Artificial Intelligence and Applications最新文献

{"title":"Towards Unsupervised Learning Driven Intelligence for Prediction of Prostate Cancer","authors":"Ejay Esugbe","doi":"10.47852/bonviewaia42022210","DOIUrl":"https://doi.org/10.47852/bonviewaia42022210","url":null,"abstract":"Prostate cancer is a widespread and global disease which affects adult males – it is said that key causes of the cancer include age, family history and ethnicity. In this study, the Kaggle prostate cancer dataset, comprising of data of 100 patients with a mixture that both had cancer and did not have cancer, was used alongside machine learning prediction models for the design of unsupervised and automated intelligent systems for the prediction of prostate cancer. Two intelligent systems were designed and underpinned by unsupervised learning algorithms, namely, fuzzy c-means and agglomerative hierarchical clustering, where the various intelligent systems were able to make a prostate cancer prediction with accuracies of over 80% for the various classification metrics, alongside being able to predict an associated stage of the prostate cancer. Both designed intelligent systems offer a complimentary alternative to each other, and their relative merits are discussed in the paper. ry alternative to each other, and their relative merits are discussed in the paper.","PeriodicalId":518162,"journal":{"name":"Artificial Intelligence and Applications","volume":"53 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141807531","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":"A Novel Ensemble Deep Learning Based Polyp Detection Using Colonoscopy Dataset","authors":"Sai Rakshana K., Antony Dennis Ananth, Gowri L.","doi":"10.47852/bonviewaia42022549","DOIUrl":"https://doi.org/10.47852/bonviewaia42022549","url":null,"abstract":"This work addresses the critical task of polyp detection and classification using the SUN colonoscopy video database, which consists of still images annotated with bounding boxes. These images categorize frames into polyp and non-polyp and encompass six distinct classes of polyps: Hyperplastic polyp, Sessile serrated lesion, Low-grade adenoma, Traditional serrated adenoma, High-grade adenoma, and Invasive carcinoma. The approach involves a two-stage classification process. Initially, MobileNetV2 is employed to distinguish between polyp and non-polyp frames. Subsequently, ResNet50 and GoogLeNet are utilized to classify the identified polyps into the six predefined categories. Data augmentation techniques are implemented to address the inherent imbalance in class distribution within the dataset, enhancing model performance and generalizability. The results highlight the effectiveness of GoogLeNet, which achieved an impressive accuracy of 98%, significantly outperforming ResNet50's accuracy of 76.16%. This substantial improvement underscores the potential of GoogLeNet in enhancing the accuracy of polyp classification. The significance of this work lies in its contribution to advancing automated polyp detection and cancer stage classification, crucial for early diagnosis and treatment. These findings provide a foundation for further research and development in this domain, with the potential to improve clinical outcomes through more accurate and timely identification of colorectal polyps.","PeriodicalId":518162,"journal":{"name":"Artificial Intelligence and Applications","volume":"15 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141648143","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 Predicting the Quality of Red Wine Using Novel Machine Learning Methods for Classification, Data Visualization and Analysis","authors":"Jovial Niyogisubizo, Jean de Dieu Ninteretse, Eric Nziyumva, Marc Nshimiyimana, Evariste Murwanashyaka, Erneste Habiyakare","doi":"10.47852/bonviewaia42021999","DOIUrl":"https://doi.org/10.47852/bonviewaia42021999","url":null,"abstract":"here is a growing concern among consumers and the wine industry regarding the quality of wine. Traditionally, wine experts determined its quality through tasting, which was time-consuming. Therefore, there is a need to predict wine quality based on specific key features to streamline these tasks. Technological developments like machine learning (ML) approaches have replaced human assessments with computational methods. However, some of these methods have faced criticism due to their low accuracy and lack of interpretability for humans. In this paper, a stacking ensemble method is introduced and demonstrates superior predictive performance when compared to other classification techniques like Logistic Regression (LR), Decision Trees (DT), Gradient Boosting (GB), Adaptive Boosting (AdaBoost), and Random Forest (RF). This evaluation is based on classification metrics such as accuracy, precision, recall, and F1-Score, all under the same conditions. Additionally, outlier detection algorithms were employed to identify exceptional or subpar wines, though their results did not match the accuracy of classification approaches. Lastly, a feature analysis study was conducted to assess the significance of each feature in the model's performance.","PeriodicalId":518162,"journal":{"name":"Artificial Intelligence and Applications","volume":"34 34","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141117767","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":"Soliton Solutions of Some Ocean Waves Supported by Physics Informed Neural Network Method","authors":"Ismail Onder, Abdulkadir Sahiner, A. Seçer, Mustafa Bayram","doi":"10.47852/bonviewaia42022277","DOIUrl":"https://doi.org/10.47852/bonviewaia42022277","url":null,"abstract":"In this study, we aim to obtain numerical results of the modified Benjamin-Bona-Mahony equation, Ostrovsky-Benjamin-Bona-Mahony equation and Mikhailov-Novikov-Wang equation via the physics-informed neural networks (PINN) method. The equations are modeled for shallow and long water waves, as well as fundamental and phenomenonal models in ocean engineering. According to the implementation, we obtained the PINN solutions of kink, bright, multisoliton (two-soliton) and mixed dark-bright soliton solutions. According to the inference from the obtained results, we achieved good results in some cases compared to other approximate solution methods in the literature. However, it was also observed that the best possible results could not be obtained in cases where the soliton type was intricate and layered. While the results were obtained, the number of hidden layers and the number of neural networks in the layers also varied. These results are shown in tables. Since it is known that the aforementioned models are not solved by the PINN method, we anticipate that the study will lead to other studies in the field of ocean engineering.","PeriodicalId":518162,"journal":{"name":"Artificial Intelligence and Applications","volume":"97 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140973306","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":"Fuzzy-Based Robot Behavior with the Application of Emotional Pattern Generator","authors":"Laura Trautmann, A. Piros, J. Botzheim","doi":"10.47852/bonviewaia42021212","DOIUrl":"https://doi.org/10.47852/bonviewaia42021212","url":null,"abstract":"The article deals with the development of human–robot interaction, where the robot measures the user’s emotional state as well as environmental factors by different devices, and it responds to the user with colorful patterns and controls the smart home through the guidance of the Internet of Things system. Before the design process, robots and their functions currently on the market, the role of emotions in communication, and technologies for measuring emotion (such as face recognition, measurement of heart rate, breath, and physical changes) are presented in detail. The designed robot (Em-Patty) uses a previously developed emotion-based automatic pattern generation system based on a fuzzy system, which is a suitable tool for handling emotions. A main and three fuzzy subsystems are fusioned in order to create the most efficient control system for Em-Patty. The nature-inspired design of the robot is also presented, as well as a description of its behavior with the help of a specific case study.","PeriodicalId":518162,"journal":{"name":"Artificial Intelligence and Applications","volume":"5 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140982505","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":"Side Collision Detection Model for Visually Impaired Using Monocular Object-specific Distance Estimation and Multimodal Real-World Location Calculation","authors":"Wenqing Song, Yumeng Sun, Qixuan Huang, Junyang Cheok","doi":"10.47852/bonviewaia42022098","DOIUrl":"https://doi.org/10.47852/bonviewaia42022098","url":null,"abstract":"Targeting the potential risk of side-vehicle collisions when the visually impaired crosses roads, this study proposed a side collision detection model, including monocular distance estimation, multimodal real-world location estimation, future location prediction and collision warning strategies tailored for visually impaired pedestrians. The proposed model employs YOLOv8 and DeepSort for vehicle detection and tracking, utilizing shallow neural networks for distance estimation based on image information and vehicle position data. Predicted vehicle distances are combined with magnetic field sensor and GPS data to compute and store real-world vehicle locations, and these location data will be used for linear regression to forecast future locations. A warning strategy is then implemented to alert users. Experimental validation shows that the monocular distance estimation network has an Absolute Relative Error of 0.043 and an ALE (Average Localization Error) of 1.249m. In real-world location estimation, the view angle ALE is 0.019, and the location ALE is 1.778m. Regarding location prediction, the accuracy in distinguishing stationary and moving vehicles reaches 0.962, and the predicted curve, based on ground truth and predicted locations, exhibits good alignment. The proposed warning strategy, evaluated on Kitti Tracking Dataset and a self-created dataset, accurately detects the majority of potential collision risks.","PeriodicalId":518162,"journal":{"name":"Artificial Intelligence and Applications","volume":"16 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140715290","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":"Exploring Intervention Techniques for Alzheimer's Disease: Conventional Methods and the Role of AI in Advancing Care","authors":"Karthikeyan Subramanian, Faizal Hajamohideen, Vimbi Viswan, Noushath Shaffi, Mufti Mahmud","doi":"10.47852/bonview42022497","DOIUrl":"https://doi.org/10.47852/bonview42022497","url":null,"abstract":"Alzheimer's disease (AD) is a neurodegenerative condition characterized by cognitive decline and functional impairment. This study compares conventional intervention techniques with emerging artificial intelligence (AI) approaches to AD. Intervention technique refers to a specific method or approach employed to bring about positive change in a particular situation. In the context of AD, such techniques are crucial as they aim to slow down the progression of symptoms, alleviate behavioral challenges, and support patients and their caretakers in managing the complexities of the condition. Conventional intervention techniques, such as cognitive stimulation and reality orientation, have demonstrated benefits in improving cognitive function and emotional well-being. Conventional intervention approaches are widely preferred as they have a proven track record of effectiveness, personalized response, cost-effectiveness, and patient-centered care. Despite these benefits, they are limited by individual variability in response and long-term effectiveness. On the other hand, AI-based approaches such as Computer Vision and Deep Learning (DL) hold the potential to revolutionize Alzheimer's interventions. These technologies offer early detection, personalized care, and remote monitoring capabilities. They can provide tailored interventions, assist decision-making, and enhance caregiver support. Although AI-based interventions face challenges such as data privacy and implementation complexity, their potential to transform Alzheimer's care is significant. This research paper compares conventional and AI-based approaches. It reveals that while traditional techniques are well-established and have proven benefits, AI-based interventions offer novel opportunities for personalized and advanced care. Combining the strengths of both approaches may lead to more comprehensive and effective interventions for individuals with AD. Continued research and collaboration are crucial to harness the full potential of AI in improving Alzheimer's care and enhancing the quality of life for affected individuals and their caregivers.","PeriodicalId":518162,"journal":{"name":"Artificial Intelligence and Applications","volume":"3 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140732960","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":"TA’KEED the First Generative Fact-Checking System for Arabic Claims","authors":"Saud Althabiti, M. Alsalka, Eric Atwell","doi":"10.5121/csit.2024.140103","DOIUrl":"https://doi.org/10.5121/csit.2024.140103","url":null,"abstract":"This paper introduces Ta’keed, an explainable Arabic automatic fact-checking system. While existing research often focuses on classifying claims as \"True\" or \"False,\" there is a limited exploration of generating explanations for claim credibility, particularly in Arabic. Ta’keed addresses this gap by assessing claim truthfulness based on retrieved snippets, utilizing two main components: information retrieval and LLM-based claim verification. We compiled the ArFactEx, a testing gold-labelled dataset with manually justified references, to evaluate the system. The initial model achieved a promising F1 score of 0.72 in the classification task. Meanwhile, the system's generated explanations are compared with gold-standard explanations syntactically and semantically. The study recommends evaluating using semantic similarities, resulting in an average cosine similarity score of 0.76. Additionally, we explored the impact of varying snippet quantities on claim classification accuracy, revealing a potential correlation, with the model using the top seven hits outperforming others with an F1 score of 0.77","PeriodicalId":518162,"journal":{"name":"Artificial Intelligence and Applications","volume":"96 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140531212","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}