检索结果-内蒙古大学图书馆

International Conference on Infrared and Millimeter Waves

作者： Puspita Chanda Naini Bajaj Aparajita Bandyopadhyay Amartya Sengupta Karl Bertling A.D. Rakic Dept of Physics Indian Institute of Technology Delhi New Delhi India School of Electrical Engineering and Computer Science The University of Queensland Brisbane Australia

ISBN: (数字)9798350370324

ISBN: (纸本)9798350370331

The rapid degradation of marble monuments and buildings in recent times due to acidification caused by anthropogenic impact on global environment poses significant concerns for heritage conservationists. The adverse effects of acid rain or the dry deposition of sulfur dioxide on marble cultural heritage structures greatly diminish their longevity and resilience. This study explores the efficacy of employing Terahertz Time Domain Spectroscopy (THz-TDS) in conjunction with Raman Spectroscopy and Energy Dispersive X-ray (EDX) methods to evaluate acid-induced damage in marble samples.

关键词： Degradation Spectroscopy Rain Raman scattering Sensors Sulfur Cultural differences Time-domain analysis Dispersion Resilience

来源：评论

学校读者我要写书评

暂无评论

FLWGAN: Federated Learning with Wasserstein Generative Adversarial Network for Brain Tumor Segmentation

FLWGAN: Federated Learning with Wasserstein Generative Adver...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Divya Peketi Vishnu Chalavadi C Krishna Mohan Yen Wei Chen Dept. of Artificial Intelligence Indian Institute of Technology Hyderabad Kandi India Dept. of Computer Science and Engineering Indian Institute of Technology Hyderabad Kandi India Dept. of Information Science and Engineering Ritsumeikan University Kyoto Japan

Recently, the potential of deep learning in identifying complex patterns is gaining research interest in medical applications specifically for brain tumor diagnosis. To segment tumors accurately in brain MRIs, there is a need for a large amount of data for training deep learning models. Also, hospitals cannot share patient data for centralization on the server since health records are prone to privacy and ownership challenges. To deal with these challenges, we set up an efficient federated learning (FL) pipeline with Wasserstein generative adversarial networks (FLWGAN) to ensure data privacy and data sufficiency. FL preserves the data privacy of clients by sharing only the trained model parameters to a centralized server instead of raw data. A modified 3D Wasserstein generative adversarial network with gradient penalty (WGAN-GP) and is incorporated at the client side to generate image-segmentation pairs for efficient training segmentation models. Here, 3D-UNet with an attention module is used for the brain MRI segmentation. The attention module is integrated into a 3D-UNet encoder network for effective brain tumor segmentation. Our approach aims to allow each client to benefit from locally available real data and synthetic data. This process enhances the learning performance while respecting data privacy. The efficacy of our proposed pipeline is demonstrated on the brain tumor task of the medical segmentation decathlon (MSD) dataset. We designed FLWGAN frameworks for predicting four segmentation tasks, i.e., whole tumor (WT), enhanced tumor (ET), tumor core (TC), and multiclass. Our proposed approach achieves state of the art performance in terms of various segmentation metrics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi Class Classification of Acute Leukemia using Transfer Learning

Multi Class Classification of Acute Leukemia using Transfer ...

引用

2022 International Conference for Advancement in technology, ICONAT 2022

作者： Abhishek, Arjun Santhanam, Naveen Jha, Rajib Kumar Sinha, Ruchi Jha, Kamlesh Indian Institute of Technology Dept. of Electrical Engineering Patna India Vellore Institute of Technology Dept. of Computer Science and Engineering Vellore India All India Institute of Medical Sciences Dept. of Pathology Lab Medicine Patna India All India Institute of Medical Sciences Dept. of Physiology Patna India

ISBN: (纸本)9781665425773

Leukemia is a fatal disease which affects blood cells. Detection of this disease using machine learning and deep learning techniques can reduce the burden of doctors and clinicians. The proposed work performs a multi level classification of acute leukemia involving transfer learning technique. An accuracy of 95% and 96% are achieved for support vector machine and logistic regression, respectively, when features extracted by ResNet50 are used for training. 95% test accuracy is obtained for k-Nearest Neighbor classifier (K=5) when features extracted by MobileNet are used for training. © 2022 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Novel Technique to Parameterize Congestion Control in 6TiSCH IIoT Networks

A Novel Technique to Parameterize Congestion Control in 6TiS...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Kushal Chakraborty Aritra Kumar Dutta Mohammad Avesh Hussain Syed Raafay Mohiuddin Nikumani Choudhury Rakesh Matam Mithun Mukherjee Dept. of Computer Science & Information Systems Birla Institute of Technology & Science Hyderabad India Dept. of Computer Science & Engineering Indian Institute of Information Technology Guwahati India Nanjing University of Information Science and Technology Nanjing China

The Industrial Internet of Things (IIoT) refers to the use of interconnected smart devices, sensors, and other technologies to create a network of intelligent systems that can monitor and manage industrial processes. 6TiSCH (IPv6 over the Time Slotted Channel Hopping mode of IEEE 802.15.4e) as an enabling technology facilitates low-power and low-latency communication between IoT devices in industrial environments. The Routing Protocol for Low power and lossy networks (RPL), which is used as the de-facto routing protocol for 6TiSCH networks is observed to suffer from several limitations, especially during congestion in the network. Therefore, there is an immediate need for some modifications to the RPL to deal with this problem. Under traffic load which keeps on changing continuously at different instants of time, the proposed mechanism aims at finding the appropriate parent for a node that can forward the packet to the destination through the least congested path with minimal packet loss. This facilitates congestion management under dynamic traffic loads. For this, a new metric for routing using the concept of exponential weighting has been proposed, which takes the number of packets present in the queue of the node into account when choosing the parent at a particular instance of time. Additionally, the paper proposes a parent selection and swapping mechanism for congested networks. Performance evaluations are carried out in order to validate the proposed work. The results show an improvement in the performance of RPL under heavy and dynamic traffic loads.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection and Prediction of Neurological Disorder Using Tremor Signals and Machine Learning Algorithms 6

Detection and Prediction of Neurological Disorder Using Trem...

引用

6th International Conference on Recent Trends on Electronics, Information, Communication and technology, RTEICT 2021

作者： Swami, Swati Krishna Prasad, S.J. Mohana Kumar, S. M S Ramaiah Institute of Technology Dept. of Electronics and Telecommunication Engineering Bangalore India M S Ramaiah Institute of Technology Bangalore Dept.of Computer Science and Engineering Bangalore India

ISBN: (纸本)9781665435598

Latest research studies have indicated that more than seven million people in the worldwide and one million people in the United States have been affected by the common neuro degenerative disorder defined as Parkinson's disease. This disease is more evident in aged people who are a formidable population around the globe. Parkinson's disease (PD) is a continuous growing disease of nervous system that affects largely the regular daily activities and impedes movement of the person. The symptoms of PD patients may vary across geography and communities. Proper and timely Parkinson's disease diagnosis and prediction is an innovative research in medicine. In existent clinical diagnosis as practiced by doctors globally, One of the diagnosing methods is to study tremor signals. Tremor assessments methods include computerized tremor analysis, clinical assessment of drawn figures, standardized rating scales and simple clinical observations. To cater purpose of a clinical research, various rating scales has been developed which suit patient's population. One of the earlier scale used is to measure tremor is Fahn- Tolosa-Marin Tremor Rating Scale (TRS). This is 5-point scale which rates tremor severity predicted from its amplitude, from 0 (no tremor) to 4 (serious tremor) in each part of the body. Primary objective of work under taken is to develop a tremor detection prototype using Raspberry Pi processor equipped with accelerometer and flex sensors. Neurological tremor thus collected from this module is used to build dataset of subjects among the population. Eventually, innovative machine learning algorithms namely Logistic Regression and Random Forest algorithms are designed to predict onset of disease using this dataset. Comparisons of both algorithms has been done for benchmarking purposes. Test results prediction accuracy is documented as 96.0% indicating the performance measure of classifier. © 2021 IEEE.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Summarizing Clustering Results using Sentence prototype based Language Models

Summarizing Clustering Results using Sentence prototype base...

引用

Electrical, computer, Communications and Mechatronics engineering (ICECCME), International Conference on

作者： Arpit Khare Dheeraj Kumar Dept. of Computer Science and Engineering National Institute of Technology Jamshedpur Jamshedpur India Dept. of Electronics and Communications Engineering Indian Institute of Technology Roorkee Roorkee India

Amount of experiment-related data in almost every domain has increased multifold. Hence, Understanding these novel datasets’ essential characteristics is vital to developing complex statistical models and testing various hypotheses. Exploratory data analysis using unsupervised techniques such as data clustering is becoming popular among researchers. Although several clustering algorithms exist, little research has been done to develop strategies to help understand the characteristics and physical implications of generated clusters. This paper proposes to use natural language to describe the results generated by a clustering algorithm linguistically for straightforward interpretation and understanding. We discuss salient characteristics of clusters that one looks for while interpreting clustering results and develop several linguistic prototype summaries for each of them. These summaries are then coherently combined to form linguistic summarization of clustering results. Numerical experiments on real-life IRIS dataset generate highly readable and easy-to-understand descriptions of the clusters generated through three popular clustering algorithms - k means, single linkage, and DBSCAN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scheduling of Flexible Manufacturing System with Penalty Cost Using Simulated Genetic Algorithm

Scheduling of Flexible Manufacturing System with Penalty Cos...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Vijai Singh Varsha Singh dept. of Computer Science and Engineering Inderprastha Engineering College Ghaziabad Uttar Pradesh India dept. of Information Technology Indian Institute of Information Technology Allahabad Prayagraj Uttar Pradesh India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

This paper discuss about the scheduling problem for flexible manufacturing systems (FMSs) using the genetic algorithm. In FMSs, the operation of a job is performed on more than one machine. Therefore, FMS scheduling is considered to be a computationally hard problem. In this paper, various approaches are reviewed that are applied to the FMS scheduling problem. This paper also attempts to find a possible solution to the scheduling problem of FMS. To identify the order in which the various jobs would be assigned to a number of machines, this paper uses a genetic algorithm with Simulated Annealing to generate a machine sequence. In this, the developed tool requires tabular input. To obtain a schedule with minimum make span, many iterations of the genetic algorithm are applied. In this system, an optimal schedule is given for FMS by taking the makespan time and minimum penalty cost, and therefore calculating the minimum combined objective function.

关键词： Schedules Job shop scheduling Frequency modulation Costs Processor scheduling Optimal scheduling Simulated annealing Manufacturing Flexible manufacturing systems Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Next Generation Intelligent Traffic Signal Control: Empowering Electronics Consumers with Edge-AIoT Capabilities

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Chavhan, Suresh Doswada, Rohit Gupta, Deepak Gunjal, Saymam Rodrigues, Joel J.P.C. School of Data Sciences Indian Institute of Science Education and Research Kerala Thiruvananthapuram India C-DoT Karnataka Bangalore India Dept. of Computer Science and Engineering Maharaja Agrasen Institute of Technology Delhi India Centre for Research Impact and Outcome Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Engineering University of Visvesvaraya College of Engineering Karnataka Bangalore India Federal University of Piaui PI Teresina Brazil

Traffic congestion has become a major issue that is being faced by the majority of road users. The increasing vehicle usage, and the lack of space and funds to construct new transport infrastructure, further complicates the issue. In this scenario, it is important to come up with an intelligent and economical solution that improves the quality of road users' service. The problem with the traffic handling framework is signal timings are fixed which is not adaptive to the density of vehicles. To address this issue we propose an Edge-Augument Artificial Intelligence of Things (AIoT) road user cooperation for traffic management. The proposed system efficiently utilizes electronic devices to learn and adapt to changing traffic conditions in real-time. By optimizing the traffic signal timings based on the actual traffic conditions, adaptive systems reduce delay, improve traffic flow, reduce fuel consumption and pollution, and improve the electronics consumers' and road users' experiences. The proposed system has been tested with real-time experiments by integrating Electronic devices like cameras, smartphones, and AGX Xavier (edge device) with Cloud (ThingSpeak). The proposed system is verified by simulating the proposed system in the SUMO traffic simulator and its reliability is concluded by comparing the waiting time, depart delay, running, and halt time with the existing traditional method. © 2025 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

SoftHealth: Softwarized 5G-Driven Network Slicing for Real-time e-Healthcare Applications using ML 14

SoftHealth: Softwarized 5G-Driven Network Slicing for Real-t...

引用

14th International Conference on COMmunication Systems and NETworkS, COMSNETS 2022

作者： Basu, Deborsi Krishnakumar, Vikram Ghosh, Uttam Datta, Raja Indian Institute of Technology G.S. Sanyal School of Telecommunications Kharagpur India SASTRA Deemed to Be University Tamil Nadu Thanjavur India Vanderbilt University Dept. of Electrical Engineering and Computer Science NashvilleTN United States Indian Institute of Technology Dept. of Electronics and Electrical Communication Engineering Kharagpur India

ISBN: (纸本)9781665421041

The recent years have whiteness the substandard situations of the modern healthcare system due to a fatal pandemic called COVID19. The rapid advancements of modern technology have disseminated the superficial benefits of medical infrastructure, but significant improvements are still extremely necessary over the massive e-healthcare system (mHS). Considering the fact of limited resources and unlimited demands, a highly stable end-to-end optimization model is required. Healthcare also struggles with real-time communication. The next-generation communication networks (e.g 5G and beyond) proficiently influence the network resource distribution for URLLC. In this work, we have envisioned a novel on-demand e-Healthcare dynamic network slice architecture that uses the ML algorithms at the edge server for real-time classification and access of the offloaded data from the central controller (vSDN-Control layer to Data plane layer). The comparative analysis over the datasets of patients consisting of special index parameters shows that our proposed model allows the end-user more efficient data accessibility over the conventional approaches. We have studied the model over the multi-classification ML models (kNN, DT and RF) and we have found an average improvement of 10% to 15% of average data offloading time efficiency from the local machines from the edge servers. This approach can be further extended as the QoS improvement of the healthcare data traffic over the dynamic network slice instances. We have kept the model simple but standard in nature. © 2022 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Recovering Shape and Size from a Single Endoscope Image using Optimization 12

Recovering Shape and Size from a Single Endoscope Image usin...

引用

12th International Congress on Advanced Applied Informatics, IIAI-AAI 2022

作者： Iwahori, Yuji Emoto, Shun Funahashi, Kenji Bhuyan, M.K. Wang, Aili Kasugai, Kunio Chubu University Dept. of Computer Science Kasugai487-8501 Japan Nagoya Institute of Technology Dept. of Computer Science Nagoya466-8555 Japan Indian Institute of Technology Guwahati Dept. of Electronics & Electrical Engineering Guwahati781039 India Harbin University of Science and Technology Dept. of Communication Engineering Harbin150080 China Aichi Medical University Dept. of Gastroenterology Nagakute480-1195 Japan

ISBN: (数字)9781665497558

ISBN: (纸本)9781665497558

Recovering the shape and size of a polyp from endoscope images is an important research topic in medical diagnosis. As a method for recovering 3D shape of polyps, the authors proposed a method that can recover the shape accurately and faster than the conventional method by deriving an equation based on the Eikonal equation from the condition that the optical and geometric constraint equations become equal from the reason that both equations determine the depth Z of the same point. To obtain the absolute size of polyp using this method, it is necessary to estimate the reflectance factor C of the object surface after converting the original image into the uniform Lambertian image. The reflectance factor is obtained by optimizing the error between the width of the entire image and the estimated width of the recovered result. The width of the entire image is defined from the assumed width of the blood vessel. The surface reflectance factor is estimated from a single endoscope image by introducing an optimization approach. © 2022 IEEE.

关键词： Endoscopy

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：