检索结果-内蒙古大学图书馆

9th International Conference on computer Science and engineering, UBMK 2024

作者： Asoh-Itambi, Clinton Binda Yüzkat, Mecit Varli, Songül Yildiz Technical University Faculty of Electrical and Electronics Department of Computer Engineering Istanbul Turkey Muş Alparslan University Health Institutes of Türkiye Faculty of Engineering and Architecture Department of Software Engineering Istanbul Turkey Yildiz Technical University Health Institutes of Türkiye Faculty of Electrical and Electronics Department of Computer Engineering Istanbul Turkey

ISBN: (纸本)9798350365887

This study presents a significant improvement in the detection and diagnosis of clinically significant prostate cancer (csPCa) in bi-parametric magnetic resonance imaging (bpMRI) by adapting the nnU-Net framework. We address the inherent limitations of traditional imaging analysis techniques by modifying the loss function used in nnU-Net, replacing the default combination of Cross-Entropy and soft Dice loss with a novel integration of Cross-Entropy loss and Focal loss. This modification targets class imbalance and enhances the detection sensitivity for less represented, clinically significant lesions, which are crucial for effective csPCa management while minimizing false diagnosis. Employing a semi-supervised learning approach, the modified nnU-Net was trained and validated on the PI-CAI (Prostate Imaging: Cancer AI) Public Training dataset (1500 cases), the current benchmark dataset for csPCa detection and diagnosis. It was also tested on the PI-CAI Hidden Testing cohort dataset consisting of 100 unseen cases. These datasets offer a comprehensive and diverse collection of prostate MRI exams, providing a robust foundation for model training and testing. We conducted a rigorous 5-fold cross-validation to ensure the robustness and reproducibility of our findings. The model's performance was evaluated with Average Precision (AP) at the lesion level and Area Under the Receiver Operating Characteristics curve (AUROC) at the patient level. Our model with AUROC and AP of 0.824 and 0.603 respectively on the Hidden Tuning cohort, outperformed the state-of-the-art U-Net, nnDetection models, and other nnU-Net variants. This work contributes to ongoing efforts to refine diagnostic tools in medical imaging, offering the potential for more accurate and timely prostate cancer screenings. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Accurate Real-World Co-ordinate Finding and the Object Classification for the Robot Manipulator 3

Accurate Real-World Co-ordinate Finding and the Object Class...

引用

3rd International Conference on Embedded Systems and Artificial Intelligence, ESAI 2024

作者： Sharan, Sudeep Thanh, Hung Do Nauth, Peter Dominguez-Jimenez, Juan Jose Frankfurt University of Applied Sciences Faculty of Computer Science and Engineering Frankfurt am Main Germany University of Cádiz UCASE Software Engineering Group School of Engineering Cádiz Spain

ISBN: (纸本)9798331522056

This paper presents an object detection and classification of the objects using Deep Learning (DL). The integration of object detection algorithms and depth camera developed is capable of providing robots, such as self developed assistive intelligent robot called 'ROSWITHA' (RObot System WITH Autonomy) with the ability to detect an object and interpret their surrounding environment. It also provides the real-world coordinates/position of the object in that environment, which helps the robot to perform some applications, such as grabbing and serving, etc. You Only Look Once (YOLO) is one of the most popular object detection algorithms which is treated as a single regression problem and is processed by a single neural network. In this work, the YOLOv5 (YOLO version 5) network is implemented on a depth camera 'RealSense' for processing object detection and estimating the position of the objects. The model is trained on reduced/filtered application-required objects (e.g. bottle and cup) from the available COCO dataset, and the training outcome alongside the performance of the overall system was evaluated. The results exhibited a satisfactory performance of the model in accurately detecting and classifying the objects with a high confidence score ranging from the least to7 2% to the highest of9 0%. The confidence score could also be adjusted by the user on the developed GUI to attain the most certain predictions. © 2024 IEEE.

关键词： Bottles

来源：评论

学校读者我要写书评

暂无评论

DeepOCL:A deep neural network for Object Constraint Language generation from unrestricted nature language

引用

CAAI Transactions on Intelligence Technology 2024年第1期9卷 250-263页

作者： Yilong Yang Yibo Liu Tianshu Bao Weiru Wang Nan Niu Yongfeng Yin School of Software Beihang UniversityBeijingChina College of Computer Science and Technology Guizhou UniversityGuiyangGuizhouChina Faculty of Information Technology Beijing University of TechnologyBeijingChina Department of Electrical Engineering and Computer Sciences University of CincinnatiCincinnatiOhioUSA

Object Constraint Language(OCL)is one kind of lightweight formal specification,which is widely used for software verification and validation in NASA and Object Management Group *** OCL provides a simple expressive syntax,it is hard for the developers to write correctly due to lacking knowledge of the mathematical foundations of the first-order logic,which is approximately half accurate at the first stage of devel-opment.A deep neural network named DeepOCL is proposed,which takes the unre-stricted natural language as inputs and automatically outputs the best-scored OCL candidates without requiring a domain conceptual model that is compulsively required in existing rule-based generation *** demonstrate the validity of our proposed approach,ablation experiments were conducted on a new sentence-aligned dataset named *** experiments show that the proposed DeepOCL can achieve state of the art for OCL statement generation,scored 74.30 on BLEU,and greatly outperformed experienced developers by 35.19%.The proposed approach is the first deep learning approach to generate the OCL expression from the natural *** can be further developed as a CASE tool for the software industry.

关键词： deep learning OCL software engineering

来源：评论

学校读者我要写书评

暂无评论

Unveiling Interpretability: Analyzing Transfer Learning in Deep Learning Models for Traffic Sign Recognition

引用

SN computer Science 2024年第6期5卷 682页

作者： Waziry, Sadaf Rasheed, Jawad Ghabban, Fahad Mahmoud Alsubai, Shtwai Elkiran, Harun Alqahtani, Abdullah Department of Software Engineering Istanbul Aydin University Isanbul 34295 Turkey Department of Computer Engineering Istanbul Sabahattin Zaim University Istanbul 34303 Turkey Faculty of Computer Science and Engineering Taibah University Medina Saudi Arabia College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al Kharj 11942 Saudi Arabia

Since the advent of automobiles and driver assistance technologies, traffic sign recognition has been of the utmost importance for Industry 4.0. In the driving system, good data pre-processing is critical. For such objectives, sophisticated transformations or fundamentally computational image processing approaches are out of the question. Convolutional Neural Networks (CNN) have been used to perform more object identification challenges, thus, improving most computer vision applications, both existing and new, because of their excellent recognition rate and rapid execution. This study introduces a method for recognizing traffic signs by utilizing a CNN-based model and the transfer learning concept. The TensorFlow library is used for training the underlying neural network model. The offered approach makes use of the German Traffic Sign Recognition Benchmark (GTSRB) and images from the Traffic Sign Images from Turkey (TSIT) databases. These datasets are dependable and vibrant, and they have been used to train many algorithms. Furthermore, after training the model, the proposed scheme acquired a testing accuracy is 99.44%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： CNN German traffic sign Image processing Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Improved Hybrid Deep Collaborative Filtering Approach for True Recommendations

引用

computers, Materials & Continua 2023年第3期74卷 5301-5317页

作者： Muhammad Ibrahim Imran Sarwar Bajwa Nadeem Sarwar Haroon Abdul Waheed Muhammad Zulkifl Hasan Muhammad Zunnurain Hussain Department of Computer Science The Islamia University of BahawalpurBahawalpurPakistan Department of Computer Science Bahria University Lahore CampusLahorePakistan Software Engineering Department Faculty of ITUniversity of Central PunjabLahorePakistan Faculty of Computer Science and Information Technology Universiti Putra MalaysiaSelangorMalaysia

Recommendation services become an essential and hot research topic for researchers *** data such asReviews play an important role in the recommendation of the *** was achieved by deep learning approaches for capturing user and product information from a short ***,such previously used approaches do not fairly and efficiently incorporate users’preferences and product *** proposed novel Hybrid Deep Collaborative Filtering(HDCF)model combines deep learning capabilities and deep interaction modeling with high performance for True *** overcome the cold start problem,the new overall rating is generated by aggregating the Deep Multivariate Rating DMR(Votes,Likes,Stars,and Sentiment scores of reviews)from different external data sources because different sites have different rating scores about the same product that make confusion for the user to make a decision,either product is truly popular or *** proposed novel HDCF model consists of four major modules such as User Product Attention,Deep Collaborative Filtering,Neural Sentiment Classifier,and Deep Multivariate Rating(UPA-DCF+NSC+DMR)to solve the addressed *** results demonstrate that our novel model is outperforming state-of-the-art IMDb,Yelp2013,and Yelp2014 datasets for the true top-n recommendation of products using HDCF to increase the accuracy,confidence,and trust of recommendation services.

关键词： Neural sentiment classification user product attention deep collaborative filtering multivariate rating artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Comparison of IDS in IoT, Mobile and Cloud based Systems 12

Comparison of IDS in IoT, Mobile and Cloud based Systems

引用

12th International Symposium on Digital Forensics and Security, ISDFS 2024

作者： Gok, Gorkem Boyaci, Aytug Ulas, Mustafa Firat University Faculty of Technology Department of Software Engineering Elaziǧ Turkey Air Force Academy National Defence University Department of Computer Engineering İstanbul Turkey Firat University Faculty of Engineering Department of Artificial Intelligence and Data Science Engineering Elaziǧ Turkey

ISBN: (纸本)9798350330366

This study is meant to research the evolution of intrusion detection and network monitoring within computer, cloud-based systems, IIoT, and mobile environments. The source has outlined the novel technologies in IDS, from 'Fast Learning Network' to hybrid classifiers aiming at protecting cloud computing. The findings highlight innovation IDS technologies that provide flexible and peculiar solutions to ward off potential cyber threats. In addition, it presented with the use of Nagios, NConf, the state of the art in network traffic monitoring, and deep learning as tools for advanced management and network protection. Besides, the research also reviewed concepts of Big Data Analytics and Federated Learning in bettering direct integration and anomaly detection in IIoT. A good comparison of the two would show that recent technological advancements are much needed for network efficiency and its cybersecurity. Based on the findings, the scope of networked system security develops dynamically amid current challenges. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Brain Tumor Classification for MR Images using ResNet50 12

Deep Learning based Brain Tumor Classification for MR Images...

引用

12th International Symposium on Digital Forensics and Security, ISDFS 2024

作者： Kokcam, Omer Mirac Boyaci, Aytug Colak, Muhammed Emre Firat University Faculty of Technology Department of Software Engineering Elaziǧ Turkey National Defence University Department of Computer Engineering Air Force Academy İstanbul Turkey Firat University Faculty of Engineering Department of Artificial Intelligence and Data Science Engineering Elaziǧ Turkey

ISBN: (纸本)9798350330366

Brain tumors are abnormal cell growths that occur in various parts of the brain, and the accurate classification of these tumors plays a critical role in determining treatment methods. Classification and diagnosis of brain tumors based on artificial intelligence and deep learning models have been made possible due to advances in medical image processing technologies. For instance, such technologies facilitate quick detection of tumors by health experts thereby improving early diagnosis rate and hence enhancing treatment outcomes. Importantly, however, one considers improvement or breakthroughs in artificial intelligence-based classification systems as a crucial step forward towards brain tumor diagnosis as well as its treatment strategy. In this study we use Google Research's ImageNet-21k pre-trained ResNet50 model for classifying brain tumor cases. This model is a deep learning-based image classification tool and is capable of learning from large data sets. The model is specifically trained for high-resolution image recognition and is designed to achieve high accuracy rates. The results showed a classification accuracy of 99.9 percent, which is an exceptional accuracy rate for this model. This accuracy rate indicates that the model is highly effective in detecting and classifying brain tumors. High accuracy rates allow for early diagnosis of patients' diseases and, as it is often said in medicine, 'Early Diagnosis Saves Lives'. This result is one of the many proofs of how effective artificial intelligence and deep learning are in medical image analysis. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Approach to Feature Elimination in House Price Estimation 2nd

Evolutionary Approach to Feature Elimination in House Pric...

引用

2nd International Conference on Advanced engineering, Technology and Applications, ICAETA 2023

作者： Günaydın, Yusuf Şevki Mintemur, Ömer Ankara Yıldırım Beyazıt University Computer Engineering Faculty of Engineering and Natural Sciences Ankara Turkey Ankara Yıldırım Beyazıt University Software Engineering Faculty of Engineering and Natural Sciences Ankara Turkey

ISBN: (纸本)9783031509193

One of the most basic human needs is the need for shelter. Since ancient times, people have been looking for a house that is both safe and affordable. However, in modern times, although safety is no longer an issue, the definition of an affordable house has changed. In the past, affordability did not depend on many parameters as it does today. However, today, this definition depends on different features, such as the location of the house, the year of construction, the number of rooms, etc. These features affect the level of affordability, and consequently the price of the house. Since houses are also used as an investment option, correct estimation of house prices is an important issue. The determination of features that have a significant impact on the price of a house is a subjective notion and, therefore, requires an objective approach. Thanks to technological developments, Artificial Intelligence algorithms remove the human factor in most of the decision-making processes. In this study, a naive approach was proposed to estimate house prices by selecting the most effective features of a house (https://***/OmerMintemur/Feature-Elimination-Using-GA.). To select the most effective features, Genetic Algorithm approach was utilized. For estimation, LightGBM was used. The AmesHouse data set was used for the experiments. The results suggested that the proposed method both reduced the features and produced lower estimation errors than other proposed methods that used the same dataset. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Feature Reduction Genetic Algorithm House Prices Prediction

来源：评论

学校读者我要写书评

暂无评论

Deep Semantic and Attentive Network for Unsupervised Video Summarization

引用

ACM Transactions on Multimedia Computing, Communications and Applications 2022年第2期18卷 1-21页

作者： Zhong, Sheng-Hua Lin, Jingxu Lu, Jianglin Fares, Ahmed Ren, Tongwei College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Electrical Engineering Computer Systems Engineering Program Faculty of Engineering at Shoubra Benha University Cairo Egypt State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China

With the rapid growth of video data, video summarization is a promising approach to shorten a lengthy video into a compact version. Although supervised summarization approaches have achieved state-of-the-art performance, they require frame-level annotated labels. Such an annotation process is time-consuming and tedious. In this article, we propose a novel deep summarization framework named Deep Semantic and Attentive Network for Video Summarization (DSAVS) that can select the most semantically representative summary by minimizing the distance between video representation and text representation without any frame-level labels. Another challenge associated with video summarization tasks mainly originates from the difficulty of considering temporal information over a long time. Long Short-Term Memory (LSTM) performs well for temporal dependencies modeling but does not work well with long video clips. Therefore, we introduce a self-attention mechanism into our summarization framework to capture the long-range temporal dependencies among the frames. Extensive experiments on two popular benchmark datasets, i.e., SumMe and TVSum, show that our proposed framework outperforms other state-of-the-art unsupervised approaches and even most supervised methods. © 2022 Association for Computing Machinery.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Performance Improvement in Blood Cell Segmentation with Deep Learning-based Image Fusion Approach 8

Performance Improvement in Blood Cell Segmentation with Deep...

引用

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024

作者： Dogu, Fatma Tuana Dogan, Hulya Dogan, Ramazan Ozgur Sezen, F. Sena Karadeniz Technical University Faculty of Engineering Department of Electrical and Electronics Engineering Trabzon Turkey Karadeniz Technical University Faculty of Engineering Department of Software Engineering Trabzon Turkey Trabzon University Faculty of Computer and Information Sciences Department of Artificial Intelligence Engineering Trabzon Turkey Karadeniz Technical University Faculty of Pharmacy Department of Pharmacology Trabzon Turkey

ISBN: (纸本)9798331531492

To overcome the limitations of examining blood cells under a microscope, several investigations have been carried out using artificial intelligence techniques. These investigations aim to automate the processes of detecting, counting, segmenting, and classifying blood cells. Typically, these investigations employ two-dimensional (2D) images to apply artificial intelligence and image processing techniques. Nevertheless, these 2D images occasionally lack optimal focus as a result of the microscope's depth of focus (DOF). Inadequate achievement of optimally focused imaging has a detrimental impact on the efficiency of automated processes. In this context, the objective of this study is founded around two primary roles. The first of these is the performance improvement of blood cell segmentation by developing a deep learning-based image fusion approach. The second is the preparation of new data sets containing images with different focuses for optimally focused imaging of blood cells. In the study, four different performance evaluation criteria, namely Accuracy (ACC), Sensitivity (SEN), Specificity (SPE), and Jaccard, are utilized to demonstrate the efficacy of the deep learning-based image fusion approach in blood cell segmentation. Both the experimental results of the performance evaluation criteria and the visual findings obtained in the study indicate that the performance in blood cell segmentation is improved with a deep learning-based approach. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：