检索结果-内蒙古大学图书馆

IEEE International Conference on Blockchain (Blockchain)

作者： Yue Liu Qinghua Lu Hye-Young Paik Guangsheng Yu Liming Zhu Data61 CSIRO Australia School of Computer Science and Engineering University of New South Wales Australia

Blockchain technology can construct a decentralised architecture design for diverse software applications. Nevertheless, the defects of on-chain algorithmic autonomy and subsequent tedious arguments for fixing the bugs raised concerns about whether blockchain can operate in a trustworthy way. Although multiple architectural patterns for blockchain governance have been summarised, concentrating on different governance dimensions (i.e., decision rights, incentives, and accountability), there is a need for guidance on the adoption of these patterns. In this paper, we present a set of decision models that can assist architects and developers in selecting appropriate patterns, to achieve governance in blockchain systems. This study provides a mapping between governance-related problems and each architectural pattern, and clarifies the trade-offs and conditions. The proposed decision models were evaluated based on expert opinions regarding the usability, correctness, and completeness collected via interviews.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MLOps: A Review

arXiv

引用

arXiv 2023年

作者： Wazir, Samar Kashyap, Gautam Siddharth Saxena, Parag Department of Computer Science and Engineering SEST Jamia Hamdard New Delhi India School of Data Science University of North Carolina Charlotte United States

Recently, Machine Learning (ML) has become a widely accepted method for significant progress that is rapidly evolving. Since it employs computational methods to teach machines and produce acceptable answers. The significance of the Machine Learning Operations (MLOps) methods, which can provide acceptable answers for such problems, is examined in this study. To assist in the creation of software that is simple to use, the authors research MLOps methods. To choose the best tool structure for certain projects, the authors also assess the features and operability of various MLOps methods. A total of 22 papers were assessed that attempted to apply the MLOps idea. Finally, the authors admit the scarcity of fully effective MLOps methods based on which advancements can self-regulate by limiting human engagement. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

data Insights as data: Quick Overview and Exploration of Automated data Insights

arXiv

引用

arXiv 2025年

作者： Wu, Shangxuan Luan, Wendi Wang, Yong Zeng, Dan Shen, Qiaomu Tang, Bo Department of Computer Science and Engineering Southern University of Science and Technology Guangdong Shenzhen China College of Computing and Data Science Nanyang Technological University Singapore Singapore Singapore School of Artificial Intelligence Sun Yat-sen University Guangdong Zhuhai China

Automated data insight mining and visualization have been widely used in various business intelligence applications (e.g., market analysis and product promotion). However, automated insight mining techniques often output the same mining results to different analysts without considering their personal preferences, while interactive insight discovery requires significant manual effort. This paper fills the gap by integrating automated insight mining with interactive data visualization and striking a proper balance between them to facilitate insight discovery and exploration. Specifically, we regard data insights as a special type of data and further present InsightMap, a novel visualization approach that uses the map metaphor to provide a quick overview and in-depth exploration of different data insights, where a metric is proposed to measure the similarity between different insights. The effectiveness and usability of InsightMap are demonstrated through extensive case studies and in-depth user interviews. Copyright © 2025, The Authors. All rights reserved.

关键词： data assimilation

来源：评论

学校读者我要写书评

暂无评论

Rore: robust and efficient antioxidant protein classification via a novel dimensionality reduction strategy based on learning of fewer features

引用

Genomics and Informatics 2024年第1期22卷 1-10页

作者： Meng, Chaolu Hou, Yongqi Zou, Quan Shi, Lei Su, Xi Ju, Ying College of Computer and Information Engineering Inner Mongolia Agricultural University Hohhot China Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application of Agriculture and Animal Husbandry Hohhot China School of Computer Science Inner Mongolia University Hohhot China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu China Department of Spine Surgery Changzheng Hospital Naval Medical University Huangpu District No. 415 Fengyang Road Shanghai China Foshan Women and Children Hospital Foshan China School of Informatics Xiamen University Xiamen China

In protein identification, researchers increasingly aim to achieve efficient classification using fewer features. While many feature selection methods effectively reduce the number of model features, they often cause information loss caused by merely selecting or discarding features, which limits classifier performance. To address this issue, we present Rore, an algorithm based on a feature-dimensionality reduction strategy. By mapping the original features to a latent space, Rore retains all relevant feature information while using fewer representations of the latent features. This approach significantly preserves the original information and overcomes the information loss problem associated with previous feature selection. Through extensive experimental validation and analysis, Rore demonstrated excellent performance on an antioxidant protein dataset, achieving an accuracy of 95.88% and MCC of 91.78%, using vectors including only 15 features. The Rore algorithm is available online at http://112.124.26.17:8021/Rore. © The Author(s) 2024.

关键词： Dimensionality reduction Protein classifier Protein sequence Robust feature

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Deep Learning based Water Potability Prediction

Design and Analysis of Deep Learning based Water Potability ...

引用

2023 International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023

作者： Arumugam, M. Vijayakumar, P. Kannan, A.C. Velmurugan, J. Arun, G. Rohith Bhat, C. Kongu Engineering College Department of Computer Technology - Pg Perundurai India Kongu Engineering College Department of Master of Computer Applications Tamil Nadu Perundurai638060 India Psna College of Engineering and Technology Department of Electrical and Electronics Engineering Dindigul624622 India Erode Sengunthar Engineering College Department of Artificial Intelligence and Data Science Thuduppathi638057 India Saveetha School of Engineering Simats Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350300857

According to the United Nations, having access to clean water for consumption is a fundamental human right. General Assembly in 2010. The importance of safe drinking water cannot be overstated. Unsafe drinking water access is a significant public health concern, especially in poor nations. In many regions of the world, waterborne illnesses including cholera, typhoid fever, and dysentery are important causes of illness and death. These diseases are especially dangerous for children, who are more vulnerable to their effects. In addition, a lack of access to clean drinking water can result in other health issues like stunted growth and malnutrition. Access to safe drinking-water is also a key component of effective policy for health protection at all levels, whether it is at the national, regional, or local level. Policies aimed at improving access to safe drinking-water can include measures such as water quality testing, water treatment, and the provision of clean water sources. Investments in water supply and sanitation can have a positive economic impact, especially in areas with inadequate access to clean drinking water. The costs of implementing the treatments may be outweighed by the reductions in unfavorable health impacts and medical expenses that may result from these investments. In conclusion, having access to clean drinking water is crucial for encouraging wellness, reducing waterborne illnesses, and raising standard of living in general. The input to the DNN could be the various water quality parameters, such as pH, hardness, chloride content, and total dissolved solids, while the output would be a binary classification indicating whether the water is potable or not. The DNN would need to be trained on a large and diverse dataset of water samples to accurately classify new samples. © 2023 IEEE.

关键词： Potable water

来源：评论

学校读者我要写书评

暂无评论

AegonKV: a high bandwidth, low tail latency, and low storage cost KV-separated LSM store with SmartSSD-based GC offloading 25

AegonKV: a high bandwidth, low tail latency, and low storage...

引用

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Zhuohui Duan Hao Feng Haikun Liu Xiaofei Liao Hai Jin Bangyu Li National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9781939133458

The key-value separation is renowned for its significant mitigation of the write amplification inherent in traditional LSM trees. However, KV separation potentially increases performance overhead in the management of Value region, especially for garbage collection (GC) operation that is used to reduce the redundant space occupation. In response, many efforts have been made to optimize the GC mechanism for KV separation. However, our analysis indicates that such solution based on trade-offs between CPU and I/O overheads cannot simultaneously satisfy the three requirements of KV separated systems in terms of throughput, tail latency, and space usage. This limitation hinders their real-world *** this paper, we introduce AegonKV, a "three-birds-one-stone" solution that comprehensively enhances the throughput, tail latency, and space usage of KV separated systems. AegonKV first proposes a SmartSSD-based GC offloading mechanism to enable asynchronous GC operations without competing with LSM read/write for bandwidth or CPU. AegonKV leverages offload-friendly data structures and hardware/ software execution logic to address the challenges of GC offloading. Experiments demonstrate that AegonKV achieves the largest throughput improvement of 1.28-3.3 times, a significant reduction of 37%-66% in tail latency, and 15%-85% in space overhead compared to existing KV separated systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The DKU Post-Challenge Audio-Visual Wake Word Spotting System for the 2021 MISP Challenge: Deep Analysis

The DKU Post-Challenge Audio-Visual Wake Word Spotting Syste...

引用

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

作者： Haoxu Wang Ming Cheng Qiang Fu Ming Li School of Computer Science Wuhan University Wuhan China Data Science Research Center Duke Kunshan University Kunshan China Alibaba Group China

This paper further explores our previous wake word spotting system ranked 2-nd in Track 1 of the MISP Challenge 2021. First, we investigate a robust unimodal approach based on 3D and 2D convolution and adopt the simple attention module (SimAM) for our system to improve performance. Second, we explore different combinations of data augmentation methods for better performance. Finally, we study the fusion strategies, including score-level, cascaded and neural fusion. Our proposed multimodal system leverages multimodal features and uses the complementary visual information to mitigate the performance degradation of audio-only systems in complex acoustic scenarios. Our system obtains a false reject rate of 2.15% and a false alarm rate of 3.44% in the evaluation set of the competition database, which achieves the new state-of-the-art performance by 21% relative improvement compared to previous systems. Related resource can be found at: https://***/Mashiro009/DKU_WWS_MISP.

关键词： Degradation Visualization Solid modeling Three-dimensional displays Convolution databases Semantics

来源：评论

学校读者我要写书评

暂无评论

InsightCube: Accelerating Interactive Insight Discovery in Exploratory data Analysis

InsightCube: Accelerating Interactive Insight Discovery in E...

引用

International Conference on Big data and Smart Computing (BIGCOMP)

作者： Hanbing Zhang Yinan Jing Wei Zhang Zhenying He Kai Zhang X. Sean Wang Zhenqiang Chen Changchun Zhang School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Data Science Shanghai China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China Transwarp Technology(Shanghai) Co. Ltd Shanghai China

ISBN: (数字)9798331529024

ISBN: (纸本)9798331529031

Exploratory data analysis (EDA) is usually human-in-the-loop and time tedious since identifying insights that show interesting characteristics and trends in data is laborious. Insight discovery helps users gain structured knowledge when understanding the dataset by categorizing interesting characteristics and trends into commonnesses and exceptions. However, existing insight discovery methods cannot interact with users when discovering insights. More importantly, the efficiency of insight discovery for these methods is low. In this paper, we propose a framework that supports and accelerates interactive insight discovery. We first divide the dataset into multiple subsets, and precompute the pattern snippets that include the distribution characteristics of subsets. Considering efficiency, we only pre-compute for subsets that cannot be further split. Then we design a novel cube structure, called InsightCube, to store precomputed pattern snippets. In order to accelerate insight discovery, we reuse the precomputed pattern snippets stored in InsightCube to infer the pattern of subsets that cannot be split. Furthermore, during insight discovery, we propose pruning strategies to accelerate the pattern inference for subsets that can be split. Experimental results on real-world datasets show that InsightCube improves the insight discovery efficiency by up to $2.5 \times$ compared to the state-of-the-art insight discovery method.

关键词： data analysis Big data Market research Human in the loop Optimization

来源：评论

学校读者我要写书评

暂无评论

FogMedX-Transform: A Transformer-Based Task Interoperability Framework for Energy-Efficient Fog-Enabled IoMT

FogMedX-Transform: A Transformer-Based Task Interoperability...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： R Jayakarthik Sajja Suneel Jayendra Gopal Thatipudi V. Jaganraja Minesh Vohra Gopinath D Dept of Computer science Saveetha College of Liberal Arts and Sciences SIMATS Department of CSE(Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Dept. of Computer Science University of North Texas Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India School of Mechanical Engineering Lovely Professional University Phagwara Department of Computer Science Kristu Jayanti College (Autonomous) Bengaluru Karnataka India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

The increasing speed of Internet of Medical Things (IoMT) development requires framework approaches that secure, efficient, and scalable for healthcare data management. The study presents FogMedX-Transform as a Transformer-based task interoperability framework purposebuilt for energy-efficient fog-enabled IoMT systems. A customized Transformer design utilizing multi-head selfattention allows the framework to deliver timely critical healthcare data processing alongside optimized energy usage. This model demonstrated a 98.7% task interoperability success rate coupled with a 97.5% anomaly detection accuracy that exceeded results from conventional models based in fog environments and the cloud. The framework improved performance through latency reduction between 50% and 70% and energy consumption minimization reached between 25% to 40% thus proving its effectiveness in resource administration. The scalability tests proved steady system functionality when dealing with different device quantities and built-in security features blocked data breaches and had a false positive rate of 2.3% during testing. FogMedX-Transform demonstrates the capability for healthcare transformation through its union of fog computing and deep learning technology integration according to test results.

关键词： Deep learning Performance evaluation Internet of Medical Things data breach Transformers data processing Energy efficiency Real-time systems Interoperability Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

The WHU-Alibaba Audio-Visual Speaker Diarization System for the MISP 2022 Challenge

The WHU-Alibaba Audio-Visual Speaker Diarization System for ...

引用

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

作者： Ming Cheng Haoxu Wang Ziteng Wang Qiang Fu Ming Li School of Computer Science Wuhan University Wuhan China Data Science Research Center Duke Kunshan University Kunshan China Alibaba Group China

This paper describes the system developed by the WHU-Alibaba team for the Multimodal Information Based Speech Processing (MISP) 2022 Challenge. We extend the Sequence-to-Sequence Target-Speaker Voice Activity Detection framework to simultaneously detect multiple speakers’ voice activities from audio-visual signals. The final system achieves a diarization error rate (DER) of 8.82% on the evaluation set of the competition database, which ranks 1st in the speaker diarization track of the MISP 2022, ICASSP Signal Processing Grand Challenge.

关键词： Voice activity detection Target tracking Error analysis databases Signal processing Acoustics

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：