PeerJ Computer Science最新文献

{"title":"A hybrid path planning algorithm combining A<i>*</i> and improved ant colony optimization with dynamic window approach for enhancing energy efficiency in warehouse environments.","authors":"Mingyu Wu, Eileen Lee Ming Su, Che Fai Yeong, Bowen Dong, William Holderbaum, Chenguang Yang","doi":"10.7717/peerj-cs.2629","DOIUrl":"10.7717/peerj-cs.2629","url":null,"abstract":"<p><p>This research presents a novel hybrid path planning algorithm combining A*, ant colony optimization (ACO), and the dynamic window approach (DWA) to enhance energy efficiency in warehouse environments. The proposed algorithm leverages the heuristic capabilities of A*, the optimization strengths of ACO, and the dynamic adaptability of DWA. Experimental results demonstrate that the IACO+A*+DWA approach consistently outperforms other hybrid methods across various metrics. In complex warehouse scenarios, the IACO+A*+DWA algorithm achieved an average energy consumption of 89.8 J, which is 13.3% lower than ACO+A*+DWA, 6.6% lower than GA+A*+DWA, and 25.8% lower than PSO+A*+DWA. The algorithm produced a path length of 95.94 m with 43 turns, compared to 97.36 m with 46 turns for ACO+A*+DWA, 104.43 m with 50 turns for GA+A*+DWA, and 97.84 m with 56 turns for PSO+A*+DWA. Time to goal was 197.93 s, 1.5% faster than GA+A*+DWA. Statistical analysis using ANOVA confirmed the significant differences between the algorithms in terms of energy consumption, path length, number of turns, and time taken, demonstrating the superior performance of IACO+A*+DWA. These results indicate that the IACO+A*+DWA algorithm minimizes energy consumption and produces shorter and more efficient paths, making it highly suitable for real-time applications in dynamic and complex warehouse environments. Future work will focus on further optimizing the algorithm and integrating machine learning techniques for enhanced adaptability and performance.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"10 ","pages":"e2629"},"PeriodicalIF":3.5,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11784801/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143080832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel trace-based sampling method for conformance checking.","authors":"Heidy M Marin-Castro, Miguel Morales-Sandoval, José Luis González-Compean, Julio Hernandez","doi":"10.7717/peerj-cs.2601","DOIUrl":"10.7717/peerj-cs.2601","url":null,"abstract":"<p><p>It is crucial for organizations to ensure that their business processes are executed accurately and comply with internal policies and requirements. Process mining is a discipline of data science that exploits business process execution data to analyze and improve business processes. It provides a data-driven approach to understanding how processes actually work in practice. Conformance checking is one of the three most relevant process mining tasks. It consists of determining the degree of correspondence or deviation between the expected (or modeled) behavior of a process <i>vs</i> the real one observed and revealed from the historical events recorded in an event log during the execution of each instance of the process. Under a big data scenario, traditional conformance checking methods struggle to analyzing the instances or traces in large event logs, increasing the associated computational cost. In this article, we study and address the conformance-checking task supported by a traces selection approach that uses representative sample data of the event log and thus reduces the processing time and computational cost without losing confidence in the obtained conformance value. As main contributions, we present a novel conformance checking method that (i) takes into account the data dispersion that exists in the event log data using a statistic measure, (ii) determines the size of the representative sample of the event log for the conformance checking task, and (iii) establishes selection criteria of traces based on the dispersion level. The method was validated and evaluated using fitness, precision, generalization, and processing time metrics by experiments on three actual event logs in the health domain and two synthetic event logs. The experimental evaluation and results revealed the effectiveness of our method in coping with the problem of conformance between a process model and its corresponding large event log.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"10 ","pages":"e2601"},"PeriodicalIF":3.5,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11784717/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143081638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DANNET: deep attention neural network for efficient ear identification in biometrics.","authors":"Deepthy Mary Alex, Kalpana Chowdary M, Hanan Abdullah Mengash, Venkata Dasu M, Natalia Kryvinska, Chinna Babu J, Ajmeera Kiran","doi":"10.7717/peerj-cs.2603","DOIUrl":"10.7717/peerj-cs.2603","url":null,"abstract":"<p><p>Biometric identification, particularly ear biometrics, has gained prominence amidst the global prevalence of mask-wearing, exacerbated by the COVID-19 outbreak. This shift has highlighted the need for reliable biometric systems that can function effectively even when facial features are partially obscured. Despite numerous proposed convolutional neural network (CNN) based deep learning techniques for ear detection, achieving the expected efficiency and accuracy remains a challenge. In this manuscript, we propose a sophisticated method for ear biometric identification, named the encoder-decoder deep learning ensemble technique incorporating attention blocks. This innovative approach leverages the strengths of encoder-decoder architectures and attention mechanisms to enhance the precision and reliability of ear detection and segmentation. Specifically, our method employs an ensemble of two YSegNets, which significantly improves the performance over a single YSegNet. The use of an ensemble method is crucial in ear biometrics due to the variability and complexity of ear shapes and the potential for partial occlusions. By combining the outputs of two YSegNets, our approach can capture a wider range of features and reduce the risk of false positives and negatives, leading to more robust and accurate segmentation results. Experimental validation of the proposed method was conducted using a combination of data from the EarVN1.0, AMI, and Human Face datasets. The results demonstrate the effectiveness of our approach, achieving a segmentation framework accuracy of 98.93%. This high level of accuracy underscores the potential of our method for practical applications in biometric identification. The proposed innovative method demonstrates significant potential for individual recognition, particularly in scenarios involving large gatherings. When complemented by an effective surveillance system, our method can contribute to improved security and identification processes in public spaces. This research not only advances the field of ear biometrics but also provides a viable solution for biometric identification in the context of mask-wearing and other facial obstructions.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"10 ","pages":"e2603"},"PeriodicalIF":3.5,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11784740/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143081938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Revolutionizing market surveillance: customer relationship management with machine learning.","authors":"Xiangting Shi, Yakang Zhang, Manning Yu, Lihao Zhang","doi":"10.7717/peerj-cs.2583","DOIUrl":"10.7717/peerj-cs.2583","url":null,"abstract":"<p><p>In the telecommunications industry, predicting customer churn is essential for retaining clients and sustaining profitability. Traditional CRM systems often fall short due to their static models, limiting responsiveness to evolving customer behaviors. To address these gaps, we developed the SmartSurveil CRM model, an ensemble-based system combining random forest, gradient boosting, and support vector machine to enhance churn prediction accuracy and adaptability. Using a comprehensive telecom dataset, our model achieved high performance metrics, including an accuracy of 0.89 and ROC-AUC of 0.91, surpassing baseline approaches. Integrated into a decision support system (DSS), SmartSurveil provides actionable insights to improve customer retention, enabling telecom companies to tailor strategies dynamically. Additionally, this model addresses ethical concerns, including data privacy and algorithmic transparency, ensuring a robust and responsible CRM approach. The SmartSurveil CRM model represents a substantial advancement in predictive accuracy and practical applicability within CRM systems.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"10 ","pages":"e2583"},"PeriodicalIF":3.5,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11784820/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143082070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep convolutional neural network architecture for facial emotion recognition.","authors":"Dayananda Pruthviraja, Ujjwal Mohan Kumar, Sunil Parameswaran, Vemulapalli Guna Chowdary, Varun Bharadwaj","doi":"10.7717/peerj-cs.2339","DOIUrl":"10.7717/peerj-cs.2339","url":null,"abstract":"<p><p>Facial emotion detection is crucial in affective computing, with applications in human-computer interaction, psychological research, and sentiment analysis. This study explores how deep convolutional neural networks (DCNNs) can enhance the accuracy and reliability of facial emotion detection by focusing on the extraction of detailed facial features and robust training techniques. Our proposed DCNN architecture uses its multi-layered design to automatically extract detailed facial features. By combining convolutional and pooling layers, the model effectively captures both subtle facial details and higher-level emotional patterns. Extensive testing on the benchmark Fer2013Plus dataset shows that our DCNN model outperforms traditional methods, achieving high accuracy in recognizing a variety of emotions. Additionally, we explore transfer learning techniques, showing that pre-trained DCNNs can effectively handle specific emotion recognition tasks even with limited labeled data.Our research focuses on improving the accuracy of emotion detection, demonstrating the model's capability to capture emotion-related facial cues through detailed feature extraction. Ultimately, this work advances facial emotion detection, with significant applications in various human-centric technological fields.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"10 ","pages":"e2339"},"PeriodicalIF":3.5,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11784769/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143081940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"YH-RTYO: an end-to-end object detection method for crop growth anomaly detection in UAV scenarios.","authors":"Yihang Li, WenZhong Yang, Zhifeng Lu, Houwang Shi","doi":"10.7717/peerj-cs.2477","DOIUrl":"10.7717/peerj-cs.2477","url":null,"abstract":"<p><strong>Background: </strong>Small object detection <i>via</i> unmanned Aerial vehicle (UAV) is crucial for smart agriculture, enhancing yield and efficiency.</p><p><strong>Methods: </strong>This study addresses the issue of missed detections in crowded environments by developing an efficient algorithm tailored for precise, real-time small object detection. The proposed Yield Health Robust Transformer-YOLO (YH-RTYO) model incorporates several key innovations to advance conventional convolutional models. The model features an efficient convolutional expansion module that captures additional feature information through extended branches while maintaining parameter efficiency by consolidating features into a single convolution during validation. It also includes a local feature pyramid module designed to suppress background interference during feature interaction. Furthermore, the loss function is optimized to accommodate various object scales in different scenes by adjusting the regression box size and incorporating angle factors. These enhancements collectively contribute to improved detection performance and address the limitations of traditional methods.</p><p><strong>Result: </strong>Compared to YOLOv8-L, the YH-RTYO model achieves superior performance in all key accuracy metrics, with a 13% reduction in the scale of model. Experimental results demonstrate that the YH-RTYO model outperforms others in key detection metrics. The model reduces the number of parameters by 13%, facilitating deployment while maintaining accuracy. On the OilPalmUAV dataset, it achieves a 3.97% improvement in average precision (AP). Additionally, the model shows strong generalization on the RFRB dataset, with AP₅₀ and AP values exceeding those of the YOLOv8 baseline by 3.8% and 2.7%, respectively.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"10 ","pages":"e2477"},"PeriodicalIF":3.5,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11784890/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143082169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel optimization method for hazardous materials vehicle routing with temperature-based time windows.","authors":"Lu Ding, Fangwei Zhang, Jun Ye, Fanyi Kong, Minhui Jiao","doi":"10.7717/peerj-cs.2586","DOIUrl":"10.7717/peerj-cs.2586","url":null,"abstract":"<p><p>As a concrete achievement of sharing economy, sharing intermediate bulk containers (IBCs) have emerged and developed in recent years. Meanwhile, high temperature is one of the essential factors in routing optimal problems for vehicles with hazardous material (hazmat). Therefore, to address the above issue, a variant of the hazmat vehicle routing problem of sharing IBCs is proposed. Correspondingly, a mixed non-linear integer programming model is refined considering temperature-based time windows. Specifically, the given problem is solved by using a novel adaptive large neighborhood search (ALNS) algorithm. The main innovation points are as follows. Firstly, temperature-based time windows are quantified and integrated into the proposed hazmat vehicle routing optimal model. Secondly, novel heuristic operators are introduced in the ALNS algorithm. Finally, 18 numerical examples for the Solomon set demonstrate that the proposed algorithm is suitable to solve this kind of hazmat vehicle routing optimal problem.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"10 ","pages":"e2586"},"PeriodicalIF":3.5,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11784799/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143081475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SA-FLIDS: secure and authenticated federated learning-based intelligent network intrusion detection system for smart healthcare.","authors":"Radjaa Bensaid, Nabila Labraoui, Ado Adamou Abba Ari, Hafida Saidi, Joel Herve Mboussam Emati, Leandros Maglaras","doi":"10.7717/peerj-cs.2414","DOIUrl":"10.7717/peerj-cs.2414","url":null,"abstract":"<p><p>Smart healthcare systems are gaining increased practicality and utility, driven by continuous advancements in artificial intelligence technologies, cloud and fog computing, and the Internet of Things (IoT). However, despite these transformative developments, challenges persist within IoT devices, encompassing computational constraints, storage limitations, and attack vulnerability. These attacks target sensitive health information, compromise data integrity, and pose obstacles to the overall resilience of the healthcare sector. To address these vulnerabilities, Network-based Intrusion Detection Systems (NIDSs) are crucial in fortifying smart healthcare networks and ensuring secure use of IoMT-based applications by mitigating security risks. Thus, this article proposes a novel Secure and Authenticated Federated Learning-based NIDS framework using Blockchain (SA-FLIDS) for fog-IoMT-enabled smart healthcare systems. Our research aims to improve data privacy and reduce communication costs. Furthermore, we also address weaknesses in decentralized learning systems, like Sybil and Model Poisoning attacks. We leverage the blockchain-based Self-Sovereign Identity (SSI) model to handle client authentication and secure communication. Additionally, we use the Trimmed Mean method to aggregate data. This helps reduce the effect of unusual or malicious inputs when creating the overall model. Our approach is evaluated on real IoT traffic datasets such as CICIoT2023 and EdgeIIoTset. It demonstrates exceptional robustness against adversarial attacks. These findings underscore the potential of our technique to improve the security of IoMT-based healthcare applications.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"10 ","pages":"e2414"},"PeriodicalIF":3.5,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11784809/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143082046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging deep learning for toxic comment detection in cursive languages.","authors":"Muhammad Shahid, Muhammad Umair, Muhammad Amjad Iqbal, Muhammad Rashid, Sheeraz Akram, Muhammad Zubair","doi":"10.7717/peerj-cs.2486","DOIUrl":"https://doi.org/10.7717/peerj-cs.2486","url":null,"abstract":"<p><p>Social media platforms enable individuals to publicly express opinions, support, and criticism. Influencers can launch campaigns to promote ideas. Most people can now share their views and feelings through visual or textual comments, which can range from appreciation to hate speech, potentially inciting societal violence and hatred. Detecting these noxious comments and thoughts is critical to protecting our communities from their negative social, psychological, and political impact. Although Urdu (a low-resource language) is one of the most popular Asian languages around the globe, a standard tool does not exist to detect toxic comments posted in this language. Tokenization and then categorizing cursive text is challenging due to its complex nature, especially when dealing with toxic comments, which are often ungrammatical and very brief. This study proposes a novel model to identify salient features in Urdu sentences. It uses transformers to identify and flag toxic comments using deep learning binary classification of the text. Statistically, the proposed fine-tuned model outperforms the existing ones by achieving a precision of 88.38%. Among the models evaluated, bidirectional encoder representations from transformers (BERT) demonstrated superior performance with an accuracy 85.45%, precision 85.71%, recall 85.45%, F1 score 85.41%, and a Cohen Kappa 70.83% on the full feature set. Conversely, GPT-2 was identified as the lowest-performing model. The outcomes of this research represent a noteworthy advancement in the broader endeavor to improve and optimize content moderation mechanisms across diverse languages and platforms.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"10 ","pages":"e2486"},"PeriodicalIF":3.5,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11784787/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143081452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal Alzheimer's disease classification through ensemble deep random vector functional link neural network.","authors":"Pablo A Henríquez, Nicolás Araya","doi":"10.7717/peerj-cs.2590","DOIUrl":"10.7717/peerj-cs.2590","url":null,"abstract":"<p><p>Alzheimer's disease (AD) is a condition with a complex pathogenesis, sometimes hereditary, characterized by the loss of neurons and synapses, along with the presence of senile plaques and neurofibrillary tangles. Early detection, particularly among individuals at high risk, is critical for effective treatment or prevention, yet remains challenging due to data variability and incompleteness. Most current research relies on single data modalities, potentially limiting comprehensive staging of AD. This study addresses this gap by integrating multimodal data-including clinical and genetic information-using deep learning (DL) models, with a specific focus on random vector functional link (RVFL) networks, to enhance early detection of AD and mild cognitive impairment (MCI). Our findings demonstrate that ensemble deep RVFL (edRVFL) models, when combined with effective data imputation techniques such as Winsorized-mean (Wmean), achieve superior performance in detecting early stages of AD. Notably, the edRVFL model achieved an accuracy of 98.8%, precision of 98.3%, recall of 98.4%, and F1-score of 98.2%, outperforming traditional machine learning models like support vector machines, random forests, and decision trees. This underscores the importance of integrating advanced imputation strategies and deep learning techniques in AD diagnosis.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"10 ","pages":"e2590"},"PeriodicalIF":3.5,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11784893/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143081493","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}