检索结果-内蒙古大学图书馆

4th International Informatics and Software Engineering Conference, IISEC 2023

作者： Ouared, Abdelkader Benali, Ahmed Ala Eddine Siabdelhadi, Ahmed University of Tiaret Department of Computer Science Tiaret Algeria University of Salento Innovation Engineering Department Lecce Italy Amar Telidji University Computer Science and Mathematics Laboratory Laghouat Algeria

ISBN: (纸本)9798350318036

Database deployment automation involves dealing with the diversity of deployment platforms and the panoply of options to improve the efficiency of query workload. Designers must compare different scenarios and alternatives to find a good physical configuration. This requires hardware experimentation on a target platform or a simulation during the physical design phase. We aim to provide a solution that allows designers to reason up the causality of a given choice at the level of conceptual design and realize the selection of a physical configuration in a transparent way for the designers. In order to tackle this problem, we propose an approach based on goaloriented modeling which helps database designers to automatize and ease the traditional workflow dedicated to choosing an appropriate physical configuration. This latter captures a physical design vocabulary at a higher level of abstraction in order to focus on requirement user and application constraints and not on low level implementation details. Our Goal Model with its generator quickly produces the script related to the database materialization and speeds up the database creation process. We demonstrate the feasibility of our approach presenting a prototype tool. © 2023 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

TapFinger: Task Placement and Fine-Grained Resource Allocation for Edge Machine Learning 42

TapFinger: Task Placement and Fine-Grained Resource Allocati...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Li, Yihong Zeng, Tianyu Zhang, Xiaoxi Duan, Jingpu Wu, Chuan Sun Yat-sen University School of Computer Science and Engineering China Peng Cheng Laboratory Department of Communications China The University of Hong Kong Department of Computer Science Hong Kong

ISBN: (纸本)9798350334142

Machine learning (ML) tasks are one of the major workloads in today's edge computing networks. Existing edge-cloud schedulers allocate the requested amounts of resources to each task, falling short of best utilizing the limited edge resources flexibly for ML task performance optimization. This paper proposes TapFinger, a distributed scheduler that minimizes the total completion time of ML tasks in a multi-cluster edge network, through co-optimizing task placement and fine-grained multi-resource allocation. To learn the tasks' uncertain resource sensitivity and enable distributed online scheduling, we adopt multi-agent reinforcement learning (MARL), and propose several techniques to make it efficient for our ML-task resource allocation. First, TapFinger uses a heterogeneous graph attention network as the MARL backbone to abstract inter-related state features into more learnable environmental patterns. Second, the actor network is augmented through a tailored task selection phase, which decomposes the actions and encodes the optimization constraints. Third, to mitigate decision conflicts among agents, we novelly combine Bayes' theorem and masking schemes to facilitate our MARL model training. Extensive experiments using synthetic and test-bed ML task traces show that TapFinger can achieve up to 28.6% reduction in the average task completion time and improve resource efficiency as compared to state-of-the- art resource schedulers. © 2023 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

InGaPχ^((2))integrated photonics platform for broadband,ultra-efficient nonlinear conversion and entangled photon generation

引用

Light(science & Applications) 2024年第12期13卷 3090-3098页

作者： Joshua Akin Yunlei Zhao Yuvraj Misra A.K.M.Naziul Haque Kejie Fang Holonyak Micro and Nanotechnology Laboratory and Department of Electrical and Computer Engineering University of Illinois at Urbana-ChampaignUrbanaIL 61801USA Illinois Quantum Information Science and Technology Center University of Illinois at Urbana-ChampaignUrbanaIL 61801USA

Nonlinear optics plays an important role in many areas of science and *** advance of nonlinear optics is empowered by the discovery and utilization of materials with growing optical *** we demonstrate an indium gallium phosphide(InGaP)integrated photonics platform for broadband,ultra-efficient second-order nonlinear *** InGaP nanophotonic waveguide enables second-harmonic generation with a normalized efficiency of 128,000%/W/cm^(2)at 1.55μm pump wavelength,nearly two orders of magnitude higher than the state of the art in the telecommunication C ***,we realize an ultra-bright,broadband time-energy entangled photon source with a pair generation rate of 97 GHz/mW and a bandwidth of 115 nm centered at the telecommunication C *** InGaP entangled photon source shows high coincidence-to-accidental counts ratio CAR>10^(4)and two-photon interference visibility>98%.The InGaP second-order nonlinear photonics platform will have wide-ranging implications for non-classical light generation,optical signal processing,and quantum networking.

关键词： nonlinear optics coincidence

来源：评论

学校读者我要写书评

暂无评论

AutoML for Explainable Anomaly Detection (XAD)

AutoML for Explainable Anomaly Detection (XAD)

引用

The Provenance of Elegance in Computation - Essays Dedicated to Val Tannen 2024

作者： Myrtakis, Nikolaos Tsamardinos, Ioannis Christophides, Vassilis Department of Computer Science University of Crete Heraklion Greece ETIS Laboratory CY Cergy Paris Université ENSEA France

ISBN: (纸本)9783959773201

Numerous algorithms have been proposed for detecting anomalies (outliers, novelties) in an unsupervised manner. Unfortunately, it is not trivial, in general, to understand why a given sample (record) is labelled as an anomaly and thus diagnose its root causes. We propose the following reduced-dimensionality, surrogate model approach to explain detector decisions: approximate the detection model with another one that employs only a small subset of features. Subsequently, samples can be visualized in this low-dimensionality space for human understanding. To this end, we develop PROTEUS, an AutoML pipeline to produce the surrogate model, specifically designed for feature selection on imbalanced datasets. The PROTEUS surrogate model can not only explain the training data, but also the out-of-sample (unseen) data. In other words, PROTEUS produces predictive explanations by approximating the decision surface of an unsupervised detector. PROTEUS is designed to return an accurate estimate of out-of-sample predictive performance to serve as a metric of the quality of the approximation. Computational experiments confirm the efficacy of PROTEUS to produce predictive explanations for different families of detectors and to reliably estimate their predictive performance in unseen data. Unlike several ad-hoc feature importance methods, PROTEUS is robust to high-dimensional data. © Nikolaos Myrtakis, Ioannis Tsamardinos, and Vassilis Christophides;licensed under Creative Commons License CC-BY 4.0.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Seeing Through the Lies: A Vision Transformer-Based Solution 3rd

Seeing Through the Lies: A Vision Transformer-Based Solution

引用

3rd International Conference on Artificial-Business Analytics, Quantum and Machine Learning: Trends, Perspectives, and Prospects, Com-IT-Con 2023

作者： Rasool, Aale Katarya, Rahul Big Data Analytics and Web Intelligence Laboratory Department of Computer Science Delhi Technological University New Delhi India

ISBN: (纸本)9789819725076

Deepfake technology has become increasingly sophisticated and poses a growing threat to society, as it can be used to create convincing fake videos for malicious purposes. Therefore, detecting deepfakes has become crucial to ensure the authenticity of visual content. This paper proposes a novel deepfake detection approach that utilizes InceptionResNetV2 for feature extraction and Vision Transformer (ViT) with Nyström Attention mechanism for classification. Our model achieves high accuracy, AUC, precision, and recall on the CelebDFv2 dataset and outperforms state-of-the-art techniques like EfficientNet, XceptionNet, and ResNet. We also perform evaluations on the CelebDFv1 and DFDC datasets. Furthermore, we conduct a comprehensive literature survey to highlight the existing research in deepfake detection. We provide a roadmap for future work in this field, highlighting potential research directions that can further improve the effectiveness and applicability of deepfake detection models. The proposed model shows great potential for real-world applications, and the suggested future work can help to address some of the remaining challenges in this area. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Multiscale Optimisation Algorithm for Shape and Material Reconstruction from a Single X-ray Image 24

A Multiscale Optimisation Algorithm for Shape and Material R...

引用

7th International Conference on Image and graphics Processing, ICIGP 2024

作者： Westmacott, Henry Ivrissimtzis, Ioannis Weinzierl, Tobias Department of Computer Science Durham University Durham United Kingdom Mrc Laboratory of Molecular Biology Cambridge United Kingdom

ISBN: (纸本)9798400716720

We produce thickness and bone to soft tissue ratio estimations from a single, 2D medical X-ray image. For this, we simulate the scattering of the rays through a model of the object and embed this simulation into an optimiser which iteratively adjusts the model to match the X-ray simulation to the observed X-ray image. Utilising a combination of different techniques, first, a CNN-based image segmentation serves as a regularisation term to the underlying cost function to guide the descent, while domain knowledge about physical parameter correlations is injected by additional penalty terms. Next, the optimiser is embedded into a multilevel framework which, similar to multi-grid's philosophy, successively improves the model on varying resolutions while individual resolutions focus on particular terms of the cost function. Initial results suggest that we can obtain meaningful thickness and material estimations. © 2024 Owner/Author.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Feature Embedding Representation for Unsupervised Speaker Diarization in Telephone Calls 3rd

Feature Embedding Representation for Unsupervised Speaker Di...

引用

3rd International Conference on Intelligent Systems and Pattern Recognition, ISPR 2023

作者： Hamouda, Meriem Bahi, Halima LISCO Laboratory Badji Mokhtar University Annaba Algeria Computer Science Department Badji Mokhtar University Annaba Algeria

ISBN: (纸本)9783031463341

Speaker diarization aims to segment an audio recording, where different speakers are involved, into speech segments based on the speaker's identity. This study proposes a feature embedding representation for unsupervised speaker diarization in case of telephone conversations. First, the speech waveform is segmented into speech and non-speech segments using a voice activity detection algorithm. Then, a deep autoencoder performs feature embedding representation of the speech segments which are fed to the K-means algorithm to perform the clustering. Indeed, in the case of telephone calls speech data is often unequally shared between the two speakers, and an accurate feature representation helps to overcome limitations related to the varying width across clusters of the K-means algorithm. Experiments carried out on the CALLHOME dataset show the positive impact of the embedding representation in terms of Diarization Error Rate (DER) with an improvement of about 56%. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Efficiently Enumerating All Spanning Trees of a Plane 3-Tree: (Extended Abstract) 13th

Efficiently Enumerating All Spanning Trees of a Plane 3-Tr...

引用

13th International Symposium on Algorithms and Complexity, CIAC 2023

作者： Yanhaona, Muhammad Nur Nomaan, Asswad Sarker Rahman, Md. Saidur Department of Computer Science and Engineering BRAC University Dhaka Bangladesh Graph Drawing and Information Visualization Laboratory Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh

ISBN: (纸本)9783031304477

A spanning tree T of a connected, undirected graph G is an acyclic subgraph having all vertices and a minimal number of edges of G connecting those vertices. Enumeration of all possible spanning trees of undirected graphs is a well-studied problem. Solutions exist for enumeration for both weighted and unweighted graphs. However, these solutions are either space or time efficient. In this paper, we give an algorithm for enumerating all spanning trees in a plane 3-tree that is optimal in both time and space. Our algorithm exploits the structure of a plane 3-tree for a conceptually simpler alternative to existing general-purpose algorithms and takes time and space, where the given graph has n vertices, m edges, and spanning trees. This is a substantial improvement in both time and space complexity compared to the best-known algorithms for general graphs. We also propose a parallel algorithm for enumerating spanning trees of a plane 3-tree that has (formula presented) space complexities for p parallel processors. This second algorithm is useful when storing the spanning trees is important. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Undirected graphs

来源：评论

学校读者我要写书评

暂无评论

CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns 38

CycleNet: Enhancing Time Series Forecasting through Modeling...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Lin, Shengsheng Lin, Weiwei Hu, Xinyi Wu, Wentai Mo, Ruichao Zhong, Haocheng School of Computer Science and Engineering South China University of Technology China Pengcheng Laboratory China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong College of Information Science and Technology Jinan University China

The stable periodic patterns present in time series data serve as the foundation for conducting long-horizon forecasts. In this paper, we pioneer the exploration of explicitly modeling this periodicity to enhance the performance of models in long-term time series forecasting (LTSF) tasks. Specifically, we introduce the Residual Cycle Forecasting (RCF) technique, which utilizes learnable recurrent cycles to model the inherent periodic patterns within sequences, and then performs predictions on the residual components of the modeled cycles. Combining RCF with a Linear layer or a shallow MLP forms the simple yet powerful method proposed in this paper, called CycleNet. CycleNet achieves state-of-the-art prediction accuracy in multiple domains including electricity, weather, and energy, while offering significant efficiency advantages by reducing over 90% of the required parameter quantity. Furthermore, as a novel plug-and-play technique, the RCF can also significantly improve the prediction accuracy of existing models, including PatchTST and iTransformer. The source code is available at: https://***/ACAT-SCUT/CycleNet. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Method for Revealing Implicit Emphasized Criteria for Decision Makers on Social Issues 13

A Method for Revealing Implicit Emphasized Criteria for Deci...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Ito, Toshio Matsuzoe, Shizuko Iwahashi, Tadashi Yamaoka, Hisatoshi Ueki, Miwa Nagakane, Kota Morozumi, Hideaki Ikeda, Koki Ono, Isao Converging Technologies Laboratory Fujitsu Limited Kawasaki Japan Tokyo Institute of Technology Department of Computer Science Yokohama Japan

ISBN: (纸本)9798350308365

Social issues are complex, and solving them from a single perspective has other negative effects. We set up various Key Performance Indicators (KPIs), in which balanced measures need to be implemented to achieve KPIs. However, it is not easy to find an effective measure that considers the values of each decision maker because the emphasized criteria for the decision maker may not be clear. Furthermore, in addition to the best per-spective, the decision maker may consider multiple perspectives, such as the next best perspective. In this paper, we propose a method for revealing implicit emphasized criteria for the decision maker on social issues, visualizing multiple perspectives such as the best perspective and the next best perspective of the decision maker, and output multiple perspectives. After the decision maker confirms the effect and influence of the measure, the proposed method generates a distribution, defined as a Goodness distribution, that indicates whether the measure is good or bad. Thus using the Goodness distribution, the method reveals implicit emphasized criteria for the decision maker, visualizes multiple important perspectives for the decision maker, and presents the effective measure. © 2024 IEEE.

关键词： Multiobjective optimization

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：