federated regressions VANE.
BKB Paud Ceria is an early childhood education institution that has traditionally disseminated school information through manual channels, requiring prospective students’ parents to visit the school. This study aims to develop a web-based company profile using WordPress as a medium for information and promotion. The system was developed using the Waterfall method over four months (May–August 2026), with system design represented through use case, activity, and class diagrams. Functional testing used Black Box Testing with fourteen scenarios, while user acceptance was evaluated using a ten-item Likert-scale questionnaire covering Usability, Reliability, and Usefulness. The questionnaire was distributed through Google Forms to 27 respondents selected using purposive sampling. The results show that all fourteen test scenarios were valid (100%), while the User Acceptance Test obtained a score of 1,234 out of 1,350, equivalent to 91.4%, which falls into the Very Good category. The results indicate that the website was well accepted as a medium for providing school information and supporting communication with parents through its integrated WhatsApp feature.
The development of Internet of Things (IoT) technology supports the implementation of automated student attendance systems to address limitations in attendance recording, data recapitulation, and real-time monitoring. This study aims to implement a Radio Frequency Identification (RFID)-based student attendance system integrated with IoT. The Prototype method was used, consisting of requirement analysis, system design, implementation, and testing. The system utilizes an RFID Reader RC522, NodeMCU ESP8266, HTTP Request communication, PHP API, and MySQL database. RFID data is transmitted through a Wi-Fi network and displayed on a web-based dashboard. Testing with 10 trials resulted in a 100% success rate for UID reading, data transmission, student validation, attendance data storage, and dashboard visualization. The average response time from card detection to data display on the dashboard was 1.82 seconds. These results indicate that the system can support real-time IoT-based student attendance monitoring.
Hospitals are essential healthcare institutions, making an efficient drug logistics system highly important. This study aimed to identify, analyze, and minimize activities that generated waste or did not provide added value in the pharmacy warehouse of RS. XYZ. Value Stream Mapping was employed to map the actual operational flow and produce a Current Value Stream Map, while Process Activity Mapping was used to classify activities into Value-Added, Non-Value-Added, and Necessary Non-Value-Added categories. Direct observation identified two dominant types of waste, namely Defect and Delay/Waiting, whose root causes were determined through Root Cause Analysis using the 5 Why method and Fishbone Diagram. Several improvement proposals were then developed, including routine Standard Operating Procedure training and additional staff, and illustrated in a Future Value Stream Map representing the improved process flow. Process Cycle Efficiency increased from 2.2% in the Current Value Stream Map to 57.5% in the Future Value Stream Map, an improvement of 55.3%, indicating that the implementation of Value Stream Mapping and Root Cause Analysis effectively reduced waste and improved the efficiency of the drug logistics system in the pharmacy warehouse.
Abstract Transportation revitalization index (TRI) forecasting is crucial for monitoring post-pandemic urban recovery and supporting adaptive traffic management. Existing methods mainly use graph-based spatiotemporal models to encode pairwise intercity relations and directly fuse epidemic observations with TRI features. However, TRI recovery under pandemic shocks often involves group-level intercity co-movements, while epidemic variables contribute unevenly to forecasting, limiting the modeling of heterogeneous higher-order dependencies and selective auxiliary effects. To address these issues, we propose PGSTHFM, a prototype-guided spatiotemporal hypergraph fusion model for regional multi-city TRI forecasting. Specifically, PGSTHFM employs a prototype-guided relation-decoupled hypergraph convolution module to encode hyperedge semantics and disentangle heterogeneous higher-order dependencies into multiple latent relation channels. We further introduce a two-stage epidemic-aware data fusion module that summarizes epidemic signals conditioned on TRI representations and then refines TRI features through epidemic-guided node-wise interactions. Finally, a residual gated temporal convolution module is employed to capture both short-term fluctuations and long-range temporal dynamics. Experiments on a real-world TRI dataset covering 29 Chinese cities demonstrate that PGSTHFM consistently outperforms representative baselines across multiple forecasting horizons and evaluation metrics. Compared with the strongest hypergraph baseline, PGSTHFM reduces the average MAE, RMSE, and MAPE by 7.69%, 8.43%, and 11.95%, respectively.
Abstract Due to too much ambiguity and lexical overlap in today’ social media texts, cyberbullying detection has been difficult. To detect cyberbullying contents and address gaps, a hybrid decoding-enhanced bidirectional encoder representations from transformers (BERT) with disentangled attention-bidirectional gated recurrent unit (DeBERTa-BiGRU)-Attention model (explainable context-aware cyberbullying BERT-based hybrid model) is proposed for multiclass classification, which outperformed baseline approaches across different metrics. DeBERTa model is used to model content and positional embeddings and enable fine-grained contextual representation; it utilizes disentangled attention with improved relative positional encoding. BiGRU is utilized resulting embeddings from DeBERTa, for sequential dependency and capturing bidirectional token relations. A token-level attention layer is used on top of these models for prioritizing both enhancing interpretability and predicting performance. The sequential integration of all three techniques together complements recurrent modeling with the transformer model, yielding a +4.2% F1-score over standalone DeBERTa. In this study, explainability evaluation demonstrates a high alignment between attention weights and gradient-based importance scores at the token level to preserve faithfulness. An efficient and comprehensible framework for fine-grained multi-class cyberbullying detection is provided by combining DeBERTa with BiGRU and an Attention layer, as demonstrated by experiments.
Abstract Recent advances in artificial neural networks (ANNs) have greatly enhanced the accuracy of WiFi-based indoor localization. However, their high computational demand and energy consumption severely limit practical deployment in mobile and embedded environments. To overcome these limitations, we introduce SNNLoc, an intelligent, hierarchical localization framework built upon deep spiking neural networks (SNNs). Unlike traditional ANNs, SNNLoc adopts a biologically inspired, event-driven computation model in which neurons fire only when activation thresholds are reached, thereby drastically reducing unnecessary operations and improving energy efficiency. The proposed system integrates two learning stages: a building and floor recognition module that offers coarse-level spatial classification, followed by a position estimation module that delivers fine-grained localization using hierarchical reasoning. Both components are trained using received signal strength indicator data and are jointly optimized to balance precision and resource efficiency. Additionally, a dedicated hardware simulator is employed to evaluate and compare energy usage across architectures. Extensive experiments on two benchmark datasets validate the effectiveness of our method, demonstrating comparable or superior localization performance while achieving over 90% reduction in energy consumption. This research contributes to the development of neuromorphic, energy-aware intelligent systems for real-world ubiquitous computing scenarios.
Achieving accurate air quality predictions depends on a variety of factors, including meteorological conditions, the spatial distribution of pollution sources, and the geographic environment of the target area. This complexity poses challenges in capturing the intricate spatiotemporal dependencies inherent in air quality data. To address this issue, this work proposes a spatiotemporal graph network called GA$<^>{2}$Transformer, as a novel Transformer-based encoder-decoder architecture, to capture fine-grained spatiotemporal dependencies of air quality data. The proposed GA$<^>{2}$Transformer integrates a multilevel discrete wavelet decomposition module for extracting trend and periodicity clues at multiple levels from air quality data, and a graph-assisted attention module for modeling graph-structured spatiotemporal dependencies of air quality data. Extensive experiments on the real-world collected Beijing dataset show the validity of the proposed GA$<^>{2}$Transformer in air quality prediction tasks, outperforming other used methods.
Abstract This editorial commemorates Prof. Sir Charles Antony Richard Hoare FRS FREng (1934–2026), one of the defining figures of modern computer science. It reflects on his enduring contributions to algorithms, programming languages, formal reasoning, and concurrency, with particular attention to his 1962 paper on quicksort in The Computer Journal. It also notes the journal’s intention to mark his legacy further through a dedicated collection.
Multimodal sentiment analysis (MSA has gained attention for its capacity to overcome the limitations of unimodal approaches by integrating multiple modalities. We propose a hidden state-based fusion model with a gating mechanism for efficient multimodal feature integration. The proposed model achieves strong performance on the CMU-Multimodal Opinionlevel Sentiment Intensity(CMU-MOSI), CMU Multimodal Opinion Sentiment and Emotion Intensity(CMU-MOSEI), and Chinese Multimodal Sentiment Analysis(CH-SIMS) datasets while maintaining favorable parameter efficiency. By operating on hidden states and using an extensible gating design, the framework supports additional modalities with controlled computational cost. Experimental results demonstrate its effectiveness in improving prediction performance, generalization, and resource efficiency. These findings highlight the value of optimized fusion architectures for MSA.
Deterministic wallets (DW) and stealth addresses (SA) mechanisms significantly bolster user privacy and security in cryptocurrency transactions, thus were widely adopted. This benefits from their fundamental key derivation mechanism, which enables the generation of numerous derived secret keys from a single master key. To capture and enhance the functionality, security and privacy of DW and SA, the notion of a key-insulated and privacy-preserving signature scheme with publicly derived public keys (PDPKS) was introduced. Regarding privacy, PDPKS guarantees that neither the derived verification keys nor their corresponding signatures leak any information that could be traced back to the master public key from which they were derived. However, this type of privacy can be broken easily once an adversary compromises the master secret key. This means that once the master secret key is leaked, all of the user's historical transactions can be traced back. This scenario starkly contrasts with the strong privacy achievable through cash transactions. Once cash leaves a physical wallet, it is essentially forgotten. The current owner of the physical wallet cannot trace the evolution of the balance, including the number of transactions, their timing, the parties involved, and the amounts exchanged. In this paper, we propose the notion of forward-secure PDPKS, ensuring that even if the current master secret key is compromised, the privacy of historical transactions remains protected. We formalize this notion, propose a concrete construction and prove its security within the defined frameworks. Furthermore, we implement the construction, and the results show its efficiency.
Protocol reverse engineering can be applied to various security applications, including fuzzing, malware analysis, and intrusion detection. It aims to acquire an unknown protocol's format and semantics, where format extraction is the primary task. Currently, there are already methods such as multiple sequence comparison, statistical analysis, and deep learning to extract field formats from network traffic. However, they mainly locate key fields and learn boundary information through heuristic rules or comparative analysis, and they have limitations in processing large datasets and generalization inference. This paper proposes EBPFI, a novel framework that integrates deep learning with self-supervised boundary learning to enhance field boundary detection. This method stacks multiple network traffic to form an image, designs a field boundary guidance module, and adds self-supervised boundary learning to the loss function, realizing the recognition of field boundaries for fixed-format protocols. We evaluate the proposed approach on 10 widely used protocols. The experimental results demonstrate that EBPFI achieves superior performance in protocol format inference, consistently outperforming all compared methods in terms of F1-score and inference efficiency.
The rapid growth of distributed data has intensified the problem of "data silos," motivating federated learning (FL) as a privacy-preserving paradigm for collaborative model training. Decentralized FL (DFL) further eliminates reliance on a central server, improving scalability and robustness. However, existing DFL schemes still face serious challenges in security and efficiency. Many privacy-preserving solutions rely on costly homomorphic encryption, assume semi-honest adversaries, or incur high communication overhead without effectively identifying malicious participants. In this paper, we propose PRA-DFL, a privacy-preserving ring-based aggregation framework for DFL that achieves strong security guarantees with low overhead. PRA-DFL organizes participants into a ring topology, where each node and its two neighbors form a three-party computation system based on replicated secret sharing. This structure enables secure model aggregation while maintaining constant per-node communication complexity, independent of network size. Moreover, PRA-DFL is resilient to both semi-honest and malicious adversaries. By incorporating the SPDZ-style secret sharing, the framework supports malicious node identification in the reconstruction phase. We evaluate PRA-DFL on four datasets. Experimental results show that PRA-DFL achieves accuracy comparable to that of existing centralized and decentralized FL approaches, while incurring low computational and communication overhead, making it suitable for resource-constrained decentralized learning environments.
