检索结果-内蒙古大学图书馆

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Bhambu, Pawan Manjunatha, R. Srivastava, Pratima Vivekananda Global University Department of Computer Science and Engineering Jaipur India School of Sciences Department of Data Analytics and Mathematical Sciences Karnataka Bangalore India Arka Jain University Department of Biotechnology Jharkhand Jamshedpur India

ISBN: (纸本)9798350381931

The Open structure for allotted and Cooperative Media Algorithms (OADCMA) is an open-deliver framework imparting a plug-in platform that lets customers, without problem, develop distributed and cooperative media algorithms to utilize the computational assets of diverse heterogeneous structures. It's miles designed for operations along with video capture, transmission, and machine operations. OADCMA affords unified APIs for allotted and cooperative media algorithms, which simplifies the implementation of distributed and cooperative media algorithms. Additionally, OADCMA permits green parallel computing while averting scalability problems. OADCMA helps a widespread fashion of verbal exchange networks, including allotted finite discipline computing. It is appropriate for an extensive kind of allotted and cooperative media programs together with video surveillance and broadcasting. © 2024 IEEE.

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pipelining 42

PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pi...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Shi, Shaohuai Pan, Xinglin Chu, Xiaowen Li, Bo Harbin Institute of Technology School of Computer Science and Technology Shenzhen China Hong Kong Baptist University Department of Computer Science Hong Kong Data Science and Analytics Thrust Hong Kong The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350334142

Large models have attracted much attention in the AI area. The sparsely activated mixture-of-experts (MoE) technique pushes the model size to a trillion-level with a sub-linear increase of computations as an MoE layer can be equipped with many separate experts, but only one or two experts need to be trained for each input data. However, the feature of dynamically activating experts of MoE introduces extensive communications in distributed training. In this work, we propose PipeMoE to adaptively pipeline the communications and computations in MoE to maximally hide the communication time. Specifically, we first identify the root reason why a higher pipeline degree does not always achieve better performance in training MoE models. Then we formulate an optimization problem that aims to minimize the training iteration time. To solve this problem, we build performance models for computation and communication tasks in MoE and develop an optimal solution to determine the pipeline degree such that the iteration time is minimal. We conduct extensive experiments with 174 typical MoE layers and two real-world NLP models on a 64-GPU cluster. Experimental results show that our PipeMoE almost always chooses the best pipeline degree and outperforms state-of-the-art MoE training systems by 5%-77% in training time. © 2023 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid AI Framework for Real-Time Prediction and Risk Assessment of Vector-Borne Epidemics using Spatiotemporal data 4

A Novel Hybrid AI Framework for Real-Time Prediction and Ris...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Munirathnam, Rajesh Maindola, Meenakshi Bhargav, H.K. Patil, Prachi Ramesh Bhatt, Pooja Natrayan, L. TechnoGen Inc. Data & Analytics Division NJ United States Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun India Department of Computer Science and Engineering Tumakuru India Jagdambha College of Engineering and Technology Department of Electronics and Telecommunication Engineering Yavatmal India Parul institute of Engineering and Technology Parul University Faculty of Engineering and Technology Department of Computer science and Engineering Vadodara India Saveetha School of Engineering Simats Department of Mechanical Engineering Chennai India

ISBN: (纸本)9798350352931

Vector-borne epidemics constitute major threats to global health that call for improved modeling systems for managing diseases. In order to incorporate such factors into an actual model, a traditional forecasting process may fail to grasp the nature of disease transmission adequately. We present a hybrid AI system based on LSTM and GCN for forest bug outbreak detection in real time. The framework also integrated a spatial-temporal analysis of climate variability, vector population fluctuations, and human mobility with climate variables across 15 regions over a five-year period (2019-2023). The hybrid framework also produced superior results, achieving a 94.2% prediction rate for health risk disease outbreaks, compared to a 17.3% improvement in traditional machine learning. When used to distinguish between high-risk and low-risk zones, the model demonstrated the following metrics: sensitivity of 92.8% and specificity of 95.1%. Real-time risk assessment demonstrated 89.6% effectiveness in indicating early warning and the best prediction lead time average of 21 days. This framework significantly enhances the prediction of vector-borne diseases by offering a dependable, real-time platform for disease surveillance and risk assessment. Its high accuracy and early warning capabilities make the system a useful tool in epidemiological and public health campaigns and control measures. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Optimization Study of Renal CT Image Classification Using Convolution Neural Networks 14

Optimization Study of Renal CT Image Classification Using Co...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Afnaan, K. Nagaraja, K.V. Singh, Tripty Bhanu Prakash, K.N. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India Amrita Vishwa Vidyapeetham Amrita School of Engineering Department of Mathematics Bengaluru India A∗STAR Clinical Data Analytics and Radiomics Singapore

ISBN: (纸本)9798350335095

computer tomography (CT), also known as computed tomography, is a medical imaging method that generates detailed and precise horizontal or axial images of targeted regions of the body for diagnostic purposes. In this particular study, the focus was on performing image classification of CT scan images of the Kidney. This organ plays an essential role in detoxification, fluid balance, and maintaining electrolyte levels in the human body. The dataset used for the study contained 12,446 images into four labeled classes - Cyst, Tumor, Stone, and Normal. Convolution Neural Network (CNN) model is built for binary (Normal and Tumor) and multi-image Classification to classify the Renal CT images into four classes. CNN uses ReLU as an activation function for classifying these images. The Model is evaluated and compared based on Accuracy and Loss performance metrics by compiling the CNN model with different deep learning TensorFlow Keras optimizers for Version 2.11.0 for Binary Image Classification at 10,20, and 50 epochs. The CNN model is assembled with Adam Optimizer and Follows the Regularized Leader (FTRL) Optimizer. The Testing and training Accuracy and Losses achieved are evaluated with a learning rate of 0.001 and 0.0001. Adam Optimizer outperforms to be the best Optimizer for Binary and Multi-Image Classification. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Protein Structure Prediction Using A New Optimization-Based Evolutionary and Explainable Artificial Intelligence Approach

引用

IEEE Transactions on Evolutionary Computation 2024年第3期29卷 1-1页

作者： Hong, Jun Zhan, Zhi-Hui He, Langchong Xu, Zongben Zhang, Jun School of Computer Science and Engineering South China University of Technology Guangzhou P. R. China Health Science Center School of Pharmacy Xi’an Jiaotong University Xi’an P. R. China National Engineering Laboratory for Big Data Analytics Xi’an Jiaotong University Xi’an P. R. China College of Artificial Intelligence Nankai University Tianjin P. R. China

Protein structure prediction (PSP) is an important scientific problem because it helps humans to understand how proteins perform their biological functions. This paper models the PSP problem as a multi-objective optimization problem with three fast and accurate knowledge-based energy functions. This way, using evolutionary computation (EC)-based artificial intelligence (AI) approach to solve this multi-objective PSP problem to find the optimal structure is explainable. Considering that the multiple populations for multiple objectives (MPMO) framework shows efficient performance in solving lots of multi-objective benchmarks and real-world problems, this paper proposes a new AI approach named improved MPMO-based differential evolution (IMPMO-DE) to solve the multi-objective PSP problem. To our best knowledge, this is the first time that MPMO is applied to PSP, with three novel strategies. First, an adaptive archive-based mutation strategy is proposed to better balance the exploration and exploitation abilities by adaptively using different archive-based mutation operators in different evolutionary stages. Second, a mixed individual transfer strategy is proposed to share search information among the multiple populations to accelerate the convergence speed. Third, an evolvable archive update strategy is proposed to generate more promising solutions through evolving the archived solutions. IMPMO-DE is tested on 28 representative proteins and all the available template-free modeling proteins up to 404 residues in the famous Critical Assessment of Protein Structure Prediction (CASP14) competition. Experimental results show that IMPMO-DE performs better than the compared state-of-the-art EC-based PSP methods and ranks above average compared with all the CASP14 competitors. More importantly, IMPMO-DE is a new efficient AI approach that opens a promising optimization-based evolutionary and explainable way for efficient PSP rather than deep learning approaches like AlphaFold2,

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on Tumor Images Segmentation based on Improved Convolutional Neural Network 24

Research on Tumor Images Segmentation based on Improved Conv...

引用

5th International Symposium on Artificial Intelligence for Medicine science, ISAIMS 2024

作者： Wan, Yajie Diao, Su Jiang, Gaozhe Song, Chaoda Department of Computer Science Brown University ProvidenceRI United States Department of Industrial & Systems Engineering Auburn University AuburnAL United States Institute of Operations Research and Analytics National University of Singapore Singapore Singapore School of Engineering Department of Computer and Data Sciences ClevelandOH United States

ISBN: (纸本)9798400717826

Tumors are one of the most common tumors in humans, and the main treatment at present is surgical removal. Preoperative planning of tumors usually requires a professional doctor to manually segment the images, but this process is limited by the doctor’s technical experience, which is time-consuming and labor-intensive. In addition, segmentation is extremely difficult due to the complexity and morphological diversity of tumor lesions. We propose a tumor image segmentation method based on improved Convolutional Neural Network (CNN). The model enhances the feature extraction ability by introducing a deep separable convolutional layer and batch normalization, while using dilated convolution to increase the receptive field, thereby improving the accuracy of segmentation. We also incorporated attention mechanisms into the model to focus more accurately on the tumor area and further optimize the segmentation effect. In order to verify the effectiveness of the model, we conducted experimental analysis on multiple publicly available medical imaging datasets. Experimental results show that the improved convolutional neural network significantly improves the accuracy and efficiency of segmentation compared with traditional methods in tumor image segmentation tasks. © 2024 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Using Multi-Block Deep CNN 5

Facial Expression Recognition Using Multi-Block Deep CNN

引用

5th International Conference on Circuits, Control, Communication and Computing, I4C 2024

作者： Priyadarshini, V. Srinivasulu Reddy, U. Reddy Chirra, Venkata Rami Mrudula, M. Suneetha, M. National Institute of Technology Dept. of Computer Science & Engineering Andhra Pradesh India Machine Learning & Data Analytics Lab National Institute of Technology Dept. of Computer Applications Tiruchirappalli India School of Computer Science & Engineering VIT-AP University Amaravathi India Malla Reddy College of Engineering Department of CSE Telangana India Independent Researcher Amaravati India

ISBN: (纸本)9798331528539

Emotions play a crucial role in decision-making, moral judgments, and other cognitive processes. The goal of this work is to identify people's facial emotions from face images. Facial expression recognition (FER), a highly diverse field with many commonalities between classes, is a challenging problem. The capabilities of current FER systems are limited in this regard. In this work, a multi-block Deep Convolutional Neural Networks (DCNN) model was proposed to identify facial expressions. Five blocks with different computational components were defined in a multi-block DCNN to extract the unique characteristics from input images. The second model (DCNN-SVM) is developed with an ensemble of SVM classifier to improve predictability and stability. The third model (DCNN-MV) is based on the majority voting with 4 classifiers SVM, KNN, Random Forest, and Decision Tree. The CK+ dataset was utilized and expanded via image data augmentation to enhance model performance and generalization. By adjusting hyperparameters, the suggested DCNN model's accuracy was investigated. The DCNN model reports an accuracy score of 97.71%. Both DCNN-SVM and DCNN-MV models achieved 97.79% accuracy. On the CK+ dataset, the proposed models demonstrated good accuracy in identifying facial expressions. When compared to existing models, the proposed model outperformed existing models in terms of accuracy. © 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

VEL@LT-EDI-2023: Detecting Homophobia and Transphobia in Code-Mixed Spanish Social Media Comments 3

VEL@LT-EDI-2023: Detecting Homophobia and Transphobia in Cod...

引用

3rd Workshop on Language Technology for Equality, Diversity and Inclusion, LTEDI 2023

作者： Kumaresan, Prasanna Kumar Ponnusamy, Kishore Kumar Shanmugavadivel, Kogilavani Navaneethakrishnan, Subalalitha Chinnaudayar Priyadharshini, Ruba Chakravarthi, Bharathi Raja Insight SFI Research Centre for Data Analytics University of Galway Ireland Guru Nanak College Tamil Nadu Chennai India Kongu Engineering College Tamil Nadu India Department of Computer Science & Engineering SRM Institute of Science and Technology Tamil Nadu India Gandhigram Rural Institute-Deemed to be University Tamil Nadu India Insight SFI Research Centre for Data Analytics School of Computer Science University of Galway Ireland

ISBN: (纸本)9789544520847

Our research aims to address the task of detecting homophobia and transphobia in social media code-mixed comments written in Spanish. Code-mixed text in social media often violates strict grammar rules and incorporates non-native scripts, posing challenges for identification. To tackle this problem, we perform pre-processing by removing unnecessary content and establishing a baseline for detecting homophobia and transphobia. Furthermore, we explore the effectiveness of various traditional machine-learning models with feature extraction and pre-trained transformer model techniques. Our best configurations achieve weighted F1 scores of 0.86 on the test set and 0.86 on the development set for Spanish, demonstrating promising results in detecting instances of homophobia and transphobia in code-mixed comments. © 2023 LTEDI 2023 - 3rd Workshop on Language Technology for Equality, Diversity and Inclusion, associated with the 14th International Conference on Recent Advances in Natural Language Processing, RANLP 2023 - Proceedings. All rights reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Dermatological Diagnostics: A Unified Deep Learning Framework for Skin Lesion and Cancer Classification 1

Dermatological Diagnostics: A Unified Deep Learning Framewor...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Kumar, Vinod Jain, Isha Dongla, Durga Sritha Rai, Shivangi Rastogi, Vani Kaushik, Eva Kaushik, Rohit George Washington University School of Engineering and Applied Science WashingtonDC United States Dr. Akhilesh Das Gupta Institute of Technology and Management Computer Science and Engineering Department New Delhi India Gandhi Institute of Technology and Management Computer Science and Engineering Department Andhra Pradesh Visakhapatnam India Data Scientist DXC Technology Noida India Data Analytics Program University of Illinois CS and Mathematics Department Springfield United States

ISBN: (纸本)9798350356816

Skin pathologies encompass a spectrum of conditions, with malignancies such as melanoma representing a critical diagnostic urgency. This investigation delineates the deployment of Convolutional Neural Networks (CNNs) for the classification of dermatological anomalies, benchmarking CNN diagnostic fidelity against dermatological expert evaluations. The study underscores the efficacy of CNN classifiers in expediting the diagnostic workflow for various cutaneous disorders. Advocating for an automated diagnostic framework, the research introduces a CNN-based system aimed at reducing human diagnostic load, accelerating diagnostic timelines, and enhancing survival outcomes. Utilizing advanced image processing algorithms and deep learning architectures, the research presents an automated classification system for skin pathologies, addressing both benign and malignant presentations. The classification matrix includes nine dermatological conditions: actinic keratosis, basal cell carcinoma, benign keratosis, dermatofibroma, melanoma, nevus, seborrheic keratosis, squamous cell carcinoma, and vascular lesions. The objective is to engineer a CNN model with robust diagnostic performance across a diverse lesion dataset, ensuring accurate identification and categorization of dermatological 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

Colon Cancer Tissue Classification Using ML 6

Colon Cancer Tissue Classification Using ML

引用

6th International Conference on Information Systems and computer Networks, ISCON 2023

作者： Tripathi, Ashish Kumar, Kuldeep Misra, Anuradha Chaurasia, Brijesh Kumar Amity University Lucknow Amity School of Engineering and Technology Department of Computer Science and Engineering Uttar Pradesh Lucknow India Bond University Center for Data Analytics Bond Business School Gold CoastQLD Australia Pranveer Singh Institute of Technology Department of Computer Science and Engineering Uttar Pradesh Kanpur India

ISBN: (纸本)9798350346961

In this paper, the classification of colon cancer tissues by means of machine learning approaches is evaluated. In today's world, a revolutionary advancement has come in the classification and diagnosis of diseases in the medical and healthcare sectors. Deep learning classifiers and machine learning methods are now broadly applied to accurately diagnose a number of diseases. Cancer is one of the world's most significant roots of death, appealing to the lives of one person out of every six. As per the national library of medicine, the third leading cause of death worldwide is colorectal cancer. Identifying an illness at a premature stage increases the chances of survival. Automated diagnosis and the classification of tissues from images can be completed much more quickly with the use of artificial intelligence. A publicly available IoT dataset CRC-VAL-HE-7K consisting of 7180 images, distributed among nine types of colorectal tissues: background, lymphocytes, adipose, mucus, colorectal adenocarcinoma epithelium, normal colon mucosa, debris, cancer-associated stroma, and, smooth muscle is used after preprocessing. Feature extraction is done by applying Differential-Box-Count on all blocks of images. The dataset is evaluated by these Machine Learning (ML) procedures: K-Nearest Neighbor, Support Vector Machine, Decision Tree, Random Forest, Extreme Gradient Boosting, and Gaussian Naive Bayes. Results show that the performance of Extreme Gradient Boosting is the best and most viable approach.. © 2023 IEEE.

关键词： Image classification

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：