检索结果-内蒙古大学图书馆

Enhancing Skin Cancer Diagnosis with Deep Learning:A Hybrid CNN-RNN Approach

computers, Materials & Continua 2024年第4期79卷 1497-1519页

作者： Syeda Shamaila Zareen Guangmin Sun Mahwish Kundi Syed Furqan Qadri Salman Qadri Faculty of Information Technology Beijing University of TechnologyBeijing100124China Computer Science International Engineering Collage Maynooth UniversityKildareW23 F2H6Irland Research Center for Data Hub and Security Zhejiang LabHangzhou311121China Computer Science Department MNS University of AgricultureMultan59220Pakistan

Skin cancer diagnosis is difficult due to lesion presentation variability. Conventionalmethods struggle to manuallyextract features and capture lesions spatial and temporal variations. This study introduces a deep learning-basedConvolutional and Recurrent Neural Network (CNN-RNN) model with a ResNet-50 architecture which usedas the feature extractor to enhance skin cancer classification. Leveraging synergistic spatial feature extractionand temporal sequence learning, the model demonstrates robust performance on a dataset of 9000 skin lesionphotos from nine cancer types. Using pre-trained ResNet-50 for spatial data extraction and Long Short-TermMemory (LSTM) for temporal dependencies, the model achieves a high average recognition accuracy, surpassingprevious methods. The comprehensive evaluation, including accuracy, precision, recall, and F1-score, underscoresthe model’s competence in categorizing skin cancer types. This research contributes a sophisticated model andvaluable guidance for deep learning-based diagnostics, also this model excels in overcoming spatial and temporalcomplexities, offering a sophisticated solution for dermatological diagnostics research.

关键词： Skin cancer classification deep learning Convolutional Neural Network(CNN) RNN ResNet-50

来源：评论

学校读者我要写书评

暂无评论

data-Augmented Few-Shot Object Detection for Efficient Identification of Invasive Weed Seedlings 1

Data-Augmented Few-Shot Object Detection for Efficient Ident...

引用

1st IEEE International Conference on Advances in data-Driven Analytics and Intelligent Systems, ADACIS 2023

作者： Alli, Smaran Baidya, Sabur Carnegie Mellon University Department of Data Science PA United States University of Louisville Department of Computer Science and Engineering KY United States

ISBN: (纸本)9798350344158

Invasive weeds have continued to ravage crops across the world and with their population starkly rising, intelligent technologies need to be incorporated to mitigate the spread of these weeds. This research aims at employing Deep Learning models on invasive weed seedlings images in order to be able to detect them in images before they have grown. Due to the lack of images available on weed seedlings, more images were collected of weed seedlings, which were then combined with the limited available pre-existing images found in the Aarhus dataset. However, due to the dataset being still comparably small, a Few-Shot Object Detector (FSOD) is employed for better object detection performance. This FSOD was created through transfer learning with the universal COCO dataset. We also investigate data augmentation techniques by varying different attributes of images. We compare our proposed data-augmented FSOD with a 16-layer CNN-based object detector and also with the models without any augmentation. With experimental results, we show that the FSOD model achieves a higher mean Average Precision (mAP50) than the 16-layer CNN for both augmented (0.839 to 0.834) and non-augmented data (0.814 to 0.808). The FSOD detector also runs faster than the CNN model, and thus can be useful in real-time autonomous detection of the weed seedling and hence, in mitigating spreading of these invasive weeds. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Utilization of Machine Learning in Breast Cancer Detection 25

Utilization of Machine Learning in Breast Cancer Detection

引用

25th International Arab Conference on Information Technology, ACIT 2024

作者： Momani, Mutaz Yousef, Nidal Aljawazneh, Qotadeh Issa, A.T. Abuowaida, Suhaila Alazaidah, Raed Khouj, Mohammed Talat Batyha, Radwan Elsoud, Esraa Abu Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan Al-Albayt University Faculty of Information Technology Department of Computer Science Mafraq Jordan Zarqa University Department of Data Science and Ai Faculty of Information Technology Zarqa Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia Private University Faculty of It Applied Science Department of Computer Science Amman Jordan

ISBN: (纸本)9798331540012

Breast cancer is the most prevalent cancer among women and can be deadly, necessitating early detection to enhance patient outcomes and treatment effectiveness. Recently, Machine Learning (ML) techniques have shown potential in medical diagnostics, especially in breast cancer screening. ML algorithms examine extensive medical databases, including patient records, to identify subtle patterns and anomalies indicative of cancer. These algorithms excel at recognizing intricate patterns that may be missed by human analysis. Thereby, increasing the precision of breast cancer diagnoses. By evaluating and analyzing medical data, ML algorithms can detect minute anomalies, facilitating early identification of potential cancer cases. A significant advantage of ML-based breast cancer detection is its capacity for continuous learning and adaptation. In this study, we utilized 34 classifiers and five feature selection methods on three datasets. The first dataset comprises 286 instances with 10 integer-type features. The second dataset includes 699 instances with 10 integer-type features, and the third dataset consists of 286 instances with 13 integer-type features. For dataset 1, Filtered Classifier and J-48 yielded the best results, while the Bayesnet classifier performed best on dataset 2. In dataset 3, SimpleLogistic and LMT achieved the best outcomes. Regarding feature selection, the study showed that the GainRatioAttributeEval, InfoGainAttributeEval, and CorrelationAttributeEval techniques are the best among the feature selection methods tested in the study. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Image Caption Generation using CNN and Audio Conversion 2

Image Caption Generation using CNN and Audio Conversion

引用

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

作者： Priya, K. Babu, R.Vijay Reddy, M.Muralidhar Mohan Reddy, T.H. Maanesh, M. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Artificial Intelligence & Data Science Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science & Engineering Chennai India Arizona state university Department of Data Science Tempe United States

ISBN: (纸本)9798350368413

This research focuses on developing a system that can generate descriptive captions for images and convert them into audio output. The system employs a Convolutional Neural Network (CNN) to extract visual features from images, which are then fed into a Gated Recurrent Unit (GRU) to generate textual descriptions. The generated captions are subsequently converted into audio using text-to-speech techniques. By training the model on a large dataset of image-caption pairs, the system learns to associate visual information with textual descriptions, enabling accurate and coherent caption generation. This research contributes to the advancement of image understanding and generation, with potential applications in various fields such as image search, accessibility, and content creation. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Food-Health-Chain: A Food Supply Chain for Internet of Health Things Using Blockchain

Food-Health-Chain: A Food Supply Chain for Internet of Healt...

引用

International Conference on Network Security and Blockchain Technology, ICNSBT 2023

作者： Das, Puja Haldar, Amrita Singh, Moutushi Pise, Anil Audumbar Guha Roy, Deepsubhra Department of Computer Science HMM College for Women Dakshineswar Kolkata700035 India Department of Computer Science and Business Studies IEM Kolkata700091 India Department of Information Technology IEM Salt Lake Kolkata700091 India Department of Data Science and Machine Learning Computer Science University of the Witwatersrand Johannesburg South Africa Institute of Engineering and Management Kolkata700091 India

ISBN: (纸本)9789819944323

Foodborne disease is still a major public health concern in both advanced and emerging economies. In terms of adopting new technology, the health industry continues to lag behind all other sectors. India has traditionally relied on food farming to make money but which food item is good for whom we have no proper idea. Especially when it comes to healthcare sectors, the Internet of health things (IoHT) and blockchain can play an important role. It can enhance the quality of care for its users and reduce costs by allocating the correct food chain to the targeted users. We are currently employing blockchain in supply chain management to cluster the patients based on their health care type. For example, diabetic patients prefer a particular type of food. Segregating the food type within the supply chain can reduce a lot of effort and cost. Blockchain can provide a solution to the issues that arise in the healthcare-based supply chain system because of its decentralized and immutable nature. The service's execution has been depicted in pictures and accompanied by detailed descriptions. The ultimate result of this study was to demonstrate the immutability, availability, and transparency security of blockchain in the healthcare-based supply chain. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Probe Machine Based Computing Model for Maximum Clique Problem

引用

Chinese Journal of Electronics 2022年第2期31卷 304-312页

作者： CUI Jianzhong YIN Zhixiang TANG Zhen YANG Jing Department of Computer Huainan Union University School of Electronic and Information Engineering Anhui University of Science & Technology School of Mathematics Physics and Statistics Shanghai University of Engineering Science School of Mathematics and Big Data Anhui University of Science & Technology

Probe machine(PM) is a recently reported mathematic model with massive parallelism. Herein,we presented searching the maximum clique of an undirected graph with six vertices. We constructed data library containing n sublibraries, each sublibrary corresponded to a vertex in the given graph. Then, probe library according to the induced subgraph was designed in order to search and generate all maximal cliques. Subsequently,we performed probe operation, and all maximal cliques were generated in parallel. The advantages of the proposed model lie in two aspects. On one hand, solution to NP-complete problem is generated in just one step of probe operation rather than found in vast solution *** the other hand, the proposed model is highly *** work demonstrates that PM is superior to TM in terms of searching capacity when tackling NP-complete problem.

关键词： maximal cliques maximum clique problem searching capacity data library NP-complete problem computational complexity model lie induced subgraph probe operation undirected graph mathematic model graph theory parallel algorithms optimisation parallelism computing model vertex probe library probe machine

来源：评论

学校读者我要写书评

暂无评论

The Impact of 5G Technology on the Functionality and Performance of Internet of Things (IoT) Devices 8

The Impact of 5G Technology on the Functionality and Perform...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Yesankar, Prajyot Gourshettiwar, Palash Gote, Pradnyawant Jiet, Moses Makuei Gadkari, Ayush Faculty of Engineering and Technology Department of Computer Science & Design Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Computer Science & Medical Engineering Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence & Data Science Maharashtra Wardha442001 India

ISBN: (纸本)9798350376425

The design of wireless mobile devices of the next generation 5G promises to address the demands of complex IOT designs in terms of connectivity technologies. This The study illuminates the architecture, benefits, and needs that5G can satisfy. drawbacks of the 5G network. Numerous sites throughout the world have conducted extensive analyses of IOT devices with 5G capabilities and research on this kind of network. A new era of communication has begun with the introduction of 5G technology, which promises unheard of velocity, low latency, and enormous capacity. The significant effects of 5G on the operation and efficiency of connected Internet of Things (IoT) gadgets are examined in this research. IoT devices stand to gain from improved communication capabilities as 5G networks proliferate, opening the door for creative applications in a variety of industries. The first section of the article gives a summary of the main characteristics of 5G technology, highlighting how it has the potential to completely change how Internet of Things devices interact and communicate. Real-time data transfer is made possible by 5G networks far lower latency and higher capacity, which open up possibilities for faster and smooth interactions between IoT *** report also explores how 5G may affect how much electricity Internet of Things devices use. 5G has the ability to solve a long-standing issue in the IoT ecosystem by extending the life of the batteries of IoT devices with the adoption of cost-effective communication protocols and increased network efficiency. A solution that can efficiently handle enormous volumes of information being transferred at very high capacity is required as the Internet of Things gains popularity One of the main demands or goals that need to be reached in the near future, or the next generation of IOT devices, is more capacity, a faster data transfer speed and less delay. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

An optimal hybrid cascade regional convolutional network for cyberattack detection

An optimal hybrid cascade regional convolutional network for...

引用

作者： Alqahtani, Ali Khan, Surbhi Bhatia Department of Networks and Communications Engineering College of Computer Science and Information Systems Najran University Najran Saudi Arabia Department of Data Science School of Science Engineering and Environment University of Salford Salford United Kingdom Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

Cyber-physical systems (CPS) and the Internet of Things (IoT) technologies link urban systems through networks and improve the delivery of quality services to residents. To enhance municipality services, information and communication technologies (ICTs) are integrated with urban systems. However, the large number of sensors in a smart city generates a significant amount of delicate data, like medical records, credit card numerics, and location coordinates, which are transported across a network to data centers for analysis and processing. This makes smart cities vulnerable to cyberattacks because of the resource constraints of their technology infrastructure. Applications for smart cities pose many security challenges, such as zero-day attacks resulting from exploiting weaknesses in various protocols. Therefore, this paper proposes an optimal hybrid transit search-cascade regional convolutional neural network (hybrid TS-Cascade R-CNN) to detect cyberattacks. The proposed model combines the hybrid transit-search approach with the cascade regional convolutional neural network to create an optimal solution for cyberattack detection. The cascade regional convolutional network uses a hybrid transit search algorithm to enhance the effectiveness of cyberattack detection. By integrating these two approaches, the system can leverage both global traffic patterns and local indicators to improve the accuracy of attack detection. During the training process, the proposed model recognizes and classifies malicious input even in the presence of sophisticated attacks. Finally, the experimental analysis is carried out for various attacks based on different metrics. The accuracy rate attained by the proposed approach is 99.2%, which is acceptable according to standards. © 2023 John Wiley & Sons Ltd.

关键词： Zero-day attack

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal LLM Driven computer Interface 8

Multi-Modal LLM Driven Computer Interface

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Sowmiya, R. Revathi, P. Ragunath, D. Sindhuja, S. Gokila, P. Kalaivani, T. Sns College of Engineering Department of Artificial Intelligence and Data Science Tamilnadu Coimbatore India Bannari Amman Institute of Technology Department of Computer Science and Engineering Tamilnadu Sathyamangalam India Tamilnadu Coimbatore India Info Institute of Engineering Department of Computer Science and Engineering Tamilnadu Coimbatore India

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376425

This study presents a framework for multimodal models to control and interact with computers: The Multimodal-driven computer Interface. A decision-making module is used by the framework to determine what actions are acceptable after it processes user input through a variety of modalities, such as speech, text, and gestures, and runs it through a multimodal fusion algorithm. Platform-specific APIs are then used to carry out these operations on the computer. It runs on Linux, Mac, and Windows platforms and is currently integrated with the multimodal LLM. Although the framework shows promising results, there are still issues with adjusting to different user demands and preferences and increasing the accuracy of mouse click position prediction. Potentially revolutionizing human-computer interaction, the Multimodal-driven computer Interface offers new avenues for accessibility, productivity, and pleasure. © 2024 IEEE.

关键词： Windows operating system

来源：评论

学校读者我要写书评

暂无评论

AI for Smart Agriculture - A Deep Learning Based Turmeric Leaf Disease Detection 9

AI for Smart Agriculture - A Deep Learning Based Turmeric Le...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Selvaraj, R. Devasena, M. S. Geetha Satheesh, T. Sathishkumar, C. Dr.N.G.P. Institute of Technology Department of Computer Science and Engineering Coimbatore India Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India Dr.N.G.P. Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Department of Computer Science and Engineering RVS Technical Campus-Coimbatore Coimbatore India

ISBN: (纸本)9798350377972

Plants is one of the major food sources for world population. In addition to that, some plants and their outcomes are used in food preparation. One of the plants which is widely used in foods and having huge medicinal value is turmeric. Curcuma long the botanically named spice turmeric has large anti-inflammatory properties, antioxidants, etc., the tropical perennial plant is cultivated worldwide. Diseases in plant leaves is one of the serious factors that affects the turmeric cultivation. Leaf disease reduces the production and it requires continuous monitoring to avoid total loss. Manual monitoring is challenging when the crop is planted in large fields. Due to industrial revolution and smart agriculture concepts, artificial intelligence- based disease detection procedure is presented in recent times. Thus, in this research work a deep learning-based turmeric leaf disease detection model is presented using AlexNet. The leaf disease classification model is experimented with our own dataset which includes diseases like Leaf Spot Disease, Leaf Blight, Leaf Rot, and Leaf Curl. The experimentation results provide the maximum accuracy of proposed leaf disease classification model as 95.5% which is better than traditional machine learning models. © 2024 IEEE.

关键词： AlexNet classification Deep learning Turmeric Leaf disease

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：