检索结果-内蒙古大学图书馆

International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT)

作者： Sanjeev Thakur Rohit Bele Tarun Yarlagadda Ved Prakash Chaubey Shamneesh Sharma Saikat Gochhait School of Computer Science and Engineering Lovely Professional University Jalandhar Punjab India Delivery and Student Success upGrad Education Private Limited Bangalore Karnataka India SIDTM Symbiosis International Deemed University Pune Maharashtra India NRI Samara State Medical University Russia

ISBN: (数字)9798331533137

ISBN: (纸本)9798331533144

This paper analyzes the Speech Emotion Recognition (SER) procedure, a tool that helps IT systems increase their intelligence by recognizing persons' emotions from the signals put into words, by employing deep learning methods. The audio data was preprocessed by extracting the Mel-frequency cepstral coefficients (MFCCs) and later augmented by adding white noise, time shifting, pitch shifting and time stretching. The models used in this paper are Long Short-Term Memory (LSTM) networks, and Convolutional Neural Networks (CNNs). CNN architecture has convolutional operation layers, batch normalization layers followed by max-pooling layers, and dropout layers to learn speech features and to avoid overfitting. With these results, we stress the importance of the synergy of CNNs with solid preprocessing and augmentation methods in the context of SER and envision their tremendous potential in HCI, education, and health. It is worth stressing that including models such as SVM and LSTM certifies the novelty and the genetic soundness of the approach.

关键词： Support vector machines Emotion recognition Technological innovation Education Speech recognition White noise Solids Convolutional neural networks Long short term memory Overfitting

来源：评论

学校读者我要写书评

暂无评论

Influence of GFP GAN on Melanoma Classification

Influence of GFP GAN on Melanoma Classification

引用

IEEE Integrated STEM Education Conference (ISEC)

作者： Ayushi Kumar Avimanyou Vatsa Deep Chain Lab Fairleigh Dickinson University and a Monroe Township High School student Monroe Township NJ Department of Computer Science Gildart Haase School of Computer Sciences & Engineering Fairleigh Dickinson University Teaneck NJ

ISBN: (纸本)9781665484305

Imaging is widely used to detect and diagnose Melanoma skin cancer early. The ISIC facilitates public reposit to collect, label, and categorize malignant and benign images. It also provides relevant metadata for these images from dermatologists, radiologists, or researchers. The ever-growing uses of dermoscopy and the complexity of the imaging process make it difficult to find the correct pattern in images of Melanoma skin cancer. Thus, while evaluation of performance metrics of classification methods continues to be inappropriate or not as per our expectations, many artifacts and noise such as hair, veins, and water residue make images very ***, inspired and motivated by our previous study outcome when applying classification methods (CNN, RNN, and XG-Boost) on Melanomas’ images dataset, we found that the border detection and feature extraction for classification methods was challenging. Therefore, we applied Generative Facial Prior (GFP) Generative Adversarial Network (GAN) method to preprocess the Melanoma images. We also changed a few architectures and optimization methods for these classification algorithms. Finally, an extensive evaluation of the validation dataset is conducted. After that, it is compared with the values of performance metrics with previous results. This outcome impacts the dermatologist, scientific, and medical community. As a result, it is an excellent service to humanity to cure the deadliest form of skin cancer - Melanoma.

关键词： Measurement Humanities Veins Optimization methods Melanoma Metadata Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Machine Learning, Deep Learning and Data Preprocessing Techniques for Detection, Prediction, and Monitoring of Stress and Stress-related Mental Disorders: A Scoping Review

arXiv

引用

arXiv 2023年

作者： Razavi, Moein Ziyadidegan, Samira Mahmoudzadeh, Ahmadreza Kazeminasab, Saber Baharlouei, Elaheh Janfaza, Vahid Jahromi, Reza Sasangohar, Farzan Department of Industrial and Systems Engineering Texas A&M University United States Department of Computer Science and Engineering Texas A&M University United States Harvard Medical School Harvard University United States Department of Computer Science University of Houston United States Engineering Academic and Student Affairs College of Engineering Texas A&M University United States Ford Motor Company Global Data Insight & Analytics

Background: Mental stress and its consequent mental disorders (MDs) constitute a significant public health issue. With the advent of machine learning (ML), there's potential to harness computational techniques for better understanding and addressing mental stress and MDs. This comprehensive review seeks to elucidate the current ML methodologies employed in this domain to pave the way for enhanced detection, prediction, and analysis of mental stress and its subsequent mental disorders. Objective: This review aims to investigate the scope of Machine Learning (ML) methodologies employed in the detection, prediction, and analysis of mental stress and its consequent mental disorders (MDs). Methods: Utilizing a rigorous scoping review process with Preferred Reporting Items for Systematic Reviews and Meta-Analyses extention for Scoping Reviews (PRISMA-ScR) guidelines, this investigation delves into the latest ML algorithms, preprocessing techniques, and data types employed in the context of stress and stress-related MDs. Results and Discussion: Total of 98 peer-reviewed publication were examined for this review. The findings highlight that Support Vector Machine (SVM), Neural Network (NN), and Random Forest (RF) models consistently exhibit superior accuracy and robustness among all machine learning algorithms examined. Physiological parameters such as heart rate measurements and skin response are prevalently used as stress predictors due to their rich explanatory information concerning stress and stress-related MDs, as well as the relative ease of data acquisition. The application of dimensionality reduction techniques, including mappings, feature selection, filtering, and noise reduction, is frequently observed as a crucial step preceding the training of ML algorithms. Conclusion: The synthesis of this review identifies significant research gaps and outlines future directions for the field. These encompass areas such as model interpretability, model personalization, the i

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing and Comparison based on Service and Performance between Amazon AWS, Microsoft Azure, and Google Cloud

Cloud Computing and Comparison based on Service and Performa...

引用

Technological Advancements and Innovations (ICTAI), International Conference on

作者： Prakarsh Kaushik Ashwin Murali Rao Devang Pratap Singh Swati Vashisht Shubhi Gupta Student of Computer Science and Engineering Amity School of Engineering and Technology Greater Noida India Amity School of Engineering and Technology Greater Noida India

ISBN: (纸本)9781665420884

Cloud computing is the on-request supply of computing resources through the Web with pay-as-you-use billing. Instead of purchasing, operating, and maintaining physical computers, hardware, and servers, cloud solutions providers such as Microsoft Azure of Microsoft, Amazon Web Services (AWS) of Amazon, and Google Cloud Platform (GCP) by Google offer cloud solutions such as processing power, memory, and databases on an as-needed basis. This research paper discusses the architecture and types of cloud computing services, as well as comparison of the performance and service among three main Cloud Computing platforms: Microsoft Azure, Amazon AWS, and Google Cloud Platform. All three systems have been evaluated in identical virtual environments, specifically micro instance of Ubuntu 16.04. The benchmark application Phoronix Test Suite 10.4 is used to assess performance, and the results for the Apache, Dbench, and RAM speed benchmarks are evaluated in this paper.

关键词： Cloud computing Technological innovation Web services Linux Random access memory Virtual environments Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

XANNLight: A Novel Hybrid Ensemble Model for Accurate Health Insurance Prediction and Trend Forecasting

XANNLight: A Novel Hybrid Ensemble Model for Accurate Health...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Kafila Sajja Suneel Jayendra Gopal Thatipudi M Jini Kumari K. Penyameen Anubhav Sharma School of Business SR University Warangal Telangana India Department of CSE(Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Dept. of Computer Science Jayendra Gopal Thatipudi Student University of North Texas USA Department of ECE Chennai Institute of Technology Velammal College Of Engineering And Technology Madurai Department of CSE IES institute of Technology and management IES University Bhopal Mp India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Health insurance is a critical industry that requires precise data analysis and predictive capabilities to ensure operational efficiency and cost management. In an era where large datasets are readily available, machine learning models have become indispensable for predicting claims and identifying trends in insurance data. The rapid growth of the health insurance industry has increased the need for accurate prediction models to optimize claim management and trend forecasting. This study presents XANNLight, a novel hybrid ensemble model that integrates Artificial Neural Networks (ANN) and LightGBM to predict health insurance claims with high precision. The proposed model handles complex, non-linear relationships using ANN while LightGBM provides fast and accurate predictions for structured data. The dataset used for model training and evaluation consists of 1338 records, with features including age, sex, BMI, number of children, smoker status, and region. The model's performance is evaluated based on accuracy, precision, recall, and F1 score. The XANNLight model achieves an accuracy of 98.12%, outperforming nine existing models, including Logistic Regression, Decision Tree, Random Forest, and Gradient Boosting, which achieved accuracy levels between 85% and 96%. Furthermore, XANNLight demonstrates superior precision (97.83%), recall (97.90 % ), and F1 score (97.86 % ). These results highlight the model's efficiency in processing large datasets and predicting insurance claims, making it an effective tool for health insurance companies aiming to enhance operational efficiency and cost management.

关键词： Industries Accuracy Costs Computational modeling Insurance Artificial neural networks Predictive models Market research Data models Forecasting

来源：评论

学校读者我要写书评

暂无评论

Accurate Classroom Person Detection Based on Multi-Frame Feature Fusion with Attention

Accurate Classroom Person Detection Based on Multi-Frame Fea...

引用

International Conference on Image, Vision and Computing (ICIVC)

作者： Guoan Cheng Jiandong Ren Yuping Li Shengke Wang Yougang Ding Hao Wang School of information & Electrical Engineering Qingdao Harbour Vocational & Technical College Qingdao China Student Work Department Qingdao Harbour Vocational & Technical College Qingdao China College of Computer Science and Engineering Ocean University of China Qingdao China Mathematics Teaching and Research Group Experimental School Affiliated to Shandong University Heze China

In recent years, object detection technology has developed rapidly and is widely used in the field of intelligent video monitoring, especially in the classroom scenes, where incorporating the intelligent object detection technique into the video monitoring systems for intelligent monitoring purpose has important practical significance. However, surveillance videos may encounter issues such as object occlusion, motion blur, posture changes, and video defocus, which poses great challenges to object detection in the surveillance video scenarios. Therefore, in this paper, we conduct in-depth research on human detection in classroom multi camera surveillance video scenes and propose a multi frame feature fusion network based on the attention mechanism. The algorithm first adds the dilated convolution layers to the ResNet50 backbone network to expand the receptive field and retain more feature information; Secondly, a multi frame feature fusion strategy based on the attention mechanism was proposed to enhance the feature representation ability of the deep detector by fusing the feature information of adjacent frames, thereby improving the accuracy of human detection in the classroom monitoring video. To verify the effectiveness of the proposed method, we have compiled and produced a large-scale classroom monitoring video dataset, named OUC-ClassVideo. The proposed object detection network, which is developed based on the attention mechanism and multi frame feature fusion strategy, has achieved satisfactory performance on both the public dataset ImageNet VID and the OUC-ClassVideo dataset collected by ourselves.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Automatic Path Planning of Wind Turbines Inspection Based on Combined UAV

Research on Automatic Path Planning of Wind Turbines Inspect...

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Zhaoying Li Junqi Wu Jian Xiong Bo Liu Department of Electronic Engineering Shanghai Jiao Tong University Shanghai China Student Innovation Center Shanghai Jiao Tong University Shanghai China State key Laboratory of Networking and Switching Technology (Beijing University of Posts and Telecommunications) School of Computer Science University of Technology Sydney Ultimo NSW Australia

ISBN: (数字)9798350364262

ISBN: (纸本)9798350364279

Wind energy is a clean and widely deployed alternative to reduce human’s dependence on fossil fuels for power generation. Under this trend, more turbines and wind farms will be built all around the world. Inspecting the turbines of wind farms is a challenging task due to the difficult conditions, which puts workers at high risk who need to work at considerable heights. Increasing number of turbines also requires longer time which may bring huge cost. In this regard, unmanned aerial vehicles (UAVs) can play an important role in the automatic inspection of turbines. In this paper, we propose a method to inspect wind turbines based on combined UAV, which is able to plan the inspection path of the wind turbine and combine image processing technology to identify wind turbine defects, so as to make wind turbines inspection more efficient.

关键词： Wind energy Inspection Wind farms Autonomous aerial vehicles Path planning Wind turbines Synchronization

来源：评论

学校读者我要写书评

暂无评论

Reversible Data Hiding Simultaneously Using Substitution of MSB and Compression of LSB of Encrypted Image 14

Reversible Data Hiding Simultaneously Using Substitution of ...

引用

14th International Conference on Digital Image Processing, ICDIP 2022

作者： Sui, Liansheng Liu, Jie Cheng, Ying Xiao, Zhaolin Tian, Ailing School of Computer Science and Engineering Xi’an University of Technology Xi’an710048 China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an710048 China Student’s Affairs Division Xi’an University of Technology Xi’an710048 China Shaanxi Province Key Lab of Thin Film Technology and Optical Test Xi’an Technological University Xi’an710048 China

ISBN: (纸本)9781510657564

With the development of privacy protection, reversible data hiding methods in encrypted image have drawn extensive research interest. Among them, a new method is proposed based on embedding prediction errors, i.e., EPE-based method, where secret information is embedded in the encrypted most significant bit plane. Not only the original image can be recovered with high quality but also the payload can reach close to 1 bit per pixel (bpp). However, there are potential errors in the process of extracting secret data, because most significant bits of a part of pixels are used as flags to mark prediction error location. In this paper, a reversible data hiding method in encrypted image with high capacity is proposed by combining most significant bit prediction with least significant bit compression. At first, most significant bit of each pixel is predicted and a location map of prediction errors in the original image is generated. In the same time, the original image is encrypted using a stream cipher method. Then, the location map is embedded into the vacated space generated with compressing least significant bits and the secret data is embedded into most significant bits of a part of pixels without prediction errors. In this way, the marked encrypted image is obtained. Finally, the original image can be recovered without any error and the secret information can be extracted correctly from the marked encrypted image. Experimental results show that the proposed method has better performance than EPE-based and other methods. © 2022 SPIE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Impact of Image Enhancement for Osteoporosis Detection Based on Deep Learning Algorithm

Impact of Image Enhancement for Osteoporosis Detection Based...

引用

computer System, Information Technology, and Electrical engineering (COSITE), International Conference on

作者： Riza Dianil Iman Roslidar Roslidar Kahlil Muchtar Amalia Amalia Mohammad Syaryadhi Alfatirta Mufti Novi Maulina Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh Indonesia Department of Computer Science Universitas Sumatera Utara Medan Indonesia Graduate School of System Designs Tokyo Metropolitan University Tokyo Japan Doctorate Student of Doctoral Program in Medical Sciences Faculty of Medicine Universitas Syiah Kuala Banda Aceh Indonesia

Osteoporosis can be defined as a degenerative disease with reduced bone mass and changes in bone architecture that can lead to bone fragility and the risk of fractures. This abnormality can be indicated by the bone density which in visual can be determined using X-Ray images. However, X-Ray images are susceptible to noise, while in image analysis image contrast affects deep learning abilities. Hence, the CLAHE (Contrast Limited Adaptive Histogram Equalization) algorithm is used as a contrast enhancement technique in X-Ray images. This study aims to build a deep learning model using the CLAHE-enhanced image dataset with the ResNet-50 and ResNet-101 architectures. The model was built using two different datasets, namely the original image dataset and the CLAHE-enhanced image dataset. The result shows that the highest performance is given by the ResNet-101 model using the CLAHE-enhanced image dataset with an accuracy rate of 96%, precision of 95%, specificity of 95%, recall of 97% and an Fl-score of 96%, respectively. By using the CLAHE algorithm, the resulting image has high contrast and looks better at displaying features in the image so as to produce better model performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An AI-Centred Adaptive Cognitive Network Traffic Modeling & Measurement Technique for EIS

An AI-Centred Adaptive Cognitive Network Traffic Modeling & ...

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： L. Bharathi Nimish H. Vasoya Lavish Kansal Anita Gehlot Bajila Swathi Suyeb Ahmed Khan Department of Electronics and Communication Engineering Ramachandra College of Engineering Eluru Andhra Pradesh Department of Student Startup Children's University Gandhinagar Gujarat Lovely Professional University Phagwara Uttaranchal Institute of Technology Uttaranchal University India School of Computer Science and Artificial Intelligence SR University Warangal Telangana India Baba Kuma Singh Ji Engineering College Amritsar

The IoT is the foundation of the Enterprise Information System (EIS), which collects a lot of business information. For EIS, timely, accurate data analysis & transfer are crucial. For net management & traffic optimization in EIS, Network infrastructure traffic is crucial. Nevertheless, the needs for fine-grain traffic monitoring are in conflict with the monitoring overheads & precision. Long-standing promises of artificial intelligence (AI) include the ability to recognise the physical attributes of network activity & take appropriate steps in response. In order to decrease network monitoring overheads & increase measurement precision, we present an AI centred between light Adapt Measuring System (ALAMM) for SDN in this study. Initially, we simulate & forecast the network congestion information using AI. We suggest an adaptive strategy to choose the rate of traffic sample centred on the outcomes of traffic forecasting. Next, we instruct switching devices to evaluate the coarse-grain traffic of flow pattern & networks using the measuring primitives. In order to retrieve the Fine grained (FG) assessment & optimise the measured values, the matrices refilling & optimizing approach is finally suggested. Simulated outcomes demonstrate that our method can accurately and efficiently determine network activity.

关键词：

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：