检索结果-内蒙古大学图书馆

5th International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2023

作者： Mishra, Awakash Mehta, Deepak Arya, Rakesh Prasad, P.S. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bengaluru India Department of Computer Science and Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India

ISBN: (纸本)9789819780426

SVMs had been effectively applied to various signal processing tasks in Telecommunications, along with goal detection and category in cognitive radio networks, channel estimation, exploiting spatial variety for multipath wireless conversation channels, interference cancellation, and era of feature vectors for sign type. In goal detection and category in Wi-Fi conversation networks, SVMs may be used to come across and classify specific types of wireless signals with an excessive diploma of accuracy. The input characteristic vectors are comprised of the signal’s spectrum and temporal features, and they are used for the education of the SVM classifier. In channel estimation, SVMs may be used to estimate the unknown channel parameters in Wi-Fi conversation channels with a low but suitable suggest-squared-blunders charge. That is viable via exploiting the diversity of more than one received signal replicas and the usage of the predicted channel parameters to improve signal reception. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Anomaly Detection for Multimodal Data Distributions 14

Weakly-Supervised Anomaly Detection for Multimodal Data Dist...

引用

14th IEEE International Conference on Signal Processing, Communications and computing, ICSPCC 2024

作者： Tan, Xu Chen, Junqi Rahardja, Sylwan Yang, Jiawei Rahardja, Susanto School of Computing University of Eastern Finland Kuopio Finland University of Turku Department of Computing Turku Finland School of Marine Science and Technology Northwestern Poly technical University Xi'an China Singapore Institute of Technology Engineering Cluster Singapore Singapore

ISBN: (纸本)9798350366556

Weakly-supervised anomaly detection can outper-form existing unsupervised methods with the assistance of a very small number of labeled anomalies, which attracts increasing attention from researchers. However, existing weakly-supervised anomaly detection methods are limited as these methods do not factor in the multimodel nature of the real-world data distribution. To mitigate this, we propose the Weakly-supervised Variational-mixture-model-based Anomaly Detector (WVAD). WVAD excels in multimodal datasets. It consists of two components: a deep variational mixture model, and an anomaly score estimator. The deep variational mixture model captures various features of the data from different clusters, then these features are delivered to the anomaly score estimator to assess the anomaly levels. Experimental results on three real-world datasets demonstrate WVAD's superiority. © 2024 IEEE.

关键词： anomaly detection multimodal outlier detection variational mixture model weakly-supervised

来源：评论

学校读者我要写书评

暂无评论

Activation Control of Vision Models for Sustainable AI Systems

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3470-3481页

作者： Burton-Barr, Jonathan Fernando, Basura Rajan, Deepu Institute of High-Performance Computing The Centre for Frontier AI Research Agency for Science Technology and Research 138632 Singapore Nanyang Technological University Nanyang School of Computer Science and Engineering 639798 Singapore

As artificial intelligence (AI) systems become more complex and widespread, they require significant computational power, increasing energy consumption. Addressing this challenge is essential for ensuring the long-term sustainability of AI technology. AI-on-AI control refers to a system with a set of AI functions controlled by an upper-level AI model. Previous work in AI-on-AI control focuses on boosting accuracy or expanding system capability by increasing overall system cost. Alternatively, we focus on applying AI-on-AI control to decrease system cost and increase the sustainability and viability of a system with multiple AI functions. Our supervised image classification evaluative controller (SICEC) is a cost-reduction oriented AI-on-AI controller that learns when vision models within an AI system should be activated based on input features. The function controller (FC) preprocesses an input and activates relevant functions, functions being distinct units of AI functionality within the system. Some functions have a set of same functional models (SFMs). These models take the same input and produce the same output but have architectural differences. We introduce a same functional controller to select a SFM using the FC's decision confidence. Results are promising, with a decrease of up to 48.9% in inference time, 67.8% in floating point operations (FLOPs), and 66.4% in energy usage. With SICEC showing significant reductions in inference time and energy cost, our work contributes to limited resource computing and sustainable AI technology. © 2020 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

An algorithm/hardware co-optimized method to accelerate CNNs with compressed convolutional weights on FPGA

An algorithm/hardware co-optimized method to accelerate CNNs...

引用

作者： Shang, Jiangwei Zhang, Zhan Zhang, Kun Li, Chuanyou Qian, Lei Liu, Hongwei School of Computer Science and Technology Harbin Institute of Technology Harbin China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi China School of Computer Science and Engineering Southeast University Nanjing China

Convolutional neural networks (CNNs) have shown remarkable advantages in a wide range of domains at the expense of huge parameters and computations. Modern CNNs still tend to be more complex and larger to achieve better inference accuracy. However, the complex and large structures of CNNs could slow down the inference speed. Recently, Compressing the convolutional weights to be sparse by pruning the unimportant parameters has been demonstrated as an efficient way to reduce the computations of CNNs. On the other hand, field-programmable gate arrays (FPGAs) have been a popular hardware platform to accelerate CNN inference. In this paper, we propose an algorithm/hardware co-optimized method for accelerating CNN inference on FPGAs. For the algorithm, we take advantage of unstructured and structured parameter sparsifying methods to achieve high sparsity and keep the regularity of convolutional weights. Correspondingly, hardware-friendly index representations of sparse convolutional weights are proposed. For the hardware architecture, we propose row-wise input-stationary dataflow, which is tightly coupled with the algorithm. A row-wise computing engine (RConv Engine) is proposed, which is based on the dataflow. Inside the RConv Engine, the scalar-vector structure is applied to implement the basic processing elements (PEs). To flexibly calculate the feature map with various sizes, the PEs are organized in a 2D structure with two work modes. The experimental results demonstrate that our co-optimized method implements high sparsity of convolutional weights, and the computing engine achieves high computation efficiency. Compared with other accelerators, our co-optimized method implements a 10.9 (Formula presented.) speedup on FPS at most with the highest sparsity of convolutional weights and negligible accuracy loss. © 2024 John Wiley & Sons Ltd.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

Real-Time Classification of Defects During Automated Valve Testing and Inspection 5th

Real-Time Classification of Defects During Automated Valve T...

引用

5th International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2023

作者： Singh, Shweta Agarwal, Trapty Haripriya Hemlata School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India Department of Computer Science and Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Dehradun India

ISBN: (纸本)9789819780426

This paper offers a singular method for actual-time type of defects at some point of computerized valve testing and inspection. Mainly, an image processing gadget is developed to discover and classify various defects which includes cracks, dents, foreign items, and different floor irregularities. The machine includes a high-decision digital camera, LED lighting fixtures, processing unit, and defect reputation algorithm. The image processing system captures the picture and methods it to pick out the illness regions. The gadget then extracts the features from every of the detected regions and classifies them the usage of a guide Vector device. The model is demonstrated with manually received pics, and the outcomes show true overall performance in terms of accuracy and speed. Similarly, the system can alert the consumer whilst a potential disorder is identified and the defects can then be in addition inspected and repaired. This approach has the ability to lessen inspection time, enhance manufacturing efficiency, and reduce charges. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Lighting fixtures

来源：评论

学校读者我要写书评

暂无评论

SARIMA model to predict land surface temperature for the UHI effect

SARIMA model to predict land surface temperature for the UHI...

引用

International Conference on Artificial Intelligence, Blockchain, computing and Security, ICABCS 2023

作者： Jagannathan, J. Divya, C. Thanjaivadivel, M. School of Information Technology and Engineering Vellore Institute of Technology Vellore Dt Tamil Nadu Katpadi India Centre for Information Technology and Engineering Manonmaniam Sundaranar University Abishekapatti Tirunelveli India School of Computing and Information Technology Reva University Bengaluru India

ISBN: (纸本)9781032669663

Human activities are causing global warming, which raises the heating of seas, the earth’s surface, and the atmosphere. Cities’ urbanisation leads to a rise in temperature and the formation of an urban heat island. Climate change forecasting has lately become a crucial demand for many industry and government agencies. Because of the dynamic swings in climatic circumstances, the researchers found it difficult to predict the climatic conditions with greater precision. However, when compared to other models, the accuracy of the forecast utilising machine learning approaches can be higher. Variation in land temperature has become a serious concern in today’s big metropolitan communities. Based on hourly temperature data acquired from the Indian Meteorological Department IMD over 117 years from 1900 to 2017, this work attempts to construct a SARIMA model to forecast monthly and daily temperature change. Temperature variation, autocorrelation function, partial autocorrelation, and residual distribution function were all used to assess the model’s correctness. Then, using the adfuller function and the error of determination for evaluation and root mean square deviation, determine if the series is stationary. In addition, the SARIMA model was used to anticipate average monthly and daily temperatures using historical data. The obtained data and model’s correctness, fitness, and timeliness are investigated, and the findings are linked. The monthly temperature trend in Chennai is researched and compared for the next years. The SARIMA (3,0,0), (0,1,1,12)),‘c’ model has an RMSE of 0.4811 degrees Celsius. The findings show that the SARIMA parameters were successfully matched, that the projected values match the true values, and that the seasonal pattern is also followed. © 2024, CRC Press/Balkema. All rights reserved.

关键词： Global warming

来源：评论

学校读者我要写书评

暂无评论

LMR-CBT: learning modality-fused representations with CB-Transformer for multimodal emotion recognition from unaligned multimodal sequences

引用

Frontiers of Computer Science 2024年第4期18卷 39-47页

作者： Ziwang FU Feng LIU Qing XU Xiangling FU Jiayin QI School of Computer Science(National Pilot Software Engineering School) Beijing University of Posts and TelecommunicationsBeijing 100876China Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Beijing 100876China Shanghai International School of Chief Technology Officer East China Normal UniversityShanghai 200062China School of Computer Science and Technology East China Normal UniversityShanghai 200062China School of Cyberspace Security Guangzhou UniversityGuangdong 510006China

Learning modality-fused representations and processing unaligned multimodal sequences are meaningful and challenging in multimodal emotion *** approaches use directional pairwise attention or a message hub to fuse language,visual,and audio ***,these fusion methods are often quadratic in complexity with respect to the modal sequence length,bring redundant information and are not *** this paper,we propose an efficient neural network to learn modality-fused representations with CB-Transformer(LMR-CBT)for multimodal emotion recognition from unaligned multi-modal ***,we first perform feature extraction for the three modalities respectively to obtain the local structure of the ***,we design an innovative asymmetric transformer with cross-modal blocks(CB-Transformer)that enables complementary learning of different modalities,mainly divided into local temporal learning,cross-modal feature fusion and global self-attention *** addition,we splice the fused features with the original features to classify the emotions of the ***,we conduct word-aligned and unaligned experiments on three challenging datasets,IEMOCAP,CMU-MOSI,and *** experimental results show the superiority and efficiency of our proposed method in both *** with the mainstream methods,our approach reaches the state-of-the-art with a minimum number of parameters.

关键词： modality-fused representations cross-model blocks multimodal emotion recognition unaligned multimodal sequences computational affection

来源：评论

学校读者我要写书评

暂无评论

Lightweight Blockchain Prototype for Food Supply Chain Management 17

Lightweight Blockchain Prototype for Food Supply Chain Manag...

引用

17th International Conference on Security of Information and Networks, SIN 2024

作者： Rusakov, Alexey Moradpoor, Naghmeh Akbarzadeh, Aida School of Computing Engineering and the Built Environment Edinburgh Napier University Edinburgh United Kingdom Norwegian University of Science and Technology Faculty of Information Technology and Electrical Engineering Gjovik Norway

ISBN: (纸本)9798331509736

The modern food supply chain often involves multiple layers of participants spread across different countries and continents. This complex system offers significant benefits to businesses worldwide;however, it also presents several challenges. One major problem is the inability to trace the product flow back to its origin, a critical issue in many industries. Another issue is the lack of trust among supply chain participants. Blockchain technology can help address these and other challenges faced by the supply chain industry. However, it is surprising that, globally, there are still not many examples of the technology's adoption, with most projects remaining in the pilot stage. This paper explores the field of custom blockchain design tailored to specific applications, with a focus on supply chain operations in the food industry. It includes the development of a lightweight yet fully featured Python prototype for a decentralized blockchain system. In addition to common features like block validation and state updates, the prototype includes a newly designed type of transaction tailored specifically for supply chain operations. These transactions eliminate the need for smart contracts, making the system more lightweight compared to general-purpose blockchain platforms such as Ethereum and less prone to security vulnerabilities. The prototype is designed as a public blockchain network, with Proof of Work selected as the consensus algorithm. The novelty of this research work lies in advancing the concept of a custom blockchain solution for the food industry. The key elements of the prototype have been unit tested. The overall evaluation was completed using a Python script that simulates product flow through an example supply chain, allowing product provenance to be determined by tracing the product flow back to its origin. © 2024 IEEE.

关键词： Food industry

来源：评论

学校读者我要写书评

暂无评论

Visualization of Community Safety Threats with Time Series Evaluation 5th

Visualization of Community Safety Threats with Time Series E...

引用

5th International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2023

作者： Alam, Intekhab Gobi, N. Yadav, Renu Shankar, J. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India Department of Electronic and Communication Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India

ISBN: (纸本)9789819780426

The fast proliferation of connected gadgets on networks and the more and more pervasive use of technology in everyday lives is primary to more danger of cyber threats, making it vital to recognize the behavior of malicious actors as an excellent way to shield each structure and users better. Time collection analysis is a powerful tool to correctly understand and visualize the dynamic conduct of community security threats. This technique can help detect threats as they manifest within the community environment and provide insights into the underlying patterns and tendencies of malicious sports. This era allows us to appropriately come across, classify, and tune safety threats and anomalous community behavior in real-time. With the aid of visualizing the temporal styles of community protection threats, directors can benefit from a green and comprehensive view of the threat panorama and reply quickly. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： anomalous activities directors threats visualizing

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Transfer Learning for Automatic Discovery of Polyp in Colonoscopy Imagery 5th

Leveraging Deep Transfer Learning for Automatic Discovery of...

引用

5th International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2023

作者： Ahamed, Mohamadi Begum Syed Riaz Savita Beemkumar, N. Singh, Arjun School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bengaluru India Department of Electronic and Communication Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Dehradun India

ISBN: (纸本)9789819780426

Deep Switch latest is a rising technology that uses contemporary pre-skilled convolution neural networks or CNNs as a starting point for further evaluation. It leverages already-educated deep networks to fast, and it should be analyzed big information units and has been implemented for numerous imaginative and prescient problems such as object and scene reputation, item detection, and segmentation. This era has been implemented to detect today’s polyps in colonoscopy picas automatically. It is a crucial task because timely detection of today's polyps can cause early diagnosis and treatment of trendy colorectal cancers, one of the leading causes of modern cancers demise worldwide. This paper describes a trendy deep switch technique to detect contemporary polyps in colonoscopy images automatically. Finally, we evaluate our proposed approach at the available Endoscope dataset and exhibit how our trained version can accurately locate polyps in real-international colonoscopy photos. Our trained model achieves country-modern day-the artwork accuracy, making it an able candidate for deployment in scientific settings. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

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：