检索结果-内蒙古大学图书馆

Enhancing Diagnostic Accuracy and Early Detection Through the Application of Deep Learning Techniques to the Segmentation of Colon Cancer in Histopathological Images

Enhancing Diagnostic Accuracy and Early Detection Through th...

引用

International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)

作者： Mahaveerakannan R Shailee Lohmor Choudhary Rinku Sharma Dixit Srikanth Mylapalli M. Sathish Kumar Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of Artificial Intelligence and Machine Learning New Delhi Institute of Management Delhi Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur A. P Department of Information Technology Nehru Institute of Engineering and Technology Coimbatore Tamil Nadu

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376432

Youth and elderly deaths are rising due to cancer. If it is not discovered early in cancer cell development, mortality will increase since it is deadly. Colon cancer arises when colon or rectum cells grow abnormally. Early colorectal cancer screening can prevent these abnormal growths from becoming cancerous. In health care systems, colon cancer diagnosis and categorization are crucial. Histopathology slide images are used to train a deep learning algorithm to detect colon cancer. The suggested model uses Vision Transformer (ViT) and Swin Transformer, a new type of ViT. Using an upgraded Swin Transformer model, the model accurately classifies tumours as benign or malignant. Effectiveness of colorectal diagnostics and precision cancer due to optimization concerns Their upgraded CNN models, ResNet34 and EfficientNet34, may not be enough to prevent optimization concerns from lowering colorectal cancer classification accuracy and efficiency. ResNet-101, Swin Transformer, ViT, and a revised Swin Transformer are also compared in this study. The proposed method uses LC25000 for training and testing. The test model has 99.80% precision using the modified Swin Transformer technique, 99.64% using the Swin Transformer itself, 99.36% using the ViT model, and 98.27% using ResNet-101.

关键词： Training Deep learning Accuracy Computational modeling Colorectal cancer Transformers Public healthcare Optimization Testing Tumors

来源：评论

学校读者我要写书评

暂无评论

Dual Weighted Inverted Specific-Class Distance Measure for Nominal Attributes

SSRN

引用

SSRN 2023年

作者： Gong, Fang Lu, Tao Guo, Xingfeng Wang, Dianhong Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan430073 China School of Computer Science and Engineering Wuhan Institute of Technology Wuhan430205 China School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan430205 China School of Mechanical and Electronic Information China University of Geosciences Wuhan430074 China

The inverted specific-class distance measure (ISCDM) continues to be one of the top distance metrics addressing only address nominal attributes when missing values and noises exist in the training set. However, its attribute independence assumption fails to hold true in applications with sophisticated attribute dependencies. To alleviate this assumption, several attribute weighting-based and instance weighting-based improved versions have been proposed. However, all of them are limited to focusing solely on either attribute weighting or instance weighting;they ignore the enhancement of the measuring performance by the combination of attribute weighting and instance weighting. Thus, in this study, we developed a novel dual-weighting scheme that considers attribute weighting and instance weighting simultaneously, denoted as dual weighted ISCDM (DWISCDM). We incorporate the attribute and instance weights into the difference formulas of two attribute values and instances, respectively. Extensive experimental results demonstrate the effectiveness of the proposed DWISCDM against ISCDM and some existing state-of-the-art baselines in terms of negative conditional log likelihood and root relative squared error. © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Performance and Scalability in Cell-Free Massive MIMO Networks with Gradient Descent Algorithms

Improving Performance and Scalability in Cell-Free Massive M...

引用

information Systems and Computing technology (ISCTech), International Conference on

作者： Yibeltal Abebaw Molla Zenebe Melesew Yetneberk Birhanu Dessie Ayalew Umar Zeb Tong-Xing Zheng Isayiyas Nigatu Tiba School of Electrical and Computing Adama Science and Technology University Adama Ethiopia School of Information and Communications Engineering Xi’an Jiaotong University Xi’an P.R. China Department of Electrical and Computer Engineering Jimma Institute of Technology Jimma University Jimma Ethiopia

ISBN: (数字)9798350379860

ISBN: (纸本)9798350379877

Scalable cell-free massive MIMO (CF-mMIMO) systems are essential for addressing the increasing capacity and coverage demands of modern wireless networks. Despite their potential, existing CF-mMIMO architectures encounter scalability limitations, including increased latency and bandwidth requirements as network sizes expand. To address these challenges, this study proposes a novel and efficient partial minimum mean square error (PMMSE) precoding technique, optimized using a gradient descent (GD) algorithm. The proposed gradient descent-based PMMSE (GD-PMMSE) method significantly enhances the performance and scalability of CF-mMIMO systems. Our simulation results demonstrate that GD-PMMSE achieves notable improvements in spectral efficiency and signal-to-interference-plus-noise ratio (SINR) compared to conventional techniques such as PMMSE, local partial minimum mean square error (LPMMSE), and partial regularized zero-forcing (PRZF). These improvements are particularly pronounced in densely populated scenarios with high access point (AP) and user equipment (UE) densities, showcasing its superior adaptability to dynamic user demands while maintaining high spectral efficiency and reduced bit error rates (BER). Furthermore, the integration of dynamic cluster optimization strengthens CF-mMIMO system designs, enabling robust and efficient operation under varying conditions without performance degradation. This work provides a promising framework for the advancement of next-generation wireless communication systems.

关键词： Spectral efficiency Scalability Wireless networks Simulation Precoding Bit error rate Massive MIMO Mean square error methods Optimization Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Utilizing Advanced Machine Learning Techniques for Effective Prediction and Control of Pandemic Outbreaks

Utilizing Advanced Machine Learning Techniques for Effective...

引用

Trends in Quantum Computing and Emerging Business Technologies (TQCEBT), International Conference on

作者： R. Thalapathi Rajasekaran H. Shanmugavalli P. Jayalakshmi S. Ambika V. Balaji Dept. of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai Dept. of Computer Science and Engineering GRT Institute of Engineering and Technology Tiruttani Tamil Nadu India Dept. of Computer Science and Engineering Sri Krishna College of Engineering Arakkonam Department of Information Technology E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India Department of CSE (Cyber Security) Easwari Engineering College Chennai

ISBN: (数字)9798350384277

ISBN: (纸本)9798350384284

The health and social implications of pandemic epidemics are substantial. Accurate forecasting and management of such epidemics are of utmost importance to lessen the blow of such epidemics. To tackle this pressing problem, we employ state-of-the-art machine learning methods in our research. In this paper, we investigate the potential of cutting-edge algorithms for modeling, predicting, and controlling the spread of pandemics. These algorithms include LSTM, Random Forest, GNN, RL, DRL, Bayesian Networks, and SVM. We run a battery of experiments and analyses using real-world data sources, such as COVID-19 case data, mobility data, contact tracking data, vaccination distribution data, intervention strategy data, and resource allocation data. These advanced machine-learning approaches have the ability to enhance the accuracy of pandemic predictions, optimize the allocation of resources, decrease transmission rates, and enable more effective intervention measures, according to our findings. For example, our RL algorithm optimized vaccination distribution by 20% while our LSTM model averaged a 92% success rate in forecasting new cases each day. Our research further emphasizes the significance of early detection and intervention. With a 90% success rate, the SVM-based early detection system could spot epidemics ten days before conventional approaches could, buying precious time for focused and efficient responses.

关键词： Adaptation models Machine learning algorithms Pandemics Predictive models Prediction algorithms Vaccines Resource management

来源：评论

学校读者我要写书评

暂无评论

Delay-Optimal and Incentive-Aware Computation Offloading for Reconfigurable Intelligent Surface-Assisted Mobile Edge Computing

IEEE Networking Letters

引用

IEEE Networking Letters 2022年第3期4卷 127-131页

作者： Kumar, Vikas Mukherjee, Mithun Lloret, Jaime Zhang, Qi Kumari, Mamta Bharat Sanchar Nigam Ltd. Network and Co-ordination Section Patna800001 India Nanjing University of Information Science and Technology School of Artificial Intelligence Nanjing210044 China Instituto de Investigacion Para la Gestion Integrada de Zonas Costears Universitat Politecnica de Valencia Valencia46022 Spain Aarhus University Department of Electrical and Computer Engineering Digit Aarhus8000 Denmark Ramchandra Chandravansi Institute of Technology Department of Computer Science and Engineering Bishrampur822124 India

To take the advantage of computing resource of edge server, the end-users must pay the service charge for task processing. However, the transmission delay plays an important role in communication-computation of edge computing. To address this, we aim to leverage reconfigurable intelligent surface (RIS) in mobile edge computing (MEC). In this letter, we propose an offloading policy to maximize the revenue of edge server while satisfying the end-user's goal of minimizing both the latency and cost based on the price by edge server. We provide an insight on required computing resources at the edge server for delay-sensitive task processing. © 2019 IEEE.

关键词： computation offloading

来源：评论

学校读者我要写书评

暂无评论

Classification of Common Insects Using Transfer Learning and ResNet50

Classification of Common Insects Using Transfer Learning and...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： Sakshi Chetan Sharma Jaydeep Kishore Vivek Bhardwaj Amity Institute of Information Technology Amity University Noida India upGrad Education Private Limited Bangalore India School of Computer Science and Engineering Manipal University Jaipur Jaipur India

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

The escalation of the global temperature and the pressure on the fields is at an all-time high. To feed the rising population, insecticides, and pesticides are likewise at an all-time high. With the growing temperature due to global warming and the increasing employment of pesticides to feed the people, one class of creatures suffers the direct hit: insects. On the other hand, the growing warmth leaves them vulnerable to death due to bad environmental circumstances. On the other hand, the increasing employment of pesticides extirpates innocuous insects with hazardous insects. There is a continual requirement to monitor the growth and condition of such insects to maintain the sustainability of the environmental system. However, accomplishing such a big work manually is not only impossible but fruitless, too, since few insects of various classes provide identical looks. To cope with such challenges related to this work, a transfer learning-based ResNet50 network is presented to automatically detect, categorize, and consequently track the insect populations to take future measures. The model obtains a recognition accuracy of 91.45%.

关键词： Hands Temperature sensors Insects Employment Transfer learning Pesticides Feeds Sustainable development Monitoring Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Cross-modality Person Re-identification Method Using Cross-dimensional Interactive Attention Mechanism

Cross-modality Person Re-identification Method Using Cross-d...

引用

Intelligent Management and Software engineering (IMSE), International Conference on

作者： Jin Wang Kaiwei Jiang Ze Lu Xin Lu Zhenbo She School of Computer & Information Engineering Nantong Institute of Technology Nantong Jiangsu China School of Information Science & Technology Nantong University Nantong Jiangsu China Shanghai Shanyi Intelligent Technology Co. Ltd. Shanghai China

The task of cross-modality person re-identification seeks to identify individuals from pedestrian images captured by diverse cameras, catering to the recognition needs across different scenarios. Variability in shooting time, location, and viewpoint introduces notable intra-modality and cross-modality discrepancies in the pedestrian images, diminishing recognition accuracy. Consequently, we proposed a cross-modality person re-identification technique (CDiNet), leveraging a cross-dimensional interactive attention mechanism. During the feature extraction phase, we integrated cross-dimensional interactive attention into the network, bolstering the feature representation. In the metric learning phase, we introduced a group loss, substituting the conventional triplet loss, and amalgamated it with identity loss to refine the network's constraints. The experimental results show that on the SYSU-MM01 dataset, the evaluation metrics Rank-1 and mAP achieve 54.43% and 52.46% respectively in All-search mode, and 62.73% and 68.96% in Indoor-search mode. The recognition accuracy of the proposed method CDiNet is better than similar methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Sentiment Analysis: Exploring the Power of Deep Learning Techniques in Opinion Mining

Deep Learning for Sentiment Analysis: Exploring the Power of...

引用

Evolutionary Algorithms and Soft Computing Techniques (EASCT), International Conference on

作者： L Sindhu M. Rameshkumar Gotte Ranjith Kumar B. N. Manjunath Sapna Kumari C Department of Information Technology Sona College of Technology Salem India Department of Computer Science and Engineering Paavai Engineering College India School of Computer Science & Artificial Intelligence SR University Warangal India Department of Computer Science & amp Engineering R.L. Jalappa Institute of Technology Bangalore India Department of Electronics and Communication Engineering Nitte Meenakshi Institute of Technology Bengaluru India

Sentiment analysis (SA) is a popular method for collecting relevant and arbitrary information from text-based data. To locate, examine, extract reactions, and emotions from the data or states, it applies computational linguistics, biometrics, text analysis, and Natural Language Processing (NLP). A SA model can be developed and improved with the use of the features analysis method. However, it can be difficult to find the best classification methods for this type of data. When compared to current feature-based methods, deep learning models for the analysis of sentiment, are capable of providing precise representation and improved performance. In this paper, the deep learning method was proposed for improving sentiment classification performance with a sophisticated embedding word method and develop a network of Convolutional Neural Network and Long short-term memory (CNN-LSTM). For the purpose of predicting the sentiment of tweets for classification, a large amount of Amazon data is analysed. This study, concentrate on improving sentiment analysis performance by building a CNN-LSTM network and particularized model of deep learning with novel word embedding techniques. The CNN-LSTM model has achieved 98.20% accuracy, 99.86% precision, 99.50% recall, and 98.78% recall in sentiment analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Evaluation of Digital Image Sampling and Quantization for Serial and Parallel Image Processing

An Evaluation of Digital Image Sampling and Quantization for...

引用

Emerging Research in Computational science (ICERCS), International Conference on

作者： Balakumar P Pawan S. Wawage Varun Mishra Dhyan Yadav Sireesha Manchoori Deepak Minhas Department of Information Technology Prince Shri Venkateshwara Padmavathy Engineering College Chennai India Department of Information Technology Vishwakarma Institute of Information Technology Pune India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science and Information Technology Jain (Deemed to be University) Bangalore Karnataka India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

this paper presents an evaluation of the virtual image Quantization (DIQ) method for parallel photo processing. This approach is primarily based on the idea of parallelizing the operation of quantizing a picture with the aid of subdividing the picture into a number of rectangular sections. These sections are then processed in parallel on multiple processors. The results of the assessment show that DIQ is a viable technique for parallel picture processing, with an estimated benefit of up to 2 hundred% in speedup over a conventional serial quantization method. Moreover, the effects additionally indicate that, while used correctly, DIQ can achieve considerably higher outcomes in comparison to serial strategies. The paper also includes a discussion of the potential programs and obstacles of DIQ.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-driven Optimal Cooperative Output Regulation of Unknown Linear Discrete-time Multi-agent Systems

Data-driven Optimal Cooperative Output Regulation of Unknown...

引用

第35届中国控制与决策会议

作者： Dong Liang Yi Dong Chaoli Wang Engang Tian Department of Control Science and Engineering School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology College of Electronic and Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University

The cooperative output regulation problem has been extensively studied on the basis of the distributed observer ***,the majority of the existing research assumes that the dynamics is known *** remove this condition,the cooperative output regulation problem is further solved via the data-driven framework where the dynamics of the plant is ***,a data-driven distributed observer is established to estimate the state of the leader with unknown dynamics subject to external ***,the unknown regulator equations are solved using the iterative recurrent neural network ***,the state-based data-driven distributed control law is synthesized to solve the *** optimal gains are derived by solving convex optimization problems using input and state ***,a numerical example is presented to verify the feasibility of the proposed framework.

关键词： Linear systems multi-agent systems cooperative output regulation data-driven control optimal control

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：