检索结果-内蒙古大学图书馆

26th International Conference on Information Fusion, FUSION 2023

作者： Flemmen, Henrik D. Mester, Rudolf Stahl, Annette Bryne, Torleiv H. Brekke, Edmund Førland Norwegian University of Science and Technology Department of Engineering Cybernetics Norway Norwegian University of Science and Technology Department of Informatics and Computer Science Norway

ISBN: (纸本)9798890344854

Future autonomous ships will need several redundant positioning systems to navigate reliably. Global Navigation Satellite Systems are highly accurate but they are susceptible to disruptions and intentional jamming. Maritime radars have long range and are robust against bad weather and darkness, but the use for ownship motion estimation has received relatively little attention in the research field. In this work, we present a radar odometry estimation method inspired by advances in visual odometry and simultaneous localization and mapping. The method works on raw radar data in a coastal environment and combines the Kanade-Lucas-Tomashi tracker with a factor graph back-end. We test it on data from a large ship with a maritime radar with a range of 19 km. We find that it is robust with only a small drift and no erroneous jumps in the estimate. © 2023 International Society of Information Fusion.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Multiple Disease Prediction from Retinal Images Using Deep Learning Algorithm

Multiple Disease Prediction from Retinal Images Using Deep L...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Rishikesh, B. Karthikayani, K. Srm Institute of Science and Technology Department of Computer Science and Engineering Vadapalani Campus Tamilnadu Chennai26 India

ISBN: (纸本)9798331508685

Retinal imaging serves as an essential tool for the early identification and diagnosis of numerous systemic diseases. This model framework is used for predicting multiple diseases simultaneously using retinal images. The implementation begins with the collection of annotated retinal images, enabling the identification of ailments as glaucoma, age-related macular degeneration, diabetic retinopathy, including hypertensive retinopathy. Preprocessing techniques are applied to enhance data quality and reduce noise. Feature extraction is conducted using the pretrained VGG16 convolutional neural network (CNNis essential for deep learning model training. Multi-label categorization and multi-task learning are employed to predict multiple diseases concurrently. Strict measures, including as accuracy, sensitivity, specificity, including the area under the receiver operating characteristic curve (AUC-ROC), are used to assess the system's performance. Clinical validation also evaluates its efficacy in practical settings. The incorporation of this predictive system into clinical workflows is facilitated by ensuring regulatory compliance and seamless communication with healthcare professionals. Experimental Results show that the suggested VGG16-based system accomplishes an impressive 98.7% accuracy in detecting multiple retinal diseases. The implementation underscores the transformative potential of leveraging advanced deep learning techniques in ophthalmology. Future efforts are focused on enhancing algorithm performance through larger datasets and refining models to further improve diagnostic precision, enabling timely and effective treatment strategies for retinal conditions. © 2025 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

NOMA—Non-offensive Messaging Application Framework Using Machine Learning Technique for Online Communication Through Social Media 1st

NOMA—Non-offensive Messaging Application Framework Using Ma...

引用

1st International Conference on Human-Centric Smart Computing, ICHCSC 2022

作者： Brar, Gursimran Sharma, Geetanjali Singh, Pahuldeep Gupta, Nitish Kalra, Nidhi Parashar, Anshu Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Punjab Patiala India

ISBN: (纸本)9789811954023

Nowadays, the usage trend of social media platforms such as Facebook, Twitter, and WhatsApp has increased among all age groups, especially teenagers. Despite its positive aspects, the circulation of offensive/hate/abusive text to the online community undermines its reputation, scares away users, and directly affects their mental growth. To address this issue, in this work, we have proposed a machine learning-based framework, which detects, classify, filter, and block the offensive/hate/abusive text at the sender level particularly in three languages (English, Hinglish, and Punglish) during the online communications through social media applications. We have built, trained, and tested the proposed model and evaluated its performance. The proposed model gives the accuracy around and above 90 per cent. Further, we have implemented the proposed model and built an Android-based application named Non-offensive Messaging Application (NOMA) having the in-built machine learning-based feature of offensive/hate/abusive text detection and filtration at the sender level. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Advancements and Applications of AI and ML Techniques in Breast Cancer Prognosis: A Comprehensive Survey 4th

Advancements and Applications of AI and ML Techniques in Bre...

引用

4th International Conference on Smart IoT Systems: Innovations and Computing, SSIC 2023

作者： Jagetiya, Anurag Dadheech, Pankaj Department of Computer Science and Engineering Swami Keshvanand Institute of Technology Management & Gramothan Rajasthan Jaipur302017 India

ISBN: (纸本)9789819751990

This paper provides an overview of the advancements and applications of machine learning (ML) techniques in breast cancer research. It discusses the use of ML algorithms for classifying cancers, predicting survival status, and forecasting recurrence. The survey reveals that machine learning approaches were employed for cancer classification, prognosis, and the identification of prognostic factors, while deep learning approaches were used for predicting patient survival subtypes, identifying concealed features, and predicting metastasis. Artificial neural network (ANN) approaches are effective in classifying cancer types, while logistic regression and K-nearest neighbours (KNN) perform poorly on certain datasets. SVM shows moderate performance. Feature ranking and filtering improve results and aid in prognosis. Random forest adapts well to multiple datasets. ML techniques are also applied to identify prognostic factors for breast cancer survival. It is found that genomic factors combined with clinicopathological data aid in early detection and recurrence prediction. ML models help identify genes responsible for recurrence. Various techniques, including survival analysis and mechanistic models, are employed. CNN shows promise in predicting breast cancer from microscopic images. LDA and random forest perform well in predicting metastasis. The survey emphasizes the need for validation on external datasets and the inclusion of larger datasets and varied data sources for improved accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Security Assessment Tool for Modern Power Systems with Massive RES Penetration 3

A Dynamic Security Assessment Tool for Modern Power Systems ...

引用

3rd International Conference on Energy Transition in the Mediterranean Area, SyNERGY MED 2024

作者： Therapontos, Phivos Charalambous, Charalambos A. Aristidou, Petros Electricity Authority of Cyprus Distribution System Operator Nicosia Cyprus University of Cyprus Department of Electrical and Computer Engineering Nicosia Cyprus Cyprus University of Technology Dept. of Electrical & Computer Engineering & Informatics Limassol Cyprus

ISBN: (纸本)9798350375923

Modern power systems are facing significant challenges due to the massive penetration of renewable energy sources (RES). Recently, issues related to frequency security, system strength, and excessive fault levels have been experienced in some power systems. Classical dynamic security assessment (DSA) tools have not been developed to identify and analyze these new challenges that are critical in low-inertia grids. In this paper, a DSA tool has been developed that evaluates frequency security, system strength, and maximum fault levels to allow for secure system planning and operation. Furthermore, to increase the accuracy of the DSA tool, inverter-based resources' (IBRs') protections and capabilities have been incorporated in the DSA tool. A real-time operation and an operational planning application of the DSA tool are showcased using the islanded Cyprus Power System. © 2024 IEEE.

关键词： Dynamic security assessment frequency security IBR modeling low-inertia grids system strength

来源：评论

学校读者我要写书评

暂无评论

Merging the Strengths of GPT-4 and DeepLab for Semantic Text Understanding in Digital Textbooks

Merging the Strengths of GPT-4 and DeepLab for Semantic Text...

引用

2024 International Conference on Communication, computer Sciences and engineering, IC3SE 2024

作者： Anusha, B. Borah, Asha Rani Mishra, Gaurav Thethi, H Pal Al-Allak, Mustafa Abdulhussein Vidhya, B. Veda Institute Of Aeronautical Engineering Department Of Computer Science And Engineering Telangana Hyderabad India New Horizon College Of Engineering Department Of Computer Science Engineering Bangalore India Amity School Of Engineering And Technology Amity University Greater Noida India Lovely Professional University Phagwara India College Of Medical Technology The Islamic University Najaf Iraq Mlr Institute Of Technology Department Of Computer Science And Engineering Telangana Hyderabad India

ISBN: (纸本)9798350366846

Gathering all the necessary data is the major objective of this study so that a comprehensive picture can be painted of how new technologies might improve students' understanding of semantic content in digital textbooks. The recommendations for this approach make use of TIFA, CEG, and ACA, or the Adaptive Complexity Adjustment. This approach combines the best features of various algorithms. TIFA makes these learning aids easy to completely comprehend by combining written and visual material. Answering students' queries and providing answers that make sense in the context is CEG's responsibility. To make learning more tailored to everyone, ACA changes the difficulty of the content depending on performance metrics. Conversely, when students ask CEG questions, it finds answers. We compare the proposed method, Semantix Blend, to two more popular approaches, Textbook Classic and Trad Edu. Interpreting text, evaluating visual information, ensuring consistency in context, enabling customisation, making content more accessible, enhancing learning results, and many more advantages are all possible with Semantix Blend. The study's findings will contribute to the improvement of digital textbooks, leading to improved instruction for students in the long term. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A framework for object tracking in videos with complex backgrounds and obstructions

引用

Neural Computing and Applications 2025年 1-20页

作者： Chang, Tsui-Ping Chen, Tzer-Long Hsiao, Tsung-Chih Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung Taiwan Department of Healthcare Administration and Medical Informatics Kaohsiung Medical University Gaoxiong807 Taiwan Department of Radio Television and Film Shih Hsin University Taipei11604 Taiwan

The research of object tracking in videos utilizes computer vision and machine learning techniques to identify and track objects in the consecutive image frames of videos. The popular algorithms used in the research are YOLO, DeepSORT, StrongSORT, and ByteTrack. YOLO has gained recognition for its hardware efficiency and impressive performance in object detection tasks. It efficiently detects objects in the consecutive image frames of videos. On the other hand, DeepSORT, StrongSORT, and ByteTrack leverage the prediction capabilities to estimate the positions of objects in the next image frames. These algorithms play a significant role to enhance the capabilities of object tracking systems. Recently, many researchers have proposed their methods to enhance the accuracy in object tracking tasks. However, the division of videos into the consecutive image frames for tracking objects can pose challenges, especially when the videos have complex backgrounds and many obstructions in the image frames. In fact, the complex backgrounds with many obstructions in image frames decrease the accuracy of tracking objects in applications. In this study, we present TraObs, a framework for object Tracking in complex backgrounds with Obstructions in the image frames of videos. In TraObs, two novel mechanisms CFM and M-controller are proposed for detectors and trackers to enhance the accuracy of object tracking performance. CFM addresses the tracked objects which are missing in some image frames of videos, while M-controller makes sure the tracked objects with the correct object ids in the system. Some experiments with four testing datasets and benchmark datasets are designed and used respectively to analyze the performance of TraObs. Furthermore, the HOTA and MOTA metrics are used to evaluate our proposed methods. The experimental results also prove the effectiveness of CFM and M-controller in our framework TraObs. © The Author(s), under exclusive licence to Springer-Verlag London Ltd.,

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Dynamic Topology Management In Ad-Hoc Networks For Improved Performance 2

Dynamic Topology Management In Ad-Hoc Networks For Improved ...

引用

2nd IEEE International Conference on Advances in Information technology, ICAIT 2024

作者： Anakath, A.S. Kannadasan, R. Margarat, G. Simi Pandian, A. Pasumpon Antony Sibiya Varghese, V. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology VIT University Tamil Nadu Vellore India Department of Computer Science and Engineering New Prince Shri Bhavani College of Engineering and Technology Tamil Nadu Chennai India Department of Computer Science and Engineering CARE College of Engineering Trichy India Department of Artificial Intelligence and Data Science GRT Institute of Engineering and Technology Tamil Nadu Tiruttani India

ISBN: (纸本)9798350383867

Optimization in ad hoc networks is a highly specialized task because the structure of the network is loosely formed, and each node is independently responsible for its operation. In order to obtain a better result from this solely formed networks this report offer extensive Dynamic Topology Management (DTM) method. Dynamic routing protocols lager lines, dividend balancing, Life-saving administration, guarantee of reliability, cross-layer design, security aspects and the on-time monitoring and discovery of topology changes are the main objectives and steps to be accomplished. Real-time Location monitoring and forest structure discovery are made possible by employing adaptive routing protocols, namely Dynamic Source Routing(DSR) and Ad-Hoc On-Demand Distance Vector(AODV). Also, the algorithms are capable of making advance adjustments to routing routes and resource allocations drawn from the mobility patterns forecasting which is vital. Load balancing methods, which distribute traffic in a network evenly, enable the system to run efficiently and avoid problems caused by overloading. Algorithms that are energy-efficient and make the best use of energy resources having their topology's optimized are introduced to the streamlined energy distribution systems. These algorithms are focused on the node's energy level. Through fault tolerance techniques which recognize and handle failures in nodes and partitioned networks, connectedness activity is a continuous one. Through QoS perception, the network topology might automatically be tailored to conform to the given quality criteria, thus not restricting the choice for differing applications. The proposed could have defenses against adversary nodes and their potential DDoS attacks which will enhance network protection. Yet another advantage of an architectural style that promotes cross-layer collaboration is enhanced topology management which is the goal around which the functions of various levels of the protocol stack revolve

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

RIS-Aided MIMO Downlink Transmission for Ultradense LEO Satellite-Terrestrial Networks

引用

IEEE Internet of Things Journal 2025年第11期12卷 15304-15318页

作者： Zhang, Xin Qin, Xiaohan Zhang, Zitian Cai, Lin X. Zhou, Haibo Zhuang, Weihua Nanjing University School of Electronic Science and Engineering Nanjing210023 China Zhejiang Gongshang University School of Information and Electronic Engineering Hangzhou310018 China Illinois Institute of Technology Department of Electrical and Computer Engineering ChicagoIL60616 United States University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

Ultradense low-Earth orbit (LEO) satellite-terrestrial network (ULSN) has evolved as a new paradigm to provide ubiquitous and high-capacity communications in next generation wireless networks. However, the direct LEO satellite broadband connectivity faces significant challenges in urban environments due to the masking effect, which limits the reliability and availability of communication links in ULSNs. To address this, reconfigurable intelligent surface (RIS) is emerging as a promising solution in ULSNs. In this article, we investigate RIS-aided downlink data transmission in urban environments of multiusers in ULSNs. We set up a mixed-integer programming (MIP) model for maximizing the sum rate of terrestrial users in ULSNs. To solve the complex MIP problem, we propose a two-phase joint optimization algorithm with a deep learning phase and an alternative optimization (AO) phase. In the deep learning phase, a deep neural network (DNN) algorithm is employed to obtain the optimal user association matrix based on the positions of terrestrial users and LEO satellites. Then in the AO phase, successive convex approximation is utilized to transform the nonconvex subproblems of beamforming and RIS phase design into convex formulations and iteratively solve them. Simulation results demonstrate that the proposed algorithm outperforms other baseline algorithms. © 2014 IEEE.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Neural Network Approaches for Long Document Classification 2022

Hierarchical Neural Network Approaches for Long Document Cla...

引用

14th International Conference on Machine Learning and Computing, ICMLC 2022

作者： Khandve, Snehal Ishwar Wagh, Vedangi Kishor Wani, Apurva Dinesh Joshi, Isha Mandar Joshi, Raviraj Bhuminand Computer Engineering Department Pune Institute of Computer Technology India Department of Computer Science and Engineering Indian Institute of Technology Madras India

ISBN: (纸本)9781450395700

Text classification algorithms investigate the intricate relationships between words or phrases and attempt to deduce the document's interpretation. In the last few years, these algorithms have progressed tremendously. Transformer architecture and sentence encoders have proven to give superior results on natural language processing tasks. But a major limitation of these architectures is their applicability for text no longer than a few hundred words. In this paper, we explore hierarchical transfer learning approaches for long document classification. We employ pre-trained Universal Sentence Encoder (USE) and Bidirectional Encoder Representations from Transformers (BERT) in a hierarchical setup to capture better representations efficiently. Our proposed models are conceptually simple where we divide the input data into chunks and then pass this through base models of BERT and USE. Then output representation for each chunk is then propagated through a shallow neural network comprising of LSTMs or CNNs for classifying the text data. These extensions are evaluated on 6 benchmark datasets. We show that USE + CNN/LSTM performs better than its stand-alone baseline. Whereas the BERT + CNN/LSTM performs on par with its stand-alone counterpart. However, the hierarchical BERT models are still desirable as it avoids the quadratic complexity of the attention mechanism in BERT. Along with the hierarchical approaches, this work also provides a comparison of different deep learning algorithms like USE, BERT, HAN, Longformer, and BigBird for long document classification. The Longformer approach consistently performs well on most of the datasets. © 2022 ACM.

关键词： Learning algorithms

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：