检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Moreno-Cartagena, Daniel Cabrera-Vives, Guillermo Protopapas, Pavlos Donoso-Oliva, Cristobal Pérez-Carrasco, Manuel Cádiz-Leyton, Martina Department of Computer Science Universidad de Concepción Chile Data Science Unit Universidad de Concepción Edmundo Larenas 310 Concepción Chile Chile Chile John A. Paulson School of Engineering and Applied Science Harvard University CambridgeMA02138 United States

We conducted empirical experiments to assess the transferability of a light curve transformer to datasets with different cadences and magnitude distributions using various positional encodings (PEs). We proposed a new approach to incorporate the temporal information directly to the output of the last attention layer. Our results indicated that using trainable PEs lead to significant improvements in the transformer performances and training times. Our proposed PE on attention can be trained faster than the traditional non-trainable PE transformer while achieving competitive results when transfered to other datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Advanced Deep Learning Models for Groundwater Contaminant Dynamics at the Savannah River Site

Advanced Deep Learning Models for Groundwater Contaminant Dy...

引用

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

作者： Jayesh Soni Himanshu Upadhyay Haruko Wainwright Zexuan Xu Leonel Lagos Applied Research Center Florida International University Miami USA Electrical and Computer Engineering Florida International University Miami USA Nuclear Science and Engineering Massachusetts Institute of Technology Cambridge USA Climate Dept Lawrence Berkeley National Laboratory Berkeley USA Moss Department Of Construction Management Florida International University Miami USA

ISBN: (数字)9798350391213

ISBN: (纸本)9798350391220

Advances in sensor technology have greatly enhanced the monitoring and assessment of environmental conditions. However, groundwater monitoring presents unique challenges, primarily in accurately detecting anomalies amidst sensor noise, fluctuations, and other inconsistencies in the data. The introduction of low-cost in-situ sensors has dramatically increased data volumes, requiring more advanced analytical techniques. This paper investigates the potential of Artificial Intelligence and Machine Learning (AI/ML), specifically Long Short-Term Memory (LSTM) Autoencoder models and Transformers, to tackle these challenges. LSTM Autoencoders, a specialized form of recurrent neural networks, are well-suited for sequential data analysis and anomaly detection, particularly in time-based sensor readings. The LSTM Autoencoder can compress the data and reconstruct normal patterns by training on historical sensor data representing normal groundwater conditions, thus identifying deviations that signal potential contamination. Meanwhile, transformer models, known for their attention mechanism and ability to capture long-range dependencies, are incorporated to enhance further their ability to distinguish between natural data variations and significant anomalies in complex, dynamic groundwater environments. We apply these LSTM Autoencoder and Transformer approaches to US-DoE Savannah River Site F-Area datasets, demonstrating their robustness and adaptability in identifying subtle and progressive groundwater contamination. This approach improves the accuracy of groundwater monitoring and supports a proactive stance in environmental preservation and public health protection.

关键词： Attention mechanisms Groundwater Autoencoders Transformers Data models Rivers Public healthcare Protection Long short term memory Contamination

来源：评论

学校读者我要写书评

暂无评论

Fundamentals of Clustered Molecular Nanonetworks

arXiv

引用

arXiv 2022年

作者： Azimi-Abarghouyi, Seyed Mohammad Dhillon, Harpreet S. Tassiulas, Leandros The School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Wireless@VT Bradley Department of Electrical and Computer Engineering Virginia Tech BlacksburgVA United States The School of Engineering & Applied Science The Yale Institute for Network Science Yale University New HavenCT United States

We present a comprehensive approach to the modeling, performance analysis, and design of clustered molecular nanonetworks in which nano-machines of different clusters release an appropriate number of molecules to transmit their sensed information to their respective fusion centers. The fusion centers decode this information by counting the number of molecules received in the given time slot. Owing to the propagation properties of the biological media, this setup suffers from both inter- and intra-cluster interference that needs to be carefully modeled. To facilitate rigorous analysis, we first develop a novel spatial model for this setup by modeling nanomachines as a Poisson cluster process with the fusion centers forming its parent point process. For this setup, we first derive a new set of distance distributions in the three-dimensional space, resulting in a remarkably simple result for the special case of the Thomas cluster process. Using this, total interference from previous symbols and different clusters is characterized and its expected value and Laplace transform are obtained. The error probability of a simple detector suitable for biological applications is analyzed, and approximate and upper-bound results are provided. The impact of different parameters on the performance is also investigated. © 2022, CC0.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

Bounds on the ground state energy of quantum p-spin Hamiltonians

arXiv

引用

arXiv 2024年

作者： Anschuetz, Eric R. Gamarnik, David Kiani, Bobak T. Institute for Quantum Information and Matter Caltech Walter Burke Institute for Theoretical Physics Caltech MIT Center for Theoretical Physics MIT United States Operations Research Center Statistics and Data Science Center Sloan School of Management MIT United States John A. Paulson School of Engineering and Applied Sciences Department of Electrical Engineering and Computer Science MIT Harvard United States

We consider the problem of estimating the ground state energy of quantum p-local spin glass random Hamiltonians, the quantum analogues of widely studied classical spin glass models. Our main result shows that the maximum energy achievable by product states has a well-defined limit (for even p) as n → ∞ and is Eproduct∗ = √2 log p in the limit of large p. This value is interpreted as the maximal energy of a much simpler so-called Random Energy Model, widely studied in the setting of classical spin glasses. The proof of the limit existing follows from an extension of Fekete’s Lemma after we demonstrate near super-additivity of the (normalized) quenched free energy. The proof of the value follows from a second moment method on the number of states achieving a given energy when restricting to an ǫ-net of product states. Furthermore, we relate the maximal energy achieved over all states to a p-dependent constant γ (p), which is defined by the degree of violation of a certain asymptotic independence ansatz over graph matchings. We show that the maximal energy achieved by all states E∗ (p) in the limit of large n is at most pγ (p)Eproduct∗ . We also prove using Lindeberg’s interpolation method that the limiting E∗ (p) is robust with respect to the choice of the randomness and, for instance, also applies to the case of sparse random Hamiltonians. This robustness in the randomness extends to a wide range of random Hamiltonian models including SYK and random quantum max-cut. Copyright © 2024, The Authors. All rights reserved.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

Efficient Task Offloading in NOMA-assisted Vehicular Fog Computing for Customer Applications

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Aslam, Muhammad Kashif Javed, Muhammad Awais Srivastava, Gautam Ranjha, Ali Alvi, Ahmad Naseem Ali, Bakhtiar Mirza, Jawad Department of Electrical and Computer Engineering Islamabad45550 Pakistan Brandon University Department of Math and Computer Science BrandonMBR7A 6A9 Canada China Medical University Research Centre for Interneural Computing Taichung40402 Taiwan Chitkara University Institute of Engineering and Technology Chitkara University Centre for Research Impact and Outcome Punjab Rajpura140401 India École de Technologie Supérieure MontréalQCH3C 1K3 Canada

Future Fog computing networks are basis of many smart customer applications in the areas of transportation and healthcare. Timely execution of application related tasks is a key challenge in such fog computing networks so that application reliability and customer satisfaction can be maximized. In this paper, we focus on vehicular fog computing scenario and utilize Non-Orthogonal Multiple Access (NOMA) to improve the spectral efficiency of task transmission from vehicles to fog nodes. To tackle the NOMA pairing problem, we propose a Hungarian-based algorithm to minimize the task computational delay. We consider multiple factors such as task priority, vehicle to fog node transmission rate and current load at the fog nodes to optimize the pairing of vehicles for task transmission. For multi-criteria decision making, we utilize Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) to evaluate the ranking scores that are used in the Hungarian algorithm. Realistic simulation results for the proposed technique shows improved task computational delay for high priority tasks as compared to other techniques in the literature. © 2024 IEEE.

关键词： Fog computing NOMA Task offloading Vehicular Networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid Time-Frequency Domain Analysis for Cardiovascular Disease Forecasting Over ECG Data 1st

Hybrid Time-Frequency Domain Analysis for Cardiovascular Dis...

引用

1st International Conference on Advanced Network Technologies and Computational Intelligence, ICANTCI 2024

作者： Zaidi, Abdelhamid Byeon, Haewon Keshta, Ismail Soni, Mukesh Kumar, K. Keshav Garg, Ansh Department of Mathematics College of Science Qassim University P.O.Box 6644 Buraydah51452 Saudi Arabia Department of Digital Anti-Aging Healthcare Inje University Gimhae Korea Republic of Computer Science and Information Systems Department College of Applied Sciences AlMaarefa University Riyadh Saudi Arabia Dr. D. Y. Patil School of Science and Technology Tathawade Pune India College Telangana Hyderabad500 104 India Institute of Engineering and Technology Chitkara University Chitkara University Punjab India

ISBN: (纸本)9783031860683

Due to the few data samples available for computer-aided systems, arrhythmia, a common cardiovascular ailment, creates hurdles for accurate identification. This paper presents a unique methodology for feature extraction in arrhythmia classification that uses a hybrid time-frequency domain analysis within a Convolutional Neural Network (CNN) architecture. The suggested method combines temporal information from RR intervals, frequency-domain information from the Hilbert-Huang transformation, and combined time-frequency information from the continuous wavelet transformation. Following that, a CNN is trained with Focal Loss as the designated loss function. The approach has been carefully tested and verified on an arrhythmia database, proving its ability to classify four unique types of electrocardiogram (ECG) data. Empirical results show that the proposed hybrid time-frequency domain feature extraction method outperforms current classification methodologies in terms of accuracy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Hilbert-Huang transform

来源：评论

学校读者我要写书评

暂无评论

Rapid Energy Consumption Modelling for CNC Based Milling Process

引用

Procedia CIRP 2024年 130卷 1764-1769页

作者： Wen-Tse Hsu Pang-Hsiang Hung Bing-He Chou Po-Han Chen Shang-Yu Lin Tay-Jyi Lin Yuh-Chung Hu Pei-Zen Chang Wei-Chang Li Institute of Applied Mechanics National Taiwan University No. 1 Sec 4 Roosevelt Rd. Taipei 106319 Taiwan Computer Science and Information Engineering National Chung Cheng University 168 University Rd. Chiayi 621301 Taiwan Department of Mechanical and Electro-Mechanical Engineering National Ilan University No. 1 Sec. 1 Shen-Lung Rd. Yilan 260 Taiwan

This study introduces a methodology for rapidly establishing an energy consumption model based on NC code for CNC milling operations. The approach significantly reduces the time needed to gather training and validation data through two key techniques: (1) magnetic voltage sensors, facilitating direct installation onto electrical joints within the electrical box without the need for modifications to the machine tool electricity, and (2) a greatly reduced amount of cutting experiments required for collecting the training data based on a modified Taguchi method. The power consumption measurements are divided into two parts: (1) experiments conducted at varying spindle speeds and feed rates without cutting, and (2) cutting experiments conducted at varying spindle speeds, feed rates, depth of cut, and width of cut. The combinations of cutting parameters are significantly reduced based on the nature of the dependency of the parameters to the energy consumption, and using the Taguchi method and the cross-validation approach. The overall time required for obtaining the power consumption model is around 30 minutes, including 15 minutes estimated for electrical sensors installation. The methodology is applied to 10 distinct machine tools, demonstrating the versatility and applicability of the modeling process across diverse machining environments. The achieved error rate of up to 3.98% underscores the efficacy of this approach. Furthermore, the energy consumption data gleaned from these 10 machine tools are made readily available for open-source utilization, fostering accessibility and collaborative research in energy-efficient CNC milling processes.

关键词： CNC milling CNC machining energy model cutting power consumption power consumption model

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Evaluation of Driver Drowsiness Identification System using Camera based Improved Deep Learning Methodology

A Comprehensive Evaluation of Driver Drowsiness Identificati...

引用

International Conference on Smart Structures and Systems (ICSSS)

作者： P. Malathi Sivakami Sundari M S. Karkuzhali Umamaheswari. B A Thenmozhi Velu Aiyyasamy Department of Data Analytics Saveetha College of Liberal Arts and Sciences SIMATS Chennai Tamil Nadu India Department of Mathematics Agni College of Technology OMR Chennai Chennai Tamil Nadu India Department of General Engineering R.M.K. Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering Kings Engineering College Chennai Tamil Nadu India Department of M.E.- Applied Electronics Meenakshi Sundararajan Engineering College Chennai Tamil Nadu India

Particularly on highways, drowsy driving causes a large number of collisions while driving. With the goal to identify driver sleepiness while enhancing roadway security, it is now vital to grasp the situation and take early remedial steps. Using a proposed Image based Learning Strategy for Drowsiness Identification (ILSDI) and cross-validation with the conventional model called Convolutional Neural Network (CNN), the suggested framework offers an approach to assess the degree of fatigue among drivers according to modifications in a driver eyeballs motion. This will assist in deal with the problem concerning roadway protection. In addition, four types of expressions on the face were identified and categorized—open, closed, blinking, and no gazing using ILSDI and CNN models, indicating levels of tiredness. Finding, following, and analyzing the driver’s face and eyes in real-time to calculate a sleepiness index is the goal of this technology, which operates in different lighting circumstances. Avoiding these kinds of accidents is possible with the help of a driver sleepiness monitoring structure, which uses a digital camera and accompanying software to measure the rate of blinking as well as the dimension of the driver’s eyes. The driver sleepiness recognition system can identify when the driver is getting sleepy and sound an alarm if necessary. It is based on an offline implementation of a deep learning algorithm that uses ILSDI and CNN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Morpho-Mechanical Analysis of Porcine Growth Plate Tissue Mechanics Under Torsional Shear

SSRN

引用

SSRN 2024年

作者： Hucke, Lucie Quelhas Teixeira, Graciosa Seitz, Andreas Martin Gámez, Antonio Huß, Armin Hammer, Niels Wittek, Andreas Niestrawska, Justyna A. Personalized Biomedical Engineering Laboratory Department 2: Computer Science and Engineering Frankfurt University of Applied Sciences Frankfurt Germany Department of Mechanical Engineering and Industrial Design School of Engineering Universidad de Cádiz Cádiz Spain Division of Macroscopic and Clinical Anatomy Gottfried Schatz Research Center Medical University of Graz Graz Austria Institute of Orthopedic Research and Biomechanics Ulm University Medical Centre Ulm Germany Department of Orthopaedic and Trauma Surgery University of Leipzig Leipzig Germany Fraunhofer IWU Dresden Germany

This study aimed to investigate the microstructural and mechanical properties of growth plate tissue under torsional loading, focusing on variations across individuals, growth plate types, and anatomical locations.A total of 398 samples from three distinct growth plates in five porcine subjects were subjected to cyclic torsion tests followed by ultimate failure testing. Additionally, histological analyses were performed using Movat's pentachrome staining to assess tissue *** testing revealed significant differences in shear moduli across growth plate types;notably, the proximal femur exhibited a higher primary shear modulus compared to both the distal femur and proximal tibia. Correlation analyses showed a negative relationship between hypertrophic zone thickness and primary shear modulus (rho = -0.49 at 0.5 °/s, p © 2024, The Authors. All rights reserved.

关键词： Shear strain

来源：评论

学校读者我要写书评

暂无评论

The classification of stages of epiretinal membrane using convolutional neural network on optical coherence tomography image

引用

Methods (San Diego, Calif.) 2023年 214卷 28-34页

作者： Che-Lun Hung Keng-Hung Lin Yu-Kai Lee Dariusz Mrozek Yin-Te Tsai Chun-Hsien Lin Institute of Biomedical Informatics National Yang Ming Chiao Tung University Taiwan ROC Computer Science and Communication Engineering Providence University Taiwan ROC. Electronic address: clhung@nycu.edu.tw. Department of Ophthalmology Taichung Veterans General Hospital Taiwan ROC. Electronic address: linkh@vghtc.gov.tw. Department of Computer Science and Information Engineering Providence University Taiwan ROC. Electronic address: s1091906@gm.pu.edu.tw. Department of Applied Informatics Silesian University of Technology Poland. Electronic address: dariusz.mrozek@polsl.pl. Computer Science and Communication Engineering Providence University Taiwan ROC. Electronic address: yttsai@pu.edu.tw. Department of Ophthalmology Taichung Veterans General Hospital Taiwan ROC. Electronic address: linchunhsien@vghtc.gov.tw.

BACKGROUND AND OBJECTIVE:The gold standard for diagnosing epiretinal membranes is to observe the surface of the internal limiting membrane on optical coherence tomography images. The stages of the epiretinal membrane are used to decide the condition of the health of the membrane. The stages are not detected because some of them are similar. To accurately classify the stages, a deep-learning technology can be used to improve the classification accuracy. METHODS:A combinatorial fusion with multiple convolutional neural networks (CNN) algorithms are proposed to enhance the accuracy of a single image classification model. The proposed method was trained using a dataset of 1947 optical coherence tomography images diagnosed with the epiretinal membrane at the Taichung Veterans General Hospital in Taiwan. The images consisted of 4 stages; stages 1, 2, 3, and 4. RESULTS:The overall accuracy of the classification was 84%. The combination of five and six CNN models achieves the highest testing accuracy (85%) among other combinations, respectively. Any combination with a different number of CNN models outperforms any single CNN algorithm working alone. Meanwhile, the accuracy of the proposed method is better than ophthalmologists with years of clinical experience. CONCLUSIONS:We have developed an efficient epiretinal membrane classification method by using combinatorial fusion with CNN models on optical coherence tomography images. The proposed method can be used for screening purposes to facilitate ophthalmologists making the correct diagnoses in general medical practice.

关键词： Classification Combintorial Fusion Convolutional Neural Network Epiretinal Membrane Optical Coherence Tomography

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：