检索结果-内蒙古大学图书馆

Skin Cancer Detection and Classification using Deep Learning Techniques

Procedia computer Science 2024年 235卷 2793-2802页

作者： C. Kavitha S. Priyanka M. Praveen Kumar V. Kusuma Electronics and Communication Engineering Sreenivasa Institute of Technology and Management Studies Chittoor 517127 India School of Electronics Engineering VIT -AP University Amaravati Vijayawada-522237 India ACG Worldwide Mumbai India Computer Engineering University of North Carolina Charlotte

In recent years, one of the deadliest malignancies is skin cancer. If it is not detected and treated in a timely manner, it is expected to spread to other body parts. An accurate automated system for skin lesion recognition is essential for early detection to save human lives. Although there are many other forms of skin cancer, basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and melanoma are the three most prevalent. With early identification and appropriate treatment, these three kinds of skin cancer can be successfully treated by using deep learning techniques. One of the main benefits of using deep learning for skin cancer detection is its ability to accurately classify images with subtle differences. In this paper, Image pre-processing is employed at an initial diagnosis for removing the artifacts present in the raw dataset and further Convolutional Neural Network (CNN) is employed to improve classification and detection of skin cancer with improved accuracy. For analyzing enormous volumes of data, R-CNN algorithms are proved to be incredibly effective in terms of accuracy of 84.32%. Due to its precision, effectiveness, objectivity, and accessibility, R-CNN algorithm have proven to be very helpful in the identification and categorization of skin cancer.

关键词： Deep Learning Image Processing CNN Transfer Learning ResNet50

来源：评论

学校读者我要写书评

暂无评论

Insights into Ocular Disease Recognition: A Machine Learning Approach

Insights into Ocular Disease Recognition: A Machine Learning...

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： Sosmita Paul Geet Bhatt Aditya Dey BE in Electronics and Communication Engineering Sarvajanik College of Engineering and Technology Surat Gujarat India BE in Computer Engineering L D College of Engineering Ahmedabad Gujarat India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

This study reviews the potential benefits of machine learning techniques in diagnosing ocular disorders, aiming to address the limitations of traditional diagnostic methods. Various Machine Learning (ML) algorithms, including Support Vector Machine, Decision Tree, K-Nearest Neighbor, Random Forest, Naïve Bayes, and Extra Trees, are compared to determine the effectiveness of each algorithm in identifying eye diseases. Through analysis and testing, the study concludes that Extra Trees (ET) has achieved the highest accuracy rate of 97%. This finding suggests that ET could be the most suitable option for enhancing the accuracy and efficiency of eye disease detection systems. Overall, these research discoveries contribute to the ongoing efforts to improve diagnostic tools for ocular health, highlighting the potential of Machine Learning (ML) in transforming healthcare.

关键词： Support vector machines Accuracy Machine learning algorithms Reviews Eye diseases Robustness Bayes methods

来源：评论

学校读者我要写书评

暂无评论

A Multicriteria Aware Multipath Routing Method to Increase the QoS for Future 6G Networks

A Multicriteria Aware Multipath Routing Method to Increase t...

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Valmik Tilwari Debashree Sharma Sourabh Solanki Nilotpal Chakraborty MWP Maduranga Department of Electronics & Communication Engineering Indian Institute of Information Technology Guwahati India Department of Electronics & Communication Engineering National Institute of Technology Warangal India Department of Computer Science Engineering Indian Institute of Information Technology Guwahati India Department of Computer Engineering General Sir Jhon Kotelawala Defence University Colombo Sri Lanka

ISBN: (数字)9798350305463

ISBN: (纸本)9798350305470

The optimal solution of creating a communications network in isolated places is still a challenging task. Establishing end-to-end connectivity via mobile ad-hoc networks (MANETs) is a better solution for the above issue. However, the limitation of the mobility of nodes and battery resources between the overlay and mobile ad-hoc network protocols is still a challenge for trustable wireless connections. Therefore, this paper presented a routing scheme named Mobility and Energy consumption aware multipath routing (MEMR) in mobile ad-hoc networks. The proposed routing scheme provides reliable communication with stable route and high lifetime routes to support efficient data transmission in the network. For this purpose, it uses a multicriteria decision-making approach to select the intermediate nodes with the highest energy and lowest mobility for selecting the optimal route. The obtained results indicate that the proposed routing method can significantly improve the overall network performance and deliver packets with acceptable throughput. At the same time, it reduces the energy consumption of the nodes compared with the conventional MP-OLSRv2 routing protocol.

关键词： Energy consumption Wireless networks Simulation Spread spectrum communication Routing Throughput Ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Low Power, High Speed Current Starved Ring Oscillator based ADC using 18nm FinFET technology

Low Power, High Speed Current Starved Ring Oscillator based ...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Gokul Chandrasekaran P Pavithara P M Dinesh V Arun Kumar J S Sharanyanivasini K Kavin Kumar Department of Electronics and Communication Engineering Karpagam Institute of Technology Coimbatore Department of Electronics and Communication Engineering Kongu Engineering College Perundurai Erode Department of Electronics and Communication Engineering Sona College of Technology Salem Department of Electrical and Electronics Engineering Nandha Engineering College Erode India Department of Computer Science and Engineering Erode Sengunthar Engineering College Perundurai Thuduppathi

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The goal of achieving high performance, low power consumption, and small area footprint is still central to the field of analog-to-digital converters (ADCs). This work describes a new methodology that enables the design of Current Starved Ring Oscillator (CSRO) architecture using 18nm FinFET technology. The CSRO based ADC meets the growing needs of contemporary electronic systems with promised improvements in speed, power efficiency, and portability. The intrinsic qualities of FinFET transistors are utilized by the CSRO architecture to produce high performance metrics such as improved sub threshold behavior, lower leakage currents, and superior gate control, all of which are essential for low power consumption and high speed operation. In addition, compared to conventional ADC designs, the 18 nm production node enables tighter component integration, resulting in a compact ADC design. The precise analog-to- digital conversion is made possible by controlling the oscillation frequency through the use of current starving techniques. In order to reduce power consumption, mitigate electromagnetic interference and extend the battery life, starving ring oscillators are employed. The ability of the GDI (Gate Diffusion Input) technique to lower space overhead and power consumption provides an effective solution for low-power and high-density applications in contemporary integrated circuits. The proposed CSRO based ADC with GDI technique experiences a delay of 1.208 ns and power consumption of 356.08 mW while the ADC without GDI technique involves a delay of 1.44 ns and 391 mW of power consumption. This shows that the proposed ADC exhibits 14% improvement inspeed and 9% improvement in power compared to the ADCwithout GDI technique.

关键词： Ring oscillators Performance evaluation Power demand Production Logic gates Signal processing FinFETs Delays Transistors Propagation delay

来源：评论

学校读者我要写书评

暂无评论

Personal Safety and Health Monitoring System for Emergency Assistance using IOT

Personal Safety and Health Monitoring System for Emergency A...

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： K B Poovanna Arjun Rai Sritama Roy Department of Computer Science Vellore Institute of Technology Chennai India School of Electronics Engineering Vellore Institute of Technology Chennai India

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

Internet of Things (IoT) has the potential to transform how we live and work. One of the most promising applications of IoT is in the area of emergency response. In this research work, we have presented a smart medical application through IoT environment that combines a pulse rate sensor, a geographic sensor, and an SMS sender using SIM800L and Arduino microcontroller. The work has designed to help people in distress by sending their location and pulse rate to the police or a concerned person. The work has the potential to be used to help people in a variety of situations, such as when they are lost, injured, or being attacked. It is significant because it demonstrates the potential of IoT to be used to improve emergency responses. It also highlights the importance of using open source hardware and software in IoT domain.

关键词： GSM Microcontrollers Law enforcement Transforms Medical services Emergency services Software

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Solving Challenges in computer Vision Applications and Exploring Evolving Patterns 7

Deep Learning Approaches for Solving Challenges in Computer ...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Gejji, Sujay Supreeth, B.R. Khan, Pathan Firoze Venkat, S. Pradeepa, K. Kaliappan, S. S. G. Balekundri Institute of Technology Department of Electronics & Communication Engineering Karnataka Belagavi India Oxford Degree and Pg College Department of Computer Science Sir. M. Visveshwaraiah Layout Bangalore India Madanapalle institute of Technology & Science Department of Computer Science & Technology Andhra Pradesh Madanapalle India S. A. Engineering College Department of Electronics and communication Engineering Tamil Nadu Chennai India Kpr College of Arts Science and Research Department of Artificial Intelligence and Data Science Tamil Nadu Coimbatore India Lovely Professional University Division of Research and Development Punjab Phagwara India

ISBN: (纸本)9798350350067

Deep learning has brought substantial advancements to computer vision in recent years by providing answers to challenging visual interpretation problems. It investigates several DL methodologies, such as self-supervised learning strategies, hybrid CNN-RNN models, enhanced CNNs, generative adversarial networks (GANs), and vision transformers (ViTs). Novel CNN architectures are designed, GANs are used for image synthesis, hybrid models are used to integrate spatial and temporal information, self-attention is used in ViTs, and self-supervised learning is used for feature extraction. The results of the study show significant improvements: the accuracy of Enhanced CNNs was 81.6%, the accuracy of GANs was 14.8%, the accuracy of Hybrid CNN-RNN models was 86.2%, the accuracy of ViTs was 79.2%, and the accuracy of transfer for self-supervised learning techniques was 76.8%. These findings demonstrate the improved effectiveness and performance of the suggested techniques, highlighting their potential to resolve challenging problems in feature extraction, video analysis, object recognition, picture enhancement, and image classification. It concludes that advances in computer vision will be facilitated by the ongoing development of DL methods. These advancements will lead to more precise and adaptable applications in a range of fields, including autonomous driving, medical imaging, surveillance, and augmented reality. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Investigating Low & High Transfers Training for Multi-task Face Identification Using a Semi-supervised Neuronal Networks 3

Investigating Low & High Transfers Training for Multi-task F...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Kavadi, Durga Prasad Hasan, Asif Tanna, Rajesh Singh, Rajesh Lande, Jayapal Tiwari, Mohit Department of Cse Hyderabad India Aligarh Muslim University Department of Psychology Aligarh India Vignan's Institute of Information Technology Department of Electrical and Electronics Engineering Duvvada India Uttaranchal University Uttaranchal Institute of Technology India Sr University School of Computer Science and Artificial Intelligence Telangana Warangal India Bharati Vidyapeeth's College of Engineering Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350399264

Recently years have seen a significant increase in research on visual identification issues including identification, aging, sexuality, & expression identification. This same classification of the majority of non-verbal Living beings Interactions scenarios became dependent on their implementation in robotics systems. Deep convolutional neuronal systems have demonstrated to be efficient in this respect when analyzing various face expressions, but at a heavy price: they need a sizable quantity of task-specific labelled information to attain maximal generalisation. A uniform semi-supervised deep network system is suggested in this research to deal with this issue. Our combination model consists of a set of permutation networks that fine-tunes the high-level faces notions for the identification of individuality, time of life team, sex, & facial expressions, as well as an unsupervised deep generative confrontational connection that gets to know basic character traits of face *** the way you look. To avoid the need for a significant quantity of highly labelled learning information, our system uses continuous laterally interconnections among the convolutional streams so that it can exchange the high-abstraction specifics of all of such jobs. We suggest a number of tests to assess each component of our hybrids system, particularly the influence of the progressing interconnections on acquiring the individual image identification problems, & we find that our framework outperforms task-specific systems. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Impact of PHEV operating conditions and demand side management on the economic operation of a community microgrid system 33

Impact of PHEV operating conditions and demand side manageme...

引用

33rd Southern African Universities Power engineering Conference, SAUPEC 2025

作者： Dey, Bishwajit Fose, Nande Krishnamurthy, Senthil Ratshitanga, Mukovhe Moodley, Prathaban Cape Peninsula University of Technology Centre for Intelligent Systems and Emerging Technologies Department of Electrical Electronics and Computer Engineering P.O. BOX 1906 Bellville7535 South Africa Upper Grayston Office Park Sandton2146 South Africa

ISBN: (纸本)9798331535162

By classifying loads into shiftable and non-shiftable groups and rearranging a distribution system's load demand model, demand-side management (DSM) reduces operating expenses. This is possible by shifting variable loads when utility costs per unit are lower. This work adopts a bi-level optimization technique to minimize the operational costs of a low-voltage microgrid (MG) system that incorporates plug-in hybrid electric vehicles (PHEVs), renewable energy sources, and fossil fuel generators while operating in grid-connected mode. According to the DSM participation level, the load model is reconfigured at the first optimization stage. Then, the restructured load demand models are considered, and recommendations for distributed generator scheduling are developed to reduce the production costs of the second-level microgrid system. The study's optimization technique used the popular differential evolution (DE) method applied to several power system optimization issues. When DSM, various grid participation and pricing schemes, and other factors were considered, the cost of producing active power was reduced. To ascertain their effect on the MG system's generation cost, scenarios involving different PHEV state of charge (SoC) levels and a taxable rate during V2G were also investigated. © 2025 IEEE.

关键词： Demand side management

来源：评论

学校读者我要写书评

暂无评论

Advancing Chronic Kidney Disease Detection: Improving Biomarkers and CT Imaging for Enhanced Detection 2

Advancing Chronic Kidney Disease Detection: Improving Biomar...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication Systems, ICIICS 2024

作者： Dhaka, Aanya Singh Rani, Ritu Jaiswal, Garima Sharma, Arun Dev, Amita Department of Information Technology Indira Gandhi Delhi Technical University for Women Kashmere Gate India Department of Electronics and Communication Engineering Bhagwan Parshuram Institute of Technology Rohini India Department of Computer Science Engineering Bennett University Noida India Centre of Excellence-Artificial Intelligence Indira Gandhi Delhi Technical University for Women Kashmere Gate India

ISBN: (纸本)9798331504960

Chronic Kidney Disease (CKD) is one of the biggest health concerns globally, affecting millions. This research aims to enhance the early detection and diagnosis of CKD by utilizing advanced machine-learning models for two different types of data: biomarkers and CT scan images. Each model has been trained and then individually validated. The Random Forest model has given the best average accuracy of 99.4% using different cross-validation methods while the CNN model has reached a validation accuracy of 99.41%, showing minimum overfitting in each. Thus, both of these models can offer a high level of improvement in accuracy in the detection of CKD if applied separately. Future studies are needed to identify how these models can be incorporated into clinical practice for the betterment of early diagnosis and enhanced patient outcomes. © 2024 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing healthcare: A review on cutting-edge innovations in Raspberry Pi-powered health monitoring sensors

引用

computers in Biology and Medicine 2025年 190卷 110109-110109页

作者： Baraneedharan, P. Kalaivani, S. Vaishnavi, S. Somasundaram, K. Department of Electronics and Communication Engineering Saveetha Engineering College Thandalam Tamilnadu Chennai602105 India Department of Computer Science and Engineering Chennai Institute of Technology Tamilnadu Chennai600 069 India

The integration of Raspberry Pi technology into health care is a significant advancement that has the potential to revolutionise the delivery of healthcare. This study highlights the inventive uses of Raspberry Pi devices, emphasizing their economical nature, mobility, and capacity to be customised for unique healthcare requirements. Healthcare practitioners may utilize the computational capabilities of Raspberry Pi to create portable monitoring devices that can gather, analyze, and send patient data in real-time. An important benefit of Raspberry Pi-based systems is their capability to facilitate remote patient monitoring, which allows for early diagnosis of diseases and personalized healthcare interventions. This capacity shows potential for people in situations with low resources, when typical monitoring methods may not be available or feasible. Moreover, the capacity of Raspberry Pi technology to easily adjust and be used by a wide range of people makes it a powerful tool for tackling many healthcare concerns. The article promotes the need for ongoing study and advancement in health monitoring systems that utilize Raspberry Pi technology. It emphasizes the need of collaboration among technology enthusiasts, healthcare practitioners, and researchers. By cultivating these collaborations, progress in healthcare solutions based on Raspberry Pi may be expedited, resulting in enhanced patient results and more efficient healthcare provision. The Raspberry Pi technology has the capacity to bring about significant changes in healthcare by effectively meeting the changing needs of current healthcare systems. Healthcare practitioners may optimize patient care, facilitate early intervention, and ultimately boost global health outcomes by utilizing the capabilities of Raspberry Pi devices. © 2025

关键词： Electronic health record

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：