检索结果-内蒙古大学图书馆

Communication, Control and Intelligent Systems (CCIS)

作者： Eshika Jain Amanveer Singh Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura Punjab India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India

ISBN: (数字)9798331528201

ISBN: (纸本)9798331528218

Deepfake voice recognition has lately been one of the critical challenges in the domain of cybersecurity and digital forensics, as it has recently become increasingly used with deep learning models to create absolutely indistinguishable audio imitations. This paper proposes a CNN-based approach to detect and classify deepfake audio clips. The model is trained on an exhaustive dataset that includes both real and deepfake voice records, putting much attention into the difference between natural and manipulated speech patterns. Our approach is based on the spectrogram analysis-a method of audio signal processing by converting it into a visual format that the CNN then analyzes to extract and categorize features. We test the performance of this model, which has gone through rigorous training with an accuracy of 82.6% and a test loss of 0.386. Results indicate that the proposed CNN architecture successfully learns nuanced acoustic variations between real and synthetic voices, setting up a robust framework for the detection of deepfakes. Moreover, the generalizability of the model has been checked multiple times, keeping the training and validation metrics very close. Future works will further improve the detection accuracy by including more pre-processing techniques and increasing the dataset with more varieties of deepfake sources. The study therefore adds to the ever-increasing demand for reliable and capable tools in the identification of audio forgeries, which seriously threatens privacy, security, and integrity of information in our time.

关键词： Training Deep learning Deepfakes Visualization Accuracy Speech recognition Feature extraction Forgery Convolutional neural networks Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Advanced Gradient Boosting Techniques for Predicting Obesity Risk: A Comprehensive Machine Learning Approach

Advanced Gradient Boosting Techniques for Predicting Obesity...

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

Obesity, a major global health concern, is linked to several life-threatening conditions such as cardiovascular diseases, diabetes, and cancer. Early detection of obesity is crucial for effective intervention and prevention strategies. In this study, we investigate the performance of advanced machine learning techniques, specifically gradient boosting models-XGBoost, LightGBM, and CatBoost-for predicting obesity risk levels using medical, demographic, and lifestyle data. Rigorous preprocessing, hyperparameter tuning, and cross-validation were employed to ensure robust model development. XGBoost emerged as the most accurate model with an outstanding validation accuracy of 91.67%, followed by LightGBM and CatBoost. Despite minor overfitting in LightGBM, all three models demonstrated exceptional generalization capabilities. The findings highlight the potential of gradient boosting models for enhancing early obesity detection and personalized risk management in healthcare settings. Future work could focus on expanding the dataset, integrating explainable AI for better model interpretation, and exploring hybrid or deep learning models to further improve predictive performance. These results provide a solid foundation for implementing machine learning-based systems in public health programs aimed at combating the obesity epidemic.

关键词： Deep learning Obesity Accuracy Explainable AI Prevention and mitigation Predictive models Boosting Data models Tuning Thermal stability

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Classification of Bitter Gourd Varieties in India: CNN-PCA Synergy

AI-Driven Classification of Bitter Gourd Varieties in India:...

引用

Global Conference for Advancement in technology (GCAT)

作者： Rishabh Sharma B Reddy Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura Punjab India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

This study looks at different types of bitter gourd in India using a mixed method with Convolutional Neural Network (CNN) and Principal Component Analysis (PCA). The set of images contains 15,000 high-quality photos of four important types of bitter gourds like Priya and Preethi. They were well chosen from many places around the world as they can be found at different stages of growth and have different shapes. Preprocessing meant making pictures the same size (224x224 pixels) and adjusting pixel values to improve model work better. The CNN idea, with layers that use convolutions and max-pooling plus fully connected parts, showed strong skill at taking in features. This gave an impressive total correctness of 97.7%. But sometimes, people get mixed up between Pusa Do Mausami and Pusa Vishesh because they look very alike. The Confusion Matrix study gave detailed information about differences in classifications. It helped improve future model designs. These results show that automated picture-based grouping systems in farming can be very useful. They provide real uses for growing crops, improving plant breeds, and dividing markets. This study builds a basic structure to use advanced machine-learning techniques for identifying types of crops. It greatly helps in improving farm technologies.

关键词： Learning systems Shape Image processing Computational modeling Crops Machine learning Convolutional neural networks Principal component analysis Farming Sorting

来源：评论

学校读者我要写书评

暂无评论

Microfluidic impedance flow cytometer leveraging virtual constriction microchannel and its application in leukocyte differential

引用

Microsystems & Nanoengineering 2024年第6期10卷 493-503页

作者： Minruihong Wang Jie Zhang Xiao Chen Yimin Li Xukun Huang Junbo Wang Yueying Li Xiaoye Huo Jian Chen State Key Laboratory of Transducer Technology Aerospace Information Research InstituteChinese Academy of SciencesBeijing 100190People’s Republic of China School of Future Technology University of Chinese Academy of SciencesBeijing 100049People’s Republic of China CAS Key Laboratory of Genomic and Precision Medicine Collaborative Innovation Center of Genetics and DevelopmentBeijing Institute of GenomicsChinese Academy of SciencesBeijing 100101People’s Republic of China China National Center for Bioinformation Beijing 100101People’s Republic of China School of Electronic Electrical and Communication EngineeringUniversity of Chinese Academy of SciencesBeijing 100049People’s Republic of China

Microfluidic impedance flow cytometry has been widely used in leukocyte differential and counting,but it faces a bottleneck due to the trade-off between impedance detection throughput and *** this study,a microfluidic impedance flow cytometer based on a virtual constriction microchannel was reported,in which the virtual constriction microchannel was constructed by crossflow of conductive sample and insulated sheath fluids with underneath micro-electrodes for impedance *** to conventional mechanical constriction microchannels,this virtual counterpart could effectively avoid direct physical contact between cells and the microchannel walls to maintain high throughputs,and significantly reduce the volume of the impedance detection region for sensitivity *** the developed microfluidic impedance flow cytometer,impedance pulses of three leukemia cell lines,K562,Jurkat,and HL-60,were detected,achieving a 99.8%differentiation accuracy through the use of a recurrent neural ***,impedance pulses of four white blood cell subpopulations(neutrophils,eosinophils,monocytes,and lymphocytes)from three donors were detected,achieving a classification accuracy of≥99.2%.A classification network model was established based on purified white blood cell and applied to impedance pulses of two white blood cell mixtures,resulting in proportional distributions of four leukocyte subpopulations within theoretical *** results indicated that the developed microfluidic impedance flow cytometer based on the virtual constriction microchannel could achieve both high detection throughput and high sensitivity,showing great potentials for clinical diagnostics and blood analysis.

关键词： fluid leukocyte impedance

来源：评论

学校读者我要写书评

暂无评论

Automated Classification of Kidney Diseases Using Deep Learning: A Comparative Analysis with Machine Learning Models on CT Images

Automated Classification of Kidney Diseases Using Deep Learn...

引用

Intelligent Computing and Sustainable Innovations in technology (IC-SIT), International Conference on

作者： Eshika Jain Vinay Kukreja Pratham Kaushik Aseem Aneja Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura Punjab India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India

ISBN: (数字)9798350369175

ISBN: (纸本)9798350369182

Kidney disease diagnosis with the use of a medical image plays an important role in diagnosis and treatment on time. This survey presents a comparison between different machine learning algorithms and deep learning models that classify kidney conditions from the CT KIDNEY DATASET, containing four distinct classes: Normal, Cyst, Tumor, and Stone. The authors have reviewed the performance of CNNs while comparing them against traditional machine learning models like Decision Trees, Random Forests, Gradient Boosting, AdaBoost, Support Vector Classifiers (SVC), Logistic Regression, K-Neighbors, Naive Bayes, and Long Short-Term Memory (LSTM) networks. The best performance, by the CNN model, is 93.87%, which states the power of deep learning in image processing regarding medical applications. In contrast, Random Forest and Decision Tree models remain competitive within traditional classifiers with validation accuracies of 83.37% and 83.05%, respectively. Gradient Boosting, AdaBoost, and SVC models come next with validation accuracies ranging from 82.73% to 79.60%, whereas KNeighbors and Naive Bayes are still farther behind, although each was performing consistently. It reflects the particular challenges associated with the application of recurrent models to static image data, best suited for temporal data. Our LSTM model realizes a test accuracy of $\mathbf{75.18 \%}$. It also points to the fact that CNNs exhibit a far better capability in detecting kidney diseases, whereas traditional models are quite viable alternatives with competitive accuracy. In fact, this essentially points out that model selection is an important issue in clinical applications, as accuracy and computational efficiency go hand in hand to enable accurate diagnosis.

关键词： Deep learning Accuracy Computational modeling Computed tomography Boosting Decision trees Kidney Random forests Long short term memory Diseases

来源：评论

学校读者我要写书评

暂无评论

What motivates knowledge sharing? Evaluating the quality of answer contribution in online Q&A communities

引用

Data and Information Management 2024年

作者： Wu, Jiang Xu, Zhoucan Huang, Qian Cai, Jingxuan School of Information Management Wuhan University Wuhan China Center for Ecommerce Research and Development Wuhan University Wuhan China School of Business Suzhou University of Science and Technology Suzhou China

The Online Q&A community provides platforms for Internet users to exchange and share knowledge. Its rapid development has caused the problem of information overload, which promotes users' demand for precise and personalized information. In light of this, we innovatively analyze the correlation between knowledge quality and user behaviors. First, we propose a novel approach method to evaluate the answer quality through a machine learning approach, which applies the information adoption theory to the design of a text classification model. Hereafter, with applications of motivation crowding theory, this paper introduces the classification results of answer quality by machine learning algorithms into the empirical research model to explore the factors that motivate users in both participation and high-quality user-generated content creation. Results show that both extrinsic and intrinsic factors determine the quality of knowledge contributors' answers. Further, certain external interventions (monetary rewards) can crowd out the effects of knowledge contributors’ intrinsic motivations (knowledge self-efficacy). It enriches the research on user knowledge contribution behavior in online Q&A communities and also provides theoretical guidance and suggestions for community operation. © 2024 The Authors

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Combining CNN and SVM for Robust Cattle Disease Classification in Veterinary Applications

Combining CNN and SVM for Robust Cattle Disease Classificati...

引用

Intelligent Computing and Sustainable Innovations in technology (IC-SIT), International Conference on

作者： Shiva Mehta Danish Kundra Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura Punjab India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India

ISBN: (数字)9798350369175

ISBN: (纸本)9798350369182

Noteworthy problems in the cattle livestock sector stem from infectious diseases that impact the health of animals and the production output. Precise and prompt detection is essential for both treatment and prevention to be successful. This study presents a CNN-SVM model to enhance the exactness of categorizing cattle diseases. The dataset included 2,000 photographs put into five illness classifications (Healthy, Foot-and-Mouth illness, Mastitis, Bovine Respiratory Disease, and Lameness), with 80 % for training and 20% for evaluation. CNN turned to ImageNet, which turned out to be a feature extractor, and the SVM with a radial basis function (RBF) kernel categorized the identified features. Experimental results reveal that the hybrid model outperforms the independent CNN and SVM models. Ultimately, the success rate of the CNN-SVM model is 92.7 %, more successful than the CNN (88.4%) and SVM models (84.5%). Also, the hybrid model attained an average accuracy of 91.5 %, a recall of 90.8 %, and an F1 score of 91.1%, showing a balanced performance concerning all criteria. The figure of 0.93 for the Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) curve for all illness categories, on average, suggests the model has outstanding discriminative capabilities. The evidence reveals that the CNN-SVM hybrid model is a valid and valuable classification method for recognizing diseases in cattle, which stands out as an essential development from other techniques. Additional research is required to better the dataset and examine alternative model frameworks to elevate performance and relevance under actual circumstances.

关键词： Support vector machines Training Technological innovation Accuracy Sensitivity Surveillance Cows Feature extraction Convolutional neural networks Diseases

来源：评论

学校读者我要写书评

暂无评论

OralGuard: Harnessing Inception-ResNet-v2 for Cutting-Edge Oral Health Diagnostics

OralGuard: Harnessing Inception-ResNet-v2 for Cutting-Edge O...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： Pratham Kaushik Saniya Khurana Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura Punjab India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

This paper considers the application of the InceptionResNetV2 architecture in the classification of pathologies of the mouth. Six classes are focused on: calculus, caries, ulcers, gingivitis, discoloration of tooth enamel, and hypodontia. The performance of the model is benchmarked on a set containing 1166 labeled images, taking into account the prevalence and severity of each condition. The results indicate that, among all of the scenarios, InceptionResNetV2 has achieved an accuracy of $\mathbf{9 3 \%}$. Accuracy in distinguishing classes: calculus, 0.76; caries, 0.99; ulcers, 1.00; gingivitis, 0.79; discoloration of tooth, 0.99; and hypodontia, 0.99. Its macro average for precision, recall, and F1-score are 0.91, 0.92, and 0.91, respectively. The results showed that the InceptionResNetV2 model could differentiate between classes for a variety of common oral pathologies, thus being able to be very helpful in improving diagnostic accuracy and efficiency in dental practice. Further studies are required to confirm generalizability of these results to larger and more diverse datasets and to real-world clinical settings.

关键词： Pathology Accuracy Soft sensors Neural networks Teeth Benchmark testing Calculus Data models Dentistry Faces

来源：评论

学校读者我要写书评

暂无评论

A Review of Dynamic Analysis and Fault Diagnosis for Split-Torque Transmission System

A Review of Dynamic Analysis and Fault Diagnosis for Split-T...

引用

TEPEN International Workshop on Fault Diagnostics and Prognostics, TEPEN-IWFDP 2024

作者： Yang, Weixin Wang, Zhi Yin, Mei Hu, Lei Xu, Yuandong AECC Hunan Aviation Powerplant Research Institute Zhuzhou412002 China Aero-Engine Vibration Technology in Aeronautical Science Key Laboratory Zhuzhou412002 China Laboratory of Science and Technology on Integrated Logistics Support NUDT Changsha410073 China Beijing Tangzhi Technology Development Co. Ltd. Beijing100043 China Hunan Provincial Key Laboratory of Health Maintenance for Mechanical Equipment Hunan University of Science and Technology Xiangtan411201 China

ISBN: (纸本)9783031694820

Split-torque transmission systems (STTS) of helicopters are designed as alternatives to traditional planetary gearboxes. STTS has the advantages of a large reduction ratio, lower energy losses, low noise levels from gear meshes, and high power density, etc. However, STTS has a more complex structure, more degrees of freedom, more complex external excitations and faults that are more difficult to diagnose. Therefore, research on the dynamics and fault diagnosis of STTS is of great significance to improve operational reliability. This paper reviews the current research status of STTS dynamic modelling and load sharing performance first, then the research on STTS fault diagnosis, followed by a summary of challenges and future research. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Epicyclic gears

来源：评论

学校读者我要写书评

暂无评论

Efficient Handwritten Digit Classification using Convolutional Neural Networks: A Robust Approach with Data Augmentation

Efficient Handwritten Digit Classification using Convolution...

引用

Automation, Computing and Renewable Systems (ICACRS), International Conference on

ISBN: (数字)9798331532420

ISBN: (纸本)9798331532437

Categorization of image digits finds very important real-world applications in recognizing postal codes, processing bank checks, and digitizing forms automatically. This paper proposes an effective Convolutional Neural Network model for image digit classification based on the publicly available dataset, where each image is in 28x28 grayscale format. CNNs are also ideal because of their innate capabilities to represent spatial hierarchies in images. The dataset consists of 42,000 training images and 28,000 test images, where the intensity of each pixel ranges between 0 and 255. Preprocessing involved the normalization of data, scaling values of pixels within a range from 0 to 1, and reshaping images to match the shape expected by the CNN input layer. One-hot encoding of labels was also done, which means that after all these processes, the model could predict one class from a possible ten corresponding to the digits 0 through 9. Some of the data augmentation techniques applied are rotation, zoom, and shifts with an aim to improve generalization and prevent overfitting. It contains a CNN architecture of three convolutional layers followed by batch normalization, Leaky ReLU activation, and max-pooling layers. Further, it harnesses the power of dropout layers to prevent network overfitting and trains the network using the Adam optimizer. It finally converged to more than 99% accuracy on the test set, as verified by a confusion matrix and a classification report showing high precision recall for each digit class in *** work primarily exhibits the ability of CNN in digit classification; hence, it presents a well-optimized model that achieves a balance between performance and complexity.

关键词： Training Handwriting recognition Accuracy Shape Data preprocessing Computer architecture Data augmentation Data models Convolutional neural networks Overfitting

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：