检索结果-内蒙古大学图书馆

Rice Variety Classification Based on Optimized Near-Infrared Spectral Classification Model

Rice science 2024年第1期31卷 6-9,I0009-I0012页

作者： YANG Sen WANG Zhenmin ZHANG Houqing SONG Wenlong College of Computer and Control Engineering Northeast Forestry UniversityHarbin 150040China The 49th Research Institute of China Electronics Technology Group Corporation Harbin 150000China

Accurate classification of rice variety is essential to ensure the brand value of high-quality rice *** the impact of sample state on modeling optimization algorithms,rice samples after grinding and sealing were *** enhance the accuracy of rice variety classification,we introduced a spectral characteristic wavelength selection method based on adaptive sliding window permutation entropy(ASW-PE).

关键词： sealing Infrared grinding

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of ML Algorithms for Forecasting Time Series Stock Returns 4

Comparative Analysis of ML Algorithms for Forecasting Time S...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Bondili, Bala Karthikeya Singh Bolagani, Sai Pavan Thatikonda, Rakshith Vnr Vignana Jyothi Institute of Engineering and Technology Computer Science and Engineering Telangana India Koneru Lakshmaiah Education Foundation Computer Science and Engineering Andra Pradesh India Cmr Technical Campus Electronics and Communication Engineering Telangana India

ISBN: (纸本)9798331523923

Forecasting stock returns is a challenging task due to high data variability, noise, and the inherent unpredictability of financial markets. Traditional methods like ARIMA and regression lack scalability and fail to capture complex data patterns. Recent advancements in machine learning, including ensemble methods such as Random Forest and Boosting, have shown promise in improving predictive accuracy. However, these methods face challenges such as overfitting, computational complexity, and data dependency. This paper evaluates the performance of various machine learning algorithms and their ability to address these challenges to improve forecast reliability. By using techniques like dimensionality reduction and hyperparameter tuning, the study identifies strategies to enhance prediction accuracy while reducing computational complexity and costs. © 2025 IEEE.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Multi-layer composite autoencoders for semi-supervised change detection in heterogeneous remote sensing images

引用

Science China(Information Sciences) 2023年第4期66卷 124-125页

作者： Jiao SHI Tiancheng WU Hanwen YU A.K.QIN Gwanggil JEON Yu LEI School of Electronics and Information Northwestern Polytechnical University School of Resources and Environment University of Electronic Science and Technology of China Department of Computer Science and Software Engineering Swinburne University of Technology Department of Embedded Systems Engineering Incheon National University

With the increasing complexity of application scenarios, the fusion of different remote sensing data types has gradually become a trend, which can greatly improve the utilization of massive remote sensing *** the problem of change detection for heterogeneous remote images can be much more complicated than the traditional change detection for homologous remote sensing images,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting Lung Cancer Disease Using Optimized Weighting-Based Enhanced Neural Network Classification 3

Predicting Lung Cancer Disease Using Optimized Weighting-Bas...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Chitra, T. Hemanth, S.V. Karthikeyan, S. Reddy, Vallem Ranadheer Banupriya, K.M. Amirthayogam, G. Christian College of Engineering and Technology Department of Electronics and Communication Engineering Tamilnadu Oddanchatram624619 India Hyderabad Institute of Technology and Management Department of Computer Science and Engineering Telangana Hyderabad501401 India PSNA College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Dindigul624622 India Vaagdevi Engineering College Department of Computer Science and Engineering Telangana Bollikunta506005 India Arunai Engineering College Department of Computer Science and Engineering Tamil Nadu Tiruvannamalai606603 India Department of Information Technology Tamilnadu Chennai603103 India

ISBN: (纸本)9798350372120

Lung cancer is a highly lethal disease, claiming the lives of approximately 1 million individuals annually. Cancer is characterized by abnormal and rapid cell growth, making it difficult to control, though early diagnosis through Computed Tomography (CT) scan images can significantly improve chances of survival. However, detecting lung cancer early is challenging and can increase the risk of complications such as infection, inflammation, and tumor growth in the lungs. Moreover, the current methods for analyzing lung cancer prognosis have low accuracy. To solve this problem, we proposed an Optimized Weighting-Based Enhanced Neural Network (OWENN) method to classify patients based on attributes accurately. Furthermore, they utilize the Adaptive Median Filter (AMF) technique during image pre-processing to calculate the mean value of each pixel and remove noise. Moreover, Improved Particle Swarm Optimization (IPSO) can be implemented to extract tumors from lung images efficiently. Finally, the OWENN method improves the accuracy of cancer or non-cancer detection by classifying patients based on their selected attributes. Afterward, the experimental results indicate that the suggested OWENN approach can attain lung cancer prediction by evaluating sensitivity, precision, accuracy, and time delay. © 2024 IEEE.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

A novel convolution neural network architecture with fully connected network for efficient speech emotion recognition system

引用

International Journal of Information technology (Singapore) 2025年 1-9页

作者： Singh, Vandana Prasad, Swati Electronics and Communication Engineering Department Birla Institute of Technology Mesra Jharkhand Ranchi 835215 India Computer Science & Engineering Birla Institute of Technology Mesra (Noida Off Campus) Uttar Pradesh Noida 201301 India

Speech emotion recognition determines the emotion of a speaker utilizing only his/her spoken utterance. This research faces difficulty in achieving high speech emotion recognition accuracy due to differences in speaker’s emotional intensity. This study has proposed a novel 1D CNN architecture integrated with fully connected layers which is able to capture the emotion characteristics in speech efficiently for addressing the above mentioned issue. Experiments conducted on RAVDESS dataset which consists of two levels of speaker emotion intensity, namely, ‘strong’ and ‘normal’ have shown better overall performance for the proposed architecture over the Baseline. The proposed method has achieved 4.1% improvement in average speech emotion recognition accuracy compared to the Baseline across 8 different emotions. Further the proposed method has demonstrated superior performance for recognizing neutral & sad emotions. It has achieved 14 percent and 9 percent higher speech emotion recognition accuracy over the Basline method for neutral and sad emotions, respectively. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Convolutional neural network Data augmentation Fully connected network Human–computer interaction RAVDESS Speech emotion recognition

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation in 6G Network for High-Speed Train Using D2D Outband Communication 3rd

Resource Allocation in 6G Network for High-Speed Train Using...

引用

3rd International Conference on Machine Vision and Augmented Intelligence, MAI 2023

作者： Garg, Aakansha Arya, Rajeev Singh, Maheshwari Prasad Wireless Sensor Network Lab Department of Electronics and Communication Engineering Patna India Department of Computer Science and Engineering National Institute of Technology Patna India

ISBN: (纸本)9789819743582

The growth of 6G results in rising data transmission rate in static scenario. To achieve fast communication and computation with quality service in high-speed train is a challenge. This is due to fast handover and Doppler shift. To effectively communicate in high-speed train, the placement of a mobile relay (MR) with small server at the rooftop of train coach is proposed. The base station sends channel state information to mobile relay which stores it in the stack. The resource assignment has been conducted by an improved grey wolf optimization algorithm. The focus is at improving throughput with reduction in latency and energy consumption. The simulation outcomes manifests that the presented algorithm carry-out finer in comparison of the Hungarian algorithm. The accomplished results are refined almost three times in respect of energy consumption, latency, and throughput. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Identification of Medicinal Plants and Related Fungal Diseases based on Deep Learning Model 6

Identification of Medicinal Plants and Related Fungal Diseas...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Kani, Mathina M. Mahalakshmi, R. Shunmugavel, V. Kareem, Abdul M. Department of Computer Science and Engineering Sethu Institute of Technology Virudhunagar India Department of Electrical and Electronics Engineering Quantanics TechServ pvt Ltd Madurai India

ISBN: (纸本)9798331522667

In today’s technological landscape, manual methods are increasingly being replaced by automated computer systems, streamlining tasks and enhancing efficiency. Within the realm of agricultural research, two critical areas plant identification and disease classification have shifted toward computerized solutions. With millions of plant species globally, medicinal plants hold particular significance due to their healing properties in traditional medicine. These readily accessible and culturally important remedies not only contribute to affordable healthcare but also sustain livelihoods in indigenous and rural communities. To address these challenges, our study evaluates the performance of two widely used pre-trained deep learning models U-Net and F-Net. By comparing their accuracy levels, we aim to enhance disease detection. Additionally, we present performance metrics such as accuracy and error rates, visualized through graphs. Our user interface (UI) leverages Kivy, an open-source multiplatform GUI development library for Python. Kivy enables cross-device app development, emphasizing code reusability and rapid prototyping, making it a valuable tool for interaction design across iOS, Android, Windows, OS X, and GNU/Linux platforms. © 2025 IEEE.

关键词： Medicinal chemistry

来源：评论

学校读者我要写书评

暂无评论

Investigation of the Temperature Impact on the Performance Characteristics of the Field-Plated Recessed Gate III-Nitride HEMT on β-Ga2 O3 Substrate 3rd

Investigation of the Temperature Impact on the Performance C...

引用

3rd International Conference on Micro and Nanoelectronics Devices, Circuits and Systems, MNDCS 2023

作者： Purnachandra Rao, G. Lenka, Trupti Ranjan Boukortt, Nour El. I. Nguyen, Hieu Pham Trung Department of Electronics and Communication Engineering National Institute of Technology Assam Silchar India Department of Electronics and Communication Engineering Kuwait College of Science and Technology Doha Kuwait Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States

ISBN: (纸本)9789819944941

In this chapter, a field-plated recessed gate III-nitride High Electron Mobility Transistor (HEMT) grown on β-Ga2O3 substrate is designed. The electrical characteristics of the proposed HEMT is investigated by using the thermal models of ATLAS TCAD simulations. The impact of temperature on the transport properties is studied. Influence of the substrate thickness with temperature changes on drain characteristics are also discussed. A field-plate and gate length of 20 nm each with 30 nm recessed depth is considered for the analysis. Self-heating effect in drain current characteristics are investigated with temperature changes. The maximum drain saturation current observed with 180 nm (230 nm) substrate thickness are 1.1 (1.06) A/mm, 0.708 (0.705) A/mm and 0.502 (0.499) A/mm for 300 K, 550 K and 800 K, respectively. The influence of substrate layer thickness on drain current is less apparent at a higher temperature. The findings demonstrated that scattering processes that emerge when temperature increases above a particular amount cause both the mobility and the carrier concentration of 2DEG to decrease. Furthermore, A kink effect is seen in the drain current–voltage characteristics for gate voltage VGSâ€‰=â€‰− 2 V. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： High electron mobility transistors

来源：评论

学校读者我要写书评

暂无评论

Enhancing Blurred Image Processing with IoT Integration for Improved Clarity 2

Enhancing Blurred Image Processing with IoT Integration for ...

引用

2nd IEEE International Conference on Emerging Research in Computational Science, ICERCS 2024

作者： Tummalapalli, Geetamma Summia Parveen, H. Ramesh, S.M. Monica, P. Santhiya, B. Rajasekaran, Arun Sekar GMR Institute of Technology Department of Electronics and Communication Engineering Rajam India Sri Eshwar College of Engineering Department of Computer Science Engineering Coimbatore India KPR Institute of Engineering and Technology Department of Electronics and Communication Engineering Coimbatore India GITAM Deemed to be University Department of Electronics and Communication Engineering GST Visakhapatnam India Bannari Amman Institute of Technology Department of Information Technology Sathyamangalam India SR University Department of Electronics and Communication Engineering Warangal India

ISBN: (纸本)9798331534950

A blurred image is an image that has undergone a blurring or smoothing effect, resulting in a loss of sharpness and clarity. Blurring is a technique used in image processing to reduce noise, remove unwanted details, or create a visual effect. It involves averaging or blending neighboring pixels to create a smoother appearance. The specific processing techniques and algorithms used will depend on the nature and extent of the blur, the intended outcome, and the available software or programming tools. It's important to experiment with different methods and parameters to achieve the desired result. IoT (Internet of Things) can be used in image processing in several ways to enhance functionality, efficiency, and data processing capabilities enhances image processing by enabling real-time analysis, edge computing capabilities, integration with other IoT devices, and remote monitoring and control. These advancements facilitate applications such as object detection, image recognition, and real-time decision-making, contributing to more efficient and intelligent systems in various domains. Here is a proposed model for blurred image processing with IoT. This proposed model demonstrates the integration of IoT devices, image processing techniques, and cloud-based analytics to address the challenges of blurred image processing. It combines edge processing for real-time analysis and cloud-based processing for more complex algorithms, enabling efficient and intelligent image processing applications in various domains. © 2024 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Audio-Visual Speech Enhancement via Attention-based Sparse Graph Convolutional Neural Networks with Fire Hawk Optimization 3

Enhanced Audio-Visual Speech Enhancement via Attention-based...

引用

3rd International Conference on Automation, Computing and Renewable Systems, ICACRS 2024

作者： Hebri, Dheeraj Joon, Rakesh Kumar Mohan, M. Ramapraba, P.S. Dhulipudi, Venkata Satish Narasimharao, Jonnadula Department of Master of Computer Applications Srinivas Institute of Technology Karnataka Mangalore574143 India Department of Electronics and Communication Engineering Ganga Institute of Technology and Management Haryana 124104 India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Tamil Nadu Chennai641407 India Department of Electrical and Electronics Engineering Panimalar Engineering College Tamil Nadu Chennai600123 India Department of Electronics and Communication Engineering BVC Institute of Technology and Science Andhra Pradesh 533221 India Department of Computer Science and Engineering CMR Technical Campus Telangana Hyderabad501401 India

ISBN: (纸本)9798331532420

Audio-Visual Speech Enhancement (AVSE) has the vision to enhance speech quality and requite intelligibility by using both audio and video inputs, which is quite useful in noisy conditions. This approach acknowledges the fact that modalities such as lip movement may be equally informative of the auditory signals as the actual sound in cases where audio signals are distorted. In this research, an innovation approach to the AVSE is presented, which involves several state-of-the-art techniques. The data preprocessing step uses Z-score Min-Max Normalization to normalize the input data to help enhance the feature extraction process. Differentiable adaptive short-time Fourier transform (DA-STFT) is employed as the method of audio feature extraction that provides key temporal information. In the feature extraction process, a local directional structural pattern (LDSP) is utilized for the extraction of visual features since it examines the moving patterns on the face effectively. The fusion of data is done using a quadruplet depth-wise separable fusion convolutional neural network (QDSFCNN), which enhances the amalgamation of the audio and visual cues. Classification is done using an attention-based sparse graph convolutional neural network, known as ASGCNN, since the focus is on the relevant stipulations. Finally, to achieve the highest performance level, the fire hawk optimizer (FHO) is used for tuning parameters in the presented model. This combined approach presents advanced developments in AVSE, which provide improved speech quality in difficult conditions. © 2024 IEEE.

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：