检索结果-内蒙古大学图书馆

3rd IEEE Asian Conference on Innovation in Technology, ASIANCON 2023

作者： Panwar, Minakshi Sharma, Ashish Mahela, Om Prakash Khan, Baseem Maulana Azad University Department of Computer Science Rajasthan Jodhpur India Rvpn Power System Planning Division Jaipur India Hawassa University Department of Electrical Engineering Ethiopia University of Johannesburg Department of Eeet South Africa

ISBN: (纸本)9798350302288

The personalized suggestions using the intelligent methods are becoming promising ways to change eating habits to-ward more desirable diets. This has necessitated the requirements of intelligent food recommender system (FRS). This paper has designed a FRS using the Fuzzy Inference system (FIS) to suggest the food preference (FP). This is achieved using the different system blocks such as Rule Base, Database, Decision-making Unit, Fuzzification Interface Unit (FIU), and Defuzzification Interface Unit (DIU). The FP is decided by processing the input variables such as Age, Income and Calorific values. This is achieved with an accuracy of higher than 95%. Efficacy of proposed FRS is established by comparing the performance with the rule based FRS reported in literature. Study is performed using the coding environment of MATLAB. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semanti...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Weizhao He Yang Zhang Wei Zhuo Linlin Shen Jiaqi Yang Songhe Deng Liang Sun Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society School of Computer Science University of Nottingham China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and their performances degrade significantly while applied to a distinct domain. To this end, we propose to leverage the cutting-edge foundation model, the segment Anything Model (SAM), for generalization enhancement. The SAM however performs unsatisfactorily on domains that are distinct from its training data, which primarily comprise natural scene images, and it does not support automatic segmentation of specific semantics due to its interactive prompting mechanism. In our work, we introduce APSeg, a novel auto-prompt network for cross-domain few-shot semantic segmentation (CD-FSS), which is designed to be auto-prompted for guiding cross-domain segmentation. Specifically, we propose a Dual Prototype Anchor Transformation (DPAT) module that fuses pseudo query prototypes extracted based on cycle-consistency with support prototypes, allowing features to be transformed into a more stable domain-agnostic space. Additionally, a Meta Prompt (MPG) module is introduced to automatically generate prompt embeddings, eliminating the need for manual visual prompts. We build an efficient model which can be applied directly to target domains without fine-tuning. Extensive experiments on four cross-domain datasets show that our model outperforms the state-of-the-art CD-FSS method by 5.24% and 3.10% in average accuracy on 1-shot and 5-shot settings, respectively.

关键词： Training Metalearning Visualization Semantic segmentation Semantics Prototypes Training data

来源：评论

学校读者我要写书评

暂无评论

Split Lohmann computer holography: fast generation of 3D hologram in single-step diffraction calculation

引用

Advanced Photonics Nexus 2024年第3期3卷 1-13页

作者： Chenliang Chang Xian Ding Di Wang Zhizhou Ren Bo Dai Qi Wang Songlin Zhuang Dawei Zhang University of Shanghai for Science and Technology School of Optical-Electrical and Computer EngineeringEngineering Research Center of Optical Instrument and SystemMinistry of Education and Shanghai Key Laboratory of Modern Optics SystemShanghaiChina Beihang University School of Instrumentation and Optoelectronic EngineeringBeijingChina

Holographic display stands as a prominent approach for achieving lifelike three-dimensional(3D)reproductions with continuous depth ***,the generation of a computer-generated hologram(CGH)always relies on the repetitive computation of diffraction propagation from point-cloud or multiple depthsliced planar images,which inevitably leads to an increase in computational complexity,making real-time CGH generation ***,we report a new CGH generation algorithm capable of rapidly synthesizing a 3D hologram in only one-step backward propagation calculation in a novel split Lohmann lens-based diffraction *** introducing an extra predesigned virtual digital phase modulation of multifocal split Lohmann lens in such a diffraction model,the generated CGH appears to reconstruct 3D scenes with accurate accommodation abilities across the display *** with the conventional layer-based method,the computation speed of the proposed method is independent of the quantized layer numbers,and therefore can achieve real-time computation speed with a very dense of depth *** simulation and experimental results validate the proposed method.

关键词： computer holography holographic display diffraction calculation.

来源：评论

学校读者我要写书评

暂无评论

Feature Map Guided Strategy for Robust Multi-Resolution Image Dehazing

Feature Map Guided Strategy for Robust Multi-Resolution Imag...

引用

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

作者： Kumar, Avishek Kumar, Nagendra Mishra, Akhilesh Kumar Pathak, Gouransh Chatterjee, Amit IIT Delhi Centre for Sensors Instrumentation and Cyber-Physical System Engineering New Delhi110016 India NIT Jamshedpur Department of Electronics and Communication Engineering Jamshedpur831014 India IILM Univeristy Department of Electrical and Electronics Engineering Greater Noida201306 India PIEMR-Indore Department of Computer Science and Engineering Indore452010 India DIT University School of Computing Dehradun248009 India

ISBN: (纸本)9798350378092

Presence of haze in digital images poses significant challenges in computer vision applications, adversely impacting tasks like image segmentation and object detection. To tackle this issue, this paper introduces a fusion-based dehazing strategy by integrating color conversion, adaptive gamma correction, and parameter estimation. Through multi resolution fusion of chromatic and brightness maps, the algorithm efficiently removes haze, surpassing conventional single-image approaches while maintaining computational efficacy. From comparative analysis it is evident that, the proposed strategy is highly effective in terms of improving image quality for diverse applications. © 2024 IEEE.

关键词： Demulsification

来源：评论

学校读者我要写书评

暂无评论

Tree Regularization for Visual Explanations of Cancer Cell Classification

Tree Regularization for Visual Explanations of Cancer Cell C...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Muhammad Umair Raza Jie Chen Li Wang Adil Nawaz Victor C.M. Leung Jianqiang Li College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The challenge of interpretability remains a significant barrier to adopting deep neural networks in healthcare domains. Although tree regularization aims to align a deep neural network’s decisions with a single axis-aligned decision tree, however, relying on one tree for all inputs often leads to sub-optimal performance and interoperability. To address this limitation, we propose an enhanced tree regularization method that integrates a post-hoc visual explainable model such as Grad-CAM. This approach guides the deep model to be well-approximated by decision trees tailored to the salient regions identified by Grad-CAM in the input space. We rigorously validate the effectiveness of this framework on two cancer cell datasets: CNMC, which focuses on acute lymphoblastic leukemia cells, and ISBI2016, which comprises benign and malignant skin lesions. The results demonstrate that the proposed method delivers simpler and more interpretable explanations without compromising accuracy, thereby advancing the interpretability of deep learning models in critical healthcare applications.

关键词： Visualization Accuracy Decision making Artificial neural networks Predictive models Skin Decision trees Lesions Biological cells Cancer

来源：评论

学校读者我要写书评

暂无评论

Modeling & Evaluating the Performance of Convolutional Neural Networks for Classifying Steel Surface Defects

arXiv

引用

arXiv 2024年

作者： Chaudhry, Nadeem Jabbar Bilal, M. Khan Javaid, M. Iqbal Yasir, Siddiqui Muhammad Department of Computer Science Superior University Lahore Pakistan Department of Computer Science University of Central Punjab Lahore Pakistan Department of Mechanical System Engineering Tongmyong University Busan Korea Republic of

Recently, outstanding identification rates in image classification tasks were achieved by convolutional neural networks (CNNs). to use such skills, selective CNNs trained on a dataset of well-known images of metal surface defects captured with an RGB camera. Defects must be detected early to take timely corrective action due to production concerns. For image classification up till now, a model-based method has been utilized, which indicated the predicted reflection characteristics of surface defects in comparison to flaw-free surfaces. The problem of detecting steel surface defects has grown in importance as a result of the vast range of steel applications in end-product sectors such as automobiles, households, construction, etc. The manual processes for detections are time-consuming, labor-intensive, and expensive. Different strategies have been used to automate manual processes, but CNN models have proven to be the most effective rather than image *** fine-tuning, easily compare their performance and select the best-performing ***,itisimportantthatusingdifferent CNN models either from fine tuning can be computationally expensive and time-consuming. Therefore, our study helps the upcoming researchers to choose the CNN without considering the issues of model complexity, performance, and computational resources. In this article, the performance of various CNN models like Visual Geometry Group, VGG16, VGG19, ResNet152, ResNet152V2, Xception, InceptionV3, InceptionResNetV2, NASNetLarge, MobileNetV2, and DenseNet201 with transfer learning techniques are evaluated. These models were chosen based on their popularity and impact in the field of computer vision research, as well as their performance on benchmark datasets. According to the outcomes, DenseNet201 outperformed the other CNN models and had the greatest detection rate on the NEU dataset, falling in at 98.37 percent. ©

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Distraction Detection in Driving Using Pose Extraction and Machine Learning Techniques 7

Distraction Detection in Driving Using Pose Extraction and M...

引用

7th International Conference on Information Technology, Information systems and Electrical engineering, ICITISEE 2023

作者： Bachtiar, Fitra Abdurrachman Arwani, Issa Prasetyo, Ridwan Aji Budi Pangestu, Gusti Soetedjo, Riza Setiawan Mahesa, Al Ravie Muthiar Brawijaya University Informatics Engineering Department Malang Indonesia Brawijaya University Information System Department Malang Indonesia Brawijaya University Psychology Department Malang Indonesia School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798350382266

There are a lot of technologies have been implemented in the modern cars these days, ranging from preventive braking system to driving assistance. It is believe that equipping car with modern technology would enhance safety. However, there are other aspects need to be considered in safety driving, that is human factor. Human factors are believed have high contribution in road accidents. Human factors such as emotional control and distraction may leads to dangerous driving behaviours. This study investigates the driver pose distraction. The distracted driver pose detected through pose detection using landmark feature extraction. The dataset used in this study is State Farm Distracted Driving Detection which is a secondary dataset. The extracted driver pose are in numeric form and used as the input for the classification model to detect ten kinds of driving distraction ranging from safety driving to talking to passenger. Four classifiers used to detect distracted driver are CatBoost, Decision Tress, Random Forest and SVM. The model performance evaluated using Precision, Recall, Accuracy, and F1-score. Furthermore, prediction time recorded to determine the best model to detect driver distraction. The results shows that CatBoost model outperformed all other model with F1-score and prediction time of 0.899 and 0.014 second. Random Forest model performance is the second highest compared to four other with F1-score and prediction time of 0.881 and 0.028 seconds. CatBoost model is the best model even though Cat Boost model execution time is not the highest and the model performance is not significantly different compared to Random Forest. © 2023 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Adaptive Evolutionary Reinforcement Learning Algorithm with Early Termination Strategy 24

Adaptive Evolutionary Reinforcement Learning Algorithm with ...

引用

Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent systems

作者： Xiaoqiang Wu Qingling Zhu Qiuzhen Lin Weineng Chen Jianqiang Li College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798400704864

Evolutionary reinforcement learning algorithms (ERLs), which combine evolutionary algorithms (EAs) with reinforcement learning (RL), have demonstrated significant success in enhancing RL performance. However, most ERLs rely heavily on Gaussian mutation operators to generate new individuals. When the standard deviation is too large or small, this approach will result in the production of poor or highly similar offspring. Such outcomes can be detrimental to the learning process of the RL agent, as too many poor or similar experiences are generated by these individuals. In order to alleviate these issues, this paper proposes an Adaptive Evolutionary Reinforcement Learning (AERL) method that adaptively adjusts both the standard deviation and the evaluation process. By tracking the performance of new individuals, AERL maintains the mutation strength within a suitable range without the need for additional gradient computations. Moreover, the proposed AERL approach early terminates unnecessary evaluations and discards experiences arising from poor individuals, thereby resulting in enhanced learning efficiency. Empirical assessments conducted on a variety of continuous control problems demonstrate the effectiveness of the AERL method.

关键词： evolutionary algorithm evolutionary reinforcement learning reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

5G Beyond for Healthcare: Leveraging AI/ML and Diverse Datasets for Cybersecurity 2nd

5G Beyond for Healthcare: Leveraging AI/ML and Diverse Dat...

引用

2nd International Workshop on Secure and Resilient Digital Transformation of Healthcare, SUNRISE 2024

作者： Sodhro, Ali Hassan Mughal, Muhammad Irfan Younas Iqbal, Muhammad Javed Department of Computer Science Kristianstad University Kristianstad29188 Sweden Computer System Engineering Sukkur IBA University Sukkur65200 Pakistan Institute of Space Science and Technology University of Karachi Karachi75270 Pakistan

ISBN: (纸本)9783031855573

The rapid adoption of 5G networks, space networks, and Internet of Things (IoT) technologies in healthcare has significantly expanded the attack surface for cybersecurity threats. This evolving landscape demands robust defense mechanisms that can anticipate and neutralize sophisticated cyber-attacks. Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) technologies are pivotal in developing such advanced cybersecurity solutions. A critical factor influencing the effectiveness of these AI/ML models is the quality and diversity of the datasets used in their training. This paper presents a systematic review of various datasets used for AI/ML-based cybersecurity model training across multiple domains, with a focus on 5G networks, IoT healthcare, and space networks. By employing a structured Goal-Question-Metric (GQM) methodology and Quasi-Gold Standard (QGS) validation, we assessed the characteristics, applications, and limitations of real, synthetic, and hybrid datasets in enhancing cybersecurity measures. The review identifies key trends, gaps, and future research directions, highlighting the need for more diverse datasets, standardized benchmarks, and privacy-preserving techniques. Our findings offer insights into improving the resilience of AI/ML models for cybersecurity, guiding the development of more effective and adaptable defense strategies across emerging network technologies. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

ENHANCING TWITTER BOT DETECTION VIA MULTIMODAL INVARIANT REPRESENTATIONS

arXiv

引用

arXiv 2024年

作者： Gong, Jibing Peng, Jiquan Qu, Jin Du, ShuYing Wang, Kaiyu School of Information Science and Engineering Yanshan University The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province China

Detecting Twitter Bots is crucial for maintaining the integrity of online discourse, safeguarding democratic processes, and preventing the spread of malicious propaganda. However, advanced Twitter Bots today often employ sophisticated feature manipulation and account farming techniques to blend seamlessly with genuine user interactions, posing significant challenges to existing detection models. In response to these challenges, this paper proposes a novel Twitter Bot Detection framework called BotSAI. This framework enhances the consistency of multimodal user features, accurately characterizing various modalities to distinguish between real users and bots. Specifically, the architecture integrates information from users, textual content, and heterogeneous network topologies, leveraging customized encoders to obtain comprehensive user feature representations. The heterogeneous network encoder efficiently aggregates information from neighboring nodes through oversampling techniques and local relationship transformers. Subsequently, a multi-channel representation mechanism maps user representations into invariant and specific subspaces, enhancing the feature vectors. Finally, a self-attention mechanism is introduced to integrate and refine the enhanced user representations, enabling efficient information interaction. Extensive experiments demonstrate that BotSAI outperforms existing state-of-the-art methods on two major Twitter Bot Detection benchmarks, exhibiting superior performance. Additionally, systematic experiments reveal the impact of different social relationships on detection accuracy, providing novel insights for the identification of social bots. © 2024, CC BY.

关键词： Tweets

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：