检索结果-内蒙古大学图书馆

Computational, Communication and Information technology (ICCCIT), International Conference on

作者： RVS Praveen Meenakshi Maindola Anandhi R J Nagarjuna Thandra Saloni Bansal Vishal Sharma Digital Engineering and Assurance LTIMindtree Limited Hyderabad Telangana India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Department of Information Science Engineering New Horizon College of Engineering Bangalore Dept. Computer Science and Engineering MLR Institute of Technology Hyderabad Telangana Department of Computer Engineering and Applications GLA University Mathura Lovely Professional University Phagwara India

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512972

The degradation of image quality caused by things like light absorption, scattering, and distortion makes object detection in underwater environments a unique challenge. Applications like marine research, environmental monitoring, and autonomous underwater vehicles (AUVs) are restricted in their effectiveness by traditional image processing techniques, which often struggle with these complexities. Recent years have seen the rise of deep learning techniques as a potent weapon in the fight against these obstacles. In order to accurately detect objects underwater, this paper investigates the use of deep learning models, specifically convolutional neural networks (CNNs). We explore cutting-edge models and methods like attention mechanisms, transfer learning, and hybrid deep learning architectures to improve detection performance in challenging underwater environments. Furthermore, we utilize data augmentation techniques and synthetic dataset generation to tackle the critical issue of limited labeled underwater datasets. From a detection accuracy and robustness perspective, the experimental results show that our suggested deep learning method is light years ahead of the competition. Marine exploration, autonomous underwater vehicle navigation, and underwater surveillance systems can all benefit from this study's new insights into how to better detect objects in real time while submerged.

关键词： Deep learning Autonomous underwater vehicles Accuracy Transfer learning Object detection Data augmentation Real-time systems Data models Environmental monitoring Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

EEG signal classification for mental stress during arithmetic task using wavelet transformation and statistical features

EEG signal classification for mental stress during arithmeti...

引用

2021 International Conference on Automation, Control and Mechatronics for Industry 4.0, ACMI 2021

作者： Islam, Ariful Sarkar, Ajay Krishno Ghosh, Tonmoy Rajshahi University of Engineering and Technology Dept. of Electrical and Electronic Engineering Rajshahi Bangladesh University of Alabama Dept. of Electrical and Computer Engineering TuscaloosaAL United States

ISBN: (纸本)9781665438438

This paper on electroencephalogram (EEG) analysis describes a feature extraction model based on discrete wavelet transforms for the classification of EEG signals during a mental arithmetic task as mental stress. Stress is a normal part of life. Stress analysis is more important than sleep analysis because stress causes sleeping disorders. The EEG is used to monitor the electrical activities of the brain. The features were computed in time-frequency domain using wavelet decomposition and they were extracted from single-channel EEG signal during and before a mental arithmetic task. The amplitude, power, and frequency of extracted decomposed signals changed significantly during mental stress compared to the state before the mental arithmetic task. 12 state-of-art statistical features were computed from each decomposed signal (5 decomposed frequency bands gave a total of 60 features) of a fixed window of 10 seconds. The Neighborhood Component Analysis (NCA) feature selection method was used to find the most significant features, which resulted in the discovery of four features. Finally, mental stress was classified using the selected four features and Ensemble Subspace KNN classifier. The classifier's performance was evaluated on 11 subjects using a five-fold cross-validation technique, which crossed state-of-the-art methodologies in the literature by 77.3 percent. © 2021 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Equitable Federated Learning for Skin Cancer Detection: A Fairness-Driven Approach

Equitable Federated Learning for Skin Cancer Detection: A Fa...

引用

International Conference on computer and Information technology (ICCIT)

作者： Mrityunjoy Gain Sumit Kumar Dam Apurba Adhikary Yu Qiao Anupam Kumar Bairagi Rameswar Debnath Avi Deb Raha AI Innovation Lab Khulna Bangladesh Computer Science and Engineering Discipline Khulna University Khulna Bangladesh Dept. of ICE Noakhali Science and Technology University Noakhali Bangladesh Department of Computer Science and Engineering Kyung Hee University Korea

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

Skin cancer is a prevalent malignancy where early detection is vital for improving patient outcomes. Traditional deep learning methods often rely on centralized data, raising concerns over privacy and security. Federated learning (FL) offers a decentralized alternative, enabling model training across multiple institutions without sharing sensitive data. However, the performance of existing FL approaches depends heavily on balanced data distribution, which is often unrealistic in realworld scenarios. In this study, we propose a fairness-aware FL framework for skin cancer detection, leveraging diverse and heterogeneous dermatological image datasets from multiple healthcare institutions. Unfair or biased client models can negatively impact global model convergence and overall performance. To address this, our framework incorporates a global validation dataset to evaluate each client’s local model during every training round. Specifically, the server evaluates the performance of client-submitted models against the global dataset and enforces a predefined performance threshold. Only client models that surpass this threshold are incorporated into the global model aggregation process, ensuring that only high-performing and equitable models contribute to the collective learning. The proposed framework is evaluated against baseline FL approaches using critical performance metrics, including accuracy, sensitivity, and specificity. Empirical results demonstrate that the fairnessaware FL framework surpasses traditional methods, achieving a maximum accuracy of 85.29% and enhanced robustness in the detection of skin cancer. In our approach, the overall performance improvement ranges from 5% to 8%, depending on the degree of unfairness and the number of clients involved.

关键词： Training Accuracy Federated learning Distributed databases Medical services Sensitivity and specificity Data models Servers Skin cancer Convergence

来源：评论

学校读者我要写书评

暂无评论

Advanced Lung Nodule Segmentation and Classification for Early Detection of Lung Cancer using SAM and Transfer Learning

arXiv

引用

arXiv 2024年

作者： Asha, V. Bhavanishankar, K. Dept. of Computer Science and Engineering RNS Institute of Technology Karnataka Bengaluru560098 India Visvesvaraya Technological University Karnataka Belagavi590018 India

Lung cancer is an extremely lethal disease primarily due to its late-stage diagnosis and significant mortality rate, making it the major cause of cancer-related demises globally. Machine Learning (ML) and Convolution Neural network (CNN) based Deep Learning (DL) techniques are primarily used for precise segmentation and classification of cancerous nodules in the CT (Computed Tomography) or MRI images. This study introduces an innovative approach to lung nodule segmentation by utilizing the Segment Anything Model (SAM) combined with transfer learning techniques. Precise segmentation of lung nodules is crucial for the early detection of lung cancer. The proposed method leverages Bounding Box prompts and a vision transformer model to enhance segmentation performance, achieving high accuracy, Dice Similarity Coefficient (DSC) and Intersection over Union (IoU) metrics. The integration of SAM and Transfer Learning significantly improves computer-Aided Detection (CAD) systems in medical imaging, particularly for lung cancer diagnosis. The findings demonstrate the proposed model effectiveness in precisely segmenting lung nodules from CT scans, underscoring its potential to advance early detection and improve patient care outcomes in lung cancer diagnosis. The results show SAM Model with transfer learning achieving a DSC of 97.08% and an IoU of 95.6%, for segmentation and accuracy of 96.71% for classification indicates that, its performance is noteworthy compared to existing techniques. © 2024, CC BY.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Smooth Switching Between Two Different Control Methods Based on Kalman Filter for Grid-Connected Inverter

Smooth Switching Between Two Different Control Methods Based...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Yanqi Cheng Weimin Wu Mohamed Orabi Koutroulis Eftychios Henry Chung Frede Blaabjerg Dept. of Electrical Engineering Shanghai Maritime University Shanghai China Dept. of Electrical Engineering Anhui University of Science and Technology Anhui China Dept. of Engineering Aswan University Aswan Egypt Dept. of Electronic and Computer Engineering Technical University of Crete Chania Greece Dept. of Electrical Engineering CityU of Hongkong Hongkong China Dept. of Engery Techique Aalborg University Aalborg Denmark

ISBN: (数字)9798350360868

ISBN: (纸本)9798350360875

The stable and efficient operation of the grid-connected inverter (GCI) is facing severe challenges under the large short-circuit ratio (SCR) fluctuations. In order to ensure the operation quality of the GCI, the dual-mode control was proposed to select the current source mode (CSM) or voltage source mode (VSM) according to the SCR. However, due to the different principles of the dual-mode, when the GCI directly switches from the CSM to the VSM, the grid-injected current and the PCC voltage will have large oscillations. In this paper, a smooth switching dual-mode control method is proposed by using a Kalman Filter observer to suppress the oscillations during mode switching process. The proposed method has been fully verified through simulations and experiments.

关键词： Adaptation models Fluctuations Process control Switches Control systems Inverters Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Circuit Decompositions and Scheduling for Neutral Atom Devices with Limited Local Addressability

Circuit Decompositions and Scheduling for Neutral Atom Devic...

引用

Quantum Computing and engineering (QCE), IEEE International Conference on

作者： Natalia Nottingham Michael A. Perlin Dhirpal Shah Ryan White Hannes Bernien Frederic T. Chong Jonathan M. Baker Dept. of Computer Science University of Chicago Chicago IL USA Global Technology Applied Research JPMorganChase New York NY USA Pritzker School of Molecular Engineering University of Chicago Chicago IL USA Dept. Electrical & Computer Engineering University of Texas at Austin Austin TX USA

ISBN: (数字)9798331541378

ISBN: (纸本)9798331541385

Despite major ongoing advancements in neutral atom hardware technology, there remains limited work in systems-level software tailored to overcoming the challenges of neutral atom quantum computers. In particular, most current neutral atom architectures do not natively support local addressing of single-qubit rotations about an axis in the xy-plane of the Bloch sphere. Instead, these are executed via global beams applied simultaneously to all qubits. While previous neutral atom experimental work has used straightforward synthesis methods to convert short sequences of operations into this native gate set, these methods cannot be incorporated into a systems-level framework nor applied to entire circuits without imposing impractical amounts of serialization. Without sufficient compiler optimizations, decompositions involving global gates will significantly increase circuit dept., gate count, and accumulation of errors. No prior compiler work has addressed this, and adapting existing compilers to solve this problem is nontrivial. In this paper, we present an optimized compiler pipeline that translates an input circuit from an arbitrary gate set into a realistic neutral atom native gate set containing global gates. We focus on decomposition and scheduling passes that minimize the final circuit's global gate count and total global rotation amount. As we show, these costs contribute the most to the circuit's duration and overall error, relative to costs incurred by other gate types. Compared to the unoptimized version of our compiler pipeline, minimizing global gate costs gives up to 4.77x speedup in circuit duration. Compared to the closest prior existing work, we achieve up to 53.8x speedup. For large circuits, we observe a few orders of magnitude improvement in circuit fidelities.

关键词： Costs Circuits Pipelines Qubit computer architecture Logic gates Hardware Software Error correction Optimization

来源：评论

学校读者我要写书评

暂无评论

Classification and Detection of Breast Cancer Review

Classification and Detection of Breast Cancer Review

引用

International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET)

作者： Azhar Kassem Flayeh Ali Douik Salam Thajeal dept. National Engineering school of Sousse NOCCS Laboratory University of Sousse Sousse Tunisia Department of computer science University of Technology Baghdad Iraq

ISBN: (数字)9798350350845

ISBN: (纸本)9798350350852

The Cancer is the second-leading cause of death for women aged 20–59 worldwide and very few men. Compared to other cancers, breast cancer kills more people. According to ***, 13% of American women are at risk of having this cancer, and approximately 80% of them advance, which decreases recovery and treatment success. Deep learning methods for BC detection have been successful thanks to AI. This improves early diagnosis, increasing patient survival. This publication provides a detailed review of the deep learning-based BC diagnosis literature. It aims to help practitioners and researchers understand this domain's issues and trends. This article reviews looks at deep learning methods for breast cancer detection. Next, we examine and synthesize the latest AI-based breast cancer diagnostic studies using multiple breast DL modalities. We also provide a complete overview of breast-cancer imaging datasets, emphasizing their importance in AI-driven algorithms and deep learning model training. The investigation found that the CNN is the most widely used and accurate BC diagnosis model. Also, accuracy measures are the key way to evaluate such models. To provide a complete reference for breast cancer imaging researchers from the details of the researchers works. we can say that The performance of breast cancer detection is influenced by three factors: (1) the efficacy of the CAD system, (2) the characteristics of the population under analysis, and (3) the proficiency of the radiologists utilizing the system. CAD can assist in detecting microcalcifications, which may serve as potential indicators of

关键词： Deep learning Solid modeling Design automation Reviews Databases Signal processing algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Novel Direct Formula Based Technique for Predicting the Class Label of New Unseen Test Tuple without Learning

A Novel Direct Formula Based Technique for Predicting the Cl...

引用

Emerging Techniques in Computational Intelligence (ICETCI), International Conference on

作者： D. Mabuni S. Aquter Babu C. Sudarsana Reddy Dept. of Computer Science and Technology Dravidian University Kuppam Andhra Pradesh India Chadalawada Ramanamma Engineering College Tirupati Andhra Pradesh India

ISBN: (数字)9798350387063

ISBN: (纸本)9798350387070

Supervised learning is an important task in many machine learning applications. In this paper, a direct formula is proposed for predicting the class label of a generalized new unseen instance. The mostimportant attractive feature of the proposed class label prediction formula is that it requires no training step. In other words, intermediate learning steps are not required and as a result of this there exists no intermediate models for class label prediction. Proposed formula directly predicts class label of thenew test tuple. Proposed class label prediction formula is based on the aggregate class label counts of the values of the attributes of the given entire training dataset. For optimal performance, proposed formula is normalized and normalized formula is used for prediction. For brevity, proposed class label prediction technique is named as Direct Class Label Prediction (DCLP). Experiments are conducted on many of the UCI machine learning datasets.

关键词： Training Machine learning algorithms Accuracy Computational modeling Supervised learning Machine learning Predictive models Prediction algorithms Numerical models Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

On the Permittivity of XT-CF20

On the Permittivity of XT-CF20

引用

IEEE International Symposium on Electromagnetic Compatibility (EMC)

作者： Aaron Harmon Wei Zhang Victor Khilkevich Dept. of Electrical and Computer Engineering – Electromagnetic Compatibility Laboratory Missouri University of Science and Technology Rolla MO USA

In this work, the permittivity of a 3D-printed carbon fiber-loaded anisotropic material, XT-CF20, is examined further. The microstructure of XT-CF20 is first examined via optical imaging and is shown to be composed of inclusions that are aligned with the print direction of the sample. The permittivity tensor for the aligned microstructure is then measured using a capacitive measurement technique and simulations are provided to demonstrate the validity of this measurement method. The simulated permittivity values for XT-CF20 samples with varying infill structures are then presented and compared to the measured permittivity values of said samples. An error of less than 12% between the simulated and measured permittivity values was observed validating the measured permittivity tensor and claims about the cause of the anisotropy presented in this work. The pronounced effect of a sample’s infill on the permittivity tensor of the sample is then discussed along with the conclusions of this work and possible future topics of work for the authors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Based Examination of the Field of Ophthalmology 10

Artificial Intelligence Based Examination of the Field of Op...

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and computer engineering, UPCON 2023

作者： Bhargavi, V.Sesha Selvaraj, Krishnamoorthy Koti, Valli Madhavi Maheshwari, Rajeev Kumar Radhamahendran, S. Chandra, Sukumar G Narayanamma Institute of Technology & Science Department of Information Technology Shaikpet Hyderabad India Department of Erp Keller India Giet Degree College Department of Computer Science Andhra Pradesh Rajahmundry India R D Engineering College Computer Science&Engg. Dept. Ghaziabad India Department of Bioinformatics Chennai117 India Pingla Thana Mahavidyalaya Department of Physics West Bengal Medinipur India

ISBN: (纸本)9798350382471

Early and correct diagnosis is critical for optimal care and prevention of visual loss due to glaucoma, the leading cause of permanent blindness globally. New possibilities for better glaucoma identification and monitoring have emerged the progress that has been made in the field of AI and machine learning. Using a unique use of both SVM and CNN, or support vector machines and convolutional neural networks, to solve a problem., this study automates the examination of ophthalmological results relevant to glaucoma. In this paper, we introduce a hybrid SVM-CNN algorithm that draws from the most promising aspects of both existing these two approaches to machine learning. In order to lay a solid groundwork for further investigation, SVM is combined first- class classification and feature extraction. CNN is used to refine and improve classification accuracy since it is a potent deep learning architecture that can automatically learn complicated characteristics from raw data. The algorithm is educated on a large collection of ophthalmic pictures used in glaucoma diagnosis, such as fundus photos, examinations of the eye's visual acuity and OCT scans (optical coherence tomography). Noise is removed, contrast is increased, and the format is standardized in these preprocessed photos. The presence or absence of glaucoma is subsequently determined by feature extraction and classification using the SVM-CNN hybrid model. This study's findings support the use of the SVM-CNN hybrid algorithm for reliable detection of glaucoma-related pathology in ophthalmic pictures. The suggested AI-based methodology has various benefits over conventional manual diagnosis approaches, including increased efficiency, more consistency, and the possibility of earlier detection. It can also help ophthalmologists by offering automated preliminary assessments, so the specialists can devote their time and energy where it is most needed. This study concludes the promise of AI-based approaches, and in partic

关键词： Artificial Intelligence CNN (Convolutional Neural Networks) etc Glaucoma Ophthalmology SVM (Support Vector Machines)

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：