检索结果-内蒙古大学图书馆

Disruptive Technologies (ICDT), International Conference on

作者： Gautam Jaiswal Aryan Uttam Devesh Dhar Dubey Pawan Kumar Mall Applied Computer Science and Engineering G.L. Bajaj Institute of Technology and Management Greater Noida

The Resume Analyser is a streamlit-based web app that is used to analyse resumes which are in PDF format to extract information from it using different NLP techniques. We have proposed a hybrid system which includes BERT for Name entity recognition and NLP pipeline to streamline the workflow. Our hybrid system excels in extracting key information from the resumes which include skills, experiences, and qualifications etc. This enables a more state of the art performance, achieving higher accuracy and faster execution time. SP ACY's advanced linguistic features empower the system to discern not only the explicit qualifications but also the implicit nuances that playa crucial role in candidate-job alignment. It returns a resume score based on the presence of key elements such as a Declaration, qualifications, Experience etc. It also suggests jobs and internships based on the analysis of the resume and also helps in filtering resumes. This analyzer reduces the need for people to manually check their resumes. This analyzer works using natural language processing and text mining to deduce information from the resume. Finally, we were able to create such a hybrid model whose efficiency was approximately 95% and was able to perform its job on many different structures of resumes very efficiently.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CNN segmentation of skin melanoma in pre-processed dermoscopy images 2

CNN segmentation of skin melanoma in pre-processed dermoscop...

引用

2nd International Conference on Machine Learning and Data Engineering, ICMLDE 2023

作者： Kadry, Seifedine Verdú, Elena Damasevicius, Robertas Abualigah, Laith Singh, Vijendra Rajinikanth, Venkatesan Department of Applied Data Science Noroff University College Kristiansand Norway Ajman University Ajman346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Higher School of Engineering and Technology Universidad Internacional de la Rioja Logroño26006 Spain Department of Applied Informatics Vytautas Magnus University Kaunas53361 Lithuania Computer Science Department Al Al-Bayt University Mafraq25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan MEU Research Unit Middle East University Amman11831 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia School of Computer Science University of Petroleum and Energy Studies Dehradun248007 India Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai602105 India

Using medical data to improve diagnosis accuracy has recently become common practice in hospitals. A modern computing environment has enabled real-time diagnosis of medical data using Convolutional Neural Networks (CNNs). To extract and evaluate skin melanoma recorded with digital dermatoscopy images (DDI), we developed a CNN segmentation framework. In this proposal, four phases are proposed: (i) DDI collection and resizing, (ii) DDI enhancement using pre-processing techniques, (iii) CNN segmentation for lesion extraction, (v) Comparing the extracted sections to the ground truth images, and (v) Verifying whether the framework is valid. Using DDI pre-processed with (i) Traditional procedures, (ii) Otsu's thresholding, (iii) Kapur's thresholding, and (iv) Fuzzy-Tsallis thresholding, this proposal examines the different CNN segmentation schemes presented in the literature. For mining skin lesions, the Moth-Flame Algorithm (MFA) combined with tri-level thresholding achieves an optimal threshold for the DDI. With Fuzzy-Tsallis thresholding images, the VGG-UNet performs better than the alternatives. This framework helps to achieve better values of Jaccard (88.47±2.13%), Dice (93.08±1.17%), and Accuracy (98.64±0.71%) on the chosen DDI database. © 2024 Elsevier B.V.. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

IMAN: An Adaptive Network for Robust NPC Mortality Prediction with Missing Modalities

arXiv

引用

arXiv 2024年

作者： Huo, Yejing Huang, Guoheng Cheng, Lianglun He, Jianbin Chen, Xuhang Yuan, Xiaochen Zhong, Guo Pun, Chi-Man School of Computer Science and Technology Guangdong University of Technology China School of Computer Science and Engineering Huizhou University China Faculty of Applied Sciences Macao Polytechnic University China School of Information Science and Technology Guangdong University of Foreign Studies China Department of Computer and Information Science University of Macau China

Accurate prediction of mortality in nasopharyngeal carcinoma (NPC), a complex malignancy particularly challenging in advanced stages, is crucial for optimizing treatment strategies and improving patient outcomes. However, this predictive process is often compromised by the high-dimensional and heterogeneous nature of NPC-related data, coupled with the pervasive issue of incomplete multi-modal data, manifesting as missing radiological images or incomplete diagnostic reports. Traditional machine learning approaches suffer significant performance degradation when faced with such incomplete data, as they fail to effectively handle the high-dimensionality and intricate correlations across modalities. Even advanced multi-modal learning techniques like Transformers struggle to maintain robust performance in the presence of missing modalities, as they lack specialized mechanisms to adaptively integrate and align the diverse data types, while also capturing nuanced patterns and contextual relationships within the complex NPC data. To address these problem, we introduce IMAN: an adaptive network for robust NPC mortality prediction with missing modalities. IMAN features three integrated modules: the Dynamic Cross-Modal Calibration (DCMC) module employs adaptive, learnable parameters to scale and align medical images and field data;the Spatial-Contextual Attention Integration (SCAI) module enhances traditional Transformers by incorporating positional information within the self-attention mechanism, improving multi-modal feature integration;and the Context-Aware Feature Acquisition (CAFA) module adjusts convolution kernel positions through learnable offsets, allowing for adaptive feature capture across various scales and orientations in medical image modalities. Extensive experiments on our proprietary NPC dataset demonstrate IMAN’s robustness and high predictive accuracy, even with missing data. Compared to existing methods, IMAN consistently outperforms in scenarios with incom

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Time Series of EDFA Pump Currents to Monitor Degeneration Processes using Fuzzy Clustering

Anomaly Detection in Time Series of EDFA Pump Currents to Mo...

引用

Machine Learning for Communication and Networking (ICMLCN), IEEE International Conference on

作者： Dominic Schneider Lutz Rapp Christoph Ament Advanced Technology Adtran Meiningen Germany Faculty of Applied Computer Science University of Augsburg Augsburg Germany

ISBN: (数字)9798350343199

ISBN: (纸本)9798350343205

This article proposes a novel fuzzy clustering based anomaly detection method for pump current time series of EDFA systems. The proposed change detection framework (CDF) strategically combines the advantages of entropy analysis (EA) and principle component analysis (PCA) with fuzzy clustering procedures. In the framework, EA is applied for dynamic selection of features for reduction of the feature space and increase of computational performance. Furthermore, PCA is utilized to extract features from the raw feature space to enable generalization capability of the subsequent fuzzy clustering procedures. Three different fuzzy clustering methods, more precisely the fuzzy clustering algorithm, a probabilistic clustering algorithm and a possibilistic clustering algorithm are evaluated for performance and generalization. Hence, the proposed framework has the innovative feature to detect changes in pump current time series at an early stage for arbitrary points of operation, compared to state-of-the-art predefined alarms in commercially used EDFAs. Moreover, the approach is implemented and tested using experimental data. In addition, the proposed framework enables further approaches of applying decentralized predictive maintenance for optical fiber networks.

关键词： Change detection algorithms Time series analysis Clustering algorithms Erbium-doped fiber amplifiers Feature extraction Prediction algorithms Entropy

来源：评论

学校读者我要写书评

暂无评论

A class of evolutionary history-dependent variational-hemivariational inequalities with strong and weak solutions

引用

SeMA Journal 2024年 1-25页

作者： Migórski, Stanisław Dudek, Sylwia School of Science Southwest Petroleum University Chengdu 610500 China Chair of Optimization and Control Jagiellonian University in Krakow ul. Lojasiewicza 6 Krakow 30348 Poland Department of Applied Mathematics Faculty of Computer Science and Telecommunications Krakow University of Technology ul. Warszawska 24 Krakow 31155 Poland

In this paper we examine the well-posedness of evolutionary variational-hemivariational inequalities involving a constraint set and history-dependent operators. The strong and weak formulations of such inequalities are studied. First, the existence and uniqueness of solutions to both formulations are proved, and results on the dependence of solution on functional parameters are delivered. Next, the well-posedness is established for a general form of history-dependent variational-hemivariational inequalities with constraints by using a fixed point theorem. Finally, the results are applied to a dynamic frictional contact problem in viscoelasticity in which the contact is described by Signorini-type unilateral boundary condition with a nonmonotone Clarke’s relation. © The Author(s) 2024.

关键词： 35K86 49J20 49J53 74M15 Fixed point Frictional contact problem Strong and weak formulations Unilateral constraint Variational-hemivariational inequality

来源：评论

学校读者我要写书评

暂无评论

RUBY - A versatile and customizable social robot

RUBY - A versatile and customizable social robot

引用

IEEE Asia-Pacific Conference on Circuits and Systems

作者： Andreas Kitzig Edwin Naroska Shanq-Jang Ruan Marcus Weberskirch Sinan Yavuz Department of Electrical Engineering and Computer Science Niederrhein University of Applied Sciences Krefeld Germany Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan

ISBN: (数字)9798350378771

ISBN: (纸本)9798350378788

The RUBYDemenz project investigated the effectiveness and optimization of personalized human-robot interaction, which serves as support and relief in the home care of people with dementia. The system, in the form of a puppet interacting with the user via voice, offers a low-threshold and playful integration into everyday life. It was developed by a consortium of various research institutions, companies, and social institutions and was carried out over a period of 42 months. The Niederrhein University of applied sciences developed the technical system of the puppet. The consortium owns the rights, plans, and developed major parts of the software. The development of the system included the construction of the hardware, mechanics, and electronics, the software, and the interfaces to enable numerous functions. The system is versatile, flexibly expandable, and cost-effective, making it ideal for studies with many field deployments. Due to this properties, it can be easily adapted to various application scenarios making it a perfect system platform for social robot research efforts.

关键词： Circuits and systems Social robots Asia Companies Software Hardware Optimization Dementia

来源：评论

学校读者我要写书评

暂无评论

Exploring and Preprocessing of Crunchbase Data for Accurate Startup Success Prediction

Exploring and Preprocessing of Crunchbase Data for Accurate ...

引用

Information and Communication Technologies (ZCICT), Zimbabwe Conference of

作者： Ajai Kumar Misra Dharm Singh Jat Durgesh Kumar Mishra Computer Science Namibia University of Science and Technology Windhoek Namibia SCSIT Symbiosis University of Applied Sciences Indore India

ISBN: (数字)9798331520335

ISBN: (纸本)9798331520342

Startups are the backbone of the country's economy. The growth of startups is supporting the country by providing jobs and also directly generating revenue for the government. On the other hand, the failure of startups is impacting the economy's growth. Therefore, we need to explore and study the factors of startup success and failure. However, there is very fewer source of information about the startup's activity available openly, but the databases like Crunchbase are collecting and providing data about the startups for conducting study. In this paper, we are focusing on Crunchbase data for exploring the essential facts and attributes which are significantly contributing to startup success and failure. Additionally, we also proposed a machine learning model to accurately predict startup success and failure by utilizing the concluded attributes. The aim of the proposed model is to identify how the funding influences the operational status of the company. Thus, the Crunchbase dataset is considered where 66368 companies' data are used for evaluation and experiment. According to the conducted experiments we have found that venture capital financing is the main source of getting funds, 63.99% of companies are able to secure only the first round of funding, and less than 1 % of companies are able to get funding more than 10 times. The combination of the proposed preprocessing technique and learning algorithms provides highly accurate results and is able to predict 80% success and failure.

关键词： Hands Accuracy Machine learning algorithms Supervised learning Companies Machine learning Venture capital Predictive models Prediction algorithms Information and communication technology

来源：评论

学校读者我要写书评

暂无评论

qgym: A Gym for Training and Benchmarking RL-Based Quantum Compilation 4

qgym: A Gym for Training and Benchmarking RL-Based Quantum C...

引用

4th IEEE International Conference on Quantum Computing and Engineering, QCE 2023

作者： Van Der Linde, Stan De Kok, Willem Bontekoe, Tariq Feld, Sebastian Applied Cryptography & Quantum Algorithms The Hague Netherlands Bernoulli Institute University of Groningen Faculty of Science and Engineering Groningen Netherlands QuTech Delft University of Technology Quantum & Computer Engineering Delft Netherlands

ISBN: (纸本)9798350343236

Compiling a quantum circuit for specific quantum hardware is a challenging task. Moreover, current quantum computers have severe hardware limitations. To make the most use of the limited resources, the compilation process should be optimized. To improve currents methods, Reinforcement Learning (RL), a technique in which an agent interacts with an environment to learn complex policies to attain a specific goal, can be used. In this work, we present qgym, a software framework derived from the OpenAI gym, together with environments that are specifically tailored towards quantum compilation. The goal of qgym is to connect the research fields of Artificial Intelligence (AI) with quantum compilation by abstracting parts of the process that are irrelevant to either domain. It can be used to train and benchmark RL agents and algorithms in highly customizable environments. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Improved 2-Approximation Algorithm for the Rectilinear Steiner Tree Problem with Minimal Number of Steiner Points 4

An Improved 2-Approximation Algorithm for the Rectilinear St...

引用

4th International Conference on applied Mathematics, Modeling and computer Simulation, AMMCS 2024

作者： Li, Jianglin Wang, Wencheng Chen, Yinhua Zhang, Tongquan School of Mathematics and Computer Science Yunnan Minzu University Yuehua Street NO.2929 Yunnan Kunming650504 China School of Applied Technology Yunnan Minzu University Yuehua Street NO.2929 Yunnan Kunming650504 China

ISBN: (纸本)9781643685519

In this paper, we present an improved algorithm for the rectilinear Steiner trees problem with minimal number of Steiner points. Given a set X of n terminal points in the L1 plane and a positive constant L, it is asked to construct a Steiner tree T interconnecting of these n terminal points, with the length of each edge in that tree T is no more than L. It has been proven that this problem is NP-hard and there exists a 2-approximation algorithm in time O(n3). By using the strategies of the sweep-line algorithm and a leaf-deletion technique in a special forest composed of selected edges from a rectilinear minimum spanning tree on X, we propose an effective 2-approximation algorithm in time O(n log n). © 2024 The Authors.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

A segment-wise extraction of multivariate time-series features for Grassmann clustering

A segment-wise extraction of multivariate time-series featur...

引用

2023 International Conference on Electronics, Information, and Communication, ICEIC 2023

作者： Heo, Sebin Nuriye, Bezawit Habtamu Oh, Beomseok Gyeongsang National University Dept. of Applied Life Chemistry Jinju Korea Republic of Gyeongsang National University Dept. of Computer Science Jinju Korea Republic of Seoul National University of Science and Technology Dept. of Applied Artificial Intelligence Seoul Korea Republic of

ISBN: (纸本)9798350320213

In this paper, a novel approach of extracting features from multivariate time-series (MTS) with different time lengths, is proposed to enhance the clustering accuracy. Particularly, the feature extraction is conducted on time-sample segments of MTS, in which several segments are defined without overlapping. As for feature extractor, the conventional two-dimensional principal component analysis (2DPCA) is deployed due to its proven effectiveness in feature representation. Our experimental results show that the proposed segment-wise extraction of 2DPCA features is helpful in enhancing the clustering accuracy. © 2023 IEEE.

关键词： Clustering Feature Extraction Grassmann Manifold Multivariate Time-Series

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：