检索结果-内蒙古大学图书馆

3D Object Detection with Attention:Shell-Based Modeling

computer Systems science & engineering 2023年第7期46卷 537-550页

作者： Xiaorui Zhang Ziquan Zhao Wei Sun Qi Cui School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing210044China Department of Electrical and Computer Engineering University of WindsorWindsorN9B 3P4Canada

LIDAR point cloud-based 3D object detection aims to sense the surrounding environment by anchoring objects with the Bounding Box(BBox).However,under the three-dimensional space of autonomous driving scenes,the previous object detection methods,due to the pre-processing of the original LIDAR point cloud into voxels or pillars,lose the coordinate information of the original point cloud,slow detection speed,and gain inaccurate bounding box *** address the issues above,this study proposes a new two-stage network structure to extract point cloud features directly by PointNet++,which effectively preserves the original point cloud coordinate *** improve the detection accuracy,a shell-based modeling method is *** roughly determines which spherical shell the coordinates belong ***,the results are refined to ground truth,thereby narrowing the localization range and improving the detection *** improve the recall of 3D object detection with bounding boxes,this paper designs a self-attention module for 3D object detection with a skip connection *** of these features are highlighted by weighting them on the feature *** training,it makes the feature weights that are favorable for object detection get ***,the extracted features are more adapted to the object detection *** comparison experiments and ablation experiments conducted on the KITTI dataset verify the effectiveness of our proposed method in improving recall and precision.

关键词： 3D object detection autonomous driving point cloud shell-based modeling self-attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Smart Advertising Based on Customer Preferences and Manage the Supermarket 4

Smart Advertising Based on Customer Preferences and Manage t...

引用

4th International Conference on Advancements in Computing, ICAC 2022

作者： Eishan Dinuka, W.H.A. Wickramasinghe, A.Y.S.W. Weerasinghe, W.S.H. Karunaratne, K.P.G. Liyanapathirana, Chethana Rupasinghe, Lakmal Department of Computer Science and Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Information Technology Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Systems Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350398090

As a developing country, Sri Lanka needs to go along with cutting-edge technologies. In the beginning phase of this digital advertising, multiple advertisements were displayed on the users' feeds, including advertisements despite their preferences. This was a terrible user experience for the users. However, smart advertising based on customer preferences can manage the flow of advertisements on the feed as per the users' preferences. This same technique can be used in handling advertisements while shopping at supermarkets. These advertisements can be directed based on demographic characteristics like face and gender and previous customer transactions. Additionally, providing the nearest supermarket they can reach based on their current location. Queue management is the next most crucial facility that needs to be provided to a supermarket. However, the manual system of queue management is not effective. But with a modernized queue management system, overcrowded supermarkets can be managed effectively. This proposed system also considers providing a chatbot service to manage customer inquiries in a reliable strategy. In this system, we mainly used the Keras model called VGGFace for face detection, the Conventional Neural Network and Keras-based model for gender detection, the TensorFlow model called Single Shot MultiBox Detection MobileNet for queue and crowd detection, the Apriori algorithm base model for predicting the buying pattern, a Keras-based model for Artificial Intelligence chatbot and finally, google map Application Programming Interface for the nearest supermarket finding are models and technology. This system was developed to manage a supermarket properly. © 2022 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

FEAT: Towards Fast Environment-Adaptive Task Offloading and Power Allocation in MEC 42

FEAT: Towards Fast Environment-Adaptive Task Offloading and ...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Ren, Tao Hu, Zheyuan He, Hang Niu, Jianwei Liu, Xuefeng Institute of Software Chinese Academy of Sciences Laboratory for Internet Software Technologies Beijing China Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing China Zhongguancun Laboratory Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (纸本)9798350334142

Mobile edge computing (MEC) has been proposed to provide mobile devices with both satisfactory computing resources and latency. Key issues in MEC include task offloading and power allocation (TOPA), for which deep reinforcement learning (DRL) is becoming a popular methodology. However, most DRL-based TOPA approaches are typically developed in a certain environment, lacking the adaptability to unseen environments. Motivated by this, this paper proposes a Fast Environment-Adaptive TOPA (FEAT) approach that could adapt to unseen environments with little fine-tuning. Specifically, we first split MEC states into the internal state and environmental state. Then, based on these two types of states, we develop two main components of FEAT - a group of internal state-dependent TOPA meta-policies and an environmental state-embedded steerer. Meta-policies learn TOPA skills within the internal state space (allowing reusing meta-policies in different environments), while the steerer learns to choose appropriate meta-policies according to embedded environmental states. When encountering an unseen environment with the same internal state space, FEAT only needs to fine-tune the steerer using the newly embedded environmental state with few internal state explorations. Extensive experimental results on simulation and testbed demonstrate that FEAT outperforms the state-of-the-art by more than 16.4% in terms of fine-tuning speeds. © 2023 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Self-Guided Autoencoders for Unsupervised Change Detection in Heterogeneous Remote Sensing Images

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2458-2471页

作者： Shi, Jiao Wu, Tiancheng Kai Qin, Alex Lei, Yu Jeon, Gwanggil Northwestern Polytechnical University School of Electronics and Information Xi'an710129 China Northwestern Polytechnical University in Shenzhen Research and Development Institute Shenzhen518057 China Chongqing Innovation Center of Northwestern Polytechnical University Chongqing401135 China Swinburne University of Technology Department of Computer Science and Software Engineering HawthornVIC3122 Australia Incheon National University Department of Embedded Systems Engineering Incheon22012 Korea Republic of

To address the problem of enormous differences in two heterogeneous images, the traditional unsupervised frameworks are most normally realized by converting two images into a common domain with various auxiliary strategies, such as transformation and alignment, which requires extensive calculation and has difficulty balancing the training tasks. To achieve a concise framework, this article proposes self-guided autoencoders (SGAE) for unsupervised change detection (CD) in heterogeneous remote sensing images (RSIs). Unlike traditional methods that aim to narrow the differences of heterogeneous images to highlight the changed information, SGAE forces the flow of identification in formation generated in unlabeled data through self-guided iterations. First, initial unsupervised networks output an elementary change map that will be screened to obtain reliable pseudolabels. The selected pseudolabeled samples will be used as the input of a supervised network to obtain another change map. Then, multiple change maps will be fused to refine the confidence of pseudolabels again, obtaining new fused pseudolabeled samples for the self-guided network, which will be trained with pseudolabeled samples and unlabeled samples. Finally, the above operations will be repeated to continuously optimize the net, which helps itself to extract the discriminative features for classification in self-guided iterations. Experiments compared with several algorithms on four datasets demonstrate the effectiveness and robustness of our method, which can help unsupervised models improve discriminative feature extraction and classification performance with a more flexible learning method. © 2020 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Location Intelligence Based Smart E-Commerce Platform for Residential Real-Estate Industry 3

Location Intelligence Based Smart E-Commerce Platform for Re...

引用

3rd International Conference on Smart Electronics and Communication, ICOSEC 2022

作者： Balasooriya, Tharindu Kavishka, Lakindu Dananjana, Isini Yumna, Maryam Thelijjagoda, Samantha Attanayaka, Buddhima Marasinghe, Lanil Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Sliit Business School Malabe Sri Lanka Department of Computer Systems Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Sysco Labs Colombo Sri Lanka

ISBN: (数字)9781665497640

ISBN: (纸本)9781665497640

Making the decision to purchase or invest in real estate can be a very crucial process due to its high financial risk. The purchasing decision of residential real estate properties can be even more decisive because, apart from the financial risk, the choice of a property can have a great impact on the future lifestyle of the buyer. When considering residential real estate, one major factor to be considered is the property location. This research sought to determine the applicability of modern technologies such as location intelligence and machine learning in the development of an e-commerce system that may assist users in making optimal residential real estate location decisions. Third-party web APIs were used to obtain location data, and as a result of the study, methodologies were defined to convert location data into meaningful insights by using statistical methods like weighted sum and the analytical hierarchy process. The functionalities in the proposed system have been designed, considering the roles of both buyers and sellers in the real estate business. In the proposed system, the location quality index framework provides overall insights on the location, the personalized insights and alternative locations are generated via the personal preference-based suitability analyzer and the price prediction system provides the current and future price fluctuations. The usefulness of image processing technologies and machine learning for making the sellers' journey easier on a real estate platform has also been assessed. © 2022 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Three-Step Procedural Paradigm for Domain-Specific Social Media Slang Analytics 2

A Three-Step Procedural Paradigm for Domain-Specific Social ...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Sundaram, Aishwarya Subramaniam, Hema Ab Hamid, Siti Hafizah Nor, Azmawaty Mohamad Universiti Malaya Institute for Advanced Studies Kuala Lumpur Malaysia Universiti Malaya Faculty of Computer Science and Information Technology Department of Software Engineering Kuala Lumpur Malaysia Universiti Malaya Faculty of Education Department of Educational Psychology and Counselling Kuala Lumpur Malaysia

ISBN: (纸本)9798350384277

Social media is a crucial aspect of modern society, shaping global communication and information exchange. Social media slang encompasses informal language expressions, abbreviations, and unconventional words on these platforms, serving purposes such as concise communication and identity establishment. Data analytics from social media slang plays a vital role in providing real-time trends, enhancing sentiment analysis, and improving the accuracy of predictive models by capturing evolving linguistic trends. This study aims to address gaps in existing social media slang analytics by proposing a three-step process for extracting and validating domain-specific social media slang terms, specifically focusing on the domain of anxiety prediction in the context of mental health. The proposed approach involves the identification of relevant users, extraction of social media slang terms, and validation by subject matter experts. A pilot study is conducted in the domain of anxiety prediction, employing a self-prepared questionnaire and involving participants aged 13-14 from schools in Selangor, Malaysia. The pilot study identifies ten social media slang terms associated with anxiety, validated by subject matter experts who are licensed mental health practitioners. The slang terms exhibit varying prevalence levels among adolescents, with some terms absent from popular slang dictionaries like Urban Dictionary. The findings highlight the need for extracting slang terms from pertinent users and subject matter expert validation in incorporating social media slang into more appropriate predictive analytics. © 2024 IEEE.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

Enabling Communication-Efficient Federated Learning via Distributed Compressed Sensing 42

Enabling Communication-Efficient Federated Learning via Dist...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Guan, Yixuan Liu, Xuefeng Ren, Tao Niu, Jianwei Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing China Zhongguancun Laboratory Beijing China Chinese Academy of Sciences Laboratory for Internet Software Technologies Institute of Software Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (纸本)9798350334142

Federated learning (FL) trains a shared global model by periodically aggregating gradients from local devices. Communication overhead becomes a principal bottleneck in FL since participating devices usually suffer from limited bandwidth and unreliable connections in uplink transmission. To address this problem, the gradient compression methods based on compressed sensing (CS) theory have been put forward recently. However, most existing CS-based works compress gradients independently, ignoring the gradient correlations between participants or adjacent communication rounds, which constrains the achievement of higher compression rates. In view of the above observation, we propose a novel gradient compression scheme named FedDCS, guided by distributed compressed sensing (DCS) theory. Following the design philosophy of separate encoding and joint decoding in DCS, FedDCS compresses gradients for participants in each round separately while reconstructing them at the central server jointly via fully exploiting correlated gradients from the previous round, which are known as side information (SI). Benefiting from this design, reconstruction performance is significantly improved with fewer decoding errors also iterations under the identical compression rate, and the total uploading bits to achieve model convergence are considerably reduced. Theoretical analysis and extensive experiments conducted on MNIST and Fashion-MNIST both verify the effectiveness of our approach. © 2023 IEEE.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Underwater image color correction via global and local two-step optimization

引用

Pattern Recognition Letters 2025年 196卷 38-44页

作者： Baiqiang Yu Ling Zhou Wenqiang Yu Peixian Zhuang Weidong Zhang School of Information Engineering Henan Institute of Science and Technology Xinxiang 453003 China School of Computer and Software Nanyang Institute of Technology Nanyang 473000 China School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing 100084 China School of Electrical and Information Engineering Zhengzhou University Zhengzhou 450001 China

Underwater images usually suffer from quality degradation due to light absorption and scattering, leading to color distortion, blurred details, and low contrast. To address these challenges, we propose a global and local two-step optimization method (GLTO). Specifically, we first analyze the statistical features of natural images in the CIELab color space. Meanwhile, we design a heuristic global optimization strategy that minimizes the feature differences between underwater and natural images to restore the color and luminance of the raw image. We develop a local optimization strategy based on luminance information, which uses guided filtering to decompose the luminance channel into large-scale and small-scale high-frequency images and weighted fusion of them to obtain a detail-enhanced luminance channel. Finally, we leverage the local illumination intensity of the image captured by the luminance channel to adjust the local color distortion. Extensive experimental evaluations have demonstrated the superiority of our proposed GLTO method in underwater image preprocessing, which substantially enhances the performance of subsequent image enhancement. The project can be found at https://***/yubaiqiang/GLTO .

关键词： Color correction Luminance information Statistical features Underwater image preprocessing

来源：评论

学校读者我要写书评

暂无评论

Generating Targeted Universal Adversarial Perturbation against Automatic Speech Recognition via Phoneme Tailoring

Generating Targeted Universal Adversarial Perturbation again...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Yujun Chen, Yanqu Wang, Jiakai Hu, Jin Tao, Renshuai Liu, Xianglong State Key Laboratory of Complex & Critical Software Environment Beihang University China School of Computer Science and Engineering Beihang University China College of Computer Science Beijing University of Technology China Zhongguancun Laboratory China School of Computer and Information Technology Beijing Jiaotong University China Institute of Data Space Hefei Comprehensive National Science Center China

ISBN: (纸本)9798350368741

There is a growing concern about adversarial attacks against automatic speech recognition (ASR) systems. Although research into targeted universal adversarial examples (AEs) has progressed, current methods are constrained by inefficient exploitation of audio features, demonstrating insufficient attack ability and robustness in the physical world. To solve this problem, we propose a phoneme-tailored attack (PTA) to improve the quality of the generated AEs. Specifically, to improve attack ability, we propose a Diverse Audio Composition Enrichment method, which enhances the utilization of audio features through phoneme-level slicing and recombination. To adapt AEs to complex environments, we propose a Natural Noise Pattern Guidance method to align AEs with natural noise patterns to improve their robustness. Experiments show that our method achieves an average accuracy of more than 72.34% and 98% with and without a norm constraint, and also demonstrates excellent performance in terms of generalization across datasets and resilience to MP3 compression. © 2025 IEEE.

关键词： Automatic speech recognition natural noise pattern phoneme-level targeted universal adversarial examples

来源：评论

学校读者我要写书评

暂无评论

Advancing Blackboard Framework: Responsive Trigger Mechanisms and Dynamic Feasibility Conditions for Optimal Knowledge Source Selection 19

Advancing Blackboard Framework: Responsive Trigger Mechanism...

引用

19th International Conference on Ubiquitous information Management and Communication, IMCOM 2025

作者： Muhd Mukhtar, Hana Munira Husin, Husna Sarirah Ismail, Suriana Rahmat, Azizah Ismail, Roslan Software Engineering Section Malaysian Institute of Information Technology Universiti Kuala Lumpur Kuala Lumpur Malaysia School of Computer Science Taylor’s University Kuala Lumpur Malaysia Centre of Innovative Digital Education & Emerging Technology Universiti Kuala Lumpur Kuala Lumpur Malaysia

ISBN: (纸本)9798331507817

Expert systems (ES) rely heavily on effective control mechanisms to navigate complex problem-solving tasks. These mechanisms govern how ES utilizes knowledge and data to make decisions and execute actions. Optimizing these mechanisms, or addressing the "control problem," remains a central challenge. Blackboard architectures, with their separation of knowledge and control processes, offer a promising approach. This study introduces an improved control mechanism for blackboard architectures. It focuses on a critical aspect—trigger mechanisms and feasible conditions—for optimal knowledge source selection to participate in the problem-solving process. By leveraging these features, this study aims to enhance decision-making and problem-solving capabilities within complex domains. This paper focuses on the technical details of exploring how it manages the flow of rule activation and execution throughout the problem-solving process. © 2025 IEEE.

关键词： Expert systems

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：