检索结果-内蒙古大学图书馆

Prediction of Parkinson’s disease based on artificial neural networks using speech datasets

Journal of Ambient Intelligence and Humanized Computing 2023年第10期14卷 13571-13584页

作者： Liu, Wei Liu, Jierong Peng, Tao Wang, Guojun Balas, Valentina Emilia Geman, Oana Chiu, Hung-Wen School of Information and Communication Engineering Hainan University Hainan Haikou570228 China School of Computer Science and Cyber Engineering Guangzhou University Guangdong Guangzhou510006 China College of Biomedical Information and Engineering Hainan Medical University Street Hainan Haikou571199 China Department of Automation and Applied Informatics Aurel Vlaicu University of Arad Arad310130 Romania Department of Health and Human Development Stefan cel Mare University of Suceava Suceava720229 Romania Graduate Institute of Biomedical Informatics Taipei Medical University Taipei Taiwan

Parkinson’s disease (PD) is a progressive disorder of the nervous system that affects movement. Early prediction of PD can increase the chances of earlier intervention and delay the onset of the disease. Vocal impairment is one of the most important signs in the early stages of PD. Therefore, PD detection based on speech analysis and vocal patterns has attracted significant attention recently. In this paper, we propose a vowel-based artificial neural network (ANN) model for PD prediction based on single vowel phonation. Firstly, we propose a novel multi-layer neural network based on speech features to predict PD. The speech samples from 48 PD patients and 20 healthy individuals are processed into four types: vowel, number, word, and short sentence. Secondly, we establish ANN models with single-type speech samples versus combinations of multi-type speech samples, respectively. Comparative experiments demonstrate that the single-type vowel model is superior to other single-type models as well as multi-type models. Finally, we build a vowel-based ANN model for PD prediction and evaluate its performance. Extensive experiments demonstrate that the proposed model has a prediction accuracy of 91%, sensitivity of 99%, specificity of 82%, and area under the receiver operating characteristic curve (AUC) of 91%, which is superior to the performance of previous methods. Overall, this study demonstrates that the proposed model can provide good classification accuracy for predicting PD and can improve the rate of early diagnosis. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Compact Millimeter-Wave Antenna Operating in 28/38 GHz Spectrum

Compact Millimeter-Wave Antenna Operating in 28/38 GHz Spect...

引用

2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022

作者： Rizvi, Syed Naheel Raza Sarfraz, Muhammad Alibakhshikenari, Mohammad Dalarsson, Mariana Falcone, Francisco Chungbuk National University Department of Information and Communication Engineering Cheongju Korea Republic of Virtual University of Pakistan Department of Computer Science Lahore Pakistan Universidad Carlos III de Madrid Department of Signal Theory and Communications Madrid Leganés28911 Spain KTH Royal Institute of Technology School of Electrical Engineering and Computer Science StockholmSE 100-44 Sweden Public University of Navarre Electric Electronic and Communication Engineering Department Pamplona31006 Spain Public University of Navarre Institute of Smart Cities Pamplona31006 Spain

ISBN: (数字)9781665496582

ISBN: (纸本)9781665496582

We present a compact wideband antenna operating in the 28 GHz and 38 GHz millimeter-wave spectrum. The proposed antenna is designed on the Rogers RT/duroid 5880 substrate. The proposed antenna has a simple geometry and compact dimensions of 17 mm × 12 mm × 0.79 mm. The antenna design is simulated using the ANSYS HFSS software. The features of the proposed antenna are also compared to similar designs from the literature, to demonstrate the potential of our antenna for use in the targeted frequency band. The results in the present paper indicate that our design is a good candidate for use in future wireless communication systems. © 2022 IEEE.

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

Rethinking the Reversal Curse of LLMs: a Prescription from Human Knowledge Reversal

Rethinking the Reversal Curse of LLMs: a Prescription from H...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Lu, Zhicong Jin, Li Li, Peiguang Tian, Yu Zhang, Linhao Wang, Sirui Xu, Guangluan Tian, Changyuan Cai, Xunliang Aerospace Information Research Institute Chinese Academy of Sciences China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences China Meituan China Dept. of Comp. Sci. and Tech. Institute for AI Tsinghua University China Department of Automation Tsinghua University China

ISBN: (纸本)9798891761643

Large Language Models (LLMs) have exhibited exceptional performance across diverse domains. However, recent studies reveal that LLMs are plagued by the "reversal curse". Most existing methods rely on aggressive sample permutation and pay little attention to delving into the underlying reasons for this issue, resulting in only partial mitigation. In this paper, inspired by human knowledge reversal, we investigate and quantify the individual influence of three potential reasons on the reversal curse: 1) knowledge clarity, 2) entity correlation modeling, and 3) pairwise relationship reasoning capability. Motivated by the analysis of these reasons, we propose a novel Pairwise entity Order- and Relationship-Enhanced (PORE) data strategy, which facilitates bidirectional entity correlation modeling and pairwise relationship reasoning to overcome the reversal curse. Specifically, PORE augments the samples with entity order-reversal and semantically preserved question-answer pairs, enhancing the encoding of entity correlations in both directions. PORE also employs entity-interleaved pairwise relationship data, which elevates the model's capability for relationship reasoning. Additionally, to improve the recall of reverse relationships, we leverage knowledge clarity to construct high-clarity data for PORE. Extensive experimental results on available and two newly assembled datasets demonstrate the effectiveness and generalization of our method in both data-sufficient and -constrained situations. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

The Symphony of Style: An Extensive Examination of Determination Mechanisms in Deep Learning-Inspired Outfit Suggestions 2

The Symphony of Style: An Extensive Examination of Determina...

引用

2nd International Conference on Computational Intelligence, communication Technology and Networking, CICTN 2025

作者： Guru Prasad, M.S. Bhosagi, Ravatappa A. Madhusudhana, K. Prithviraj Chandrappa, S. Kumar, Vikash Dehradun India School of Computing and Information Technology Reva University Bengaluru India Dept. of Electronics & Communication Engineering SDM Institute of Technology Ujire India NMAMIT Mangalore India Bengaluru India Department of Computer Application Graphic Era Deemed University Dehradun India

ISBN: (纸本)9798331530389

In the field of the fashion industry, the introduction of deep learning technology has taken an innovative revolution by providing assistance in the construction of intellectual systems that are intelligent to deliver personalized ensemble recommendations. In this research work, an innovative ensemble recommendation structure called Deep Learning VGG16 (Visual Geometry Group 16) recommender is presented. The proposed method allows a deep learning model VGG16 to understand complex patterns and developments resulting from a vast group of fashion images. In order to increase the user experience and greater participation in the well-established fashion industry, the system offers personalized ensemble ideas. The important, core and fundamental component of the system is VGG16, consisting of 13 convolutional layers and 3 fully connected layers, which is used to support the analysis of fashion images. A cutting-edge convolutional neural network (CNN) model is improved over a large and diverse collection of fashion images. Model will extract advanced high-level information and statistics with the capability to distinguish particulars in colour patterns, clothing combinations, and stylistic elements. Using this process of development, the system becomes better at identifying user preferences and fashion trends. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Intelligent and Cost-Effective IoT-Based Irrigation System Using Machine Learning 2

An Intelligent and Cost-Effective IoT-Based Irrigation Syste...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Kadiyala, Sreedevi Potluri, Chandra Srinivas Birke, Ali Hussen Mehra, Aashish Rajput, Sneha Padmavathi, Katakam Guru Nanak Institutions Technical Campus Department of Computer Science and Engineering Hyderabad India Werabe University Department of Information Technology Werabe Ethiopia Werabe University Department of Information Systems Werabe Ethiopia School of Retail Management Symbiosis University of Applied Sciences Indore India Prestige Institute of Management and Research Gwalior India Stanley College of Engineering and Technology for Women Department of Electronics and Communication Hyderabad India

ISBN: (纸本)9798350371055

This work presents and implements a low-cost irrigation system for smart agriculture that is based on the Internet of Things (IoT). In order to continuously monitor environmental data in real time, the system is equipped with a network of sensors, including pressure, temperature, moisture, and water level sensors. In order to anticipate when irrigation pumps will switch on, machine learning techniques including Artificial Neural Networks (ANN), Decision Trees (DT), Naive Bayes (NB), and Support Vector Machines (SVM) are linked depending on established parameters. The study shows that the ANN model can identify complicated patterns in the agricultural environment with an accuracy of up to 98.33%. Farmers are able to make well-informed decisions quickly thanks to the cloud connectivity and intuitive interface of remote monitoring and control. Because predictive modeling minimizes pump activation delays, it lessens the chance of both over- and under-irrigation. The suggested strategy makes the most use of available water and provides opportunities for precision farming, which is a major step forward for sustainable agriculture. The study's findings demonstrate how well the system uses resources and open the door for the future creation of innovative, scalable agricultural technology. © 2024 IEEE.

关键词： Agriculture IoT Machine Learning Precision Farming Water Management

来源：评论

学校读者我要写书评

暂无评论

Non Dominated Sorting Genetic Algorithm (NSGA-II) Modelling for AZ 31 Magnesium Alloy Composite

Non Dominated Sorting Genetic Algorithm (NSGA-II) Modelling ...

引用

Cognitive Computing in engineering, communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), International Conference on

作者： Amit Tiwari Payal Bansal Himanshu Vasnani Neny Pandel Department of Mechanical Engineering Suresh Gyan Vihar University Jaipur Rajasthan India Department of Electronics Communication & Engineering Poornima Institute of Engineering & Technology Jaipur Rajasthan India Department of Computer Science Engineering & IT Suresh Gyan Vihar University Jaipur Rajasthan India

ISBN: (数字)9798331518523

ISBN: (纸本)9798331518530

The rolling process has proven to have a significant effect on the mechanical properties of metallic alloys especially in their strength. In the present research work, process parameters are optimized with a view to maximize hardness and tensile strength of experimental alloy by employing a Multi-Objective Genetic Algorithm (NSGA-II) along with linear regression. The experimental data used in this predictive modeling was from fabricated magnesium AZ31 alloy composite produced through stir casting. As-cast alloys were homogenized at 500°C for 12 hours, followed by quenching in ice water. The as-quenched material was then hot rolled at different rolling temperatures, number of rolling passes, and initial stock thickness to study the process. The rolled materials were subjected to hardness and tensile strength measurements as dependent variables. Instead of training an artificial neural network to specify the objective function for NSGA-II, we created a mathematical model using regression analysis. This equation is used as the objective function for multi-objective optimization with NSGA-II. The NSGA-II predicted value for the maximum hardness of 107.41 VHN, is in close agreement with the obtained result of 106.6 VHN. Similarly, the maximum experimental tensile strength was 266.82 MPa whereas NSGA-II said that it will be approximately 253 MPa for this value. Under these circumstances, the predictive accuracy of NSGA-II was within 1-5% deviation from experimental results (i.e. good correspondence between the optimization strategy with experimental data).

关键词： Temperature measurement Training Composite materials Predictive models Linear programming Mathematical models Magnesium Optimization Genetic algorithms Sorting

来源：评论

学校读者我要写书评

暂无评论

VocalEyes: Enhancing Environmental Perception for the Visually Impaired through Vision-Language Models and Distance-Aware Object Detection

arXiv

引用

arXiv 2025年

作者： Chavan, Kunal Balaji, Keertan Barigidad, Spoorti Chiluveru, Samba Raju School of Electronics Engineering Vellore Institute of Technology Vellore India Department of Computer Science and Engineering S.R.M Institute of Technology Chennai India Electrical Electronics and Communication Engineering IIT Dharwad Dharwad India

With an increasing demand for assistive technologies that promote the independence and mobility of visually impaired people, this study suggests an innovative real-time system that gives audio descriptions of a user’s surroundings to improve situational awareness. The system acquires live video input and processes it with a quantized and fine-tuned Florence-2 big model, adjusted to 4-bit accuracy for efficient operation on low-power edge devices such as the NVIDIA Jetson Orin Nano. By transforming the video signal into frames with a 5-frame latency, the model provides rapid and contextually pertinent descriptions of objects, pedestrians, and barriers, together with their estimated distances. The system employs Parler TTS Mini, a lightweight and adaptable Text-to-Speech (TTS) solution, for efficient audio feedback. It accommodates 34 distinct speaker types and enables customization of speech tone, pace, and style to suit user requirements. This study examines the quantization and fine-tuning techniques utilized to modify the Florence-2 model for this application, illustrating how the integration of a compact model architecture with a versatile TTS component improves real-time performance and user experience. The proposed system is assessed based on its accuracy, efficiency, and usefulness, providing a viable option to aid vision-impaired users in navigating their surroundings securely and successfully. © 2025, CC BY.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Multi-Access Edge Computing Using Intelligent Mobile User Resource Allocation In 6G

Multi-Access Edge Computing Using Intelligent Mobile User Re...

引用

Sciences and Techniques of Automatic Control and computer engineering MI-STA, IEEE International Maghreb Meeting of the Conference on

作者： Mamoon M. Saeed Rashid A. Saeed Rania A. Mokhtar AbdulGuddoos S. A. Gaid Zeinab E. Ahmed Mohammed S. Elbasheir Department of Communications and Electronics Engineering Faculty of Engineering University of Modern Sciences (UMS) Yemen Department of Electrical and Electronic Engineering Faculty of Engineering Taif University Altaif Saudi Arabia Department of Computer Engineering College of Computers and Information Technology Taif University Taif Saudi Arabia Dept. of Communication & Computer Engineering Faculty of Engineering & Information Technology Taiz University Taiz Yemen Department of Electrical and Computer International Islamic University Malaysia Malaysia School of Electronic Engineering Sudan University of Science and Technology Khartoum Sudan

ISBN: (数字)9798350372632

ISBN: (纸本)9798350372649

Edge computing plays a crucial role in the advancement of Beyond 5G (B5G) and 6G networks. The substantial growth in network traffic and computational requirements necessitates the implementation of multi-access edge computing (MEC) as a viable solution. MEC aims to bring the capabilities of cloud computing closer to end-users by integrating them into the radio access network (RAN). This research introduces an optimal approach to connect mobile users with MEC hosts and access points, effectively distributing radio and computing resources to individual mobile users. The objective is achieved by lowering the total user transmit power while abiding by latency constraints in both the communication and computation phases, using the Grey Wolf Optimization technique (GWO). A comparison to alternative smart techniques demonstrates the effectiveness of the suggested approach

关键词： 6G mobile communication Analytical models Cloud computing Multi-access edge computing Computational modeling Conferences Telecommunication traffic

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Lifespan Prediction Modelling for Electric Submersible Pumps in Oil Wells

Machine Learning-Based Lifespan Prediction Modelling for Ele...

引用

International Conference on Computational and Characterization Techniques in engineering & Sciences (CCTES)

作者： J. Rajakala Satyaveer Gupta Pothala Mutyalu Naidu Basi Reddy A S. Revathi R. Senthamil Selvan Department of Computer Science and Engineering Sai Spurthi Institute of Technology Gangaram India Department of Electrical Engineering Delhi Technical Campus Greater Noida India Department of CSE Vignan Institute of Technology And Science Hyderabad India Department of Computer Science and Engineering School of Computing Mohan Babu University Tirupati India Department of Computer Science and Engineering Sri Ramakrishna Institute of Technology Coimbatore India Department of Electronics and Communication Engineering Annamacharya Institute of Technology and Sciences Tirupati India

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

To maintain the output flow rate and prolong the life of oil wells, artificial lift is crucial to the petroleum industry. Electric Submersible Pumps (ESP) are a widely used artificial lift technique due to their ability to generate large flow rates in very deep wells. ESPs have a much shorter lifetime than anticipated, even though they are designed to function in harsh environments including corrosion, high temperatures, and high pressure. Because ESP intervention work is far more expensive than other artificial lift techniques, particularly for offshore wells, ESP failures result in production loss and raise replacement costs. Knowing when an ESP may fail is thus highly helpful in the oil production industry and affects how oil wells are designed, built, and managed. Using three machine learning algorithms—Decision Tree, Random Forest, and Gradient Boosting Machine—this study contributes to the construction of prediction models for ESP lifespan that take into account both dynamic and static ESP features. The model that produced the best results for ESP life cycle prediction was determined by comparing the output of various models. To predict the most influential characteristics on the length of ESP, this research also assessed the influence factor of different operational parameters. By knowing more about ESP behavior, early efforts to avert possible ESP failures may be realized thanks to the study's findings.

关键词： Temperature distribution Oils Heuristic algorithms Pumps Production Predictive models Boosting Prediction algorithms Underwater vehicles Random forests

来源：评论

学校读者我要写书评

暂无评论

Self-polarized RGB device realized by semipolar micro-LEDs and perovskite-in-polymer films for backlight applications

引用

Opto-electronic Advances 2024年第3期7卷 35-49页

作者： Tingwei Lu Yue Lin Tianqi Zhang Yue Huang Xiaotong Fan Shouqiang Lai Yijun Lu Hao-Chung Kuo Zhong Chen Tingzhu Wu Rong Zhang School of Electronic Science and Engineering Fujian Engineering Research Center for Solid-State LightingXiamen UniversityXiamen 361005China Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province(IKKEM) Xiamen 361005China Department of Photonics and Graduate Institute of Electro-Optical Engineering College of Electrical and Computer EngineeringYang Ming Chiao Tung UniversityHsinchu 30010China Semiconductor Research Center Hon Hai Research InstituteTaipei 11492China.

In backlighting systems for liquid crystal displays,conventional red,green,and blue(RGB)light sources that lack polarization properties can result in a significant optical loss of up to 50%when passing through a *** address this inefficiency and optimize energy utilization,this study presents a high-performance device designed for RGB polarized *** device employs an array of semipolar blueμLEDs with inherent polarization capabilities,coupled with mechanically stretched films of green-emitting CsPbBr3 nanorods and red-emitting CsPbI3-Cs4PbI6 hybrid *** CsPbBr3 nanorods in the polymer film offer intrinsic polarization emission,while the aligned-wire structures formed by the stable CsPbI3-Cs4PbI6 hybrid nanocrystals contribute to substantial anisotropic emissions,due to their high dielectric *** resulting device achieved RGB polarization degrees of 0.26,0.48,and 0.38,respectively,and exhibited a broad color gamut,reaching 137.2%of the NTSC standard and 102.5%of the Rec.2020 *** compared to a device utilizing c-plane LEDs for excitation,the current approach increased the intensity of light transmitted through the polarizer by 73.6%.This novel fabrication approach for polarized devices containing RGB components holds considerable promise for advancing next-generation display technologies.

关键词： halide perovskite light-emitting-diodes polarized emission nanocrystals stability

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：