检索结果-内蒙古大学图书馆

2nd International Conference on Power, Electrical, Electronics and Industrial Applications, PEEIACON 2024

作者： Munni, Suraiya Akter Parvin, Farjana Rajshahi University of Engineering & Technology Department of Computer Science & Engineering Rajshahi Bangladesh

ISBN: (纸本)9798331517984

The COVID-19 outbreak stands as one of the most significant global health crises in recent memory, claiming millions of lives worldwide. The urgent and precise identification of the disease holds paramount importance for effective treatment and preventive measures due to its rapid spread. Moreover, distinguishing between COVID-19 and other pneumonia ailments is crucial for accurate diagnosis and subsequent treatment, given their similar symptomatology and physiological impacts. Leveraging x-ray imaging in medical diagnostics offers a rapid and cost-effective means of detection. In this study, a dual-stage feature selection methodology is employed on hybrid or combined deep convolutional characteristics or features extracted from x-ray images. Three convolutional neural networks (CNNs) - Inception V3,ResNet50, and Xception - are utilized in a transfer learning framework. The performance of combining features from multiple CNNs is meticulously analyzed. Initially, features from various models are selected at a specified percentage in the first level of feature selection, followed by a second level to identify the most informative features. Both levels employ the Light Gradient Boosting Machine (LGBM) algorithm for selection. The resultant feature set is then utilized to classify Viral Pneumonia, COVID-19 and non-Covid-19 chest x-ray images using a Support Vector Machines (SVM) classifier. The proposed model's efficacy is evaluated using an open-access dataset, achieving a peak accuracy of 98.49% by leveraging only 35% of the features extracted from the proposed hybrid model consisting of ResNet50, InceptionV3,and Xception networks. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A Study Of Dynamic Thresholds Power Detection Spectrum Sensing Techniques In CRN 9

A Study Of Dynamic Thresholds Power Detection Spectrum Sensi...

引用

9th International Conference on Advanced Computing and Communication Systems, ICACCS 2023

作者： Keerthika, J. AnandaKumar, H. Priya, V. Yuvalatha, S. Gayathri, N. Sri Eshwar College of Engineering Department of Computer Science and Engineering Coimbatore India Dr NGP Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Bannari Amman Institute of Technology Department of Computer Science and Business System Sathyamangalam India

ISBN: (纸本)9798350397376

A Cognitive radio is the mobile communication technologies which help to utilize the efficient need of radio spectrum origin. The performance of CRN is significantly impacted by the spectrum sensing function. The problem of bandwidth has risen as a more specific one with breakthroughs in remote communications. By forgiving unlicensed users to usage the available spectrum in primary networks is the solution to the CR Technology. An innovative method for enhancing the electromagnetic spectrum's use efficiency, cognitive radio is a encouraging technology. Spectrum sensing has high spectral resolution capabilities and aids in the detection of the spectrum holes. The various methodologies are used to enhance the spectrum sensing essence. These techniques are distinguished by a sensing threshold, which is crucial to the performance of the sensing. The most important element in selecting the best threshold to optimize spectrum sensing performance is the dynamic threshold in the proposed system's spectrum detection algorithm. The energy earned from the licensed user over a precise time of observation, then the dynamic threshold is commutated between two levels. The estimation of the noise ambiguity factor forms the basis for threshold evaluations. These criteria are used to hike the likelihood of detection and contraction the possibility of false alarms. © 2023 IEEE.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model to Predict the Breast Cancer using Stacking and Bagging Model 3

A Hybrid Model to Predict the Breast Cancer using Stacking a...

引用

3rd IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Yuvalatha, S. Nithyapriya, S. Prabhavathy, S. Priyadharshini, R. Savitha, S. Kayathri, S. Bannari Amman Institute of Technology Department of Computer Science and Business Systems Sathyamangalam India Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science Sathyamangalam India Christ the King Engineering College Department of Electronics and Communication Engineering Coimbatore India Sri Ranganathar Institute of Engineering Department of Computer Science and Engineering Coimbatore India PSR Engineering College Department of Computer and Science and Engineering Sivakasi India

ISBN: (纸本)9798350317022

Breast cancer is a malignant tumor that develops in the cells of the breast tissue. Breast cancer is one of the major causes of death for women globally. In the examination of medical data, breast cancer prediction is a difficult task. To make decisions and accurately distinguish between benign and malignant tumors, physicians and pathologists need certain automated technologies. In this paper, hybrid ensemble technique (Bagging and Stacking) is used to predict the breast tumors as benign and malignant tumors. In the proposed work, the subset of data is created from the initial Wisconsin (Diagnostic) data Set by bootstrapping technique. Each bootstrap dataset is used to train the weak learner. The weak learners are K-Nearest Neighbors (KNN) Random Forest (RF), Decision Tree (DT) and Support Vector Machine (SVM). The Logistic Regression (LR) is used as the Meta Learner. The Meta Learner uses the predictions of weak learners as its training data. The proposed hybrid ensemble model obtains an accuracy 98.7%, Precision 98.83%, Recall 98.54%, F1 Score 98.68% and 0.012% error. © 2023 IEEE.

关键词： Bagging Bootstrapping Ensemble Malignant Meta Learner Stacking

来源：评论

学校读者我要写书评

暂无评论

Sobel Filtered UNet Prototype based Date Fruit Classification 5

Sobel Filtered UNet Prototype based Date Fruit Classificatio...

引用

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Devi, M. Shyamala Pallavi, S. Ramya, A.B. Radhika, K. Revathi, K. Sarupriya, P. Panimalar Engineering College Department of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350376685

Accurate and effective fruit classification is essential for separating and analyzing in the field of agriculture. This article design a proposed model for classifying date fruit using Sobel Filtered UNet (SFU-Net). To increase feature extraction and classification accuracy, the recommended strategy incorporates Sobel edge detection into the UNet architecture. For execution, 1200 images from the KAGGLE Date Fruit dataset were used. The dataset contains 200 images for six classes of Date fruit for Sugaey, Shaishe, Ajwa, Galaxy, Natab Ali and Rutab date images. Date Fruit Images are preprocessed using the Sobel filter, which is renowned for its ability to identify edges. This Sobel filter highlights the characteristics that are essential for differentiating between various types of date fruit. Subsequently, the preprocessed Sobel filtered date fruit image input is fed into the UNet, a popular CNN that is popular for its efficiency in segmentation tasks. The prototype accomplishes precise date fruit categorization and high-resolution segmentation by using the encoder-decoder structure of UNet. Experiments show that integrating edge detection with state-of-the-art deep learning approaches can lead to notable gains in classification performance when compared to conventional methods. This method not only pushes the boundaries of fruit categorization but also has potential uses in automated sorting methods and agricultural quality control. The results show that the proposed SFU-Net model performs exceptionally well towards date fruit classification, with a high accuracy of 99.45%. © 2024 IEEE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Skin Lesion Classification System Using Shearlets

引用

computer Systems science & engineering 2023年第1期44卷 833-844页

作者： S.Mohan Kumar T.Kumanan Department of Computer Science and Engineering Meenakshi Academy of Higher Education and ResearchChennai600078Tamil NaduIndia

The main cause of skin cancer is the ultraviolet radiation of the *** spreads quickly to other body ***,early diagnosis is required to decrease the mortality rate due to skin *** this study,an automatic system for Skin Lesion Classification(SLC)using Non-Subsampled Shearlet Transform(NSST)based energy features and Support Vector Machine(SVM)classifier is ***,the NSST is used for the decomposition of input skin lesion images with different directions like 2,4,8 and *** the NSST’s sub-bands,energy fea-tures are extracted and stored in the feature database for *** classifier is used for the classification of skin lesion *** dermoscopic skin images are obtained from PH^(2) database which comprises of 200 dermoscopic color images with melanocytic *** performances of the SLC system are evaluated using the confusion matrix and Receiver Operating Characteristic(ROC)*** SLC system achieves 96%classification accuracy using NSST’s energy fea-tures obtained from 3^(rd) level with 8-directions.

关键词： Skin lesion classification non-subsampled shearlet transform sub-band coefficients energy feature support vector machine

来源：评论

学校读者我要写书评

暂无评论

Design of an Efficient Model for Health Status Prediction Using LSTM, Transformer, and Bayesian Neural Networks

Design of an Efficient Model for Health Status Prediction Us...

引用

2024 International Conference on Innovations and Challenges in Emerging Technologies, ICICET 2024

作者： Golchha, Rishi Khobragade, Prashant Talekar, Ashish Gh Raisoni College of Engineering Department of Computer Science and Engineering Nagpur India

ISBN: (纸本)9798350319019

The urgent need for health predictions has led to extensive research, but existing methods often fail to cope with the complexity of health data. While traditional methods struggle to capture the temporal and descriptive relationships expected in multimodal health data, this research offers new methods that use technology tools to overcome these limitations. By integrating long-term memory (LSTM) networks for physical modeling, Transformer architecture with multi-head listening mechanism for feature extraction, and Bayesian neural networks (BNN) for parameter estimation, clearly, our model was effective in predicting health outcomes. LSTM networks are effective at capturing long-term dependencies found in continuous health data and help identify changes in healthy patient recruitment over time. Meanwhile, the multihead Transformer takes care of the translation by focusing on important features in multivariate data, thus improving the accuracy of disease classification. Additionally, integration of Bayesian neural networks can quantify uncertainty, which is important for informed clinical decision making. Tests show that the performance is better than traditional methods, with fewer errors and defects. This principle not only increases the accuracy and reliability of health predictions, but also has the ability to change medical decisions, ultimately improving patient outcomes and healthcare. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

An effective deep learning based Idrcnn and Bdc-Lstm models for complex word identification and synonym generation

引用

International Journal of Information Technology (Singapore) 2025年第3期17卷 1703-1716页

作者： RajyaLakshmi, Tamma Vinta, Surendra Reddy Department of Computer Science Pondicherry University Puducherry Kalapet 605014 India School of Computer Science and Engineering VIT-AP University Andhra Pradesh Amaravati 522237 India

Finding words in a document that the average reader could find challenging to understand is usually the first step in identifying complex words in the text. After you've determined which terms are difficult, you might create synonyms or offer substitutes that would be simpler to read to improve the text's accessibility. As a result, inaccurate synonyms unrelated to the context may be created. In this field of study, combining the recognition of difficult words with the creation of synonyms is novel. We provide a unique deep-learning technique and algorithm to address the problems in the prior research's difficult word identification and synonym-generating tasks. This research is evaluated on the Complex Word Identification dataset. Initially, stop word removal, tokenization, punctuation removal, lowercasing, and stemming are performed in the pre-processing phase. After that, utilize the FastText method to perform word embedding on pre-processed input text. Then, the attributes of morphological and linguistics from embedded text are retrieved to enhance the classification performance. Then, recognize the complex words from the given text utilizing the Improved Deep Residual Convolutional Neural Network (IDRCNN) approach and also employ the Single Candidate Optimization Algorithm (SCOA) to enhance the classification performance by tuning and optimizing the parameters of the technique. Finally, utilize the Bi-Directional Convolutional Long Short Term Memory (BDC-LSTM) for synonyms generation for those identified words. The experimental results demonstrate that the proposed approach performs better than the alternative approaches in terms of entity synonym set construction performance. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Complex word improved deep residual convolutional neural network Fastext Feature extraction Identification Stop word removal Synonyms generation task Word embedding

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Evolved: Overcoming Sub-Optimal Local Minima with (μ/ρ+λ)-Evolution Strategies

Deep Learning Evolved: Overcoming Sub-Optimal Local Minima w...

引用

2023 Congress in computer science, computer engineering, and Applied Computing, CSCE 2023

作者： Rivas, Pablo School of Engineering and Computer Science Baylor University Department of Computer Science United States

ISBN: (纸本)9798350327595

Integrating Evolution Strategies (ES) and Backprop-agation (BP) within a deep neural network framework presents a significant challenge, as ES has previously only been shown to perform comparably to BP for smaller problems. In this study, we extend the application of ES to high-dimensional problems, using it to initialize the weights of a Deep Neural Network (DNN). Our experiments demonstrate that this novel ES approach can effectively overcome local minima and converge towards near-optimal global solutions. Following ES initialization, we employ traditional BP gradient methods to further refine the weights based on the initial set provided by ES. A key finding of our research is the potential for ES to reduce the computational time required by traditional gradient-based backpropagation learning methods. This efficiency is achieved by providing an initial set of weights close to the global optimum, enabling the network to converge more rapidly than with random or zero-weight initialization approaches. Our approach offers a promising direction for future research in the efficient training of deep neural networks and opens up new possibilities for tackling high-dimensional problems with these networks. © 2023 IEEE.

关键词： deep learning evolution strategies genetic algorithms machine learning

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Automatic Gas Leakage Detection and Fire Protection System

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2022年第21期16卷 49-70页

作者： Islam, Gazi Zahirul Hossain, Md. Mobarak Faruk, Md. Nur, Fernaz Narin Hasan, Nayeem Khan, Khalid Mahbub Tumpa, Zerin Nasrin Department of Computer Science and Engineering Southeast University Dhaka Bangladesh Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh Department of Computer Science and Engineering Notre Dame University Bangladesh Dhaka Bangladesh School of Computer Science Western Illinois University IL United States Department of Computer Science and Engineering University of Information Technology & Sciences Dhaka Bangladesh

Gas Leakage and its fatal effects are a great concern throughout the world, especially in developing countries like Bangladesh. Every year lots of people died and countless damages to assets occur due to the fire caused by the gas leakage. Not only that but gas leakage and explosion are also very harmful to the climate. Thus, a system to detect gas leakage and preventive measures is of utmost importance. In this project, we design and implement an intelligent IoT prototype to detect gas leakage, and the fire caught by gas leakage. Our goal is to minimize the effect of gas leakage by taking some protective measures. When the gas sensor, detects the gas leakage, the solenoid valve shuts off the gas line, and the exhaust fan starts to run. Again, when the flame sensor detects a fire, the sucker throws the fire extinguisher balls at the fire. The GSM SIM module notifies the user by sending a message to his smartphone. The buzzer sounds when a mishap occurs and the LCD monitor always shows the status of the system. In this way, we have efficiently designed and implemented a low-cost and intelligent gas leak detection and fire suppression system. © 2022, International Journal of Interactive Mobile Technologies. All Rights Reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Novel Image Alignment Technique Leveraging Teaching Learning-Based Optimization for Medical Images

A Novel Image Alignment Technique Leveraging Teaching Learni...

引用

International Conference on data Analytics and Management, ICDAM 2023

作者： Arora, Paluck Mehta, Rajesh Ahuja, Rohit Computer Science and Engineering Department Thapar Institute of Engineering and Technology Patiala India

ISBN: (纸本)9789819965434

In image registration, traditional optimization techniques are incapable of detecting the optimum value of geometric transformation parameters. To resolve this issue, a novel scheme of monomodal (isomodal) biomedical image registration employing teaching learning-based optimization (TLBO) is proposed. In pre-processing, reference image undergoes gaussian filtering to eliminate noise followed through normalization. During de-noising, contrast between anatomical features of an image is degraded. In order to create the floating image, rigid transformation is employed. These images are aligned by detecting optimum value of rigid transformation parameters (RTP) using TLBO with mutual information (MI) maximization as an objective function. MI and structural similarity index measure (SSIM) are used to evaluate visual quality of registered image. The proposed scheme is tested on several isomodal medical images such as magnetic resonance imaging (MRI) and computed tomography (CT). The value of MI, SSIM increases by 8% and the value of RMSE is significantly reduced from 0.4953 to 0.1306 [1] and 3.7858 to 0.1809 [2] which clearly reveals that proposed scheme is robust and effective as compared with the state-of-the-art methods. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image registration

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：