检索结果-内蒙古大学图书馆

3rd International Conference on Machine Learning and Data Engineering, ICMLDE 2024

作者： Nair, Rekha R Babu, Tina Kishore, S. Vishal, S. Mahapatra, Sheila Department of Computer Science and Engineering Alliance School of Advanced Computing Alliance University Bengaluru India Department of Computer Applications Nitte Deemed to Be University Nitte Institute of Professional Education Karnataka Mangalore India Department of Computer Applications School of Engineering Dayananda Sagar University Bengaluru India Department of Electrical and Electronics Engineering Alliance University Bangalore India

Predicting stock prices continues to be a significant challenge in the financial industry, prompting researchers to investigate various methods to improve accuracy. Hence proposed a novel approach by incorporating astrological and astronomical data into XGBoost models for stock price classification and prediction, utilizing deep neural networks (DNN). The dataset is collected from NASA JPL Horizons and Jaganath Hora software. The raw data is preprocessed with feature engineering, data cleaning, []and normalization to obtain a better forecasting stock prices and classification results. The proposed data executed with machine learning models, such as logistic regression, decision trees, random forest, SVM, XGB Classifier, LSTM, RNN, and CNN other than XGB Regressor for the forcasting. The proposed research is evaluated for classification with accuracy, precision, recall, F1 score, and forecasting with RMSE, MAE, R2, AIC, and BIC. The XGBoost classifier achieved 99% accuracy in predicting stock market movements, surpassing other models in determining whether the next day's stock price would be higher or lower than the previous day's price, while the DNN performed the best among all algorithms for overall stock price prediction. This approach could influence investment strategies, potentially affecting wealth distribution and financial market stability. © 2025 The Authors. Published by Elsevier B.V.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Experiences Porting NAMD to the Data Parallel C++ Programming Model 22

Experiences Porting NAMD to the Data Parallel C++ Programmin...

引用

2022 International Workshop on OpenCL, IWOCL 2022

作者： Hardy, David J Choi, Jaemin Jiang, Wei Tajkhorshid, Emad Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-Champaign UrbanaIL United States Department of Computer Science University of Illinois at Urbana-Champaign UrbanaIL United States Argonne Leadership Computing Facility Argonne National Laboratory LemontIL United States

ISBN: (纸本)9781450396585

HPC applications have a growing need to leverage heterogeneous computing resources with a vendor-neutral programming paradigm. Data Parallel C++ is a programming language based on open standards SYCL, providing a vendor-neutral solution. We describe our experiences porting the NAMD molecular dynamics application with its GPU-offload force kernels to SYCL/DPC++. Results are shown that demonstrate correctness of the porting effort. © 2022 ACM.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Separating Operator Hippopotamus Optimization Algorithm with Support Vector Machine for Optimizing Intrusion Detection in Internet of Things

Separating Operator Hippopotamus Optimization Algorithm with...

引用

Distributed computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： Zainab Alassedi Raheleh Ghadami Srinath Chandramohan R. Vijayarangan C. Umarani Department of Medical Devices Engineering Technologies National University of Science and Technology Dhi Qar Iraq Department of Computer Engineering Istanbul Topkapi University Istanbul Turkey Innovation and Incubation Gnanamani College of Technology Namakkal India Department of Computer Science and Applications Christ Academy Institute for Advanced Studies Bangalore India

ISBN: (数字)9798331533663

ISBN: (纸本)9798331533670

An Intrusion Detection System (IDS) is considered to identify system attacks and distinguish between normal and abnormal activities. Machine Learning (ML) techniques are enabled to IDS which is significant role identifying Intrusions. This research presents the system design of an IDS, minimize false alarm rate and increase accuracy to detect intrusion. However, enhancing volume of network traffic in Internet of Things (IoT) system makes it difficult to detect cyberattacks accurately because of huge number of features which most are redundant led to inefficiencies in detection performance. To overcome these challenges, Separating Operator-Hippopotamus Optimization Algorithm with Support Vector Machine (SOHOA-SVM) is proposed for enhancing attack detection, which eliminates redundant features and improve accuracy level. In preprocessing, numerical data then labeled data used for normalizations. The SOHOA-SVM achieves accuracy of 99.99% and 99.97% for NSL-KDD and TON-IoT when compared to SVM and Grey Wolf Optimization (GWO) and XGBoost + Mutual Information Thresholding.

关键词： Support vector machines Accuracy Intrusion detection Telecommunication traffic Feature extraction NSL-KDD Internet of Things Optimization System analysis and design Mutual information

来源：评论

学校读者我要写书评

暂无评论

Quantum Algorithms for Sampling Log-Concave Distributions and Estimating Normalizing Constants

arXiv

引用

arXiv 2022年

作者： Childs, Andrew M. Li, Tongyang Liu, Jin-Peng Wang, Chunhao Zhang, Ruizhe Joint Center for Quantum Information and Computer Science Department of Computer Science Institute for Advanced Computer Studies University of Maryland United States Center on Frontiers of Computing Studies School of Computer Science Peking University China Simons Institute Department of Mathematics UC Berkeley United States Department of Computer Science and Engineering Pennsylvania State University United States Department of Computer Science The University of Texas Austin United States

Given a convex function f: Rd → R, the problem of sampling from a distribution ∝ e−f (x) is called log-concave sampling. This task has wide applications in machine learning, physics, statistics, etc. In this work, we develop quantum algorithms for sampling log-concave distributions and for estimating their normalizing constants (Equation presented). First, we use underdamped Langevin diffusion to develop quantum algorithms that match the query complexity (in terms of the condition number κ and dimension d) of analogous classical algorithms that use gradient (first-order) queries, even though the quantum algorithms use only evaluation (zeroth-order) queries. For estimating normalizing constants, these algorithms also achieve quadratic speedup in the multiplicative error ∊. Second, we develop quantum Metropolis-adjusted Langevin algorithms with query complexity (Equation presented) and (Equation presented) for log-concave sampling and normalizing constant estimation, respectively, achieving polynomial speedups in κ, d, ∊ over the best known classical algorithms by exploiting quantum analogs of the Monte Carlo method and quantum walks. We also prove a 1/∊1−o(1) quantum lower bound for estimating normalizing constants, implying near-optimality of our quantum algorithms in ǫ. Copyright © 2022, The Authors. All rights reserved.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

A Smart Capacity Enhancement and Estimation Model for Hybrid Buildings by using Light Weight Deep Learning Model

A Smart Capacity Enhancement and Estimation Model for Hybrid...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Senthil Kumar Nageswara Rao Atyam Khadar Nawas K Shashank Awasthi M. Kotteeswaran K. S. Thirunavukkarasu KL School of Architecture Koneru Lakshmanan Education Foundation Guntur Andhra Pradesh India Electrical and Electronics Department CMR Institute of Technology Bengaluru Karnataka India School of Computing Science and Engineering Vellore Institute of Technolog Chennai Tamil Nadu India Department of Computer Science and Engineering GL Bajaj Institute of Technology and Management Greater Noida Uttar Pradesh India School of Management and Commerce Vels Institute of Science Technology and Advanced Studies (VISTAS) Pallavaram Chennai Tamil Nadu India School of Computing Science Vels Institute of Science Technology and Advanced Studies (VISTAS) Pallavaram Chennai Tamil Nadu India

Generally, for the buildings constructed in our areas, the conventional foundation known as 'shallow', i.e. from the ground level downwards, is set up in three dimensions such as length, width and depth. Foundations are not the same for all types of structures. The size and structure of the foundation varies depending on the nature of the prevailing soil, ground water level of the plot, type of building, and total load of the structure. In this paper an innovation estimation model was proposed based on light weigth deep learning technique. The proposed model introduces capacity estimation and energy efficiency plans and designs. These are all relating to commercial buildings, craft facilities and mass housing projects to enable design, construction. It also maintains the buildings under minimum energy consumption without stressing the operation of buildings. The health and comfort of the occupants are establishing compliance standards and ensure the maximum standards for energy efficiency in the plans or designs of commercial buildings. The proposed model also focuses the capacity estimation and energy efficiency programs beyond maximum standards.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ReViT: A Hybrid Approach for BCLC Staging of Hepatocellular Carcinoma Using 3D CT with Multiple Instance Learning

ReViT: A Hybrid Approach for BCLC Staging of Hepatocellular ...

引用

2024 IEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2024

作者： Chang, Shun-Cheng Yu, Hsin-Pei Hsieh, Yi-Hsien Wang, Pochuang Wang, Weichung Su, Tung-Hung Kao, Jia-Horng Lin, Che Taipei10617 Taiwan Department of Computer Science and Information Engineering Ntu Taipei10617 Taiwan Institute of Applied Mathematical Sciences Ntu Taipei10617 Taiwan National Taiwan University Hospital Division of Gastroenterology and Hepatology Department of Internal Medicine Taipei10048 Taiwan Department of Electrical Engineering Ntu Taipei10617 Taiwan Center for Advanced Computing and Imaging in Biomedicine Ntu Taipei10617 Taiwan Smart Medicine and Health Informatics Program Ntu Taipei10617 Taiwan

ISBN: (纸本)9798350351552

Deep learning has revolutionized medical imaging, offering advanced methods for accurate diagnosis and treatment planning. The BCLC staging system is crucial for staging Hepatocellular Carcinoma (HCC), a high-mortality cancer. An automated BCLC staging system could significantly enhance diagnosis and treatment planning efficiency. However, we found that BCLC staging, which is directly related to the size and number of liver tumors, aligns well with the principles of the Multiple Instance Learning (MIL) framework. To effectively achieve this, we proposed a new preprocessing technique called Masked Cropping and Padding(MCP), which addresses the variability in liver volumes and ensures consistent input sizes. This technique preserves the structural integrity of the liver, facilitating more effective learning. Furthermore, we introduced Re ViT, a novel hybrid model that integrates the local feature extraction capabilities of Convolutional Neural Networks (CNNs) with the global context modeling of Vision Transformers (ViTs). Re ViT leverages the strengths of both architectures within the MIL framework, enabling a robust and accurate approach for BCLC staging. We will further explore the trade-off between performance and interpretability by employing TopK Pooling strategies, as our model focuses on the most informative instances within each bag. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Application of BiLSTM-CRF Approach and its Application for Better Decisions in Human Resource Management Processes

Application of BiLSTM-CRF Approach and its Application for B...

引用

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Umanesan, R. Shunmugasundaram, M. Rani, Pushpa Balasubramanian, K. Rakesh, K. Chandel, Pankaj Singh Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Cse Tamil Nadu Chennai India St. Joseph's College of Engineering Department of Management Studies Chennai India Tecnia Institute of Advanced Studies Department of Management Sciences Delhi India Kalasalingam Academy of Research and Education-Deemed to Be University Department of Computer Applications India Malla Reddy Engineering College for Women Department of Ece Telangana India Dev Sanskriti Vishwavidyalaya Department of Tourism Management Haridwar India

ISBN: (纸本)9798350313987

Recent advances in information technology (IT) have had a profound effect on human resources (HR) procedures and practices. Despite this, there is a dearth of research on its effectiveness, and the studies that have been undertaken have not, in general, assessed how well these new technologies aid firms in attaining their HR goals of attracting, motivating, and retaining personnel. Current systems have limitations, such as being one-way, passive, impersonal, limiting opportunities for human connection, and creating too much physical and intellectual barrier between individuals and enterprises. Data preparation, feature extraction, and model training are the first three stages of the suggested procedure. Normalization is a tool used in the preliminary processing of data. PCA is used to extract features and identify the most informative ones. After feature extraction, the models are trained using BiLSTM-CRF. When compared to the two most common alternatives, BiLSTM and CRF, the proposed technique achieves better performance. © 2023 IEEE.

关键词： Bidirectional Long Short Term Memory (BiLSTM) Extreme Learning Machine (ELM) Principal Component Analysis (PCA

来源：评论

学校读者我要写书评

暂无评论

A BCLC Staging System for Hepatocellular Carcinoma using Swin Transformer and CT Imaging 46

A BCLC Staging System for Hepatocellular Carcinoma using Swi...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Chang, Shun-Cheng Wang, Pochuang Wang, Weichung Su, Tung-Hung Kao, Jia-Horng Lin, Che Taipei10617 Taiwan Department of Computer Science and Information Engineering Ntu Taipei10617 Taiwan Institute of Applied Mathematical Sciences Ntu Taipei10617 Taiwan Division of Gastroenterology and Hepatology Department of Internal Medicine National Taiwan University Hospital Taipei10048 Taiwan Department of Electrical Engineering Ntu Taipei10617 Taiwan Center for Advanced Computing and Imaging in Biomedicine Ntu Taipei10617 Taiwan Smart Medicine and Health Informatics Program Ntu Taipei10617 Taiwan

ISBN: (纸本)9798350371499

The Barcelona Clinic Liver Cancer (BCLC) staging system plays a crucial role in clinical planning, offering valuable insights for effectively managing hepatocellular carcinoma. Accurate prediction of BCLC stages can significantly ease the workload on radiologists. However, few datasets are explicitly designed for discerning BCLC stages. Despite the common practice of appending BCLC labels to clinical data within datasets, the inherent imbalance in BCLC distribution is further amplified by the diverse purposes for which datasets are curated. In this study, we aim to develop a BCLC staging system using the advanced Swin Transformer model. Additionally, we explore the integration of two datasets, each originally intended for separate objectives, highlighting the critical challenge of preserving class distribution in practical study designs. This exploration is pivotal for ensuring the applicability of our developed staging system in the designed clinical settings. Our resulting BCLC staging system demonstrates an accuracy of 55.81% (±7.8%), contributing to advancing medical image-based research for predicting BCLC stages. © 2024 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Continuous Bijection Supervised Pyramid Diffeomorphic Deformation for Learning Tooth Meshes From CBCT Images

引用

IEEE Transactions on Multimedia 2025年

作者： Zhang, Zechu Peng, Weilong Wen, Jinyu Tang, Keke Fang, Meie Feng, David Dagan Li, Ping Guangzhou University Metaverse Research Institute School of Computer Science and Cyber Engineering Guangzhou511400 China Guangzhou University Cyberspace Institute of Advanced Technology Guangzhou510006 China The University of Sydney Biomedical and Multimedia Information Technology Research Group School of Computer Science SydneyNSW2006 Australia The Hong Kong Polytechnic University Department of Computing School of Design and Research Institute for Sports Science and Technology Hong Kong Hong Kong

Accurate and high-quality tooth mesh generation from cone-beam computerized tomography (CBCT) is an essential computer-aided technology for digital dentistry. However, existing segmentation-based methods require complicated post-processing and significant manual correction to generate regular tooth meshes. In this paper, we propose a method of continuous bijection supervised pyramid diffeomorphic deformation (PDD) for learning tooth meshes, which could be used to directly generate high-quality tooth meshes from CBCT Images. Overall, we adopt a classic two-stage framework. In the first stage, we devise an enhanced detector to accurately locate and crop every tooth. In the second stage, a PDD network is designed to deform a sphere mesh from low resolution to high one according to pyramid flows based on diffeomorphic mesh deformations, so that the generated mesh approximates the ground truth infinitely and efficiently. To achieve that, a novel continuous bijection distance loss on the diffeomorphic sphere is also designed to supervise the deformation learning, which overcomes the shortcoming of loss based on nearest-neighbour mapping and improves the fitting precision. Experiments show that our method outperforms the state-of-the-art methods in terms of both different evaluation metrics and the geometry quality of reconstructed tooth surfaces. © 1999-2012 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Decision trees for predicting dropout in Engineering Course students in Brazil 9th

Decision trees for predicting dropout in Engineering Course ...

引用

9th International Conference on Information Technology and Quantitative Management, ITQM 2022

作者： Mariano, Ari Melo De Magalhães Lelis Ferreira, Arthur Bandeira Santos, Maíra Rocha Castilho, Mara Lucia Bastos, Anna Carla Freire Luna Campêlo Department of Production Engineering University of Brasília Brazil Department of Computer Science University of Brasilia Brazil Center for Advanced Multidisciplinary Studies University of Brasilia Brazil Federal Institute of Brasilia Brazil Universidade Federal Do sul da Bahia Brazil

The dropout of Brazilian students from higher education is a subject that has been well explored, where high rates of students who drop out are verified. However, despite the vast literature, the problems arising from student's dropout still have no solution since dropout itself is an unsolved problem. This research aims to present a classification via decision trees to predict the evasion of Engineering course students in Brazil. To reach this objective, exploratory field research was conducted, where data was collected employing surveys directed to the students, enabling the elaboration of a classificatory decision tree with the C4.5 algorithm. The survey sample consisted of 91 valid answers. The results were analyzed with the RapidMiner tool and presented a decision tree with 86.81% accuracy. Among the main factors preventing dropout is interaction with professors, the course curriculum, and issues related to mental well-being. © 2022 The Authors. Published by Elsevier B.V.

关键词： Decision trees

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：