检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Vicuna, Marc Khannouz, Martin Kiar, Gregory Chatelain, Yohan Glatard, Tristan Department of Computer Science and Software Engineering Concordia University Montreal Canada Center for the Developing Brain Child Mind Institute New YorkNY United States

Mondrian Forests are a powerful data stream classification method, but their large memory footprint makes them ill-suited for low-resource platforms such as connected objects. We explored using reduced-precision floating-point representations to lower memory consumption and evaluated its effect on classification performance. We applied the Mondrian Forest implementation provided by OrpailleCC, a C++ collection of data stream algorithms, to two canonical datasets in human activity recognition: Recofit and Banos et al. Results show that the precision of floating-point values used by tree nodes can be reduced from 64 bits to 8 bits with no significant difference in F1 score. In some cases, reduced precision was shown to improve classification performance, presumably due to its regularization effect. We conclude that numerical precision is a relevant hyperparameter in the Mondrian Forest, and that commonly-used double precision values may not be necessary for optimal performance. Future work will evaluate the generalizability of these findings to other data stream classifiers. © 2021, CC BY.

关键词： Digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

PyTracer: Automatically profiling numerical instabilities in Python

arXiv

引用

arXiv 2021年

作者： Chatelain, Yohan Yong, Nigel Kiar, Gregory Glatard, Tristan Department of Computer Science and Software Engineering Concordia University Montreal Canada Center for the Developing Brain Child Mind Institute New YorkNY United States

Numerical stability is a crucial requirement of reliable scientific computing. However, despite the pervasiveness of Python in data science, analyzing large Python programs remains challenging due to the lack of scalable numerical analysis tools available for this language. To fill this gap, we developed PyTracer, a profiler to quantify numerical instability in Python applications. PyTracer transparently instruments Python code to produce numerical traces and visualize them interactively in a Plotly dashboard. We designed PyTracer to be agnostic to numerical noise model, allowing for tool evaluation through Monte-Carlo Arithmetic, random rounding, random data perturbation, or structured noise for a particular application. We illustrate PyTracer's capabilities by testing the numerical stability of key functions in both SciPy and Scikit-learn, two dominant Python libraries for mathematical modeling. Through these evaluations, we demonstrate PyTracer as a scalable, automatic, and generic framework for numerical profiling in Python. © 2021, CC BY.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Op2Vec: An Opcode Embedding Technique and Dataset Design for End-to-End Detection of Android Malware

arXiv

引用

arXiv 2021年

作者： Khan, Kaleem Nawaz Ullah, Najeeb Ali, Sikandar Khan, Muhammad Salman Nauman, Mohammad Ghani, Anwar Department of Computer Science University of Engineering and Technology Mardan Pakistan Department of Computer Science and Technology University of Swat Pakistan AI in Healthcare Intelligent Information Processing Lab National Center of Artificial Intelligence UET Peshawar Pakistan University of Engineering and Technology Peshawar Pakistan Department of Computer Science National University of Computer and Emerging Sciences Peshawar Pakistan Department of Computer Science and Software Engineering International Islamic University Islamabad Pakistan

Android is one of the leading operating systems for smart phones in terms of market share and usage. Unfortunately, it is also an appealing target for attackers to compromise its security through malicious applications. To tackle this issue, domain experts and researchers are trying different techniques to stop such attacks. All the attempts of securing Android platform are somewhat successful. However, existing detection techniques have severe shortcomings, including the cumbersome process of feature engineering. Designing representative features require expert domain knowledge. There is a need for minimizing human experts' intervention by circumventing handcrafted feature engineering. Deep learning could be exploited by extracting deep features automatically. Previous work has shown that operational codes (opcodes) of executables provide key information to be used with deep learning models for detection process of malicious applications. The only challenge is to feed opcodes information to deep learning models. Existing techniques use one-hot encoding to tackle the challenge. However, the one-hot encoding scheme has severe limitations. In this paper, we introduce;(1) a novel technique for opcodes embedding, which we name Op2Vec, (2) based on the learned Op2Vec we have developed a dataset for end-to-end detection of android malware. Introducing the end-to-end Android malware detection technique avoids expert-intensive handcrafted features extraction, and ensures automation. Some of the recent deep learning-based techniques showed significantly improved results when tested with the proposed approach and achieved an average detection accuracy of 97.47%, precision of 0.976 and F1 score of 0.979. Copyright © 2021, The Authors. All rights reserved.

关键词： Android (operating system)

来源：评论

学校读者我要写书评

暂无评论

Image retrieval based on dual rearrangement of object corner 9

Image retrieval based on dual rearrangement of object corner

引用

9th International Conference on Smart Media and Applications, SMA 2020

作者： An, Youngeun Pan, Sungbum Kim, Taeyeun Department of IT Research Institute Chosun University Gwangju Korea Republic of Division of Electronics Engineering Chosun University Gwangju Korea Republic of National Program of Excellence in Software Center Chosun University Gwangju Korea Republic of

ISBN: (纸本)9781450389259

In this study, image search techniques are suggested based on dual rearrangement of object corner. Suggested algorithm is proceeded in the following stages. First, edges and corner points are extracted in the image. Then, the dispersion value and the number of white level are extracted in each of the corner areas. In addition, correlogram feature table is configured by using the dispersion value and the number of white level measuring the similarity of them. Suggested technique turned out to be outstanding in performance from objects with distinct structure in the image and strong against movement or rotation of an object. In addition, it represented an improved recall by about 0.05 compared to searching form in the use of corner patch histogram. © 2020 ACM.

关键词： Dispersions

来源：评论

学校读者我要写书评

暂无评论

Modification of a Herbal MRI Contrast Agent: Biological Effect and Relaxivity

Modification of a Herbal MRI Contrast Agent: Biological Effe...

引用

Iranian Conference of Biomedical engineering (ICBME)

作者： Ali Yazdani Ahmadreza Okhovat Raheleh Doosti Maryam Saber Hamid Soltanian-Zadeh Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran Central Herbarium School of Biology College of Science University of Tehran Tehran Iran College of Science University of Tehran Tehran Iran Department of Stem Cells and Developmental Biology Royan Institute for Stem Cell Biology and Technology Tehran Iran

We modified a modern herbal MRI contrast agent for biological applications. This modification was realized by omitting salinity and free ions of the contrast media. As a result, both the toxicity and the relaxivity of the product improved. We also chemically analyzed the modified agent and confirmed the elimination of some annoying free ions and molecules.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-View Self-Supervised Learning Enhances Automatic Sleep Staging from EEG Signals

引用

IEEE Transactions on Biomedical engineering 2025年 PP卷 PP页

作者： Yu, Tianyou Hu, Xinxin He, Yanbin Wu, Wei Gu, Zhenghui Yu, Zhuliang Li, Yuanqing Wang, Fei Xiao, Jun South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Pazhou Laboratory Research Center for Brain-Computer Interface Guangzhou510330 China Guangdong Work Injury Rehabilitation Hospital Department of Traumatic Brain Injury Rehabilitation and Severe Rehabilitation Guangzhou510440 China Shanghai Jiao Tong University School of Medicine Songjiang Hospital Songjiang Research Institute Shanghai Key Laboratory of Emotions and Affective Disorders Shanghai201600 China South China Normal University School of Software Guangzhou510631 China South China University of Technology School of Electric Power Engineering Guangzhou510640 China

Deep learning-based methods for automatic sleep staging offer an efficient and objective alternative to costly manual scoring. However, their reliance on extensive labeled datasets and the challenge of generalization to new subjects and datasets limit their widespread adoption. Self-supervised learning (SSL) has emerged as a promising solution to address these issues by learning transferable representations from unlabeled data. This study highlights the effectiveness of SSL in automated sleep staging, utilizing a customized SSL approach to train a multi-view sleep staging model. This model includes a temporal view feature encoder for raw EEG signals and a spectral view feature encoder for time-frequency features. During pretraining, we incorporate a cross-view contrastive loss in addition to a contrastive loss for each view to learn complementary features and ensure consistency between views, enhancing the transferability and robustness of learned features. A dynamic weighting algorithm balances the learning speed of different loss components. Subsequently, these feature encoders, combined with a sequence encoder and a linear classifier, enable sleep staging after finetuning with labeled data. Evaluation on three publicly available datasets demonstrates that finetuning the entire SSL-pretrained model achieves competitive accuracy with state-of-the-art methods—86.4%, 83.8%, and 85.5% on SleepEDF-20, SleepEDF-78, and MASS datasets, respectively. Notably, our framework achieves near-equivalent performance with only 5% of the labeled data compared to full-label supervised training, showcasing SSL's potential to enhance automated sleep staging efficiency. © 1964-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Energy-Aware Edge-Cloud Computation Offloading for Smart Connected Health 8

Energy-Aware Edge-Cloud Computation Offloading for Smart Con...

引用

8th International Conference on Future Internet of Things and Cloud, FiCloud 2021

作者： Materwala, Huned Ismail, Leila United Arab Emirates University Intelligent Distributed Computing and Systems Research Laboratory College of Information Technology Department of Computer Science and Software Engineering Abu Dhabi Al Ain15551 United Arab Emirates National Water and Energy Center United Arab Emirates University Abu Dhabi Al Ain United Arab Emirates

ISBN: (纸本)9781665425742

Smart connected healthcare is an emerging technology in the context of smart cities. The connected network aims to provide efficient and effective remote patient care. In such scenarios, edge and clouds come into the picture to offload computation from sensors and mobile devices, monitoring patient's health conditions, having limited processing capabilities to the edge and/or the cloud. The problem of optimizing the energy consumption of the edge and cloud servers in this offloading scenario is crucial. However, existing research efforts focus on sensors or cloud energy optimization. They do not consider the edge and cloud as part of the offloading strategy. In this paper, we address this void by proposing a novel energy-aware offloading algorithm for smart connected healthcare, which optimizes the energy of the edge-cloud computing platform for compute-intensive applications. The experimental results show that our proposed algorithm is a promising approach to energy savings. © 2021 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

On stability guarantees under sampling for retarded nonlinear systems

引用

Systems & Control Letters 2025年 204卷

作者： Pierdomenico Pepe Mario Di Ferdinando Department of Information Engineering Computer Science and Mathematics Center of Excellence for Research DEWS University of L’Aquila via Vetoio Coppito 1 67100 L’Aquila Italy

In this paper we deal with sampled-data implementation of Lipschitz on bounded sets global asymptotic stabilizers for retarded nonlinear systems, described by Lipschitz on bounded sets functions. We show, with no particular assumption nor requiring exhibition of any Lyapunov–Krasovskii functional, that fast sampling always ensures stabilization in the sample-and-hold sense. That is, for any ball of the origin of initial states and for any final target ball of the origin, there exists a suitably small sampling period such that all solutions starting in the former ball are driven into the latter one, with uniform overshoot and uniform settling time. Global asymptotic and locally exponentially stabilizers are also investigated, showing in this case semi-global uniform convergence to the origin under fast sampling.

关键词： Nonlinear systems Retarded systems Sampling and holding

来源：评论

学校读者我要写书评

暂无评论

Performance and energy-aware bi-objective tasks scheduling for cloud data centers

引用

Procedia computer Science 2022年 197卷 238-246页

作者： Huned Materwala Leila Ismail Intelligent Distributed Computing and Systems Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University Al Ain Abu Dhabi 15551 United Arab Emirates National Water and Energy Center United Arab Emirates University Al Ain Abu Dhabi United Arab Emirates

Cloud computing enables remote execution of users’ tasks. The pervasive adoption of cloud computing in smart cities’ services and applications requires timely execution of tasks adhering to Quality of Services (QoS). However, the increasing use of computing servers exacerbates the issues of high energy consumption, operating costs, and environmental pollution. Maximizing the performance and minimizing the energy in the cloud data center is challenging. In this paper, we propose a performance and energy optimization bi-objective algorithm to trade off the contradicting performance and energy objectives. An evolutionary algorithm-based multi-objective optimization is for the first time proposed using system performance counters. The performance of the proposed model is evaluated using a realistic cloud dataset in a cloud computing environment. Our experimental results achieve higher performance and lower energy consumption compared to a state-of-the-art algorithm.

关键词： Autonomous agents cloud computing energy-efficiency evolutionary algorithm genetic algorithm quality of service multi-objective optimization performance

来源：评论

学校读者我要写书评

暂无评论

Secure and Privacy-Preserving Lightweight Blockchain for Energy Trading 8

Secure and Privacy-Preserving Lightweight Blockchain for Ene...

引用

8th International Conference on Future Internet of Things and Cloud, FiCloud 2021

作者： Materwala, Huned Ismail, Leila College of Information Technology United Arab Emirates University Intelligent Distributed Computing and Systems Research Laboratory Department of Computer Science and Software Engineering Abu Dhabi Al Ain15551 United Arab Emirates National Water and Energy Center United Arab Emirates University Abu Dhabi Al Ain United Arab Emirates

ISBN: (纸本)9781665425742

Renewable energy is gaining wide attention to address the issues, such as depleting resources and environmental degradation, linked with the current non-renewable energy. However, storing renewable energy is challenging. Consequently, energy trading is required to transfer the surplus amount of renewable energy from the prosumers to the consumers. The current centralized energy trading system is less secure and involves large transmission losses and high overheads. The decentralization, replication, immutability, and transparency characteristics of blockchain show a promising potential to address the inherent issues of centralized energy trading. However, the existing blockchain-based energy trading suffers from the drawbacks such as limited scalability, high energy loss, and low transaction throughput. In this paper, we propose a secure and privacy-preserving lightweight blockchain for energy trading that reduces the computational and communication overhead compared to the bitcoin network. This is by clustering the prosumers and perform the energy trading through a cluster head. Our experimental results show the potential of our architecture. © 2021 IEEE.

关键词： Scalability

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：