检索结果-内蒙古大学图书馆

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Vaishnavi, Vakada G. Sai Sree Bhowmik, Biswajit National Institute of Technology Karnataka Ishwarchandra Vidyasagar Ait Lab Brics Laboratory Department of Computer Science and Engineering Mangalore Surathkal India

ISBN: (纸本)9798350384369

Neuromorphic computing is a cutting-edge field of research that focuses on designing and developing computer systems and hardware architectures inspired by the structure and functioning of the human brain. The main objective of neuromorphic computing is to create computational systems that imitate the parallel processing, learning, and energy efficiency observed in biological neural networks. Two essential tasks in the analysis of brain data from extracellular recordings are spike sorting and event detection. Spike sorting involves identifying and categorizing discrete neural spikes, while event detection focuses on recognizing specific patterns or occurrences within the spiking activity of neuromorphic networks. Typically, each neuron generates spikes with a characteristic shape, and these clusters correspond to the activity of different neurons. Here, the outcome of spike sorting is the identification of which spike corresponds to which neuron. In-depth analysis of the spike sorting and event detection which are two critical processes in interpreting the intricate neuronal activity that underpins brain function are provided. © 2024 IEEE.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

An Incremental Multi-Level, Multi-Scale Approach to Assessment of Multifidelity HPC Systems

An Incremental Multi-Level, Multi-Scale Approach to Assessme...

引用

2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024

作者： Shilpika, Shilpika Lusch, Bethany Vishwanath, Venkatram Papka, Michael E. Argonne National Laboratory Argonne Leadership Computing Facility United States Department of Computer Science University of Illinois Chicago United States

ISBN: (纸本)9798350355543

With the growing complexity in architecture and the size of large-scale computing systems, monitoring and analyzing system behavior and events has become daunting. Monitoring data amounting to terabytes per day are collected by sensors housed in these massive systems at multiple fidelity levels and varying temporal resolutions. In this work, we develop an incremental version of multiresolution dynamic mode decomposition (mrDMD), which converts high-dimensional data to spatial-temporal patterns at varied frequency ranges. Our incremental implementation of the mrDMD algorithm (I-mrDMD) promptly reveals valuable information in the massive environment log dataset, which is then visually aligned with the processed hardware and job log datasets through our generalizable rack visualization using D3 visualization integrated into the Jupyter Notebook interface. We demonstrate the efficacy of our approach with two use scenarios on a real-world dataset from a Cray XC40 supercomputer, Theta. © 2024 IEEE.

关键词： Dynamic mode decomposition high performance computing incremental analysis mrDMD online analysis scalability visualization

来源：评论

学校读者我要写书评

暂无评论

Recognition Performance Variation Across Demographic Groups Through the Eyes of Explainable Face Recognition

Recognition Performance Variation Across Demographic Groups ...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Marco Huber Anh Thi Luu Naser Damer Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

Face recognition systems are susceptible to differences in performance across demographic or non-demographic groups. However, the understanding of the behavior of face recognition models given such biases is still very limited and based mainly on observing model performance indicators when training/testing data is varied. On the other hand, very recently, face recognition explainability has gained increasing attention enabling the spatial explanation of face matching processes between two face images. This overcame the inapplicability of existing visual explainability methods to explain face matching decisions as they are designed for pure classification tasks. In this paper, and for the first time, we investigate the inner behavior of face recognition models with respect to bias using face recognition explainability tools. Using two state-of-the-art explainability tools, five models with different bias patterns, and a set of visualization tools, our investigation led to a set of interesting observations. This included noticing the tendency of more biased models to have more distributed attention on the facial image in comparison to focusing on the main facial features for the less biased models, all when considering the most discriminated demographic group.

关键词： Visualization Face recognition Focusing Gesture recognition Data models Task analysis Facial features

来源：评论

学校读者我要写书评

暂无评论

Extracting sequential frequent itemsets from probabilistic sequences database

引用

International Journal of Information Technology (Singapore) 2023年第5期15卷 2509-2515页

作者： Seddiki, Imane Nouioua, Farid Barkat, Abdelbasset Computer Science Department Mouhamed El Bachir El Ibrahimi University Bordj Bou Arreridj El Anceur 34000 Algeria Computer Science Department Laboratory of Informatics and its Applications (LIAM) University of M’sila M’sila 28000 Algeria

computers now handle large amounts of data, leading to the emergence of data mining as a science to extract useful information from this data. Frequent itemset mining is a popular technique used to discover relationships between items in big data. However, in real-life scenarios, data may be incomplete or uncertain, posing a challenge for frequent itemset mining. This paper proposes a novel approach for mining sequential frequent itemsets from uncertain sequence databases. The approach comprises two main parts: extracting a set of probabilistic frequent itemsets, and filtering this set using the sequential information in the data. At the end of the paper, we provide a comparison with an existing method to further demonstrate the value of our approach. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Data mining Frequent Itemset Probabilistic database Sequences database Uncertain

来源：评论

学校读者我要写书评

暂无评论

Beyond Spatial Explanations: Explainable Face Recognition in the Frequency Domain

arXiv

引用

arXiv 2024年

作者： Huber, Marco Damer, Naser Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany

The need for more transparent face recognition (FR), along with other visual-based decision-making systems has recently attracted more attention in research, society, and industry. The reasons why two face images are matched or not matched by a deep learning-based face recognition system are not obvious due to the high number of parameters and the complexity of the models. However, it is important for users, operators, and developers to ensure trust and accountability of the system and to analyze drawbacks such as biased behavior. While many previous works use spatial semantic maps to highlight the regions that have a significant influence on the decision of the face recognition system, frequency components which are also considered by CNNs, are neglected. In this work, we take a step forward and investigate explainable face recognition in the unexplored frequency domain. This makes this work the first to propose explainability of verification-based decisions in the frequency domain, thus explaining the relative influence of the frequency components of each input toward the obtained outcome. To achieve this, we manipulate face images in the spatial frequency domain and investigate the impact on verification outcomes. In extensive quantitative experiments, along with investigating two special scenarios cases, cross-resolution FR and morphing attacks (the latter in supplementary material), we observe the applicability of our proposed frequency-based explanations. © 2024, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A European Project on AI-based Robotics 13

A European Project on AI-based Robotics

引用

13th IEEE International Conference on Teaching, Assessment and Learning for Engineering, TALE 2024

作者： Dramnesc, Isabela Abraham, Erika Jebelean, Tudor Fachantidis, Nikolaos Kusper, Gabor Stratulat, Sorin West University of Timişoara Department of Computer Science Romania Rwth Aachen University Department of Computer Science Aachen Germany West University of Timişoara Icam Romania University of Macedonia Lires Laboratory Thessaloniki Greece Eszterházy Károly Catholic University Department of Computer Science Eger Hungary Université de Lorraine Cnrs Loria MetzF-57000 France

ISBN: (纸本)9798350376234

We introduce the project Artificial Intelligence based Robotics (AiRobo), a partnership of universities from France, Germany, Greece, Hungary, and Romania. AiRobo's aim is to significantly raise the level of competence and skills of academic staff in the field of artificial intelligence (AI) based robotics, thereby also increasing the attractivity and reputation of the related departments at the partner universities. We further address the European priority in national contexts regarding inclusion in higher education, covering social inclusion and outreach to people with less opportunities, e.g. people with disabilities or with migrant background. The project partners will collaboratively write a comprehensive book on AI-based robotics, provide tools and video tutorials to support the construction and analysis of robotic systems, develop robotic applications in various fields of high interest to the industry, implement trainings for academic staff of the partners, organize an international summer school and an international conference, and disseminate the project results through various *** outcomes of the project will include the training of 25 academic staff from partner universities in teaching AI-based robotic courses, a comprehensive set of teaching materials including the above-mentioned book, 7 robotic applications in different fields, tools and video tutorials, as well as scientific publications. © 2024 IEEE.

关键词： Personnel training

来源：评论

学校读者我要写书评

暂无评论

A Geometric Distortion Solution Specifically for Historical Observations and its Implementation

引用

Research in Astronomy and Astrophysics 2024年第11期24卷 85-94页

作者： F.R.Lin Q.Y.Peng Z.J.Zheng B.F.Guo School of Software Jiangxi Normal UniversityNanchang 330022China Sino-French Joint Laboratory for Astrometry Dynamics and Space ScienceJinan UniversityGuangzhou 510632China Department of Computer Science Jinan UniversityGuangzhou 510632China Guangdong Ocean University Zhanjiang 524000China

Geometric distortion(GD)critically constrains the precision of *** well-established methods to correct GD requires calibration observations,which can only be obtained using a special dithering strategy during the observation ***,this special observation mode is not often used,especially for historical observations before those GD correction methods were *** a result,some telescopes have no GD calibration observations for a long period,making it impossible to accurately determine the GD *** limits the value of the telescope observations in certain astrometric scenarios,such as using historical observations of moving targets in the solar system to improve their *** investigated a method for handling GD that does not rely on the calibration *** this advantage,it can be used to solve the GD models of telescopes which were intractable in the *** method was implemented in Python and released on *** was then applied to solve GD in the observations taken with the 1 m and 2.4 m telescopes at Yunnan *** resulting GD models were compared with those obtained using well-established methods to demonstrate the ***,the method was applied in the reduction of observations for two targets,the moon of Jupiter(Himalia)and binary GSC 2038-0293,to show its *** GD correction,the astrometric results for both targets show ***,the mean residual between the observed and computed position(O-C)for binary GSC 2038-0293 decreased from 36 to 5 mas.

关键词： astrometry-methods data analysis-techniques image processing

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Ensemble Deep Learning Model Technique for Breast Cancer Classification 2

Blockchain-Based Ensemble Deep Learning Model Technique for ...

引用

2nd International Conference on Computing and Data Analytics, ICCDA 2024

作者： Rahal, Hakima Rym Slatnia, Sihem Kazar, Okba Harous, Saad University of Mohammed Khider Linfi Laboratory Computer Science Department Biskra Algeria College of Arts Sciences & Information Technology University of Kalba Sharjah United Arab Emirates College of Computing and Informatics University of Sharjah Department of Computer Science Sharjah United Arab Emirates

ISBN: (纸本)9798331542573

Breast cancer is a condition brought on by the uncontrollable growth and multiplication of aberrant cells in the breast tissue. The misdiagnosis of breast cancer can result in needless or delayed therapies, mental and physical health, increased anxiety and stress, and decreased survival rates for patients. Also, the exchange of healthcare data is difficult to secure due to strict privacy laws, online threats, and the possibility of human error. Blockchain technology can enhance the security and privacy of patient data, give patients greater control over their health data, and facilitate safe data exchange between healthcare providers. In this study, we propose a Blockchain-based Ensemble Deep Learning Model method that can classify Breast Cancer either Malignant or Benign. This method is built on combining different breast cancer classification ANN models and sharing them through blockchain to use their weights to train and optimize the performance of a final model. This model achieved 98% accuracy, and showed a promising in protecting patients from fatal diagnosis mistakes. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Tackling the Qubit Mapping Problem with Permutation-Aware Synthesis 4

Tackling the Qubit Mapping Problem with Permutation-Aware Sy...

引用

4th IEEE International Conference on Quantum Computing and Engineering, QCE 2023

作者： Liu, Ji Younis, Ed Weiden, Mathias Hovland, Paul Kubiatowicz, John Iancu, Costin Argonne National Laboratory Mathematics and Computer Science Division United States Lawrence Berkeley National Laboratory Computational Research Division United States University of California Department of Electrical Engineering and Computer Science Berkeley United States

ISBN: (纸本)9798350343236

We propose a scalable, hierarchical qubit mapping and routing algorithm that harnesses the power of circuit synthesis. First, we decompose large circuits into subcircuits small enough to be directly resynthesized. For each block, we pre-synthesize them for all permutations of its input and output qubits. Following this offline step, we employ a permutation-aware, block-based generalization of the popular SABRE mapping algorithm. This mapping step stitches together blocks by choosing an input-output permutation that minimizes intrablock gate count and required inter-block communication (SWAP and bridge gates). Our approach has a twofold advantage: 1) circuit synthesis may eliminate more two-qubit gates than other optimizing compilers;2) considering all permutations of input and output qubits eliminates communication operations transparently. In contrast, other mapping algorithms can only introduce communication operations. We show that we can produce better-quality circuits than commercial compilers: shorter by up to 68% (18% on average) fewer gates than Qiskit, up to 36% (9% on average) fewer gates than Tket. We outperform BQSkit, a permutation-unaware, synthesis-based compiler, by up to 67% (21% on average) fewer gates. We also exceed experimental optimal mappers such as OLSQ in quality (10.7% shorter circuits) and time to solution. Our scalable, heuristic approach can be seamlessly integrated into any quantum circuit compiler or optimization infrastructure, and it applies well to any qubit technology, such as superconducting and trapped ions. © 2023 IEEE.

关键词： Conformal mapping

来源：评论

学校读者我要写书评

暂无评论

CSCL-DTI: Predicting drug-target interaction through cross-view and self-supervised contrastive learning

CSCL-DTI: Predicting drug-target interaction through cross-v...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Lin, Xuan Zhang, Xi Yu, Zu-Guo Long, Yahui Zeng, Xiangxiang Yu, Philip S. Xiangtan University College of Computer Science China Xiangtan University Key Laboratory of Intelligent Computing and Information Processing Ministry of Education China Singapore Hunan University College of Information Science and Engineering China University of Illinois Chicago Department of Computer Science United States

ISBN: (纸本)9798350386226

Accurately predicting drug-target interactions (DTI) is a critical step in drug discovery. Existing methods of DTI prediction primarily employ Simplified Molecular-Input Line-Entry System (SMILES) sequences or molecular graphs to learn drug representations. However, the features learned by such single-view approach is prone to incomplete. While some multiview methods that consider the views of both SMILES sequences and molecular graphs have been developed, these methods often fall in short in capturing potential interactions between views. In this work, we propose a novel dual contrastive learning framework CSCL-DTI for DTI prediction. First, we design a contrastive-enhanced cross-view representation learning (CVRL) to learn representations for drugs. In this module, Transformer-based and graph convolutional network (GCN)-based encoders are separately adopted to learn view-specific representations, followed by contrastive learning to enrich the representations by accounting for the potential interplay between local chemical context and topological structure. Second, we combine Transformer with self-supervised contrastive learning (SSCL) to learn representations for targets by modelling protein amino acids sequences. The scheme allows to effectively preserve the intrinsic characteristics of the sequences. Finally, we introduce a bilinear attention network to obtain an integrated representation by adaptively incorporating drug and target representations. Benchmarking experiments on two datasets demonstrated that CSCL-DTI1 outperforms six state-of-the-art methods. © 2024 IEEE.

关键词： Contrastive Learning

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：