IEEE Open Journal of the Computer Society最新文献

{"title":"Large Pretrained Foundation Model for Key Performance Indicator Multivariate Time Series Anomaly Detection","authors":"Xu Wang;Qisheng Xu;Kele Xu;Ting Yu;Bo Ding;Dawei Feng;Yong Dou","doi":"10.1109/OJCS.2024.3521217","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3521217","url":null,"abstract":"In the realm of Key Performance Indicator (KPI) anomaly detection, deep learning has emerged as a pivotal technology. Yet, the development of effective deep learning models is hindered by several challenges: scarce and complex labeled data, noise interference from data handling, the necessity to capture temporal dependencies in time series KPI data, and the complexity of multivariate data analysis. Despite recent progress in large models that show potential for handling complex, multidimensional tasks, the lack of extensive, high-quality datasets presents a significant barrier for directly training these models in KPI anomaly detection. This scarcity limits the models' ability to learn and generalize effectively within this specific domain. To overcome this, we propose an innovative approach to adapt fully pretrained large models from other domains to KPI anomaly detection, thereby mitigating data constraints and enhancing detection precision. Our approach involves adapting large models to anomaly detection tasks using patch operations and fine-tuning techniques, which significantly enhances the model's temporal dependency capture capabilities. Furthermore, to address the multivariate challenge, we introduce a novel feature extraction method based on channel independence to optimize information processing across multidimensional features. Additionally, we leverage frequency domain information to design a feature enhancement method, further boosting the model's detection accuracy. By integrating these innovative techniques, we have developed a large-scale KPI anomaly detection model named ViTSD. Empirical evidence from experiments on five benchmark datasets and two additional datasets demonstrates ViTSD's superior performance, outperforming existing models across various evaluation metrics.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"176-187"},"PeriodicalIF":0.0,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10811835","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"What Time Is It? Finding Which Temporal Features is More Useful for Next Activity Prediction","authors":"Lerina Aversano;Martina Iammarino;Antonella Madau;Giuseppe Pirlo;Gianfranco Semeraro","doi":"10.1109/OJCS.2024.3519815","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3519815","url":null,"abstract":"Process Mining merges data science and process science that allows for the analysis of recorded process data by capturing activities within event-logs. It finds more and more applications for the optimization of the production and administrative processes of private companies and public administrations. This field consists of several areas: process discovery, compliance monitoring, process improvement, and predictive process monitoring. Considering predictive process monitoring, the subarea of next activity prediction helps to obtain a prediction about the next activity performed using control flow data, event data with no attributes other than the timestamp, activity label, and case identifier. A popular approach in this subarea is to use sub-sequences of events, called prefixes and extracted with a sliding window, to predict the next activity. In the literature, several features are added to increase performance. Specifically, this article addresses the problem of predicting the next activity in predictive process monitoring, focusing on the usefulness of temporal features. While past research has explored a variety of features to improve prediction accuracy, the contribution of temporal information remains unclear. In this article it is proposed a comparative analysis of temporal features, such as differences in timestamp, time of day, and day of week, extracted for each event in a prefix. Using both k-fold cross-validation for robust benchmarking and a 75/25 split to simulate real scenarios in which new process events are predicted based on past data, it is shown that timestamp differences within the same prefix consistently outperform other temporal features. Our results are further validated by Shapley's value analysis, highlighting the importance of timestamp differences in improving the accuracy of next activity prediction.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"261-271"},"PeriodicalIF":0.0,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10810467","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143107125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Energy Use and Demand Prediction Using Time-Series Deep Learning Forecasting Techniques: Application for a University Campus","authors":"Bivin Pradeep;Parag Kulkarni;Farman Ullah;Abderrahmane Lakas","doi":"10.1109/OJCS.2024.3520198","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3520198","url":null,"abstract":"A growing global impetus has emerged to enhance the sustainability of energy systems and practices. The two popular levers to achieve this goal include increasing the proportion of clean energy in the energy mix and enhancing energy efficiency. The former involves reducing reliance on fossil fuel-based energy sources and increasing the adoption of renewable energy. The latter involves understanding factors that impact the current energy footprint and improving the efficiencies of the process. University campuses comprise many buildings, and it is well-known that buildings have a sizeable energy footprint. Therefore, it is beneficial to understand their energy consumption and identify ways in which this could be further optimised. Furthermore, catering to the energy demand requires appropriate provisioning with significant costs associated with energy procurement on-demand. To address this, it is vital to predict demand in advance accurately. In this article, we elaborate on these two aspects, i.e., analysis of energy consumption and demand forecasting using deep learning-based time series techniques such as Long short-term memory (LSTM), Bi-directional Long short-term memory (BiLSTM), Gated recurrent unit (GRU), and Bidirectional Gated recurrent units (BiGRU). We analyse the different parameter optimisers and history window lengths to select a better hyper-parameter set for accurate energy use and demand prediction. Findings from this study show that the prediction follows the actual demand curve with a minimum RMSE of 65.354 MWh and 65.936 MWh for window sizes of four and six for validation (testing), respectively. The window size six performs better for most time-series algorithms and hyperparameter combinations.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"189-198"},"PeriodicalIF":0.0,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10807248","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IEEE Open Journal of the Computer Society Publication Information","authors":"","doi":"10.1109/OJCS.2023.3338872","DOIUrl":"https://doi.org/10.1109/OJCS.2023.3338872","url":null,"abstract":"","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"5 ","pages":"C2-C2"},"PeriodicalIF":0.0,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10806812","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142859022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IEEE Open Journal of the Computer Society Information for Authors","authors":"","doi":"10.1109/OJCS.2023.3338889","DOIUrl":"https://doi.org/10.1109/OJCS.2023.3338889","url":null,"abstract":"","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"5 ","pages":"C3-C3"},"PeriodicalIF":0.0,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10806739","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142859020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reducing Data Volume in News Topic Classification: Deep Learning Framework and Dataset","authors":"Luigi Serreli;Claudio Marche;Michele Nitti","doi":"10.1109/OJCS.2024.3519747","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3519747","url":null,"abstract":"Withthe rise of smart devices and technological advancements, accessing vast amounts of information has become easier than ever before. However, sorting and categorising such an overwhelming volume of content has become increasingly challenging. This article introduces a new framework for classifying news articles based on a Bidirectional LSTM (BiLSTM) network and an attention mechanism. The article also presents a new dataset of 60 000 news articles from various global sources. Furthermore, it proposes a methodology for reducing data volume by extracting key sentences using an algorithm resulting in inference times that are, on average, 50% shorter than the original document without compromising the system's accuracy. Experimental evaluations demonstrate that our framework outperforms existing methodologies in terms of accuracy. Our system's accuracy has been compared with various works using two popular datasets, AG News and BBC News, and has achieved excellent results of 99.7% and 94.55%, respectively.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"152-163"},"PeriodicalIF":0.0,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10806791","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving Accuracy and Calibration of Deep Image Classifiers With Agreement-Driven Dynamic Ensemble","authors":"Pedro Conde;Rui L. Lopes;Cristiano Premebida","doi":"10.1109/OJCS.2024.3519984","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3519984","url":null,"abstract":"One of the biggest challenges when considering the applicability of Deep Learning systems to real-world problems is the possibility of failure in \u0000<italic>critical</i>\u0000 situations. Possible strategies to tackle this problem are two-fold: (i) models need to be highly accurate, consequently reducing this risk of failure; (ii) facing the impossibility of completely eliminating the risk of error, the models should be able to inform the level of uncertainty at the prediction level. As such, state-of-the-art DL models should be \u0000<italic>accurate</i>\u0000 and also \u0000<italic>calibrated</i>\u0000, meaning that each prediction has to codify its confidence/uncertainty in a way that approximates the true likelihood of correctness. Nonetheless, relevant literature shows that improvements in \u0000<italic>accuracy</i>\u0000 and \u0000<italic>calibration</i>\u0000 are not usually related. This motivates the development of Agreement-Driven Dynamic Ensemble, a deep ensemble method that - by dynamically combining the advantages of two different ensemble strategies - is capable of achieving the highest possible accuracy values while obtaining also substantial improvements in calibration. The merits of the proposed algorithm are shown through a series of representative experiments, leveraging two different neural network architectures and three different datasets against multiple state-of-the-art baselines.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"164-175"},"PeriodicalIF":0.0,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10806808","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal Attention-Enhanced Feature Fusion-Based Weakly Supervised Anomaly Violence Detection","authors":"Jungpil Shin;Abu Saleh Musa Miah;Yuta Kaneko;Najmul Hassan;Hyoun-Sup Lee;Si-Woong Jang","doi":"10.1109/OJCS.2024.3517154","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3517154","url":null,"abstract":"Weakly supervised video anomaly detection (WS-VAD) plays a pivotal role in advancing intelligent surveillance systems within the field of computer vision. Despite significant research, WS-VAD continues to face challenges, particularly with unimodal approaches that struggle to extract meaningful features effectively. A few research studies have been done on the multimodal dataset fusion-based WS-VAD system, and their performance accuracy is unsatisfactory. In response, we propose a novel WS-VAD system leveraging multimodal datasets with an attention-enhanced feature fusion approach to address these challenges. Our system integrates three distinct data modalities—RGB video, optical flow, and audio signals—where each stream extracts complementary spatial and temporal features using an enhanced attention module to improve the detection accuracy and robustness. In the RGB video stream, we employ a multi-stage, attention-driven feature enhancement process to refine spatial and temporal features. This process begins with a ViT-based CLIP module, where the top k features are concatenated with I3D- and TCA-based spatiotemporal features. Temporal dependencies are then captured through uncertainty-regulated dual memory units (UR-DMUs), allowing the simultaneous learning of normal and anomalous patterns. The final stage selects the most relevant features, yielding a refined representation of RGB-based data. The second stream extracts enhanced spatiotemporal features from flow data using a deep learning and attention module. Lastly, the audio stream detects anomalies in sound patterns through an attention module integrated with the VGGish model, capturing auditory cues. The fusion of these three streams captures motion and audio signals often missed by visual analysis alone, significantly enhancing anomaly detection accuracy and robustness. Our multimodal fusion achieves an average precision (AP) of 88.28% on the XD-Violence dataset, outperforming prior models by nearly 2%, and attains AUCs of 98.71% on the ShanghaiTech dataset and 90.26% on the UCF-Crime dataset. These results underscore the effectiveness of our approach, consistently surpassing existing methods across three benchmark datasets and validating its robustness in WS-VAD applications.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"129-140"},"PeriodicalIF":0.0,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10798463","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Revolutionizing User Authentication Exploiting Explainable AI and CTGAN-Based Keystroke Dynamics","authors":"Hussien Abdel Raouf;Mostafa M. Fouda;Mohamed I. Ibrahem","doi":"10.1109/OJCS.2024.3513895","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3513895","url":null,"abstract":"Due to the reliability and efficiency of keystroke dynamics, enterprises have adopted it widely in multi-factor authentication systems, effectively strengthening user authentication and thereby boosting the security of online and offline services. The existing works that detect imposter users suffer from performance and robustness degradation. Therefore, this article introduces a novel methodology to enhance user authentication and identify imposter users who attempt to have unauthorized access. We first use quantile transformation (QT) to mitigate outliers in the user's typing behavior that affects the authentication process and then employ conditional tabular generative adversarial networks (CTGAN) for data augmentation to learn the users' typing patterns better. Next, five accurate transfer learning models (VGG19, EfficientNetB0, Resnet50, MobileNetV2, and DenseNet121) are utilized for extracting effective features within the typing patterns, so our methodology can detect imposter users accurately and hence make precise decisions to enhance the user authentication process. Finally, we ensure transparency and trust in our user authentication methodology by incorporating explainable artificial intelligence (XAI), utilizing local interpretable model-agnostic explanations (LIME). Extensive experiments using a publicly available keystroke dynamics benchmark dataset from Carnegie Mellon University (CMU) showcase superior security performance and robustness using the proposed methodology compared to the state-of-the-art approaches.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"97-108"},"PeriodicalIF":0.0,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10787121","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantum Long Short-Term Memory-Assisted Optimization for Efficient Vehicle Platooning in Connected and Autonomous Systems","authors":"Mahzabeen Emu;Taufiq Rahman;Salimur Choudhury;Kai Salomaa","doi":"10.1109/OJCS.2024.3513237","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3513237","url":null,"abstract":"Vehicle platooning, especially when dedicated to carrying goods, represents a forward-looking approach to optimizing logistics and freight transportation using autonomous vehicles. In this study, we propose to employ Quantum Long Short Term Memory (QLSTM) models to predict the vehicle dynamics of a leading vehicle of the platoon. This predictive capability allows the following vehicles to adjust their behaviours dynamically. By doing so, we aim to optimize control strategies and maintain string stability within vehicle platoons. This approach leverages the unique computational advantages of quantum computing, particularly in processing complex temporal data, potentially leading to more accurate and efficient dynamic systems in vehicular platoon infrastructure. The simulation results indicate that the QLSTM model is highly efficient by learning more information in fewer epochs compared to traditional Long Short Term Memory (LSTM) models. This efficiency contributes to minimizing control errors, enhancing the precision and reliability of vehicle dynamics in the context of autonomous vehicle platooning. This research not only enhances the predictability of autonomous vehicle platoons but also opens pathways for research into how quantum computing can be integrated into real-time dynamic systems analysis and control.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"119-128"},"PeriodicalIF":0.0,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10783047","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}