检索结果-内蒙古大学图书馆

Robust Multi-Dialect End-to-End ASR Model Jointly with Beam Search Threshold Pruning and LLM

SN computer science 2025年第4期6卷 1-12页

作者： Shunmuga Priya, M.C. Karthika Renuka, D. Ashok Kumar, L. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India Department of Information Technology PSG College of Technology Coimbatore India Department of Electrical and Electronics Engineering Thiagarajar College of Engineering Madurai India

This paper aims to develop a novel robust multi-dialect end-to-end ASR system with beam search threshold pruning. The efficacy of our proposed model is evaluated using word error rate (WER). Our key contributions are: (1) To develop an end-to-end ASR system using attention-based neural network architecture and analyze the effectiveness of two features such as MFCC and log mel filter bank energies on multiple speech dialect corpora including American, Britain, and Indian accents;(2) To integrate beam search threshold pruning as a decoding mechanism to reduce the decoding time (3) To conduct an experimental analysis to test the model performance and compare the results against baseline system. (4) Post processing analysis are carried out using Llama2-7B based large language model(LLM) for enhancing the performance of proposed ASR system. The proposed model significantly improves performance by 1.91% and 4.29% over clean and noisy speech in librispeech corpus. Similarly, for the Indian accented speech, the model attains an average WER of about 6.6%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Automatic speech recognition Beam search Decoding LLM Log Mel filter bank energies

来源：评论

学校读者我要写书评

暂无评论

An efficient approach for cement strength prediction

引用

International Journal of computers and Applications 2023年第1期45卷 8-18页

作者： Gaidhane, Vilas H. Kumar, Nand Mittal, Ravi Kant Rajevenceltha, J. Department of Electrical and Electronics Engineering Birla Institute of Technology and Science Dubai Campus Pilani United Arab Emirates Department of Computer Science Birla Institute of Technology and Science Pilani Dubai Campus United Arab Emirates Department of Mechanical Engineering Birla Institute of Technology and Science Pilani India

In this paper, a simple and computationally efficient approach is proposed to predict the cement strength. It is based on the mathematical concept of covariance matrix and polynomial coefficients. The polynomial coefficients are used to represent the features of cement strength data set. The efficiency and feasibility of the proposed approach is demonstrated on the cement strength data set collected from the cement industry for 2 days, 7 days and 28 days samples. Based on the number of dynamic input variables of the cement strength, the different prediction models such as SOM, linear and nonlinear regression and artificial neural network are designed and the various experimentations are carried to evaluate the proposed approach. Experimental results have shown the effectiveness of the proposed approach in the form of RMSE, R-square coefficients and computational time. It is observed that the proposed polynomial coefficient-artificial neural network approach performs better and predict the cement strength efficiently as compared to other existing methods. © 2019 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

FEMD: Feature Enhancement-aided Multimodal Feature Fusion Approach for Smart Contract Vulnerability Detection 30

FEMD: Feature Enhancement-aided Multimodal Feature Fusion Ap...

引用

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Li, Juan Li, Rui Lu, Youshui Cai, Bowen Cao, Yulin Lin, Hang Li, Xingxing Li, Chan Qinghai Normal University School of Computer Science Xining China Xidian University The State Key Laboratory of Tibetan Intelligent Information Processing and Application School of Computer Science Qinghai Normal University School of Computer Science and Technology Xian China School of the Instrument Science and Technology School of Electrical Engineering Xi'an Jiaotong University Xian China School of Science and Engineering University of Minnesota - Twin City Minneapolis United States

ISBN: (纸本)9798331515966

Smart contracts, due to their immutability and transparency upon deployment, entail significant economic and systemic risks from any vulnerabilities present. Traditional vulnerability detection methods suffer from low automation and high false positive rates, while existing deep learning-based approaches inadequately extract contract features, thereby limiting detection accuracy. To address these issues, this paper proposes FEMD: a feature-enhanced aided multimodal feature fusion method for smart contract vulnerability detection. Building on the foundation of addressing the low automation of traditional detection tools, our method improves the model's feature extraction performance and detection capabilities. Specifically, we construct a contract graph through Comprehensive Expert-Graph Fusion, combining multi-modal feature fusion using a multi-head attention mechanism with expert patterns to ensure the capture and effective preservation of all critical information during the fusion process. To delve deeper into potential information within smart contract graphs, we employ a Feature Enhancer that leverages transpose operations on feature matrices to extract complex interaction patterns across different dimensions. Our approach is validated through batches of experiments on the Ethereum open dataset focusing on reentrancy and timestamp dependency vulnerabilities, demonstrating significant improvements in detection accuracy and robustness. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A new predictive medical approach based on data mining and Symbiotic Organisms Search algorithm

引用

International Journal of computers and Applications 2022年第5期44卷 465-479页

作者： Noureddine, Samia Zineeddine, Baarir Toumi, Abida Betka, Abir Benharkat, Aïcha-Nabila Department of Electrical Engineering LESIA Laboratory University of Biskra Biskra Algeria Department of Computer Science INSA of Lyon Lyon France

Handling very large data, in order to make the best decision, is only possible through an extraction of knowledge. Data mining has become a widely used process in data analytics to extract the most important knowledge for predictive decision making. One of the important types of data mining is clustering mechanism;its purpose is dividing data into a set of clusters with very large data, the numbers of parameters are very high, and the clustering problem is more difficult. Metaheuristics have been widely used in clustering;they can provide satisfactory solutions for complex problems. The main objective of this paper is to propose a new clustering algorithm based on a metaheuristic technique called Symbiotic Organisms Search (SOS), it was inspired from a biological process, and it simulates the symbiotic interaction between organisms of the same population. The SOS method is used to find the optimal centers of a number of clusters, as a supervised data mining technique. Experimental results have been performed through two phases. Firstly, the SOS technique is benchmarked with six well-known test functions. Secondly, different medical datasets have been used to test our proposed clustering method based on SOS, and show its credibility of treatment. © 2020 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Enhanced Efficiency in Fog Computing: A Fuzzy Data-Driven Machine Selection Strategy

引用

International Journal of Fuzzy Systems 2024年第1期26卷 368-389页

作者： Zavieh, Hadi Javadpour, Amir Ja’fari, Forough Sangaiah, Arun Kumar Slowik, Adam School of Economics and Statistics Guangzhou University Guangzhou510006 China Harbin Institute of Technology Shenzhen China Department of Computer Engineering Sharif University of Technology Tehran Iran International Graduate School of AI National Yunlin University of Science and Technology Douliu Taiwan Department of Electronics and Computer Science Koszalin University of Technology Koszalin Poland ADiT-Lab Electrotechnics and Telecommunications Department Instituto Politécnico de Viana do Castelo Porto4900–347 Portugal Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

With the rapid proliferation of IoT and Cloud networks and the corresponding number of devices, handling incoming requests has become a significant challenge. Task scheduling problems have emerged as a common concern, necessitating the exploration of new methods for request management. This paper proposes a novel approach called the Fuzzy Inverse Markov Data Envelopment Analysis Process (FIMDEAP). Our method combines the strengths of the Fuzzy Inverse Data Envelopment Analysis (FIDEA) and Fuzzy Markov Decision Process (FMDP) techniques to enable the efficient selection of physical and virtual machines while operating in a fuzzy mode. We represent data as triangular fuzzy numbers and employ the alpha-cut method to solve the proposed models. The paper provides a mathematical optimization model for the proposed method and presents a numerical example for illustration. Furthermore, we evaluate the performance of our method in a cloud environment through simulations. The results demonstrate that our approach outperforms existing methods, namely PSO + ACO and FBPSO + FBACO, in terms of key metrics, including energy consumption, execution cost, response time, gain of cost, and makespan. © The Author(s) 2023.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

A Single-Carrier Modulation Strategy for the Reduction of the DC-Link Voltage Ripple of a 5-Level Multilevel DC-Link Inverter 50

A Single-Carrier Modulation Strategy for the Reduction of th...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Kahwa, Almachius Ebot, Besong John Fujimoto, Yasutaka Mwasilu, Francis Ojo, Joseph Olorunfemi Dept. of Electrical Engineering University of Dar es Salaam Dar es Salaam Tanzania United Republic of Inst. of Multidisciplinary Science Yokohama National University Yokohama Japan Dept. of Physics Electrical and Computer Engineering Yokohama National University Yokohama Japan Dept. of Electrical and Computer Engineering Tennessee Technological University TN United States

ISBN: (纸本)9781665464543

This paper presents a simple single-carrier PWM (SC-PWM) method based on the multi-modulation technique and using the redundant switching states of the 5-level hybrid multilevel dc-link inverter to balance the dc-link voltage. The proposed SC-PWM reduces the dc-link capacitor-voltage ripple, thereby reducing the voltage stress on the switches and improving the reliability of the inverter by eliminating all the low-fundamental frequency voltage oscillations in the capacitor voltage in the full range of power factors. Additionally, the proposed modulation strategy achieves a 2-fold reduction in the size of the output filter while reducing the total harmonic distortion of the output voltage and current. The feasibility of the proposed scheme over other modulation techniques is confirmed in a comparative analysis. Finally, the steady-state performances of the SC-PWM strategy are demonstrated in simulations and experiments. © 2024 IEEE.

关键词： Capacitor bank

来源：评论

学校读者我要写书评

暂无评论

Point-based Gesture Recognition Techniques 15

Point-based Gesture Recognition Techniques

引用

15th International Conference on Developments in eSystems engineering, DeSE 2023

作者： Sharma, Varun Kolivand, Hoshang Asadianfam, Shiva Al-Jumeily, Dhiya Jayabalan, Manoj Liverpool John Moores University Department Computer Science Liverpool United Kingdom School of Computer Science and Maths Liverpool John Moores University Liverpool United Kingdom Qom University of Technology Faculty of Electrical and Computer Engineering Qom Iran Islamic Azad University Qom Branch Department of Computer Engineering Qom Iran

Gesture recognition is a computing process that attempts to recognize and interpret human gestures through the use of mathematical algorithms. In this paper, we describe Point Based Gesture Recognition and Point Cloud... 详细信息

ISBN: (纸本)9798350335149

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Parking Trajectory Modification Using Image Sensors and Ultrasonic Sensors in A Model Vehicle

引用

Journal of Institute of Control, Robotics and Systems 2022年第3期28卷 232-241页

作者： Jo, Younggon Ha, Jeongmok Hwang, Sung Soo VADAS Co. Ltd Korea Republic of School of Computer Science and Electrical Engineering Handong Global University Korea Republic of

This paper outlines a proposed method of modifying parking trajectory during the autonomous valet parking process. Most autonomous valet parking systems calculate trajectories by first finding the location of a parking space and then tracking the path between the current position and the space while driving or parking. However, these systems do not have a process of modifying parking trajectories in the middle of the action. This increases the risk of collisions due to a system failure to properly detect new obstacles or incorrectly generated parking trajectories arising from hardware errors. To address these problems, it is necessary to conduct research on how to modify parking trajectories while driving. The methods outlined in this paper utilize visual simultaneous localization and mapping (Visual SLAM), ultrasonic sensors, and models with Ackerman geometry to adjust parking trajectories. Visual SLAM determines the location of the model vehicle and the chosen parking space. Once these locations are established, ultrasonic sensors determine whether the situation requires trajectory modification. From this information, the transformed Ackerman geometric model is applied to compute any required trajectory changes. This new method is applied to experimental parking scenarios to determine whether the proposed trajectory modification method was viable. The experimental results of this study indicated that autonomous parking was successfully carried out in 81.66% and 78.33% of autonomous parking events where the parking space was located on the left and right sides of the model vehicle, respectively. These results suggest that applying this model to autonomous parking and driving scenarios makes trajectory generation a viable solution for collision avoidance. © ICROS 2022.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

MEC-IoT-Healthcare: Analysis and Prospects

引用

computers, Materials & Continua 2023年第6期75卷 6219-6250页

作者： Hongyuan Wang Mohammed Dauwed Imran Khan Nor Samsiah Sani Hasmila Amirah Omar Hirofumi Amano Samih M.Mostafa College of Computer Science Guangdong University of Science and TechnologyDongGuan523083China Department of Medical Instrumentation Techniques Engineering Dijlah University CollegeBaghdadIraq Department of Electrical Engineering University of Engineering&TechnologyPeshawar814Pakistan Center for Artificial Intelligence Technology Faculty of Information Science and TechnologyUniversiti Kebangsaan Malaysia43600BangiSelangorMalaysia Research Institute for Information Technology Kyushu UniversityFukuoka819-0395Japan Computer Science-Mathematics Department Faculty of ScienceSouth Valley UniversityQena83523Egypt

Physical sensors,intelligent sensors,and output recommenda-tions are all examples of smart health technology that can be used to monitor patients’health and change their *** health is an Internet-of-Things(IoT)-aware network and sensing infrastructure that provides real-time,intelligent,and ubiquitous healthcare *** of the rapid development of cloud computing,as well as related technologies such as fog computing,smart health research is progressively moving in the right ***,fog computing,IoT sensors,blockchain,privacy and security,and other related technologies have been the focus of smart health research in recent *** the moment,the focus in cloud and smart health research is on how to use the cloud to solve the problem of enormous health data and enhance service performance,including cloud storage,retrieval,and calculation of health big *** article reviews state-of-the-art edge computing methods that has shifted to the collection,transmission,and calculation of health data,which includes various sensors and wearable devices used to collect health data,various wireless sensor technologies,and how to process health data and improve edge performance,among other ***,the typical smart health application cases,blockchain’s application in smart health,and related privacy and security issues were reviewed,as well as future difficulties and potential for smart health *** comparative analysis provides a reference for the the mobile edge computing in healthcare systems.

关键词： IoT mobile-edge computing cloud computing e-health

来源：评论

学校读者我要写书评

暂无评论

Investigation of Formation and Ultrasonic Disassembling of Red Blood Cell Aggregation Aimed for Maintenance of Blood Channel

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, Information and Systems 2022年第6期142卷 629-636页

作者： Hatakeyama, Mayu Akamatsu, Yuichiro Sato, Takayuki Department of Electrical Engineering and Computer Science Tokyo Metropolitan University 1-1 Minamiosawa Hachioji Tokyo192-0397 Japan

Establishment of real-time monitoring technique for blood viscosity during extracorporeal circulation treatment is needed. We have demonstrated that red blood cell (RBC, hereafter) aggregation degree, which highly correlates with the blood viscosity, can be estimated by the ultrasound spectroscopic observation of the RBC and the defining of the peak frequency by the Fast Fourier Transform process. In this study, the peak frequency was measured to investigate the aggregation degree of RBC flowing in a simple heart-lung machine. In addition, to disassemble the RBC aggregations that might cause the clogging of the circuit, a disassemble technique of the RBC aggregations using a focused 5 MHz ultrasonic transducer was also proposed. As the first step of this study, the disassembling of the RBC aggregations was carried out under the still condition and its effect was confirmed by the peak frequency method. © 2022 The Institute of electrical Engineers of Japan.

关键词： Ultrasonic transducers

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：