检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ganeriwala, Parth Bhattacharyya, Siddhartha Gunther, Sean Kish, Brian Khan, Mohammed Abdul Hafeez Dhadoti, Ankur Neogi, Natasha Dept. of Computer Science Florida Institute of Technology MelbourneFL United States Dept. of Aerospace Engineering Florida Institute of Technology MelbourneFL United States Dept. of Mechanical Engineering Univeristy of Michigan Ann ArborMI United States Dept. of Computer Science BITS Pilani Dubai Campus Dubai United Arab Emirates Langley Research Center NASA HamptonVA United States

The availability of high-quality datasets play a crucial role in advancing research and development especially, for safety critical and autonomous systems. In this paper, we present AssistTaxi, a comprehensive novel dataset which is a collection of images for runway and taxiway analysis. The dataset comprises of more than 300,000 frames of diverse and carefully collected data, gathered from Melbourne (MLB) and Grant-Valkaria (X59) general aviation airports. The importance of AssistTaxi lies in its potential to advance autonomous operations, enabling researchers and developers to train and evaluate algorithms for efficient and safe taxiing. Researchers can utilize AssistTaxi to benchmark their algorithms, assess performance, and explore novel approaches for runway and taxiway analysis. Additionally, the dataset serves as a valuable resource for validating and enhancing existing algorithms, facilitating innovation in autonomous operations for aviation. We also propose an initial approach to label the dataset using a contour based detection and line extraction technique. © 2024, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure and Efficient Key Management for Deduplicated Cloud Storage Systems

Secure and Efficient Key Management for Deduplicated Cloud S...

引用

Security of Information and Networks (SIN), International Conference on

作者： Jay Dave Anshul Kanodia Raj Srivastava Kushagra Singh Prithvi Hegde Hitaishi Desai Dept. of Computer Science & Information Systems Birla Institute of Technology & Science Pilani Hyderabad India

Deduplication is a ubiquitous compression technique for cloud storage servers. It reduces storage and bandwidth requirements by avoiding duplicate copies of data. However, developing an encryption scheme for deduplication is a critical challenge because traditional encryption techniques are not compatible with deduplication. The existing state-of-the-art encryption schemes are at risk of brute-force attacks as they use deterministic techniques for key generation. Moreover, the user in the recent schemes suffers from storage overhead of deduplication metadata and encryption keys. In this paper, we introduce a secure and efficient key management scheme for deduplication. In our scheme, the user divides the file into blocks and encrypts each block using a random key. As a result, our scheme protects against brute-force attacks. In addition, the user securely shares the encryption keys on public storage servers with the aid of a private server. As a result, the proposed approach causes lower storage overhead. We implement our scheme in a real cloud scenario and evaluate the performance of our approach in terms of storage and computation overhead.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Food Detection and Nutritional Tracking Application for Personalized Health Management Using MobileNetV2

Real-Time Food Detection and Nutritional Tracking Applicatio...

引用

International Conference on Computation System and Information technology for Sustainable Solutions (CSITSS)

作者： Divyabhavani Ganpisetty Chetana R Reddy Navyashree Ganpisetty Anitha J Dept of Computer Science and Engineering RV Institute of Technology and Management Bengaluru India Dept of Electronics and Communication Engineering RV Institute of Technology and Management Bengaluru India

ISBN: (数字)9798331505462

ISBN: (纸本)9798331505479

Accurate and timely dietary assessment is essential for health management. This study presents a deep learning-based approach for real-time, personalized food analysis through image analysis. The preparation processaccurately predicts the content of food products based on images captured by a smartphone camera. The model is trained on a comprehensive database of food images along with their corresponding menu items. To enhance user experience and engagement, the system integrates a mobile application that allows users to easily record their meals by taking photos. Test resultsshow the system's effectiveness in accurately estimating macronutrients and calories, providing users with a better understanding of making dietary decisions. This research contributes to the development of smart health devices and has the potential to impact public health through health promotion.

关键词： Image analysis Databases Smart healthcare Cameras Real-time systems User experience Mobile applications Food products Public healthcare Information technology

来源：评论

学校读者我要写书评

暂无评论

The Integration of Traditional Rural Solar Dryer with LoRa and IoT technology 8

The Integration of Traditional Rural Solar Dryer with LoRa a...

引用

Joint 8th International Conference on Digital Arts, Media and technology and 6th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2023

作者： Yooyativong, Thongchai Kamyod, Chayapol Kim, Chong Ghil School of Information Technology Mae Fah Luang University Chiang Rai Thailand School of Information Technology Mae Fah Luang University Excellence Center of Industry 4.0 Computer and Communication Engineering for Capacity Building Research Center Chiang Rai Thailand Namseoul University Dept. of Computer Science Choongnam Korea Republic of

ISBN: (纸本)9798350396546

Traditional or rural dryers or Thai farmers' dryers have some drawbacks when compared to modern or commercial dryers on the market. Despite the fact that the dryer is vital and may be utilized as postharvest technology to preserve or produce some agricultural products, the farmer chose to build the traditional structure because of his limited income and resources. This research examined the needs of rural farmers and developed an integration of typical rural solar dryers or dryers using IoT technologies. The integrated design will preserve the structure's materials while increasing the system's capacity and efficiency to reduce costs. Farmers may now manage the temperature inside the dryer using the newly created mechanism. Remote monitoring and management are also made possible by the technology, minimizing the need for physical intervention. This leads to increased efficiency, lower costs, and a more sustainable energy source. © 2023 IEEE.

关键词： Agricultural products

来源：评论

学校读者我要写书评

暂无评论

FReNG: Federated Optimization by Using Regularized Natural Gradient Descent

FReNG: Federated Optimization by Using Regularized Natural G...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Mrinmay Sen C Gayatri Dept. of Artificial Intelligence Indian Institute of Technology Hyderabad Hyderabad India Dept. of Computer Science and Engineering Mahindra University Hyderabad India

Federated learning (FL) is an important area in machine learning that addresses the challenges of distributed data by collaboratively training a global model. One major issue with FL is the increased communication rounds or FL iterations between the server and the participating data sources or clients, which is caused by the presence of heterogeneous data across all the clients. To address this issue, this paper introduces FReNG, which utilizes regularized natural gradient descent with exponential moving average of the global gradient on the server. The server-based utilization of regularized natural gradient descent and exponential moving average of the global gradient leads to faster convergence of the global model in heterogeneous settings without additional local space and computational complexities, resulting in comparatively fewer communication rounds, while achieving the targeted accuracy from the global model. As FReNG uses regularized natural gradient descent, it can directly compute the update step without calculating and storing the full Fisher information matrix (FIM), which is one of the key advantage of FReNG. Extensive experimental results on image classification tasks using various heterogeneously partitioned datasets show that FReNG outperforms existing state-of-the-art FL algorithms such as FedProx, SCAFFOLD & FedInit and can compete with other state-of-the-art FL algorithms, FedGA, & DONE (with less per FL iteration communication cost & less local time complexity) in terms of reduced communication rounds, while achieving a certain precision of convergence and a targeted test accuracy from the global model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Characteristic Mode Analysis of Wideband Patch Antenna Using Dual-Mode Resonance

Characteristic Mode Analysis of Wideband Patch Antenna Using...

引用

Global Conference for Advancement in technology (GCAT)

作者： Vinaya Kumar S R Venkatesh T Puneeth Kumar Tharehalli Rajanna Dept. of Electrical and Electronics Engineering Ghousia College of Engineering Ramanagara Karnataka India Dept. of Computer Science Engineering Ghousia College of Engineering Ramanagara Karnataka India Dept. of Electronics and Telecommunication Engg Siddaganga Institute of Technology Tumkur Karnataka India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

This paper presents the characteristic mode analysis(CMA) of wideband patch antenna using dual-mode resonances. CMA is used to analyze the fundamental resonance modes of square patch antenna. It has two fundamental modes of TM01 and TM10 modes. The patch is excited using aperture coupling to excite both horizontal and vertical mode. The slot aperture length and width is optimized for better coupling. The vertical mode resonance frequency is slightly reduced by introducing the slot. These two modes combined together gives the wide bandwidth. An impedance bandwidth of 47.12%(1.93GHz-3.12GHz) is obtained. The antenna is well radiated with both modes being radiation efficiency of above 90%. The realized peak gain of 5.72dBi and 4.62dBi is obtained at 2.12GHz and 2.83GHz and good radiation pattern in the broadside direction. The cross polarization level of more than -10dB is achieved with respect to co-polarization level at resonance frequency of 2.12GHz and 2.83GHz respectively and it is suitable for WiFi and Bluetooth applications.

关键词： Couplings Surface impedance Bluetooth Patch antennas Resonant frequency Apertures Characteristic mode analysis Impedance Wideband Wireless fidelity

来源：评论

学校读者我要写书评

暂无评论

Mining sequential patterns from protein sequences associated with aggregation diseases

Mining sequential patterns from protein sequences associated...

引用

Applied Intelligence and Computing (AIC), IEEE World Conference on

作者： Anup Bhat B Tanish Sunilkumar Ayush Prabhu Dept. of Computer Science & Engg. Manipal Institute of Technology Manipal Academy of Higher Education Manipal India

ISBN: (数字)9798350384598

ISBN: (纸本)9798350384604

Protein aggregation is a hallmark of several neurodegenerative diseases. Mining patterns of amino acids from protein sequences aid in identifying regions of interest that can be validated clinically. Only a few studies have demonstrated the feasibility of employing Frequent Itemset Mining (FIM) algorithms for this task. However, these algorithms are not only computationally expensive but do not provide due consideration to the ordering of amino acids within a protein sequence. Apart from this, the number of patterns obtained remains sensitive to the input minimum support threshold. To overcome these limitations, the current study focuses on mining sequential patterns using the Top-k Sequential pattern mining algorithm that not only preserves the amino acid sequence but is also independent of any user input threshold. Across various protein sequences, the obtained sequential patterns were compared for similarity with frequent patterns by retaining as well as removing repeating amino acids. On average, about 89.31% non-repeating and 68.08% repeating sequential patterns were similar to the frequent patterns. Furthermore, a Jaccard Index close to 0.58 and 0.48 signifies the proximity of the sequential patterns with the frequent ones despite the absence of user-defined thresholds.

关键词： Itemsets Pathogenesis Amino acids Prediction algorithms Protein sequence Indexes Diseases

来源：评论

学校读者我要写书评

暂无评论

AttRes-UNet: A Dual-Model Approach for Brain Tumor Segmentation

AttRes-UNet: A Dual-Model Approach for Brain Tumor Segmentat...

引用

Advancement in Electronics & Communication engineering (AECE), International Conference on

作者： Samruddhi Maheshkumar Kolekar Agnesh Chandra Yadav Suchita Yadav Daba Prasad Dash Dept. Electrical Engineering Thaper Institue of Engineering and Technology Patiala India Dept. Electrical Engineering India Instite of Technology Patna Patna India Dept. of Computer Science and Engineering Bennett University Gr. Noida India

ISBN: (数字)9798350364729

ISBN: (纸本)9798350364736

Accurate segmentation of brain tumors in MRI images is crucial for diagnosis, treatment planning, and disease monitoring. Traditional manual segmentation methods are time- consuming and prone to variability, while standard deep learning architectures such as U-Net face challenges in capturing the complex, heterogeneous structures of brain tumors. In this study, we proposed AttRes-UNet, a novel dual-model architecture combining Attention U-Net and Residual U-Net to enhance segmentation accuracy. Attention Gates allow the model to focus on critical tumor regions, while Residual Blocks improve deep feature learning, enabling the model to handle diverse tumor morphologies with greater precision. We evaluated the model using the BraTS 2021 dataset, achieving high performance with an accuracy of 0.996, a dice coefficient of 0.8340, and an Intersection over Union of 0.8210. These results demonstrate the effectiveness of AttRes-UNet in improving segmentation accuracy, making it a valuable tool for automated brain tumor delineation, ultimately reducing manual workload and improving clinical outcomes.

关键词： Representation learning Image segmentation Accuracy Three-dimensional displays Magnetic resonance imaging Brain tumors Morphology Manuals Logic gates Brain modeling

来源：评论

学校读者我要写书评

暂无评论

The applications of nature-inspired algorithms in Internet of Things-based healthcare service: A systematic literature review

引用

Transactions on Emerging Telecommunications Technologies 2024年第6期35卷

作者： Amiri, Zahra Heidari, Arash Zavvar, Mohammad Navimipour, Nima Jafari Esmaeilpour, Mansour Department of Computer Engineering Tabriz Branch Islamic Azad University Tabriz Iran Department of Computer Engineering Faculty of Engineering and Natural Science İstanbul Atlas University Istanbul Turkey Department of Computer Engineering Sari Branch Islamic Azad University Sari Iran Department of Computer Engineering Kadir Has Universitesi Istanbul Turkey Future Technology Research Center National Yunlin University of Science and Technology Douliou Taiwan Computer Engineering Dept. Hamedan Branch Islamic Azad University Hamedan Iran

Nature-inspired algorithms revolve around the intersection of nature-inspired algorithms and the IoT within the healthcare domain. This domain addresses the emerging trends and potential synergies between nature-inspired computational approaches and IoT technologies for advancing healthcare services. Our research aims to fill gaps in addressing algorithmic integration challenges, real-world implementation issues, and the efficacy of nature-inspired algorithms in IoT-based healthcare. We provide insights into the practical aspects and limitations of such applications through a systematic literature review. Specifically, we address the need for a comprehensive understanding of the applications of nature-inspired algorithms in IoT-based healthcare, identifying gaps such as the lack of standardized evaluation metrics and studies on integration challenges and security considerations. By bridging these gaps, our paper offers insights and directions for future research in this domain, exploring the diverse landscape of nature-inspired algorithms in healthcare. Our chosen methodology is a Systematic Literature Review (SLR) to investigate related papers rigorously. Categorizing these algorithms into groups such as genetic algorithms, particle swarm optimization, cuckoo algorithms, ant colony optimization, other approaches, and hybrid methods, we employ meticulous classification based on critical criteria. MATLAB emerges as the predominant programming language, constituting 37.9% of cases, showcasing a prevalent choice among researchers. Our evaluation emphasizes adaptability as the paramount parameter, accounting for 18.4% of considerations. By shedding light on attributes, limitations, and potential directions for future research and development, this review aims to contribute to a comprehensive understanding of nature-inspired algorithms in the dynamic landscape of IoT-based healthcare services. © 2024 John Wiley & Sons, Ltd.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Optimizing Random Forest Classifier for Detection of Alzheimer's Using OASIS

Optimizing Random Forest Classifier for Detection of Alzheim...

引用

Silchar Subsection Conference (SILCON), IEEE

作者： Karri Sai Sanjana Reddy Kishor Kumar Reddy C. Srinath Doss Kari Lippert Dept. of Computer Science and Engineering Stanley College of Engineering and Technology for Women Hyderabad India Faculty of Engineering and Technology Botho University Botswana Dept. of Systems Engineering University of South Alabama Alabama USA

ISBN: (数字)9798331540821

ISBN: (纸本)9798331540838

Alzheimer's disease (AD) is a progressive brain disorder impacting behavior, memory, and cognition, with over a million cases reported annually in India. The risk significantly increases beyond age 65. Early diagnosis and treatment can result in better recovery. We propose a predictive model using the Random Forest algorithm and the OASIS dataset for early AD diagnosis, leveraging MRI data, clinical notes, genetic markers, and cognitive test results. Our model was evaluated against several others, including Decision Tree, AdaBoost, SVM, and Logistic Regression. With a 97.3% accuracy and a 2.7% error rate, our Random Forest Classifier o utperformed t he others, demonstrating superior predictive power for early AD diagnosis and potentially improving patient care.

关键词： Training Accuracy Transfer learning Predictive models Prediction algorithms Genetics Classification algorithms Alzheimer's disease Random forests Medical diagnostic imaging

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：