检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Lu Xu, Liuchi Yang, Xiong Huang, Zhenhua Cheng, Jun School of Computer Science and Engineering Northeastern University Shenyang China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic University Shenzhen China School of Computer Science South China Normal University Guangzhou China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology CAS China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)157735897X

Knowledge distillation transfers "dark knowledge" from a large teacher model to a smaller student model, yielding a highly efficient network. To improve the network's generalization ability, existing works use a larger temperature coefficient for knowledge distillation. Nevertheless, these methods may reduce the confidence of the target category and lead to ambiguous recognition of similar samples. To mitigate this issue, some studies introduce intra-batch distillation to reduce prediction discrepancy. However, these methods overlook the inconsistency between background information and the target category, which may increase prediction bias due to noise disturbance. Additionally, label imbalance from random sampling and batch size can undermine network generalization reliability. To tackle these challenges, we propose a simple yet effective Intra-class Knowledge Distillation (IKD) method that facilitates knowledge sharing within the same class to ensure consistent predictions. First, we initialize the matrix and the vector to store logits and class counts provided by the teacher, respectively. Then, in the first epoch, we calculate the sum of logits and sample counts per class and perform KD to prevent knowledge omission. Finally, in subsequent training, we update the matrix to obtain the average logits and compute the KL divergence between the student's output and the updated matrix according to the label index. This process ensures intra-class consistency and improves the student's performance. Furthermore, this method theoretically reduces prediction bias by ensuring intra-class consistency. Extensive experiments on the CIFAR-100, ImageNet-1K, and Tiny-ImageNet datasets validate the superiority of IKD. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Sentence-State LSTMs For Sequence-to-Sequence Learning 10th

Sentence-State LSTMs For Sequence-to-Sequence Learning

引用

10th CCF Conference on Natural Language Processing and Chinese computing, NLPCC 2021

作者： Bai, Xuefeng Li, Yafu Zhang, Zhirui Xu, Mingzhou Chen, Boxing Luo, Weihua Wong, Derek Zhang, Yue School of Engineering Westlake University Hangzhou China Alibaba DAMO Academy Hangzhou China NLP2CT Lab Department of Computer and Information Science University of Macau China Institute of Advanced Technology Westlake Institute for Advanced Study Hangzhou China

ISBN: (纸本)9783030884796

Transformer is currently the dominant method for sequence to sequence problems. In contrast, RNNs have become less popular due to the lack of parallelization capabilities and the relatively lower performance. In this paper, we propose to use a parallelizable variant of bi-directional LSTMs (BiLSTMs), namely sentence-state LSTMs (S-LSTM), as an encoder for sequence-to-sequence tasks. The complexity of S-LSTM is only O(n) as compared to O(n2) of Transformer. On four neural machine translation benchmarks, we empirically find that S-SLTM can achieve significantly better performances than BiLSTM and convolutional neural networks (CNNs). When compared to Transformer, our model gives competitive performance while being 1.6 times faster during inference. © 2021, Springer Nature Switzerland AG.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Cloud computing-Enhanced and Raspberry Pi-Powered Solution for Remote Ear, Nose, and Throat Consultations with AI-Driven Diagnostics

Cloud Computing-Enhanced and Raspberry Pi-Powered Solution f...

引用

Emerging technology (INCET), International Conference for

作者： Giriprasad. S T. Karpagam V. Nalini Nilamadhab Mishra N. Mohankumar N. Malathi Department of Electronics and Communication Engineering SRM Institute of Science and Technology Kattankulathur Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science R.M.K College of Engineering and Technology Chennai Tamil Nadu India Department of Mathematics Vel Tech Multi Tech Dr Rangarajan Dr Sakunthala Engineering College Chennai Tamil Nadu India School of Computing Science and Engineering VIT Bhopal University Madhya Pradesh India Department of Electronics and Communication Engineering B.V. Raju Institute of Technology Telangana India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

The cutting-edge telemedicine program presents a game-changing alternative for patients seeking ENT (ear, nose, and throat) consultations from a distant location. Utilizing the capabilities of Raspberry Pi devices, powerful artificial intelligence, and cloud computing, the system allows otoscopic tests to be performed without interruption while securely transmitting data to the cloud. On a web-based platform, interactive patient-professional consultations are made possible via real-time communication, which is made possible by WebRTC. Cloud services are very important because of their ability to provide scalable storage as well as AI-driven diagnostics for accurate evaluations. The system complies with the requirements for healthcare compliance, emphasizes security and privacy, and features encryption from beginning to finish. This integrated approach promises scalability, reliability, and advanced diagnostic capabilities, and it reshapes the landscape of remote ENT care with accessible and technologically advanced healthcare solutions. With a user-friendly interface for patients and a cloud-hosted application for healthcare professionals, this integrated approach provides patients with advanced healthcare solutions.

关键词： Cloud computing Privacy Telemedicine Scalability Nose Medical services Ear

来源：评论

学校读者我要写书评

暂无评论

Distinguishability-based genuine nonlocality with genuine multipartite entanglement

arXiv

引用

arXiv 2022年

作者： Xiong, Zong-Xing Li, Mao-Sheng Zheng, Zhu-Jun Li, Lvzhou Institute of Quantum Computing and Computer Theory School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China School of Mathematics South China University of Technology Guangzhou510640 China

A set of orthogonal multipartite quantum states is said to be distinguishability-based genuinely nonlocal (also genuinely nonlocal, for abbreviation) if the states are locally indistinguishable across any bipartition of the subsystems. This form of multipartite nonlocality, although more naturally arising than the recently popular "strong nonlocality" in the context of local distinguishability, receives much less attention. In this work, we study the distinguishability-based genuine nonlocality of a typical type of genuine multipartite entangled states — the d-dimensional GHZ states, featuring systems with local dimension not limited to 2. In the three-partite case, we find the existence of small genuinely nonlocal sets consisting of these states: we show that the cardinality can at least scale down to linear in the local dimension d, with the linear factor l = 1. Specifically, the method we use is semidefinite program and the GHZ states to construct these sets are special ones which we call "GHZ-lattices". This result might arguably suggest a significant gap between the strength of strong nonlocality and the distinguishability-based genuine nonlocality. Moreover, we put forward the notion of (s, n)-threshold distinguishability and utilizing a similar method, we successfully construct (2, 3)-threshold sets consisting of GHZ states in three-partite systems. © 2022, CC BY.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

Advancing HRM with AI Powered Recruitment Performance Management and Employee Engagement Using One Class SVMs

Advancing HRM with AI Powered Recruitment Performance Manage...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Rafiya Banu Ruchi Tripathi Saumya Sharma Loganathan Chenniappan K. Chandrasekaran Umanesan R Department of Commerce B. S. Abdur Rahman Crescent Institute of Science and Technology Chennai India Faculty of Management Studies SRM-IST Ghaziabad India Department of Management & Commerce The Northcap University Gurugram India Business Administration IBRI Sultanate of Oman Department of Mechanical Engineering K.S.R College of Engineering Tiruchengode India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

AI is making labour-intensive HRM operations like hiring, performance review, and employee engagement more efficient and effective. The incorporation of AI technology in HRM could change several sectors. Through efficient applicant sourcing, screening, and selection, AI-driven solutions simplify hiring processes and ensure fair and accurate picks. Performance management using AI-powered solutions provides data-driven feedback and customized development plans to align individual progress with organizational goals. Predictive analytics improve employee engagement by personalizing experiences and meeting needs. The method focuses on preprocessing and model training. Data are cleansed, ordinal and categorical variables encoded, scaling characteristics and engineering features applied, and dimensional homogeneity assured before processing. For model training, the simple and robust one-class SVM technique is used. One-class SVM model outperformed others with 95.28%. This method worked best compared to GAN and GRU models. AI could improve HRM by improving decision-making and offering data-driven solutions. The findings show that the proposed model outperforms current options, providing the framework for HRM AI applications.

关键词： Support vector machines Training Productivity Accuracy Uncertainty Reviews Artificial intelligence Integrated circuit modeling Predictive analytics Recruitment

来源：评论

学校读者我要写书评

暂无评论

Intelligent Inhalation Therapy for Cystic Fibrosis Using IoT and Machine Learning Solutions

Intelligent Inhalation Therapy for Cystic Fibrosis Using IoT...

引用

Sustainable Expert Systems (ICSES), International Conference on

作者： Chitra Sabapathy Ranganathan Arul Prasath A Nandhini R Kannan Shanmugam S. Velmurugan S. Srinivasan Mphasis Corporation Chennai Tamil Nadu India Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering Rajalakshmi Institute of Technology Chennai Tamil Nadu India Department of Gaming Technology School of Computing Science and Engineering VIT Bhopal University Bhopal Madhya Pradesh India Department of Electronics and Communication Engineering T.J.S. Engineering College Chennai Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

Optimal patients result in the long-term management of cystic fibrosis (CF) and need personalized treatment strategies due to the hereditary disorder's impact on respiratory problems. One potential approach to individualized CF treatment is intelligent inhalation therapy systems that combine machine learning (ML) algorithms with Internet of Things (IoT) sensors. To provide CF patients with a predictive modeling framework that can personalize their inhalation treatment using the Random Forest algorithm. The algorithm is designed to predict individual-level outcomes, including the potential of an exacerbation and the efficacy of therapy, by mining a large and varied dataset that includes patient demographics, lung function measurements, medication adherence records, environmental factors, and reports of symptoms. The Random Forest method was selected due to its capacity to manage diverse data types, detect intricate relationships between variables, and provide insights that can be understood. It shows that the Random Forest model effectively predicts important outcomes for CF care by training, validating, and evaluating it using real-world data from CF patients. Exacerbation risks and patient-specific therapy responses may be better understood by feature significance analysis, allowing for more targeted intervention approaches. The proposed predictive modeling framework will improve the efficiency and effectiveness of inhalation treatment for managing CF. Healthcare practitioners may enhance the management of CF via ML analytics and data collected through the IoT. This allows for delivering personalized treatment regimens, optimizing resource allocation, and better patient outcomes. Challenges include ensuring data accuracy, managing extensive datasets, sustaining real-time monitoring, optimizing algorithms, and ensuring system stability.

关键词： Machine learning algorithms Accuracy Lungs Medical treatment Predictive models Prediction algorithms Real-time systems Data models Internet of Things Random forests

来源：评论

学校读者我要写书评

暂无评论

Learning Multi-Modal Brain Tumor Segmentation from Privileged Semi-Paired MRI Images with Curriculum Disentanglement Learning

arXiv

引用

arXiv 2022年

作者： Liu, Zecheng Wei, Jia Li, Rui School of Computer Science and Engineering South China University of Technology Guangzhou China Golisano College of Computing and Information Sciences Rochester Institute of Technology RochesterNY United States

Due to the difficulties of obtaining multimodal paired images in clinical practice, recent studies propose to train brain tumor segmentation models with unpaired images and capture complementary information through modality translation. However, these models cannot fully exploit the complementary information from different modalities. In this work, we thus present a novel two-step (intra-modality and inter-modality) curriculum disentanglement learning framework to effectively utilize privileged semi-paired images, i.e. limited paired images that are only available in training, for brain tumor segmentation. Specifically, in the first step, we propose to conduct reconstruction and segmentation with augmented intra-modality style-consistent images. In the second step, the model jointly performs reconstruction, unsupervised/supervised translation, and segmentation for both unpaired and paired inter-modality images. A content consistency loss and a supervised translation loss are proposed to leverage complementary information from different modalities in this step. Through these two steps, our method effectively extracts modality-specific style codes describing the attenuation of tissue features and image contrast, and modality-invariant content codes containing anatomical and functional information from the input images. Experiments on three brain tumor segmentation tasks show that our model outperforms competing segmentation models based on unpaired images. Copyright © 2022, The Authors. All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

PR2: A Physics- and Photo-realistic Humanoid Testbed with Pilot Study in Competition

arXiv

引用

arXiv 2024年

作者： Liu, Hangxin Xie, Qi Zhang, Zeyu Yuan, Tao Leng, Xiaokun Sun, Lining Zhu, Song-Chun Zhang, Jingwen He, Zhicheng Su, Yao Beijing100080 China Institute for Artificial Intelligence School of Artificial Intelligence Peking University Beijing100871 China Department of Automation Tsinghua University Beijing100084 China Department of Computer Science Harbin Institute of Technology Harbin150001 China School of Mechatronics Engineering Harbin Institute of Technology Harbin150080 China Jiangsu Provincial Key Laboratory of Advanced Robotics School of Mechanical and Electric Engineering Soochow University Suzhou215000 China

This paper presents the development of a Physicsrealistic and Photo-realistic humanoid robot testbed, PR2, to facilitate collaborative research between Embodied Artificial Intelligence (Embodied AI) and robotics. PR2 offers high-quality scene rendering and robot dynamic simulation, enabling (i) the creation of diverse scenes using various digital assets, (ii) the integration of advanced perception or foundation models, and (iii) the implementation of planning and control algorithms for dynamic humanoid robot behaviors based on environmental feedback. The beta version of PR2 has been deployed for the simulation track of a nationwide full-size humanoid robot competition for college students, attracting 137 teams and over 400 participants within four months. This competition covered traditional tasks in bipedal walking, as well as novel challenges in loco-manipulation and language-instruction-based object search, marking a first for public college robotics competitions. A retrospective analysis of the competition suggests that future events should emphasize the integration of locomotion with manipulation and perception. By making the PR2 testbed publicly available at https://***/pr2-humanoid/PR2-Platform, we aim to further advance education and training in humanoid robotics. © 2024, CC BY.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

A Novel Malware Encrypted Traffic Detection Framework Based On Ensemble Learning 6

A Novel Malware Encrypted Traffic Detection Framework Based ...

引用

6th IEEE International Conference on Data science in Cyberspace, DSC 2021

作者： Zhao, Chuanyu Li, Shudong Wu, Xiaobo Han, Weihong Tian, Zhihong Chen, Maofei Cyberspace Institute Of Advanced Technology Guangzhou University Guangzhou China School Of Computer Science And Cyber Engineering Guangzhou University Guangzhou China China Telecom Corporation Limited Research Institute Guangzhou Park Guangzhou China

ISBN: (纸本)9781665418157

The number of malware attacks that use encrypted HTTP traffic to self-propagate or communicate has increased dramatically in recent years. Traditional network traffic detection methods for non-encrypted traffic are difficult to be applied to encrypted traffic detection. While encryption is good for protecting users' privacy, it also comes with a security risk: malicious traffic may hide in encrypted traffic, leading to a series of security problems. Since the encrypted payload cannot be directly observed and it is large, we need to combine domain knowledge and machine learning method to excavate the features hidden in malicious traffic, so as to realize automatic detection of malicious traffic. In this paper, we propose a malicious traffic detection framework based on ensemble learning using the encrypted traffic from real malware, including normal traffic generated by 3000 normal hosts and malicious traffic generated by 3000 malware-infected hosts, provided by DATACON2020 competition. Considering the complexity to decrypt traffic, we use statistical features and sequence features in both flow-level and in host-level perspectives to describe encrypted traffic. Then we build multiple classifiers according to heterogeneous features. Finally we do majority voting to get final result. We achieve 95.0% TPR and 8.4% FPR. © 2021 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition, CVPR 2023

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Institute for Ai Tsinghua University BNRist Center Thbi Lab Dept. of Comp. Sci. and Tech. China School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province China Saic Motor Ai Lab Zhongguancun Laboratory China

ISBN: (纸本)9798350301298

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. © 2023 IEEE.

关键词： Autonomous driving

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：