2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)最新文献

{"title":"Improving the Accuracy of Animal Species Classification in Camera Trap Images Using Transfer Learning","authors":"Moussa Mahamat Boukar, A. A. Mahamat, Oumar Hassan Djibrine, Usman Bello Abubakar","doi":"10.1109/ACDSA59508.2024.10467777","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467777","url":null,"abstract":"Understanding biodiversity, monitoring endangered species, and estimating the possible effect of climate change on particular regions all rely on animal species identification. Closed-circuit television (CCTV) cameras, which can collect huge volumes of video data, are an excellent environmental monitoring tool. However, manually evaluating these massive datasets is time-consuming, difficult, and expensive, emphasizing the need for automated ecological analysis.Deep learning models have transformed computer vision, handling problems such as object and species detection. Their cutting-edge performance qualifies them for this application. The purpose of this work was to create and test machine learning models for distinguishing diverse animal species using camera trap images. On VGG19, GoogLeNet (InceptionV3), ResNet50, and DenseNet121, we used transfer learning. The best multi-classification accuracy was attained by GoogLeNet (87%), followed by ResNet50 (83%), DenseNet (81%), and VGG19 (53%). This evidence suggests that transfer learning outperforms training models from scratch for this task.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"349 ","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating the Inclusiveness of Artificial Intelligence Software in Enhancing Project Management Efficiency – A review and examples of quantitative measurement methods","authors":"Vasileios Alevizos, Ilias Georgousis, Akebu Simasiku, Antonis Messinis, Sotiria Karypidou, Dimitra Malliarou","doi":"10.1109/ACDSA59508.2024.10467463","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467463","url":null,"abstract":"The escalating integration of Artificial Intelligence (AI) in various domains, especially Project Management (PM), has brought to light the imperative need for inclusivity in AI systems. This paper investigates the role of AI software in augmenting both the inclusiveness and efficiency within the realm of PM. The research pivots around specific criteria that define and measure the inclusiveness of AI in PM, highlighting how AI, when developed with inclusiveness in mind, can significantly enhance project outcomes. However, there are inherent challenges in achieving this inclusiveness, primarily due to biases embedded in AI learning databases and the design and development processes of AI systems. The study offers a comprehensive examination of AI's potential to revolutionize PM by enabling managers to concentrate more on people-centric aspects of their work. This is achieved through AI’s ability to perform tasks such as data collection, reporting, and predictive analysis more consistently and efficiently than human counterparts. However, the incorporation of AI in PM extends beyond mere efficiency; it represents a paradigm shift in the epistemology of PM, calling for a deeper understanding of AI's role and impact on society. Despite these advantages, the adoption of AI comes with significant challenges, particularly in terms of bias and inclusiveness. Biased AI learning databases, which use shared and reusable datasets, often perpetuate initially discriminatory algorithms. Moreover, unconscious biases and stereotypes of AI designers, developers, and trainers can inadvertently influence the behavior of the AI systems they create. This necessitates a paradigmatic shift in how AI systems are developed and governed to ensure they do not replicate or exacerbate existing social inequalities. The research proposes a methodological approach involving the development of criteria for inclusion and exclusion, alongside data extraction, to evaluate the inclusiveness and efficiency of AI software in enhancing PM. This approach is crucial for understanding and addressing the challenges and limitations of AI in the context of PM. By focusing on inclusiveness, the study underscores the importance of a synergy between technological advancement and ethical consideration, demanding a comprehensive understanding and regulation to mitigate risks and maximize benefits. In conclusion, this paper presents a detailed exploration of AI’s role in PM highlighting both its potential benefits and the ethical challenges it poses. The findings and recommendations of this study contribute to the growing discourse on the need for inclusive AI systems in PM, offering insights for AI developers and Project Managers (PMs) alike.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"1392 ","pages":"1-11"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ACDSA 2024 Committees","authors":"","doi":"10.1109/acdsa59508.2024.10467545","DOIUrl":"https://doi.org/10.1109/acdsa59508.2024.10467545","url":null,"abstract":"","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"419 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent Model For A Mini Hydropower Plant And Its Adaptive Control","authors":"Roxana-Maria Motorga, M. Abrudean, V. Muresan, V. Sita, Cristian Bondici, Adrian Popescu","doi":"10.1109/ACDSA59508.2024.10467668","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467668","url":null,"abstract":"This paper proposes a comparison between three control strategies for the power control of the mini hydropower plan. To develop and implement this controllers, the mathematical modelling of the electrical energy production is performed, by applying identification methods on based on the experiments performed during the operation of the power plant. To improve the operation process, the variation of the real power in time depending on the water flow on the turbine blades is learnt using means of artificial intelligence. The learning procedure is performed by training neural networks. The approached control structures consists of a cascade structure, with a PD controller in the internal loop and a fractional-order PID controller in its external loop. The achieved performances obtained by the process are improved furthermore by computing an adaptive system based on the strategy of converting the process between the continuous to discrete time and then back to the continuous time considering the variation in time of the sampling time. This conversion is implemented using trained neural networks, too.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"230 9","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528795","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Building Trust in AI deployments in Healthcare","authors":"Juan Cadavid, Daniela Piana, Antonin Abhervé","doi":"10.1109/ACDSA59508.2024.10467853","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467853","url":null,"abstract":"Artificial Intelligence (AI) has seamlessly integrated into the fabric of modern organizations, revolutionizing business processes, decision-making, and interactions with society. However, instilling trust in AI systems remains a formidable challenge, particularly in vital sectors such as healthcare. We introduce the \"Trust Octagon\" - a framework comprising eight key dimensions categorized into three critical domains. This framework serves as a guide, tailored for organizations and policymakers, to fortify trust in AI. We apply the Trust Octagon within the landscape of healthcare. Our approach yields a set of meticulously crafted checklists, strategically designed to nurture trust in AI implementations. To support the practical application of this framework, we unveil a robust toolkit integrated with the Modelio toolset for enterprise architecture and system design. This approach ensures that building trust in AI systems is not only an aspiration but a tangible reality, propelling the responsible and ethical integration of AI into critical industries like healthcare.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"288 2","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Afrikaans Literary Genre Recognition using Embeddings and Pre-Trained Multilingual Language Models","authors":"E. Kotzé, Burgert Senekal","doi":"10.1109/ACDSA59508.2024.10467838","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467838","url":null,"abstract":"Automatic literary genre recognition is pivotal in various domains, including digital libraries, literary studies, and computational linguistics. Efficiently categorizing texts into genres, such as poetry or prose, facilitates the organization and retrieval of literary works, enhancing accessibility for readers, researchers, and academics. Recognizing genre-specific patterns, themes, and stylistic elements enables in-depth analysis and comprehension of literary texts. This study focuses on fine-tuning several state-of-the-art multilingual pre-trained language models, including mBERT, DistilmBERT, and XLM-RoBERTa, to distinguish between Afrikaans poetry and prose. A baseline Support Vector Machine (SVM) classifier and a self-attention transformer model were also trained for comparison.Results demonstrated that the SVM model with text-embeddings-ada-002 embeddings achieved the highest test F1-score of 0.936. The XLM-RoBERTa model exhibited the best performance during validation with an F1-score of 0.924, while the DistilmBERT model surpassed all others, including the SVM during testing, achieving the highest F1-score of 0.942. Notably, the self-attention model demonstrated comparable F1-scores for training (0.923) and testing (0.929), establishing itself as the second-best performing genre classifier.This study contributes to advancing automatic literary genre recognition in Afrikaans by exploring the capabilities of state-of-the-art multilingual language models and traditional classifiers, providing insights into their comparative performance and potential applications in real-world scenarios.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"44 ","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning Based Collaborative Prediction of SSD Failures in the Cloud","authors":"Yuze Jiang, Ruiming Lu, Shuyue Zhou, Qiao Li","doi":"10.1109/ACDSA59508.2024.10467231","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467231","url":null,"abstract":"SSDs (Solid-State Drives) have become integral components in modern data centers. Under such massive deployment, ensuring their reliability, longevity, and optimal performance is crucial. Despite SSD technology and architecture advancements, accurately predicting their failures, particularly with imperfect real-world data, remains a pertinent research challenge. Dataset imbalances have led to suboptimal prediction accuracy in baseline models. This study introduces to incorporate model-wise class balancing, aiming to refine the data processing for improved accuracy in machine learning models for SSD failure detection. When tested on Alibaba’s dataset of 700k NVMe SSDs, this method yielded higher failure prediction accuracy, with the average recall increasing from 51% to 63% and precision scores rising from 59% to 78%. This improvement in recall and precision demonstrates the method’s potential to advance the field of SSD failure prediction.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"89 6","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-agent reinforcement learning for shared resource scheduling conflict resolution","authors":"Malarvizhi Sankaranarayanasamy, Ravigopal Vennelakanti","doi":"10.1109/ACDSA59508.2024.10467469","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467469","url":null,"abstract":"Transportation operations especially in railroad domain are time critical. Scheduling conflicts driven by disruptions and delays in any one zone significantly affect the overall network operations. In this work applicability of multi agent reinforcement learning approach to resolve scheduling conflicts and improve the railroad network operations was explored. Based on a custom 2D grid environment here we attempt to learn ideal coordinated agent actions based on simulated schedule conflict by introducing stochastic delays in train arrival. We were able to achieve converges for multi-agent simulation based setup with 30% malfunction rate. The focus of work is to presents the problem setup in mobility domain and simulation design for the multi-agent reinforcement learning. With respect to real world application this approach is promising as it reduces the requirement of a highly customized solution by experts and if a high-performance simulation-based reinforcement learning solution is reached this would provide an opportunity to build generalized interoperable control techniques for transit systems across the world.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"24 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Statistical Uncertainty Quantification for Robustness Stability Analysis using Appropriate Sampling in Power Systems","authors":"Suravi Thakur, N. Senroy","doi":"10.1109/ACDSA59508.2024.10467613","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467613","url":null,"abstract":"A statistical framework is presented to perform uncertainty quantification (UQ) of electric power system subjected to randomness. A statistical relationship between just the input source of randomness and output measurements needs to be built up by sampling the data at an appropriate rate. Appropriate sampling is achieved by concentrating on the dynamics caused by the uncertainty alone on the desired output measurements. The correlation amongst the multiple randomness in the power system has been considered using Gaussian Copulas. The effectiveness of performing statistical characterization of randomness using Gaussian mixture models (GMM), Statistical distance, Quantile-Quantile plots and Regression analysis has been examined by performing Robustness stability analysis of an electrical power system. Such statistical UQ can be used to test the performance and robust stability of the power system under different range of uncertainties, thereby putting a permissible limit on the range and magnitude of randomness in the power system. The above framework is tested on IEEE-9 Bus and IEEE-68 Bus systems.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"290 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards AI-enabled Cloud Continuum for IIoT: Challenges and Opportunities","authors":"Elisa Rojas, David Carrascal, Diego Lopez-Pajares, Nicolas Manso, J. M. Arco","doi":"10.1109/ACDSA59508.2024.10467357","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467357","url":null,"abstract":"The last decade has demonstrated an exponential growth in connected devices, particularly at the network edge, and this marked tendency still foresees a increase of the number of connected Internet-of-Things (IoT) devices. Accordingly, the network intelligence is moving from the core and cloud to the edge, establishing a cloud continuum. In this regard, Artificial Intelligence (AI) promotes that evolution and, at the same time, benefits from networking as well. Since Industrial IoT (IIoT) is one of the main verticals of this AI-enabled cloud continuum, in this article we explore the most recent advances in this area, the current status of standards, practical implementations, industry requirements, and, based on that analysis, we list a set of open challenges and opportunities. Our intention is to provide a summarized overview together with specific departing points for researchers in the field.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"340 ","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}