检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： He, Jiaxing Li, Liang Mao, Xingbin School of Computer Science and Engineering Chongqing University of Technology Chongqing China

ISBN: (纸本)9781665410205

In the current context of proliferation of news information, personalised news recommendation is important to help users quickly access content of interest. Existing approaches tend to ignore the diversity of users' reading behaviours and the variability of news topics within a session. They tend to assume that all the news read or clicked within a session are attributed to one main interest, while in reality, each news session may cover a variety of news with different interests corresponding to different topics. The paper introduces a news session recommendation approach that utilizes both long-and short-term representations of user interests, incorporating multi-view learning techniques, and the method treats the clicking behaviours of anonymous users as a session: initially, a multi-scale convolutional neural network is employed to capture the features of user-clicked news articles from mul-tiple viewpoints;Subsequently, a GRU multi-channel interest decoupler is crafted to identify potential interests within each clicked news item, enabling the modeling of diverse interests to capture the user's long-term preferences. Concurrently, recent user-clicked news items are considered as short-term interests. These long and short-term interests are then amalgamated to create the ultimate user interest representation;Finally, the user's preference value for the candidate news is calculated by click-summing and the final recommendation result is generated. By comparing with the benchmark method on the real data set, the findings demonstrate strong performance on objective evaluation metrics such as Area Under the ROC Curve (AUC) and Normalised Discounted Cumulative Gain (NDCG), affirming the efficacy of the proposed method for news recommendation. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning With Heterogeneous Graph Neural Network for Flexible Job Shop Scheduling Problem 10

Deep Reinforcement Learning With Heterogeneous Graph Neural ...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Liu, Boyan Yin, Huayi Xiamen University of Technology School of Computer and Information Engineering Xiamen China

ISBN: (纸本)9798331520861

Job Shop Scheduling Problem (JSP) is common in modern factories, but traditional dispatching rules (DR) and heuristic algorithms (HA) struggle with the increasing complexity of manufacturing processes. In this paper, we review research on the Flexible Job Shop Scheduling Problem (FJSP) and propose a Deep Reinforcement Learning (DRL) approach to address it. Unlike conventional methods, we represent the FJSP using a heterogeneous graph (HG) instead of a disjunctive graph (DG), allowing a Heterogeneous Graph Neural Network (HGNN) to effectively extract comprehensive node information. We model the problem as a Markov Decision Process [30] (MDP) and employ an enhanced Proximal Policy Optimization (PPO) algorithm for model training. Experimental results show that our approach outperforms some DRs and DRL method in terms of solution quality across generated small, medium, and large-scale datasets, as well as classic public benchmarks, all within an acceptable time frame. Additionally, it demonstrates significantly greater solution efficiency than advanced HA while maintaining similar solution quality, exhibiting strong stability and generalization capabilities. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Dual-Model Approach for Diabetic Retinopathy and Macular Edema Detection

Dual-Model Approach for Diabetic Retinopathy and Macular Ede...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Micheal, A. Ancy Sai, Ladi Jeevan Vellore Institute of Technology Chennai School of Computer Science and Engineering India

ISBN: (纸本)9798350378092

Diabetic Retinopathy (DR) and Diabetic Macular Edema (DME) are major causes of vision loss in diabetic patients. Early detection is crucial for preventing permanent vision impairment. This research paper proposes a novel dual-model architecture for detecting Diabetic Retinopathy and Diabetic Macular Edema. The proposed framework integrates preprocessing techniques such as circular cropping and Ben's preprocessing, followed by data augmentation. The Diabetic Retinopathy model is trained on the APTOS2019 dataset, while the Diabetic Macular Edema model is trained using the IDRid dataset. InceptionV3 outperforms other models with an accuracy of 88% for Diabetic Retinopathy classification, while MobileNetV2 outperforms other models with an accuracy of 83% for DME classification. The dual-model architecture enables simultaneous evaluation of retinal images for DR and DME diseases. The Experimental results demonstrate promising outcomes, suggesting the potential effectiveness of the proposed dual-model architecture in diagnosing diabetic eye diseases. © 2024 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Leveraging Advanced Deep Learning Techniques for Automated Dermatological Image Classification 4

Leveraging Advanced Deep Learning Techniques for Automated D...

引用

4th IEEE International Conference on Applied Electromagnetics, Signal Processing, and Communication, AESPC 2024

作者： Saha, Akashdip Suddapalli, Rishik Sahoo, Abhaya Kumar Singh, Jagannath School of Computer Engineering Kalinga Institute of Industrial Technology Bhubaneswar India

ISBN: (纸本)9798331528171

This paper examines the automatic classification of skin photos using the state-of-the-art deep learning methods, with a focus on the categorization of skin lesions. One of the main goals is to improve the accuracy and user-friendliness of dermatology diagnostics;thus, the diagnosis can be made much earlier and more accurately than now, leading to the detection of skin conditions. We use convolutional neural network-based (CNN) algorithms that are highly complex and the huge International Skin Imaging Collaboration (ISIC) library for facial recognition. This model will revolutionize skin diseases diagnosis, enabling clinical decisions to be made quickly and accurately, thereby enhancing patient care and outcomes. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Feature Fusion Network Model for Cervical Cancer Prediction

An Enhanced Feature Fusion Network Model for Cervical Cancer...

引用

2024 IEEE Silchar Subsection Annual Conference, SILCON 2024

作者： Pragatheeswari, B. Mary, Jameela Priya, S. Roshni Dhivyaa, C.R. School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9798331540821

Healthcare providers and researchers that work with patients who have cervical cancer face a significant challenge because it is one of the world's most common causes of death. Worldwide, cervical cancer is one of the major causes of death among women according to the World Health Organization (WHO). Pap smear, also called the Pap Test, is used to examine the cells present in the cervix for abnormal cells. However, manual examination of these pap smears is prone to human error. This work aims to explore the use of deep learning models to detect cancer from pap smear images and develop an ensemble model to improve the accuracy. Our proposed model uses pretrained CNN models through transfer learning to extract features, perform feature concatenation followed by dimensionality reduction and hyperparameter tuning, which are then fed into a neural network for multiclass classification. Hyperparameters are fine-tuned with the help of Bayesian optimization to improve the model's performance. Our proposed model has achieved an accuracy of 96.4%, sensitivity of 96.41% and specificity of 96.66%. © 2024 IEEE.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Binary Program Vulnerability Mining Based on Neural Network

引用

computers, Materials & Continua 2024年第2期78卷 1861-1879页

作者： Zhenhui Li Shuangping Xing Lin Yu Huiping Li Fan Zhou Guangqiang Yin Xikai Tang Zhiguo Wang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu611731China School of Electrical and Computer Engineering University ofWaterlooWaterlooN2L 3G1Canada

Software security analysts typically only have access to the executable program and cannot directly access the source code of the *** poses significant challenges to security *** it is crucial to identify vulnerabilities in such non-source code programs,there exists a limited set of generalized tools due to the low versatility of current vulnerability mining ***,these tools suffer from some *** terms of targeted fuzzing,the path searching for target points is not streamlined enough,and the completely random testing leads to an excessively large search ***,when it comes to code similarity analysis,there are issues with incomplete code feature extraction,which may result in information *** this paper,we propose a cross-platform and cross-architecture approach to exploit vulnerabilities using neural network obfuscation *** leveraging the Angr framework,a deobfuscation technique is introduced,along with the adoption of a VEX-IR-based intermediate language conversion *** combination allows for the unified handling of binary programs across various architectures,compilers,and compilation ***,binary programs are processed to extract multi-level spatial features using a combination of a skip-gram model with self-attention mechanism and a bidirectional Long Short-Term Memory(LSTM)***,the graph embedding network is utilized to evaluate the similarity of program *** on these similarity scores,a target function is determined,and symbolic execution is applied to solve the target *** solved content serves as the initial seed for targeted *** binary program is processed by using the de-obfuscation technique and intermediate language transformation method,and then the similarity of program functions is evaluated by using a graph embedding network,and symbolic execution is performed based on these similarity *** approach facilitates

关键词： Vulnerability mining de-obfuscation neural network graph embedding network symbolic execution

来源：评论

学校读者我要写书评

暂无评论

Key Management and Authentication Scheme Forward Trusted Pervasive Container Computing 2

Key Management and Authentication Scheme Forward Trusted Per...

引用

2nd International Conference on Big Data and Privacy Computing, BDPC 2024

作者： Hei, XinHong Xue, YuZhan Wang, YiChuan Liu, YiFan Peng, Chen Sun, Xiang School of Computer Science and Engineering Xi'an University of Technology Xi'an China School of Computer Science and Engineering Xi'an University of Technology Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China

ISBN: (纸本)9798350307597

Cloud computing technology is an internet-based computing model that provides high reliability and security measures, including data backup, secure access control, etc. As Docker containers play a increasingly important role in traditional cloud computing architectures, the communication needs between containers become prominent. However, existing container to container communication mainly relies on network protocols for file transfer, making it difficult to achieve the expected results in cloud cluster security. Therefore, this paper primarily focuses on container based keys and proposes a container identity trusted key management method based on Pervasive container computing architecture. The experimental results demonstrate that the container identity trusted key management method not only meets the security transmission characteristics required in the container cloud architecture, but also adopts a strategy combined with trusted hardware, providing security guarantees. In addition, the method proposed in this article that combines trusted hardware for signature verification can defend against multiple network attacks compared to traditional container architectures without using security policies. © 2024 IEEE.

关键词： Cloud computing architecture

来源：评论

学校读者我要写书评

暂无评论

Visible-Infrared Person Re-Identification Based on Dual Branch Structure and Attention 6

Visible-Infrared Person Re-Identification Based on Dual Bran...

引用

6th International Conference on Robotics and computer Vision, ICRCV 2024

作者： Zan, Guo Chen, Xiangyang Jiang, Zheng Lv, Weijie Yang, Mingyu School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9798331527426

Visible-infrared person re-identification (VI-ReID) is a difficult cross-modal pedestrian retrieval *** to the modality gaps between visible (VIS) and infrared (IR) images. In the process of visible-infrared person re-identification, it is difficult to extract effective information from modality-shared features due to the additional cross-modality discrepancy. To address this problem, we propose a visible-infrared person re-identification method based on dual-branch structure and attention. Firstly, a dual-branch convolution module is added to the ResNet-50 backbone network to extract more plentiful modality-shared features of different scales by using the dual-branch structure and dilated convolution with different expansion rates. Moreover, we design a Non- Local attention module to obtain the correlation between different pixels in spatial and channel dimensions by introducing and improving the Non-Local blocks, thereby enhancing the ability of the network to extract structural information. Finally, we design an efficient joint loss strategy to optimize the network to further reduce the modality discrepancy. Our method shows excellent performances on both SYSU-MM01 and RegDB datasets. © 2024 IEEE.

关键词： attention mechanism dual-branch structure Non-Local block ResNet VI-ReID

来源：评论

学校读者我要写书评

暂无评论

AoI-Aware Optimization in RIS-Assisted mmWave Network 10

AoI-Aware Optimization in RIS-Assisted mmWave Network

引用

10th International Conference on Web Research, ICWR 2024

作者： Asadi, Somayeh Sheikhi, Marzieh Hakami, Vesal Iran University of Science and Technology School of Computer Engineering Tehran Iran

ISBN: (纸本)9798350394986

In the era of next-generation wireless networks, real-time applications demand freshness in information delivery, notably in IoT, cyber-physical systems, and industrial IoT. We target the optimization of average Age of Information (AoI) in a multi-user RIS-assisted mmWave network, where the sensitivity of mmWave bands to propagation challenges is mitigated through reconfigurable intelligent surfaces (RIS). Notably, prior studies have overlooked AoI optimization in RIS-enhanced mmWave networks. Our contribution lies in devising a novel Markov Decision Process (MDP) framework and a model-free Deep Reinforcement Learning (DRL) algorithm tailored to high-dimensional action spaces. Our approach orchestrates user transmission timing, power allocation, base station beamforming, and RIS reflective coefficient adjustments. Through extensive simulations, we demonstrate the superiority of our method over existing schemes, showcasing enhanced network performance. This work represents an advancement in the optimization of AoI within the context of RIS-assisted mmWave communications, shedding light on efficient control policy learning for improved network operation. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Measurement of Body Vitals using Photoplethysmography (PPG) and Smartphone Sensors 2

Measurement of Body Vitals using Photoplethysmography (PPG) ...

引用

2nd International Conference on Emerging Trends in Information technology and engineering, ic-ETITE 2024

作者： Furniturewala, Mahera Sivaraman, Arjun Anand, Anmol Kannuchamy, Tarun Sasikala, R. School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350328202

Every day, millions of people use portable health gadgets to monitor body vitals such as heart rate, blood oxygen level, blood pressure, etc. However, this can also be facilitated just by using normal smartphones which are commonly available. Thus, this paper aims to provide first aid in the measurement of body vitals for early diagnosis of symptoms. The outcome of this paper is a framework to measure the key body vitals such as blood oxygen, heart rate, blood pressure and respiratory rate using the built-in sensors in a smartphone namely a camera, flashlight, accelerometer, and microphone. These vitals are captured by analyzing the photoplethysmography (PPG) signals obtained from the red intensities of the images of the fingertip and performing further arithmetic calculations on the obtained values. On the other hand, respiratory rate is calculated using the deviation in the values obtained in the accelerometer readings during the movement of the chest upwards and downwards. All the algorithms are computationally feasible on mobile devices and make use of the built-in smartphone sensors only, without the need for external devices. Also, smartphones have become cheaper than before and more people in the society have access to it, thus giving them a wider reach. The paper also compares the values for the vitals measured on pulse oximeters, blood pressure monitors, health bands, and smartphones with low-and high-quality cameras. Comparisons are made on a sample size of 100 measurements, and the mean percentage error for each type of body vital measurement is calculated with respect to each measuring device. © 2024 IEEE.

关键词： Smartphones

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：