检索结果-内蒙古大学图书馆

Automatic detection of lung nodule in CT scan slices using CNN segmentation schemes: A study

Procedia computer science 2023年 218卷 2786-2794页

作者： Seifedine Kadry Enrique Herrera-Viedma Rubén González Crespo Sujatha Krishnamoorthy Venkatesan Rajinikanth Faculty of Applied Computing and Technology Noroff University College Kristiansand 94612 Norway Research Institute in Data Science and Computational Intelligence University of Granada Granada Andalusian Spain Computer Science Department School of Engineering and Technology Universidad Internacional de La Rioja 26006 Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Chennai 600119 Tamil Nadu India

The lung is one of the prime respiratory organs in human physiology, and its abnormality will severely disrupt the respiratory system. Lung Nodule (LN) is one of the abnormalities, and early screening and treatment are necessary to reduce its harshness. The proposed work aims to implement the Convolutional-Neural-Network (CNN) segmentation methodology to extract the LN in various lung CT slices, such as axial, coronal, and sagittal planes. This work consists of the following phases; (i) Image collection and pre-processing, (ii) Ground-truth generation, (iii) CNN-supported segmentation, and (iv) Performance evaluation and validation. In this work, the merit of pre-trained CNN segmentation schemes is verified using (i) One-fold training and (ii) Two-fold training methods. The test images for this study are collected from The Cancer Imaging Archive (TCIA) database. The experimental investigation is executed using Python®, and the outcome of this study confirms that the VGG-SegNet helps to get better values of Jaccard (>88%), Dice (>93%), and Accuracy (>96%) compared to other CNN methods.

关键词： Lung nodule CT scan CNN segmentation VGG-SegNet Accuracy Detection

来源：评论

学校读者我要写书评

暂无评论

On-device Deep Learning Location Category Inference Model 1

引用

Artificial Intelligence and Machine Learning - 34th Joint Benelux Conference, BNAIC/Benelearn 2022, Revised Selected Papers

作者： Musaev, Gadzhi Mets, Kevin Tamošiūnas, Rokas Uvarov, Vadim De Schepper, Tom Hellinckx, Peter IDLab - Faculty of Applied Engineering University of Antwerp - imec Sint-Pietersvliet 7 Antwerp2000 Belgium Department of Computer Science University of Antwerp - imec Sint-Pietersvliet 7 Antwerp2000 Belgium Sentiance Korte Lozanastraat 20-26 Antwerp Belgium Faculty of Applied Engineering University of Antwerp Antwerp Belgium

ISBN: (数字)9783031391446

ISBN: (纸本)9783031391439

We define Location Category Inference (LCI) as a task of predicting the category of a visited venue, such as bar, restaurant or university, given user location GPS coordinates and a set of venue candidates. LCI is an essential part of the hyper-personalization systems as its output provides deep insights into user lifestyle (has children, owns a dog) and behavioral patterns (regularly exercises, visits museums). Due to such factors as signal obstruction, especially in urban canyons, the GPS positioning is inaccurate. The noise in the GPS signal makes the problem of LCI challenging and requires researchers to explore models that incorporate additional information such as the time of day, duration of stay or user lifestyle in order to overcome the noise-induced errors. In this paper we propose an embeddable on-device LCI model which fuses spatial and temporal features. We discuss how initial clustering of locations helps limiting the GPS noise. Then, we propose a multi-modal architecture that incorporates socio-cultural information on when and for how long people typically visit venues of different categories. Finally, we compare our model with one nearest neighbor, a simple fully connected neural network and a random forest model and show that the multi-modal neural network achieves f1 score of 73.2% which is 6.6% better than the best of benchmark models. Our model outperforms benchmark models while being almost 180 times smaller in size at around 1.9Mb. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

A wasserstein minimax framework for mixed linear regression

arXiv

引用

arXiv 2021年

作者： Diamandis, Theo Eldar, Yonina C. Fallah, Alireza Farnia, Farzan Ozdaglar, Asuman Department of Electrical Engineering & Computer Science MIT United States Faculty of Math and Computer Science Weizmann Institute of Science Israel

Multi-modal distributions are commonly used to model clustered data in statistical learning tasks. In this paper, we consider the Mixed Linear Regression (MLR) problem. We propose an optimal transport-based framework for MLR problems, Wasserstein Mixed Linear Regression (WMLR), which minimizes the Wasserstein distance between the learned and target mixture regression models. Through a model-based duality analysis, WMLR reduces the underlying MLR task to a nonconvex-concave minimax optimization problem, which can be provably solved to find a minimax stationary point by the Gradient Descent Ascent (GDA) algorithm. In the special case of mixtures of two linear regression models, we show that WMLR enjoys global convergence and generalization guarantees. We prove that WMLR’s sample complexity grows linearly with the dimension of data. Finally, we discuss the application of WMLR to the federated learning task where the training samples are collected by multiple agents in a network. Unlike the Expectation Maximization algorithm, WMLR directly extends to the distributed, federated learning setting. We support our theoretical results through several numerical experiments, which highlight our framework’s ability to handle the federated learning setting with mixture models. Copyright © 2021, The Authors. All rights reserved.

关键词： Maximum principle

来源：评论

学校读者我要写书评

暂无评论

Importance measures derived from random forests characterisation and extension

arXiv

引用

arXiv 2021年

作者： Sutera, Antonio University of LiÈge Faculty of Applied Sciences Department of Electrical Engineering & Computer Science

Nowadays new technologies, and especially artificial intelligence, are more and more established in our society. Big data analysis and machine learning, two sub-fields of artificial intelligence, are at the core of many recent breakthroughs in many application fields (e.g., medicine, communication, finance,...), including some that are strongly related to our day-to-day life (e.g., social networks, computers, smart-phones,...). In machine learning, significant improvements are usually achieved at the price of an increasing computational complexity and thanks to bigger datasets. Currently, cutting-edge models built by the most advanced machine learning algorithms typically became simultaneously very efficient and profitable but also extremely complex. Their complexity is to such an extent that these models are commonly seen as black-boxes providing a prediction or a decision which can not be interpreted or justified. Nevertheless, whether these models are used autonomously or as a simple decision-making support tool, they are already being used in machine learning applications where health and human life are at stake. Therefore, it appears to be an obvious necessity not to blindly believe everything coming out of those models without a detailed understanding of their predictions or decisions. Accordingly, this thesis aims at improving the interpretability of models built by a specific family of machine learning algorithms, the so-called tree-based methods. Several mechanisms have been proposed to interpret these models and we aim along this thesis to improve their understanding, study their properties, and define their limitations. The first part of this thesis introduces the techniques used to build these models, i.e. decision tree and ensemble of randomised trees induction algorithms. It also presents the basis of feature selection, a data analysis method aiming at identifying the essential features of a model and allowing to improve the model performances and/or i

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Microheater hotspot engineering for repeatable multi-level switching in foundry-processed phase change silicon photonics

arXiv

引用

arXiv 2024年

作者： Sun, Hongyi Lian, Chuanyu Vásquez-Aza, Francis Kari, Sadra Rahimi Huang, Yi-Siou Restelli, Alessandro Vitale, Steven A. Takeuchi, Ichiro Hu, Juejun Youngblood, Nathan Pavlidis, Georges Ríos Ocampo, Carlos A. Department of Materials Science & Engineering University of Maryland College ParkMD20742 United States Institute for Research in Electronics and Applied Physics University of Maryland College ParkMD20742 United States Department of Mechanical Engineering University of Connecticut StorrsCT06269 United States Electrical & Computer Engineering Department The University of Pittsburgh PittsburghPA15213 United States Joint Quantum Institute Department of Physics University of Maryland College ParkMD20742 United States Advanced Materials and Microsystems Group MIT Lincoln Laboratory LexingtonMA02139 United States Department of Materials Science & Engineering MIT CambridgeMA02139 United States

Nonvolatile photonic integrated circuits employing phase change materials have relied either on optical switching mechanisms with precise multi-level control but poor scalability or electrical switching with seamless integration and scalability but mostly limited to a binary response. Recent works have demonstrated electrical multi-level switching;however, they relied on the stochastic nucleation process to achieve partial crystallization with low demonstrated repeatability and cyclability. Here, we re-engineer waveguide-integrated microheaters to achieve precise spatial control of the temperature profile (i.e., hotspot) and, thus, switch deterministic areas of an embedded phase change material cell. We experimentally demonstrate this concept using a variety of foundry-processed doped-silicon microheaters on a silicon-on-insulator platform to trigger multi-step amorphization and reversible switching of Sb2Se3 and Ge2Sb2Se4Te alloys. We further characterize the response of our microheaters using Transient Thermoreflectance Imaging. Our approach combines the deterministic control resulting from a spatially resolved glassy-crystalline distribution with the scalability of electro-thermal switching devices, thus paving the way to reliable multi-level switching towards robust reprogrammable phase-change photonic devices for analog processing and computing. © 2024, CC BY-NC-SA.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Data Analysis and Machine Learning Models for Automatic Identification of Chemical Compounds Based on Terahertz spectra

Comprehensive Data Analysis and Machine Learning Models for ...

引用

International Conference on Infrared and Millimeter Waves

作者： Lim Zi Xi Josie Nan Zhang Phua Wei Ji Lijie Yu Jia Yi Kwang Angeline Tang Angeline Tiong Whei Yap Yee-Fun Lim Lin Ke Anor Technologies Pte Ltd Singapore Institute of Materials Research and Engineering Agency for Science Technology and Research Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Illicit Drugs Laboratory Applied Sciences Group Health Sciences Authority Singapore

The article describes a method for auto-identification of chemical compounds encountered in complicated real-world scenarios, with common issues such as complex spectra, mixtures, and masking of signals. This method comprised a sample treatment protocol, data processing technique, and machine learning algorithms. The data processing technique involved normalizing and filtering the chemical spectrum to isolate characteristic peaks. Principal Component Analysis and t-distributed Stochastic Neighbor Embedding were used to identify significant features and reduce data dimensionality. Machine learning models such as Support Vector Machine, Random Forest Classifier, Gradient Boosting Classifier, and Neural Network Classifier were implemented to classify the identified peaks. The accuracy of the models was tested using diluents, illicit drugs, and mixture chemicals, and over 90% accuracy were obtained across all machine learning models. This concluded that the method can potentially be incorporated into software for on-site testing and automatic identification of chemical compounds in real-world scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An intelligent trading mechanism based on the group trading strategy portfolio to reduce massive loss by the grouping genetic algorithm

引用

Electronic Commerce Research 2021年第1期23卷 3-42页

作者： Chen, Chun-Hao Chen, Yu-Hsuan Diaz, Vicente Garcia Lin, Jerry Chun-Wei Department of Information and Finance Management National Taipei University of Technology Taipei Taiwan Department of Computer Science and Information Engineering Tamkang University Taipei Taiwan School of Computer Engineering University of Oviedo Oviedo Spain Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Bergen Norway

It is always difficult and challenge to obtain suitable trading signals for the desired securities in financial markets. The popular way to deal with it is through the use of trading strategies (TSs) made up of technical or fundamental indicators. Due to the different properties of TSs, an algorithm was proposed to find trading signals by obtaining the group trading strategy portfolio (GTSP), which is composed of strategy groups that can be employed to generate various TS portfolios (TSP) instead of a single TS. The stop-loss and take-profit points (SLTP) are widely utilized by shareholders to avoid massive losses. However, the appropriate SLTP is hard to set by users. Therefore, in this paper, the algorithm, namely GTSP-SLTP algorithm, is proposed to not only obtain a reliable GTSP but also find appropriate SLTP using the grouping genetic algorithm. A chromosome is encoded by the generated SLTP and GTSP along with the weights for strategy groups that are the SLTP, grouping, weight, and strategy parts. To assess the goodness of a chromosome, the evaluation function that consists of the group balance, weight balance, risk factor, and profit factor, is employed. Genetic operators are then performed to produce new solutions for next population. The genetic process is performed iteratively until the stop conditions have achieved. Last but not the least, empirical experiments were conducted on three financial datasets with different trends and a case study is also given to reveal the effectiveness and robustness of the designed GTSP-SLTP algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Word and Gender Identification in the Speech of Transgender Individuals

引用

Journal of Voice 2024年

作者： Doyle, Kristina A. Harel, Daphna Feeny, Graham T. Novak, Vesna D. McAllister, Tara Department of Communicative Sciences and Disorders New York University New York New York United States Department of Applied Statistics Social Sciences and Humanities New York University New York New York United States Department of Electrical Engineering and Computer Science University of Cincinnati Cincinnati Ohio United States

Listeners use speech to identify both linguistic information, such as the word being produced, and indexical attributes, such as the gender of the speaker. Previous research has shown that these two aspects of speech perception are interrelated. It is important to understand this relationship in the context of gender-affirming voice training (GAVT), where changes in speech production as part of a speaker's gender-affirming care could potentially influence listeners’ recognition of the intended utterance. This study conducted a secondary analysis of data from an experiment in which trans women matched shifted targets for the second formant frequency using visual-acoustic biofeedback. Utterances were synthetically altered to feature a gender-ambiguous fundamental frequency and were presented to blinded listeners for rating on a visual analog scale representing the gender spectrum, as well as word identification in a forced-choice task. We found a statistically significant association between the accuracy of word identification and the gender rating of utterances. However, there was no statistically significant difference in word identification accuracy for the formant-shifted conditions relative to an unshifted condition. Overall, these results support previous research in finding that word identification and speaker gender identification are interrelated processes;however, the findings also suggest that a small magnitude of shift in formant frequencies (of the type that might be pursued in a GAVT context) does not have a significant negative impact on the perceptual recoverability of isolated words. © 2024 The Voice Foundation

关键词： Formants Gender Gender-affirming voice training Gender-diverse Perception Transgender

来源：评论

学校读者我要写书评

暂无评论

Modeling Energy Consumption for Task-Offloading Decisions on Mobile and Embedded Devices 2

Modeling Energy Consumption for Task-Offloading Decisions on...

引用

2nd IEEE Global Conference on Life sciences and Technologies, LifeTech 2020

作者： Niemann, Christoph Ewert, Christian Puttnies, Henning Rethfeldt, Michael Timmermann, Dirk Danielis, Peter University of Rostock Institute of Applied Microelectronics and Computer Engineering Rostock Germany University of Rostock Department of Computer Science Rostock Germany

ISBN: (纸本)9781728170633

Connected mobile and embedded devices including tablets, smartphones, and smartwatches but also IoT sensors and actuators as well as medical implants are subject to a rapid development in terms of their numbers and computing power. However, these devices have energy limitations, e.g., due to limited energy supplies. In order for networked devices to be able to manage their energy, they can offload tasks to other devices. However, they need to estimate the energy demand to execute the tasks in order to take offloading decisions. This paper proposes energy models for estimating the energy consumption for task processing derived from practical measurements for exemplary tasks. The task-processing energy consumption models are implemented in the OMNeT++ simulator to allow simulative, accurate task-offloading investigations. © 2020 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

StressFADS: Learning Latent Autonomic Factors of Stress in the Context of Trauma Recall and Neuromodulation

StressFADS: Learning Latent Autonomic Factors of Stress in t...

引用

International Workshop on Wearable and Implantable Body Sensor Networks (BSN)

作者： Asim H. Gazi Michael Chan Hao-Lun Hsu J. Douglas Bremner Christopher J. Rozell Omer T. Inan School of Electrical and Computer Engineering (ECE) Georgia Institute of Technology (GT) Atlanta GA USA School of Engineering and Applied Sciences Harvard University Cambridge MA USA Coulter Department of Biomedical Engineering (CDBME) GT Atlanta GA USA CDBME GT Atlanta GA USA Department of Computer Science Duke University Durham NC USA Department of Radiology and Imaging Sciences and the Department of Psychiatry and Behavioral Sciences Emory University School of Medicine Atlanta GA USA Atlanta Veterans Affairs Health Care System Decatur GA USA School of ECE GT Atlanta GA USA

ISBN: (数字)9798331530143

ISBN: (纸本)9798331530150

Physiological markers of stress and neuromodulation (e.g., heart rate variability) are often inconsistent when it comes to quantifying changes in autonomic nervous system function. This inconsistency is explained by the autonomic nervous system's output varying across organ systems, as well as limitations in what each marker quantifies. In this work, we present an unsupervised learning approach we term StressFADS: Stress Factor Analysis via Dynamical Systems. StressFADS overcomes single marker inconsistencies by learning underlying dynamics that are shared across physiological markers of stress. StressFADS's encoder summarizes a time window of physiological markers and initializes a recurrent neural network (RNN) with this summary. This RNN is autonomously simulated forward in time, and the output at each timestep is fed through a dimension-ality reduction stage trained to reconstruct the original window of physiological markers. This forces the model to learn latent representations that capture shared dynamics across the markers. We apply StressFADS to the analysis of approximately 50 hours of 1-Hz cardiovascular and respiratory marker time series from a double-blind, randomized controlled trial (N = 26) involving trauma recall and active or sham cervical transcutaneous vagus nerve stimulation (tVNS). We find that StressFADS learned latent factors that successfully quantify differences between stress induced by trauma recall, a neutral condition, and active or sham tVNS. This is promising and motivates future work in learning latent autonomic states that more faithfully track changes in stress and intervention effects for just-in-time stress mitigation.

关键词： Recurrent neural networks Prevention and mitigation Autonomic nervous system Time series analysis Dynamics Feedback control Neuromodulation Heart rate variability Stress Unsupervised learning

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：