检索结果-内蒙古大学图书馆

Predictive Models for the Early Diagnosis and Prognosis of Knee Osteoarthritis Using Deep Learning Techniques 1st

学校读者我要写书评

暂无评论

Predictive Models for the Early Diagnosis and Prognosis of K...

1st International Conference on Intelligent Systems in Computing and Communications, ISCComm 2023

作者： Malathi, S.Y. Bharamagoudar, Geeta Shiragudikar, Sharada K. G. Totad, Shashikumar CSE Department KLEIT Karnataka Hubballi India School of Computer Science and Engineering KLE Technological University Karnataka Hubballi India Department of Automation and Robotics KLE Technological University Karnataka Hubballi India

ISBN: (纸本)9783031756047

Uncovering hidden patterns and relationships in knee OA data using machine learning algorithms can be incredibly useful for predicting illness progression and developing more effective treatments. By analyzing large amounts of data, machine learning algorithms can identify patterns and relationships that might not be immediately apparent to human researchers. This can help us better understand the mechanisms behind knee OA and identify potential targets for treatment. By developing more potent treatments, we may be able to slow the progression of the disease and improve patient outcomes. The knee osteoarthritis dataset information was initially acquired from Kaggle and the information on knee osteoarthritis is processed before model training. The study aims to develop and apply advanced machine learning methods, such as deep learning techniques like CNN-SVM, Mobilenet v2, Resnet152v2, Resnet 50, and EfficientnetB5, to analyze knee OA data and develop accurate prediction models for early diagnosis and prognosis. The study evaluates the performance of these models on a dataset of individuals with knee OA to determine their efficacy and accuracy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： CNN EfficientNetB5 Knee osteoarthritis mobilenetV2 ResNet50

Separation Sound Event Localization and Detection Using Neural Network and Time Frequency Masking

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Ranny, Ranny Lestari, Dessi Puji Mengko, Tati Latifah Erawati Rajab School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia School of Electrical Engineering and Informatics U-CoE AI-VL Institut Teknologi Bandung Bandung Indonesia Department of Biomedical Engineering School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

Background: Sound processing frameworks have many kinds of approaches. The approaches are distinguished based on data and purpose of the sound processing research area. One of the research purposes are localization and detection of sound events. The research also uses non-overlapping data and overlapping data to test the sound processing algorithms. The previous research has a good accuracy with non-overlapping sound, but the accuracy decreased when it uses the overlapping data sound. Whereas the overlapping data sound appeared in a real condition. So, this research is developing a framework that can handle the non-overlapping and overlapping data. Objective: This research focused on overlapping sound processing. The using of overlapping sound in sound recognition system decreases the recognition accuracy. This research tries to improve the sound recognition system without eliminating the using of overlapping sound. Methods: This research uses a different approach than any other common research. This research used the non-overlapping data and separated sound data as the data train for sound event localization and detection (SELD). The separation of overlapping sound generates the separated sound and is used for detection the overlapping data sound. This new framework is called Separation ***: This Separation SELDnet framework gives 81% localization accuracy and 70% detection accuracy when the SELDnet only gives a lower accuracy for the overlapping ***: The Separation SELDnet gives a good opportunity to increase the sound recognition with using non overlapping and overlapping sound. This new method can be more adaptive with real condition. © 2023, The Authors. All rights reserved.

关键词：

Stationary Wavelet-Oriented Luminance Enhancement Approach for Brain Tumor Detection with Multi-modality Images 11th

学校读者我要写书评

暂无评论

Stationary Wavelet-Oriented Luminance Enhancement Approach f...

11th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2023

作者： Ahilan, A. Anlin Sahaya Tinu, M. Jasmine Gnana Malar, A. Muthu Kumar, B. Department of Electronics and Communication Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli627152 India Department of Electrical and Electronics Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli627152 India Department of Electronics and Communication Engineering Anna University Tamil Nadu Chennai600025 India Department of Computer Science and Engineering School of Computing and Information Technology REVA University Karnataka Kattigenahalli560064 India

ISBN: (纸本)9789819967018

A brain tumor is an abnormal growth of cells in the brain. However, manually detecting brain tumors is hard because it is hard to find erratically shaped tumors with only one modality and time-consuming. In this work, a novel stationary wavelet-oriented luminance enhancement (SOLE) approach to denoise the multi-modal images. Initially, medical images like MRI, CT, and PET are gathered from publicly available datasets. These multi-modality images are divided into low and high-frequency sub-images using stationary wavelet transform (SWT), which has the advantage of preserving temporal features so that information loss can be stopped. Then the low-frequency and high-frequency images are processed with distribution and denoising modules to remove the noise, respectively. The approximation coefficient is pre-processed using multi-scale retinex with gamma correction for efficaciously retrieving the noise-free image. Consequently, the remaining coefficients are pre-processed using a multi-scale Gaussian bilateral filter, and tracking wavelet denoising (TWD) algorithm in the denoising module dynamically enhanced the color detail information without human intervention so that observed image contrast and visibility are well preserved. Lastly, noise-free image is reconstructed from sub-enhanced images using Inverse-SWT to detect brain tumors. Experimental results show that the proposed algorithm has a mean error rate of 0.03 compared to the other filters. The proposed SOLE technique achieves a less running time of 0.97 s, whereas other existing techniques such as K-SVD, DRAN, 2-stage CNN, and AMF-AWF achieve the running time of 6.9, 1.63, 1.52, and 8.75 s. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Luminance

Risk-Aware Real-Time Task Allocation for Stochastic Multi-Agent Systems under STL Specifications

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Engelaar, Maico H.W. Zhang, Zengjie Vlahakis, Eleftherios E. Dimarogonas, Dimos V. Lazar, Mircea Haesaert, Sofie Department of Electrical Engineering Control Systems Group Eindhoven University of Technology Netherlands Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden

This paper addresses the control synthesis of heterogeneous stochastic linear multi-agent systems with real-time allocation of signal temporal logic (STL) specifications. Based on previous work, we decompose specifications into sub-specifications on the individual agent level. To leverage the efficiency of task allocation, a heuristic filter evaluates potential task allocation based on STL robustness, and subsequently, an auctioning algorithm determines the definitive allocation of specifications. Finally, a control strategy is synthesized for each agent-specification pair using tube-based model predictive control (MPC), ensuring provable probabilistic satisfaction. We demonstrate the efficacy of the proposed methods using a multi-shuttle scenario that highlights a promising extension to automated driving applications like vehicle routing. © 2024, CC BY-NC-ND.

关键词： Stochastic systems

Optimal Receive Filter Design for Misaligned Over-the-Air Computation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hellström, Henrik Razavikia, Saeed Fodor, Viktoria Fischione, Carlo School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Electrical Engineering Department Stanford University CA United States

Over-the-air computation (OAC) is a promising wireless communication method for aggregating data from many devices in dense wireless networks. The fundamental idea of OAC is to exploit signal superposition to compute functions of multiple simultaneously transmitted signals. However, the time- and phase-alignment of these superimposed signals have a significant effect on the quality of function computation. In this study, we analyze the OAC problem for a system with unknown random time delays and phase shifts. We show that the classical matched filter does not produce optimal results, and generates bias in the function estimates. To counteract this, we propose a new filter design and show that, under a bound on the maximum time delay, it is possible to achieve unbiased function computation. Additionally, we propose a Tikhonov regularization problem that produces an optimal filter given a tradeoff between the bias and noise-induced variance of the function estimates. When the time delays are long compared to the length of the transmitted pulses, our filter vastly outperforms the matched filter both in terms of bias and mean-squared error (MSE). For shorter time delays, our proposal yields similar MSE as the matched filter, while reducing the *** Codes 94A12 Copyright © 2023, The Authors. All rights reserved.

关键词： Matched filters

Energy Efficient Transmission Parameters Selection Method Using Reinforcement Learning in Distributed LoRa Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Airiyoshi, Ryotai Hasegawa, Mikio Ohtsuki, Tomoaki Li, Aohan Graduate School of Informatics and Engineering The University of Electro-Communications Tokyo Japan Department of Electrical Engineering Tokyo University of Science Tokyo Japan Department of Information and Computer Science Keio University Yokohama Japan

With the increase in demand for Internet of Things (IoT) applications, the number of IoT devices has drastically grown, making spectrum resources seriously insufficient. Transmission collisions and retransmissions increase power consumption. Therefore, even in long-range (LoRa) networks, selecting appropriate transmission parameters, such as channel and transmission power, is essential to improve energy efficiency. However, due to the limited computational ability and memory, traditional transmission parameter selection methods for LoRa networks are challenging to implement on LoRa devices. To solve this problem, a distributed reinforcement learning-based channel and transmission power selection method is proposed, which can be implemented on the LoRa devices to improve energy efficiency in this paper. Specifically, the channel and transmission power selection problem in LoRa networks is first mapped to the multiarmed-bandit (MAB) problem. Then, an MAB-based method is introduced to solve the formulated transmission parameter selection problem based on the acknowledgment (ACK) packet and the power consumption for data transmission of the LoRa device. The performance of the proposed method is evaluated by the constructed actual LoRa network. Experimental results show that the proposed method performs better than fixed assignment, adaptive data rate low-complexity (ADR-Lite), and ϵ-greedybased methods in terms of both transmission success rate and energy efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Day-Ahead Photovoltaic Power Forecasting with Limited Data

学校读者我要写书评

暂无评论

Day-Ahead Photovoltaic Power Forecasting with Limited Data

IEEE URUCON

作者： Diana Estefanía Chérrez Barragán Byron Alejandro Acuña Acurio Juan López Hugo Morais Cindy P. Guzman Luiz Silva School of Electrical Engineering Universidade Estadual de Campinas Campinas SP Brazil Faculty of Electrical Engineering Mathematics and Computer Science EEMCS University of Twente Enschede The Netherlands Department of Electrical and Computer Engineering INESC-ID Instituto Superior Técnico-IST Universidade de Lisboa Lisboa Portugal

ISBN: (数字)9798350355383

ISBN: (纸本)9798350355390

Forecasting algorithms for photovoltaic (PV) power generation play an important role in energy management systems. Nevertheless, the precision of machine learning models is significantly compromised when historical data is limited. This situation is challenging for new plants for which a long history of measurements is not yet available. The unpredictable nature of the weather gives the perception that a competitive forecast requires a substantial amount of data and a very complicated algorithm. However, in this manuscript, it was found that using five historical days for the inverse quantification of uncertainty, can implicitly describe complex non-linear relationships between last five-day records and day-ahead PV power generation. The proposed approach learns the emerging patterns across various seasons throughout the year without relying on exogenous data such as air temperature, wind speed, pressure, cloud cover, and relative humidity. Results using real-world data collected at the microgrid of the University of Campinas (UNICAMP) confirm that our proposed model outperforms previous state-of-the-art deep learning models as Long short-term memory (LSTM), Gated Recurrent Unit (GRU) and traditional Autoregressive Integrated Moving Average (ARIMA) statistical model, using limited data. The proposed approach is flexible and can be easily adapted to other PV power generation systems with limited data. The source code is available at https://***/byronacunia/***

关键词： Photovoltaic systems Adaptation models Accuracy Clouds Atmospheric modeling Wind speed Microgrids Data models Forecasting Long short term memory

Neural Network-Based Analysis of Mammography Images for Identifying Breast Cancer Histological Subtypes

学校读者我要写书评

暂无评论

Neural Network-Based Analysis of Mammography Images for Iden...

Future Machine Learning and Data science (FMLDS), IEEE International Conference on

作者： Muhammad Alqaaf Ahmad Kamal Nasution Graduate school of science and Technology Retno Supriyanti Abu Asaduzzaman Naoaki Ono Md. Altaf-Ul-Amin Shigehiko Kanaya Graduate School of Science and Technology Nara Institute of Science and Technology Ikoma Japan Department of Electrical Engineering Jenderal Soedirman University Banyumas Indonesia Department of Electrical and Computer Engineering Wichita State University Wichita U.S.A

ISBN: (数字)9798350391213

ISBN: (纸本)9798350391220

Breast cancer (BC) is a complex disease with multiple histological subtypes that exhibits distinct biological and clinical characteristics. Accurate identification of these subtypes is crucial for the implementation of personalized treatment strategies and the improvement of patient outcomes. This study aimed to leverage the potential of neural networks and mammography data to identify specific histological subtypes of BC, with a focus on distinguishing between in situ and invasive carcinoma. We used the Digital Database for Screening Mammography (DDSM) and its curated subset, CBIS-DDSM, which provides mammography images of normal and malignant cases with verified pathological information. A convolutional neural network (CNN) architecture was designed to extract relevant features from mammography images. The model was trained using data augmentation techniques to enhance diversity and mitigate overfitting, resulting in training and validation accuracies ranging from 0.98 to 1.0. The features extracted by the trained model were then used for clustering analysis using Kmeans on PCA (KM-PCA), which identified nine well-separated clusters with minimal overlap. The clustering results were validated using a subset of mammography images with confirmed invasive carcinoma types from The Cancer Genome Atlas Breast Invasive Carcinoma (TCGA-BRCA) dataset. Two validation approaches were incorporated to strengthen the hypothesis and further validate the results. Overall, this study demonstrates the potential of combining neural networks and mammography data to accurately identify BC histological subtypes, which could pave the way for personalized and effective treatment strategies.

关键词： Training Analytical models Accuracy Neural networks Network analyzers Feature extraction Breast cancer Data models Convolutional neural networks Principal component analysis

Exploring Diverse Methods in Visual Question Answering

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Panfeng Yang, Qikai Geng, Xieming Zhou, Wenjing Ding, Zhicheng Nian, Yi Department of Electrical and Computer Engineering University of Michigan Ann Arbor United States Department of Computer Science University of Illinois Urbana-Champaign Urbana United States Department of Computer Science Chongqing University Chongqing China Department of Statistics University of Michigan Ann Arbor United States Fu Foundation School of Engineering and Applied Science Columbia University New York United States Department of Computer Science University of Chicago Chicago United States

This study explores innovative methods for improving Visual Question Answering (VQA) using Generative Adversarial Networks (GANs), autoencoders, and attention mechanisms. Leveraging a balanced VQA dataset, we investigate three distinct strategies. Firstly, GAN-based approaches aim to generate answer embeddings conditioned on image and question inputs, showing potential but struggling with more complex tasks. Secondly, autoencoder-based techniques focus on learning optimal embeddings for questions and images, achieving comparable results with GAN due to better ability on complex questions. Lastly, attention mechanisms, incorporating Multimodal Compact Bilinear pooling (MCB), address language priors and attention modeling, albeit with a complexity-performance tradeoff. This study underscores the challenges and opportunities in VQA and suggests avenues for future research, including alternative GAN formulations and attentional mechanisms. © 2024, CC BY.

关键词： Generative adversarial networks