检索结果-内蒙古大学图书馆

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

作者： George, Geomol Anusuya, S. Simats School of Engineering Department of Electronics and Communication Chennai India Simats School of Engineering Department of Computer Science Chennai India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376685

Accurate segmentation of breast cancer images is crucial for effective detection and treatment. This work evaluates the efficacy of various Attention U-Net models with different attention mechanisms, including SE (Squeeze-and-Excitation) blocks and Swish activation functions, for breast cancer image segmentation. We assessed these models using several metrics: IoU, precision, recall, F1 score, MAE, dice coefficient, and specificity. The SE-Swish U-Net variant achieved the highest performance metrics, with a mean IoU of 77.71%, precision of 78.6%, recall of 73.5%, F1 score of 75.9%, dice coefficient of 75.91%, and specificity of 96.70%. The SE-Swish model also demonstrated superior accuracy and efficiency compared to other variants, though it required longer training and execution times. Qualitative analysis supported the SE-Swish model's ability to handle complex lesion borders and low-contrast areas. This work highlights how advanced attention mechanisms in U-Net architectures can enhance breast cancer image segmentation. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

The Traffic-Aware Scatter Net Scheduling (TAAS) for Multicast Wireless Protocols 2

The Traffic-Aware Scatter Net Scheduling (TAAS) for Multicas...

引用

2nd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2023

作者： Hamsa, S. Devaraj Verma, C. Department of Electronics and Communication Engineering Bangalore India Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350347456

The Traffic-Aware Scatter Net Scheduling (TASS) algorithm is an advanced scheduling strategy designed to reduce the latency of the data transmission in wireless networks. It is a hybrid technique that combines both the advantages of a random-access scheduling scheme and a deterministic scheduling scheme. The TASS algorithm is based on two main components: the "scatter"and the "aware."The scatter part of the algorithm randomly assigns nodes to different time slots, while the aware part of the algorithm takes into account the current network traffic. By using the aware part of the algorithm, the TASS algorithm can schedule transmissions in such a way that it reduces the latency of data transmission. The main advantages of the TASS algorithm are its ability to reduce the latency of data transmission and its flexibility in adapting to changes in the network traffic. The algorithm is also designed to be resilient to any changes in the network topology, allowing it to quickly adapt to changing network conditions. Furthermore, the algorithm is designed to be energy efficient, as it minimizes the number of control messages that need to be sent and received. © 2023 IEEE.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Leveraging EfficientNet-B3 with Advanced Fine-Tuning for Precise Breast Cancer Classification 16

Leveraging EfficientNet-B3 with Advanced Fine-Tuning for Pre...

引用

16th IEEE International Conference on Computational Intelligence and communication Networks, CICN 2024

作者： George, Geomol Anusuya, S. Simats School of Engineering Department of Electronics and Communication Chennai India Simats School of Engineering Department of Computer Science Chennai India

ISBN: (数字)9798331505264

ISBN: (纸本)9798331505264

This study explores the use of the pre-trained EfficientNet-B3 model for classifying breast cancer images into benign, malignant, and normal categories. The model was finetuned with layer-specific adjustments, advanced regularization techniques, and comprehensive layer fine-tuning to enhance its ability to detect complex patterns. The results demonstrated exceptional performance, with benign cases achieving a precision of 98%, recall of 94%, and F1 score of 96%;malignant cases with precision of 90%, recall of 96%, and F1 score of 93%;and normal cases showing precision of 94%, recall of 96%, and F1 score of 95%. The model also achieved 99.84% training accuracy, 0.2964 training loss, and 95.25% test accuracy with a loss of 0.4333. These findings underscore the potential of this advanced EfficientNet-B3-based method to improve diagnostic accuracy and support timely, reliable treatment decisions in breast cancer care. © 2024 IEEE.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Fractional Sparrow Optimization- Light Sensor Positioning Enabled Semiconductor Optical Amplifier based Digital Signal Processing Model 2

Fractional Sparrow Optimization- Light Sensor Positioning En...

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Deepa, K. Singh, Ashish Pandu, N.K. Department of Electronics and Communication Engineering Karnataka Nitte574110 India Department of Computer Science and Engineering Karnataka Moodbidri574225 India

ISBN: (纸本)9798350368413

An optimized Dense wavelength-division multiplexing (DWDM) optical network based on semiconductor optical amplifiers (SOAs) plans to improve its ability of signal transmission processing to eliminate the badly negative nonlinear effects caused by high-intensity optical signals. In current models, several issues exist which include nonlinearities, issues to do with optimal performance of SOA, and compatibility with the existing systems. Therefore to conquer those existing challenges in this research develop a new model optimized fractional sparrow optimization- Light Sensor Positioning based semiconductor optical amplifier-based digital signal processing method (FSO-LSP-SOA-DSP). In this research, a new model of optimized FSO is proposed along with the placement of light sensors in a semiconductor optical amplifier-based DSP technique. This new method is to change the signal quality in the DWDM system by efficiently using the FSO for fine-tuning the parameters and the harness of the light sensors placed strategically to capture and process the signals effectively. The proposed model includes optimization of the position of the light sensor and FSO which helps to provide a fuller solution to the problems associated with the non-linearities and signal fading in the optical communication system. The results show that the models have low error rates of 1.19, 3.16, 0.5557, 0.26, 56170.00, and 1.167 during a number of channels (NOC) 50 for bit error rate (BER), error vector magnitude (EVM), generalized mutual information (GMI), mutual information (MI), symbol error rate (SER), and signal to noise ratio (SNR) during CH analysis. © 2024 IEEE.

关键词： Semiconductor optical amplifiers

来源：评论

学校读者我要写书评

暂无评论

EfficientNetB3-Based Lung Cancer Classification from CT Scan Images: A Deep Learning Approach 4

EfficientNetB3-Based Lung Cancer Classification from CT Scan...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Kaur, Gurjot Sharma, Neha Chitkara University Department of Computer Science and Engineering Punjab India Chitkara University Department of Electronics and Communication Engineering Punjab India

ISBN: (纸本)9798350387490

In the field of medical diagnostics, lung cancer disease identification is a vital task. Deploying deep learning technology with EfficientNetB3 architecture as its powerhouse seeks to raise the accuracy and reliability of lung cancer classification in this study. The dataset consists of 1,187 high-resolution images showing lung cancer pathology in a variety of forms. Using the EfficientNetB3 model, 40 iterations of training have been carried out, batch size 20, and learning rate 0.001 are used. This enables the model to pick up on fractional changes that are symptomatic of different kinds of lung cancers. Model training is an arbitrary manipulation of model parameters designed to fine-tune them. The evaluation method for model performance is based on its capacity to recognize CT scan images like that from lung cancer correctly. The proposed EfficientNetB3 model, achieving an accuracy rate of 93.33%, proves remarkably successful. This result indicates the model's proficiency in distinguishing between different types of lung cancer. This enables more accurate diagnosis and treatment planning. And the findings of this recalibrate routes through which patient care is delivered. It hopes to replace conventional medical models with more efficient ones by providing diagnosis capabilities for forms of lung cancer that are both accurate and timely. Thus, misdiagnosis will decrease and targeted treatments can be pursued more effectively. Plus, the research's success illustrates the feasibility of deep learning strategies particularly EfficientNetB3 architecture for promoting medical imaging analysis and health care provision. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Random Forest, SVM, and Naive Bayes for Sentiment Analysis Optimization 2

A Comparative Study of Random Forest, SVM, and Naive Bayes f...

引用

2nd IEEE International Conference on Innovations in High-Speed communication and Signal Processing, IHCSP 2024

作者： Pandey, Ranu Patidar, Praveen Kumar Verma, Pushpalata Khan, Gousia Hazra Anjum Harne, Sachin Tiwari, Rovin Shri Rawatpura Sarkar University Department of Computer Science and Engineering Raipur India Parul University Parul Institute of Technology Department of Computer Science and Engineering Vadodara India Bhilai Institute of Technology Department of Computer Science & Engineering Raipur India Government Engineering College Department of Computer Science and Engineering Raipur India Gh Raisoni College of Engineering Department of Computer Science and Engineering Nagpur India Rgpv Department of Electronics and Communication Engineering Bhopal India

ISBN: (纸本)9798350368949

This study presents an in-depth evaluation of sentiment analysis models applied to a US Twitter dataset. The performance of machine learning models considered in this study are Random Forest, Support Vector Machine (SVM) in both optimized and non-optimized forms, Multinomial Naive Bayes, AdaBoost, and Gaussian Naive Bayes. In this work TFIDF is utilized for vectoize text. For machine learning algorithms the Random Forest and SVM achieve training accuracies of around 99%, but showing the lower test accuracies which denotes the overfitting condition. Other models such as multinomial Naive Bayes and AdaBoost showed consistent performance across both training and testing data. Gaussian Naive Bayes' underperforms in the test data due to the models sensitivity to the data properties. Highest accuracy is achieved using the optimized support vector machine that represents the importance of hyperparameter tuning on model generalization. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

An Optimized Deep-Learning-Based Low Power Approximate Multiplier Design

引用

computer Systems science & engineering 2023年第2期44卷 1647-1657页

作者： M.Usharani B.Sakthivel S.Gayathri Priya T.Nagalakshmi J.Shirisha Department of Electronics and Communication Engineering Er.Perunal Manimekalai College of EngineeringKonneripalliHosur635117India Department of Electronics and Communication Engineering Pandian Saraswathi Yadav Engineering CollegeSivagangaiTamilnadu630561India Department of Electronics and Communication Engineering R.M.D Engineering CollegeGummidipundiTamilnadu601206India Department of Computer Science and Engineering Koneru Lakshmaiah Education FoundationVaddeswaramGuntur522502India Department of Electronics and Communication Engineering Malla Reddy Engineering CollegeHyderabadTelangana500015India

Approximate computing is a popularﬁeld for low power consumption that is used in several applications like image processing,video processing,multi-media and data *** Approximate computing is majorly performed with an arithmetic circuit particular with a *** multiplier is the most essen-tial element used for approximate computing where the power consumption is majorly based on its *** are several researchers are worked on the approximate multiplier for power reduction for a few decades,but the design of low power approximate multiplier is not so *** seems a bigger challenge for digital industries to design an approximate multiplier with low power and minimum error rate with higher *** overcome these issues,the digital circuits are applied to the Deep Learning(DL)approaches for higher *** recent times,DL is the method that is used for higher learning and prediction accuracy in severalﬁ***,the Long Short-Term Memory(LSTM)is a popular time series DL method is used in this work for approximate *** provide an optimal solution,the LSTM is combined with a meta-heuristics Jel-lyﬁsh search optimisation technique to design an input aware deep learning-based approximate multiplier(DLAM).In this work,the jelly optimised LSTM model is used to enhance the error metrics performance of the Approximate *** optimal hyperparameters of the LSTM model are identiﬁed by jelly search ***ﬁne-tuning is used to obtain an optimal solution to perform an LSTM with higher *** proposed pre-trained LSTM model is used to generate approximate design libraries for the different truncation levels as a func-tion of area,delay,power and error *** experimental results on an 8-bit multiplier with an image processing application shows that the proposed approx-imate computing multiplier achieved a superior area and power reduction with very good results on error rates.

关键词： Deep learning approximate multiplier LSTM jellyﬁsh

来源：评论

学校读者我要写书评

暂无评论

Improving Cloud Data Security with Alexnet Learning Model Compare Stochastic Gradient Descent with Accuracy 3

Improving Cloud Data Security with Alexnet Learning Model Co...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Thriveni, E. Mahaveerakannan, R. Sudhakar, K. Department of Computer Science and Engineering Tamilnadu Chennai602105 India Department of Electronics and Communication Engineering Tamilnadu Chennai602105 India

ISBN: (纸本)9798350372120

The suggested method of protecting cloud data involves setting up a server to function as a third party, similar to Alexnet, and using Advanced Encryption Standard for data stored in private clouds. Stochastic Gradient Descent is used to calculate accuracy the user and the cloud in order to ensure security between the two parties. Supplies and Procedures: In this work, two groups - AlexNet and Stochastic Gradient Descent - are compared. For statistical analysis, 1300 instruction and 423 testing dataset samples from the UNSW-NB15 dataset were used. N=10, an alpha value of 0.05, a G-Power value of 0.8%, and a 95% confidence interval were employed in the ClinCalc software for each approach. Findings and Discussion: Novel Alexnet (91.081%) exhibits better accuracy than SGD (87.9396%). The significance value, as determined by looking at the Independent Sample t-Test findings, is 0.011(p © 2024 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

An Optimized Plant Disease Classification System Based on Resnet-50 Architecture and Transfer Learning 4

An Optimized Plant Disease Classification System Based on Re...

引用

4th International Conference for Emerging Technology, INCET 2023

作者： Balavani, Kola Sriram, Dasari Shankar, Malla Bhavani Charan, Devavarapu Sri Department of Electronics and Communication Engineering Mylavaram India Department of Computer Science and Engineering Mylavaram India

ISBN: (纸本)9798350335750

Automated plant disease diagnosis is a vital task in modern agriculture to ensure timely and effective management and reduce crop losses. This paper proposes a deep learning-based plant disease classification model using ResNet-50 architecture, which offers several advantages over existing methods. ResNet-50 allows accurate identification of plant diseases from images with high precision and recall, even when the diseases have similar visual characteristics. The ResNet-50 architecture has skip connections that help in reusing the learned features from previous layers, overcoming the problem of vanishing gradients and allowing it to train on deeper networks, resulting in improved accuracy compared to shallower models. Furthermore, transfer learning is utilized in the proposed model, enabling the use of pre-trained weights from a large dataset of general images, followed by fine-tuning on the plant disease dataset. This enhances the model's performance by leveraging the pre-trained weights' knowledge, leading to faster convergence, improved accuracy, and reduced training time. The model is trained and tested on a comprehensive dataset from 38 different categories of plant diseases and healthy leaves. This ensures that the model is robust and can accurately identify and classify diseases across various plant species. By leveraging the advantages of the ResNet-50 architecture and transfer learning, the proposed model can accurately and efficiently diagnose plant diseases, leading to improved agricultural productivity and reduced losses due to plant diseases. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Classification and Prediction of Employee Attrition Rate using Machine Learning Classifiers 7

Classification and Prediction of Employee Attrition Rate usi...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Garg, Umang Gupta, Neha Manchanda, Mahesh Purohit, Kamlesh Amity University Department of Computer Science And Engineering Gwalior India Amity University Department of Electronics And Communication Engineering Gwalior India Graphic Era Hill University Department of Computer Science And Engineering Dehradun India Graphic Era Deemed To Be University Department of Computer Science And Engineering Dehradun India

ISBN: (纸本)9798350359299

In today's time, employee attrition is a major problem faced by organisations. The most precious resource for a company is its workforce. They are the ones who bring value to the company both in terms of quantity and quality. A steady decline in the workforce due to retirement, death, or resignation is referred to as attrition. It is a matter of concern when employees leave their jobs of better opportunities but this leads the company to face its consequences. Employee attrition is like employee turnover. By understanding this concept, leaders can design smarter retention strategies to avoid it. This research uses a dataset to analyze attrition and find the reason why employee choose to resign. The training dataset is then analyzed for enabling effective data exploration. Machine Learning (ML) algorithms, such as Random Forest Classifier, Adaboost, XGBoost and ensemble stacking technique are considered. After data exploration, this study found Random Forest (RF) classifier as the best suited algorithm for this dataset with an accuracy of 87.41% and precision 88%. This study also concludes that the monthly income can be a reason behind employees leaving their job and finding better opportunities. © 2024 IEEE.

关键词： Adaptive boosting

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：