检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Li, Zhongjie Zhao, Bin Zhang, Gaoyan Dang, Jianwu Tianjin University Cca Lab College of Intelligence and Computing Tianjin China Japan Advanced Institute of Science and Technology Information Science Japan

ISBN: (纸本)9781728163277

Intent differentiation in speech communication relies not only on linguistic information but also on paralinguistic information. The same textual content, when pronounced with different prosodies and emotions, may express totally different intentions. The true intentions in this condition can be easily grasped by our brain. Therefore, combining text, speech, and electroencephalography (EEG) for intent discrimination on the same text may be an effective approach. Before fusing speech and text modalities, the current study focused on exploring effective EEG-based features for Chinese intent recognition as no previous research has utilized EEG signals for this purpose. To tackle this issue, we first created a Chinese multimodal spoken language intention understanding (CMSLIU) dataset, in which the same texts were pronounced with varying prosodies to express different intents. To identify effective brain features that were most relevant to intent recognition improvement, we compared the event-related spectral perturbation and effective brain connectivity patterns on two intent conditions (praise vs. irony). It was found that the praise expression tended to elicit stronger high-frequency brain activities while the irony expression involved a more suppressive network connection in the right hemisphere. These features were trained on the CMSLIU dataset and achieved an intention classification accuracy of 78.66%, which indicated a great potential of the EEG features in intent discrimination on the same text. © 2023 IEEE.

关键词： brain network features EEG Human-computer interaction Intent understanding paralinguistic information

来源：评论

学校读者我要写书评

暂无评论

PiLaMIM: Toward Richer Visual Representations by Integrating Pixel and Latent Masked Image Modeling

arXiv

引用

arXiv 2025年

作者： Lee, Junmyeong Hwang, Eui Jun Cho, Sukmin Park, Jong C. School of Computing Korea Advanced Institute of Science and Technology Korea Republic of

In Masked Image Modeling (MIM), two primary methods exist: Pixel MIM and Latent MIM, each utilizing different reconstruction targets, raw pixels and latent representations, respectively. Pixel MIM tends to capture low-level visual details such as color and texture, while Latent MIM focuses on high-level semantics of an object. However, these distinct strengths of each method can lead to suboptimal performance in tasks that rely on a particular level of visual features. To address this limitation, we propose PiLaMIM, a unified framework that combines Pixel MIM and Latent MIM to integrate their complementary strengths. Our method uses a single encoder along with two distinct decoders: one for predicting pixel values and another for latent representations, ensuring the capture of both high-level and low-level visual features. We further integrate the [CLS] token into the reconstruction process to aggregate global context, enabling the model to capture more semantic information. Extensive experiments demonstrate that PiLaMIM outperforms key baselines such as MAE, I-JEPA and BootMAE in most cases, proving its effectiveness in extracting richer visual representations. The code is available at https://***/joonmy/***. Copyright © 2025, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning Framework to Predict the Employee Performance 2

Ensemble Learning Framework to Predict the Employee Performa...

引用

2nd International Conference on Power, Control and computing Technologies, ICPC2T 2022

作者： Sujatha, P. Dhivya, R.S. Vels Institute of Science Technology and Advanced Studies Department of Information Technology Chennai India Vels Institute of Science Technology and Advanced Studies School of Computing Science Chennai India

ISBN: (纸本)9781665458580

The main goal of this research is to analyze the employee performance associated with organization's growth. The research starts with collecting the employee information and then a deep exploratory data analysis has been conducted on the collected data to identify the significance contribution towards the organization. Finally, ensemble learning framework designed to identify the potential of employees to the organization. To the best of our knowledge, this is the first work which consists of all the aspects of employee performance has been included in the dataset. Also, we have used the real time employee dataset from reputed MNC Company from Chennai. The results show that the proposed Extreme gradient boosting ensemble learning algorithm gives better results. © 2022 IEEE.

关键词： Computers Data analysis Power control Organizations Companies Boosting Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Stereoselective recognition of morphine enantiomers by μ-opioid receptor

引用

National Science Review 2024年第3期11卷 183-191页

作者： Yibo Wang Van A.Ngo Xiaohui Wang Laboratory of Chemical Biology Changchun Institute of Applied ChemistryChinese Academy of Sciences Advanced Computing for Life Sciences and Engineering Group Science Engagement Section National Center for Computational Sciences Oak Ridge National Lab School of Applied Chemistry and Engineering University of Science and Technology of China Beijing National Laboratory for Molecular Sciences

Stereospecific recognition of chiral molecules plays a crucial role in biological systems. The μ-opioid receptor（MOR） exhibits binding affinity towards（-）-morphine, a well-established gold standard in pain management, while it shows minimal binding affinity for the（+）-morphine enantiomer, resulting in a lack of analgesic activity. Understanding how MOR stereoselectively recognizes morphine enantiomers has remained a puzzle in neuroscience and pharmacology for over half-a-century due to the lack of direct observation techniques. To unravel this mystery, we constructed the binding and unbinding processes of morphine enantiomers with MOR via molecular dynamics simulations to investigate the thermodynamics and kinetics governing MOR's stereoselective recognition of morphine enantiomers. Our findings reveal that the binding of（-）-morphine stabilizes MOR in its activated state, exhibiting a deep energy well and a prolonged residence time. In contrast,（+）-morphine fails to sustain the activation state of ***, the results suggest that specific residues, namely D1142.50and D1473.32, are deprotonated in the active state of MOR bound to（-）-morphine. This work highlights that the selectivity in molecular recognition goes beyond binding affinities, extending into the realm of residence time.

关键词： stereoselective recognition thermodynamics and kinetics residence time morphine enantiomers μ-opioid receptor

来源：评论

学校读者我要写书评

暂无评论

Fault Secured JPEG-Codec Hardware Accelerator with Piracy Detective Control using Secure Fingerprint Template 36

Fault Secured JPEG-Codec Hardware Accelerator with Piracy De...

引用

36th IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2023

作者： Chaurasia, Rahul Reddy Asireddy, Abhinav Sengupta, Anirban Indian Institute of Technology Computer Science and Engineering Indore India Indian Institute of Technology Department of Computer Science and Engineering Indore India Indian Statistical Institute Advanced Computing and Microelectronics Unit Kolkata India

ISBN: (纸本)9798350315004

This paper presents a novel methodology to design fault secured JPEG-compression-decompression (codec) hardware accelerator with piracy detective control using secure fingerprint template of intellectual property (IP) vendor. In the proposed approach, firstly, the fault secured schedule for JPEG-codec design is generated from its behavioral description. Subsequently, in order to enable detective control against piracy, secure digital template corresponding to fingerprint biometric of IP vendor is generated and implanted into the design. In order to do so, firstly, fingerprint features are transformed based on IP vendor specified key-set. Subsequently, the generated secure fingerprint template in the form of encoded hardware security constraints is implanted into the design during behavioral/ high-level synthesis phase of integrated circuit (IC) design. The implanted hardware security constraints thereby ensure the seamless detection and isolation of fake/pirated design versions during piracy detection process, before their conjunction into system on chip (SoC) of electronic systems. The proposed approach achieves the following: i) fault secured hardware accelerator for JPEG-codec with integrated piracy detective control at negligible design cost overhead ii) higher resiliency against tampering attack and iii) lower probability of coincidence (indicating definitive proof of ownership for genuine IP vendor). © 2023 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Heterostructured Mn_(3)O_(4)-MnS Multi-Shelled Hollow Spheres for Enhanced Polysulfide Regulation in Lithium-Sulfur Batteries

引用

Energy & Environmental Materials 2023年第6期6卷 436-444页

作者： Bin Qin Qun Wang Weiqi Yao Yifei Cai Yuhan Chen Pengcheng Wang Yongchun Zou Xiaohang Zheng Jian Cao Junlei Qi Wei Cai State Key Laboratory of Advanced Welding and Joining Harbin Institute of TechnologyHarbin 150001China College of Chemistry and Chemical Engineering Taiyuan University of TechnologyTaiyuan 030024China State Key Laboratory of Chemical Engineering East China University of Science and TechnologyShanghai 200237China Department of Mechanical Engineering City University of Hong KongHong KongChina Center of Analysis Measurement and Computing Harbin Institute of TechnologyHarbin 150001China School of Materials Science and Engineering Harbin Institute of Technology Harbin 150001China

Constructing heterojunctions and hollow multi-shelled structures can render materials with fascinating physicochemical properties,and have been regarded as two promising strategies to overcome the severe shuttling and sluggish kinetics of polysulfide in lithium-sulfur(Li-S)***,a single strategy can only take limited *** catalytic hosts with synergistic effects are urgently ***,Mn_(3)O_(4)-MnS heterogeneous multi-shelled hollow spheres are meticulously designed by controlled sulfuration of Mn2O3 hollow spheres,and then applied as advanced encapsulation hosts for Li-S *** from the separated spatial confinement by hollow multi-shelled structure,ample exposed active sites and built-in electric field by heterogeneous interface,and synergistic effects between Mn_(3)O_(4)(strong adsorption)and MnS(fast conversion)components,the assembled battery achieves prominent rate capability and decent cyclability(0.016%decay per cycle at 2 C,1000 cycles).More crucially,satisfactory areal capacity reaches up to 7.1 mAh cm^(-2)even with high sulfur loading(8.0 mg cm^(-2))and lean electrolyte(E/S=4.0 pL mg^(-1))*** work will provide inspiration for the rational design of hollow multi-shelled heterostructure for various electrocatalysis applications.

关键词： electrocatalyst heterojunction host hollow multi-shelled structure Li-S battery Mn_(3)O_(4)-MnS

来源：评论

学校读者我要写书评

暂无评论

Cross Site Scripting Attacks Classification using Convolutional Neural Network 12

Cross Site Scripting Attacks Classification using Convolutio...

引用

12th International Conference on Computer Communication and Informatics, ICCCI 2022

作者： Kumar, Jitendra Santhanavijayan, A. Rajendran, Balaji Centre for Development of Advanced Computing Nit Trichy Bengaluru India National Institute of Technology Trichy Trichy India Centre for Development of Advanced Computing Bengaluru India

ISBN: (纸本)9781665480352

The global nature of web applications puts them at a high risk of attacks from different locations and with various levels of severity and complexity. Cross-Site Scripting (XSS) is a code injection attack that happens at the client-side i.e., through the web browsers. The attacker's main strategy is to execute the malicious injected scripts in a legitimate web application through the victim's browser. XSS vulnerabilities can be a source of other security attacks such as the spread of malware, credential theft, credential phishing, social network worms, and website defacing. Plenty of research has been carried out on the detection and prevention of XSS using machine learning techniques that involved URL-based features, HTML features, and JavaScript features and achieved an accuracy of about 98%. XSS attacks can have different forms and evolve regularly, new patterns emerge daily, feature extraction can be challenging, so there is a high probability of being not exhaustive. A Convolutional Neural network can be useful for XSS classification tasks, as because of its architecture it requires less feature extraction pre-processing task. In this paper, we used almost all the characters of XSS Scripts during feature generation and used the Convolutional Neural Network (CNN) technique to classify and detect the XSS scripts as malicious or benign and achieved the accuracy of 98.62 and precision of 98.6 and recall 98.86. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysing the Quality and Management of Data in Big Data

Analysing the Quality and Management of Data in Big Data

引用

Distributed computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： Pratheesh R V. Divya School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Department of Information Technology School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Chennai India

ISBN: (数字)9798350318609

ISBN: (纸本)9798350318616

Big data analytics delves into these immense datasets to reveal hidden patterns and correlations, yet its pervasive use raises substantial security and privacy concerns. This article centers on the specific issues concerning privacy and security within the realm of big data, distinguishing between these concerns and outlining their distinct requirements. The focus is on various privacy strategies, including L-diversity, k-anonymity, HyBrEx, and T-closeness, examining their practical applications in diverse business contexts. Privacy protection methods have surfaced throughout various stages of the big data life cycle, aiming to ensure privacy during data creation, retention, and handling. This paper provides an extensive review of these privacy mechanisms while addressing the challenges encountered by current approaches. As the extended comprehensive study is experimented with features extraction techniques such as Principle component analysis (PCA), Independent component analysis (ICA), Linear discriminant analysis(LDA) the evaluated performance in terms of accuracy achieved with 98%, 99% and 95% respectively.

关键词： Privacy Differential privacy Technological innovation Shape Reviews Big Data Security

来源：评论

学校读者我要写书评

暂无评论

A Model for the Analytical Performance of Data Lake in Stock Market Analysis with Databricks Delta Lake

A Model for the Analytical Performance of Data Lake in Stock...

引用

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

作者： Kamalakkannan, S. Yasmin, A. Arunkumar, R. Kavitha, P. School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Department of Information Technology Chennai Pallavaram India Jbas College for Women Department of Computer Science Chennai India University of South Wales Faculty of Computing Engineering and Science Treforest/Newport Campus United Kingdom School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Department of Computer Applications Chennai Pallavaram India

ISBN: (纸本)9798350300857

Stock market investments are highly rewarding but also high in risk. Modern investors use variety of tools to take informed investment decisions. In the current era of digital world, financial service industry has generated huge volume and immense verities of data with extreme speed. Due to the rapid growth in data collection and the heterogeneous nature and complexity of the data, there is a need for Big Data analytical solution that would be able to deal with the stock market data. Large volumes of unstructured, heterogeneous raw data can be stored in a massively scalable manner using data lakes, which are the ideal solution to the big data storage conundrum. The ability of a data lake to preserve data in its original format while processing it at runtime using a schema on-read technique is its key feature. The challenge faced in the data lake is performing analytics which is a significant tool to calculate and analyze the stock market. The proposed architecture of Azure Databricks DeltaLake (ADDL) with Azure DataLake Storage Generation 2 (ADLSG2) is used for analytical processes like Fibonacci retracement for better stock analysis, which aid in forecasting the market price for better investment. As a result, the research focus is to produce a storage having read as well as write capabilities by taking into consideration the Extract-Load-Transform (ELT) operation on the datasource. In this experimental databricks implementation, runtime is performed using open source of Apache Spark API and a highly improved execution engine, which results in a significant performance improvement when comparing to the standard source of Apache Spark available on the ADLS platform. Additionally, the Fibonacci retracement level calculation is achieved with the analytics and forecasting of test close price with various ML and DL techniques such as KNN, LSTM are compared with original price of the test data for better prediction of forecast close price. © 2023 IEEE.

关键词： Big data

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

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：