检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2026-2039页

作者： Wang, Mingjie Guo, Jianxiong Jia, Weijia BNU-HKBU United International College Guangdong Key Lab of AI and Multi-Modal Data Processing Department of Computer Science Zhuhai519087 China Beijing Normal University Advanced Institute of Natural Sciences Zhuhai519087 China BNU-HKBU United International College Guangdong Key Lab of AI and Multi-Modal Data Processing Zhuhai519087 China

Federated learning (FL) is a decentralized learning method used to train machine learning algorithms. In FL, a global model iteratively collects the parameters of local models without accessing their local data. However, a significant challenge in FL is handling the heterogeneity of local data distribution, which often results in a drifted global model that is difficult to converge. To address this issue, current methods employ different strategies, such as knowledge distillation, weighted model aggregation, and multitask learning. These approaches are referred to as asynchronous FL, as they align user models either locally or posthoc, where model drift has already occurred or has been underestimated. In this article, we propose an active and synchronous correlation approach to address the challenge of user heterogeneity in FL. Specifically, our approach aims to approximate FL as standard deep learning by actively and synchronously scheduling user learning pace in each round with a dynamic multiphase curriculum. A global curriculum is formed by an autoregressive autoencoder that integrates all user curricula on the server. This global curriculum is then divided into multiple phases and broadcast to users to measure and align the domain-agnostic learning pace. Empirical studies demonstrate that our approach outperforms existing asynchronous approaches in terms of generalization performance, even in the presence of severe user heterogeneity. © 2023 IEEE.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

MTMD: Multi-Scale Temporal Memory Learning and Efficient Debiasing Framework for Stock Trend Forecasting

引用

IEEE Transactions on Emerging Topics in Computational Intelligence 2025年第3期9卷 2151-2163页

作者： Wang, Mingjie Tian, Juanxi Zhang, Mingze Guo, Jianxiong Jia, Weijia BNU-HKBU United International College Guangdong Key Lab of Ai and Multi-Modal Data Processing Department of Computer Science Zhuhai519087 China Gonzaga University School of Engineering and Applied Sciences SpokaneWA99258 United States Beijing Normal University Advanced Institute of Natural Sciences Zhuhai519087 China BNU-HKBU United International College Guangdong Key Lab of Ai and Multi-Modal Data Processing Zhuhai519087 China

The endeavor of stock trend forecasting is principally focused on predicting the future trajectory of the stock market, utilizing either manual or technical methodologies to optimize profitability. Recent advancements in machine learning technologies have showcased their efficacy in discerning authentic profit signals within the realm of stock trend forecasting, predominantly employing temporal data derived from historical stock price patterns. Nevertheless, the inherently volatile and dynamic characteristics of the stock market render the learning and capture of multi-scale temporal dependencies and stable trading opportunities a formidable challenge. This predicament is primarily attributed to the difficulty in distinguishing real profit signal patterns amidst a plethora of mixed, noisy data. In response to these complexities, we propose a Multi-Scale Temporal Memory Learning and Efficient Debiasing (MTMD) model. This innovative approach encompasses the creation of a learnable embedding coupled with external attention, serving as a memory module through self-similarity. It aims to mitigate noise interference and bolster temporal consistency within the model. The MTMD model adeptly amalgamates comprehensive local data at each timestamp while concurrently focusing on salient historical patterns on a global scale. Furthermore, the incorporation of a graph network, tailored to assimilate global and local information, facilitates the adaptive fusion of heterogeneous multi-scale data. Rigorous ablation studies and experimental evaluations affirm that the MTMD model surpasses contemporary state-of-the-art methodologies by a substantial margin in benchmark datasets. © 2025 IEEE.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

AI for Space Operations: the next generation of Mission Operations for Earth Observation constellations 74

AI for Space Operations: the next generation of Mission Oper...

引用

74th International Astronautical Congress, IAC 2023

作者： Schandeler, Baptiste Lamothe, Matthieu Chouteau, Florient Future Programmes Department Airbus Defence and Space 31 rue des cosmonautes Toulouse31400 France Image and Mission Engineering Department Airbus Defence and Space 31 rue des cosmonautes Toulouse31400 France Computer Vision & Advanced Data Processing Department Airbus Defence and Space 31 rue des cosmonautes Toulouse31400 France

Earth Observation Satellite constellations are more and more requested by customers to fit their strategic needs. They offer the ability to collect large amounts of data from various places, from various sensors. They offer versatility, robustness and an undeniable strategic advantage of revisit. Classical way of operations, where every satellite, subsystems and the ground segment were operated by a team, does fit neither technically nor commercially for constellations. Artificial intelligence (AI) has proven its value in multiple applications. Automated mission operations, especially in multi-missions context, have a high impact in terms of efficiency where reduction of human interactions is foreseen: routine operations, monitoring, data processing and ground segment health. Airbus has already developed automated collision avoidance maneuver (CAM), automated mission plan uplink and advanced monitoring that already allow us to operate with a limited number of operators. AI-based image production and analysis is one of the latest developments Airbus has performed: change detection and Deepzoom are now available on the market. AI is set to play a major role in the automation of future EO systems, enabled by the significant advances in Machine Learning techniques of recent years. data-driven AI-based solutions can be developed to improve operations effectiveness. Multi-variable multi-subsystems analysis (based on neural networks) for time series can be used to predict future behaviors. Identifying a potential upcoming failure before it occurs and proposing preventive procedures to reduce the downtime is one of the leaps where the classical way of operations is outdated. The spacecraft can no longer be controlled individually by operators: the impact of on-board AI will drastically shake current CONOPS. Today, Airbus is working on artificial intelligence concepts for the next-gen EO constellations: AI on board and on ground to reach the lights-out center, where AI and a

关键词： Artificial Intelligence Constellations Earth Observation Machine Learning Satellite operations

来源：评论

学校读者我要写书评

暂无评论

Hybridization of One- and Two-Point Bandits Convex Optimization in Non-stationary Environments 24th

Hybridization of One- and Two-Point Bandits Convex Optimiz...

引用

24th International Conference on Algorithms and Architectures for Parallel processing, ICA3PP 2024

作者： Zeng, Gailun Guo, Jianxiong Advanced Institute of Natural Sciences Beijing Normal University Zhuhai China Hong Kong Baptist University Hong Kong Guangdong Key Lab of AI and Multi-modal Data Processing Department of Computer Science BNU-HKBU United International College Zhuhai China

ISBN: (纸本)9789819615278

Bandit Convex Optimization (BCO) is an imperative analysis framework when dealing with sequential decision-making problems. Considering to balance the computational cost and bounds of regrets, in this paper, we propose a hybridized algorithm of one- and two-point bandit convex models in non-stationary environments and use a more general performance measure dynamic regret, which records the cumulative difference between function loss and a feasible comparator sequence during the time horizon T. The path length of a comparator sequence PT reveals the non-stationarity of environments. Our proposed algorithm builds an upper bound of dynamic regret O((1+PT)1/2[β(λT)1/2+((1-λ)T)3/4]), where the parameter λ can dynamically adjust the bound guarantee to balance the computational cost in real applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Comparators (optical)

来源：评论

学校读者我要写书评

暂无评论

CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation

引用

International Journal of computer vision 2025年 1-20页

作者： Xie, Jinheng Deng, Songhe Hou, Xianxu Luo, Zhaochuan Shen, Linlin Huang, Yawen Zheng, Yefeng Shou, Mike Zheng Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Computer Science Wenzhou-Kean University Wenzhou325060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Show Lab National University of Singapore Singapore639798 Singapore School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou215400 China Jarvis Research Center Tencent YouTu Lab Shenzhen518703 China

While promising results have been achieved in weakly-supervised semantic segmentation (WSSS), limited supervision from image-level tags inevitably induces discriminative reliance and spurious relations between target classes and background regions. Thus, Class Activation Map (CAM) usually tends to activate discriminative object regions and falsely includes lots of class-related backgrounds. Without pixel-level supervisions, it could be very difficult to enlarge the foreground activation and suppress those false activation of background regions. In this paper, we propose a novel framework of Cross Language Image Matching with Automatic Context Discovery (CLIMS++), based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our framework is to introduce natural language supervision to activate more complete object regions and suppress class-related background regions in CAM. In particular, we design object, background region, and text label matching losses to guide the model to excite more reasonable object regions of each category. In addition, we propose to automatically find spurious relations between foreground categories and backgrounds, through which a background suppression loss is designed to suppress the activation of class-related backgrounds. The above designs enable the proposed CLIMS++ to generate a more complete and compact activation map for the target objects. Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 datasets show that our CLIMS++ significantly outperforms the previous state-of-the-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Offloading Control for Waste Sorting Based on Deep Q-Network 24th

Dynamic Offloading Control for Waste Sorting Based on Deep...

引用

24th International Conference on Algorithms and Architectures for Parallel processing, ICA3PP 2024

作者： Wang, Jing Wang, Xiaoyang Guo, Jianxiong Tang, Zhiqing Ding, Xingjian Wang, Tian Advanced Institute of Natural Sciences Beijing Normal University Zhuhai China Guangdong Key Lab of AI and Multi-modal Data Processing Department of Computer Science BNU-HKBU United International College Zhuhai China Faculty of Information Technology Beijing University of Technology Beijing China

ISBN: (纸本)9789819615278

With the increasing concern for environmental protection and resource optimization, efficient waste sorting has become a serious challenge today. In this paper, we propose a new offloading control problem that aims to solve waste sorting in wireless bin communication networks. Due to limited computational power, bins belonging to embedded devices rely on simple classification models with varying accuracy. In this scenario, consider a network of intelligent bins, each acting as an independent agent capable of deciding to offload an image to the edge server with a more accurate but resource-intensive model when the local classification is deemed inaccurate. Thus, Our goal is to find a lightweight online offloading policy that can achieve the best possible sorting accuracy while balancing transmission traffic. The method utilizes a Deep Q-network algorithm that enables each intelligent bin to make image-processing decisions autonomously. In the experiment, we validate the effectiveness of improving the performance of waste classification compared with existing flow control methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Distributed Resource Allocation Intelligent Waste Management Waste Sorting Wireless Communication Network

来源：评论

学校读者我要写书评

暂无评论

Boosting Performance and QoS for Concurrent GPU B+trees by Combining-Based Synchronization 23

Boosting Performance and QoS for Concurrent GPU B+trees by C...

引用

28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming, PPoPP 2023

作者： Zhang, Weihua Zhao, Chuanlei Peng, Lu Lin, Yuzhe Zhang, Fengzhe Lu, Yunping School of Computer Science Fudan University China Institute of Big Data Fudan University China State Key Laboratory of Mathematical Engineering and Advanced Computing China Parallel Processing Institute Fudan University China Department of Computer Science Tulane University United States

ISBN: (纸本)9798400700156

Concurrent B+trees have been widely used in many systems. With the scale of data requests increasing exponentially, the systems are facing tremendous performance pressure. GPU has shown its potential to accelerate concurrent B+trees performance. When many concurrent requests are processed, the conflicts should be detected and resolved. Prior methods guarantee the correctness of concurrent GPU B+trees through lock-based or software transactional memory (STM)-based approaches. However, these methods complicate the request processing logic, increase the number of memory accesses and bring execution path divergence. They lead to performance degradation and variance in response time increasing. Moreover, previous methods do not guarantee linearizability among concurrent requests. In this paper, we design a combined-based concurrency control framework, called Eirene, for GPU B+tree to reduce the overhead of conflict detection and resolution. First, a combining-based synchronization method is designed to combine and issue requests. It combines the requests with the same key, constructs their dependence, decides the issued request, and determines their return values. Since only one request for each key is issued, key conflicts are eliminated. Then, an optimistic STM method is used to reduce structure conflicts. The query and the update requests are partitioned into different kernels. For the update kernels, STM is involved only when the number of the retry reaches a threshold. Finally, a locality-aware warp reorganization optimization is proposed to improve memory behavior and reduce conflicts by exploiting the locality among requests. Evaluations on an NVIDIA A100 GPU show that Eirene is efficient (a throughput of 2.4 billion per second) and can guarantee linearizability. Compared to the state-of-the-art GPU B+tree, it can achieve a speedup of 7.43X and reduce the response time variance from 36% to 5%. © 2023 ACM.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

A Modified EXP3 in Adversarial Bandits with Multi-user Delayed Feedback 29th

A Modified EXP3 in Adversarial Bandits with Multi-user Del...

引用

29th International Computing and Combinatorics Conference, COCOON 2023

作者： Li, Yandi Guo, Jianxiong Advanced Institute of Natural Sciences Beijing Normal University Zhuhai519087 China Hong Kong Baptist University Hong Kong Guangdong Key Lab of AI and Multi-Modal Data Processing Department of Computer Science BNU-HKBU United International College Zhuhai519087 China

ISBN: (纸本)9783031491924

For the adversarial multi-armed bandit problem with delayed feedback, we consider that the delayed feedback results are from multiple users and are unrestricted on internal distribution. As the player picks an arm, feedback from multiple users may not be received instantly yet after an arbitrary delay of time which is unknown to the player in advance. For different users in a round, the delays in feedback have no latent correlation. Thus, we formulate an adversarial multi-armed bandit problem with multi-user delayed feedback and design a modified EXP3 algorithm named MUD-EXP3, which makes a decision at each round by considering the importance-weighted estimator of the received feedback from different users. On the premise of known terminal round index T, the number of users M, the number of arms N, and upper bound of delay dmax, we prove a regret of O(TM2lnN(Ne+4dmax)). © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Machine learning predicts long-term mortality after acute myocardial infarction using systolic time intervals and routinely collected clinical data

引用

Intelligent Medicine 2024年第3期4卷 170-176页

作者： Bijan Roudini Boshra Khajehpiri Hamid Abrishami Moghaddam Mohamad Forouzanfar Department of Systems Engineering School of Advanced TechnologyUniversity of QuebecMontrealCanada Machine Vision and Medical Image Processing(MVMIP)Laboratory Faculty of Electrical and Computer EngineeringK.N.Toosi University of TechnologyTehranIran Research Center of the Montreal University Institute of Geriatrics MontrealCanada

Background Precise estimation of current and future comorbidities of patients with cardiovascular disease is an important factor in prioritizing continuous physiological monitoring and new *** learning(ML)models have shown satisfactory performance in short-term mortality prediction in patients with heart disease,whereas their utility in long-term predictions is *** study aimed to investigate the performance of tree-based ML models on long-term mortality prediction and effect of two recently introduced biomarkers on long-term *** This study used publicly available data from the Collaboration Center of Health Information Appli-cation at the Ministry of Health and Welfare,Taiwan,*** collected data were from patients admitted to the cardiac care unit for acute myocardial infarction(AMI)between November 2003 and September *** collected and analyzed mortality data up to December *** records were used to gather demo-graphic and clinical data,including age,gender,body mass index,percutaneous coronary intervention status,and comorbidities such as hypertension,dyslipidemia,ST-segment elevation myocardial infarction,and non-ST-segment elevation myocardial *** the data,collected from 139 patients with AMI,from medical and demographic records as well as two recently introduced biomarkers,brachial pre-ejection period(bPEP)and brachial ejection time(bET),we investigated the performance of advanced ensemble tree-based ML algorithms(random forest,AdaBoost,and XGBoost)to predict all-cause mortality within 14 years.A nested cross-validation was performed to evaluate and compare the performance of our developed models precisely with that of the conventional logistic regression(LR)as the baseline *** The developed ML models achieved significantly better performance compared to the baseline LR(C-Statistic,0.80 for random forest,0.79 for AdaBoost,and 0.78 for XGBoost,vs.0.77 for LR)(PRF<0.001,PAdaBoost<0.001,a

关键词： Electrocardiogram Predication Mortality prediction Machine learning

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

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：