检索结果-内蒙古大学图书馆

IEEE International Conference on Data Mining (ICDM)

作者： Yawei Li Zhao Zhang Suiyi Zhao Jicong Fan Haijun Zhang Mingliang Xu School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Kunming China Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China Department of Computer Science Harbin Institute of Technology Shenzhen China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China

Video super-resolution (VSR) on mobile devices aims to restore high-resolution frames from their low-resolution counterparts, satisfying the requirements of performance, FLOPs and latency. On one hand, partial feature processing, as a classic and acknowledged strategy, is developed in current studies to reach an appropriate trade-off between FLOPs and accuracy. However, the splitting of partial feature processing strategy are usually performed in a blind manner, thereby reducing the computational efficiency and performance gains. On the other hand, current methods for mobile platforms primarily treat VSR as an extension of single-image super-resolution to reduce model calculation and inference latency. However, lacking inter-frame information interaction in current methods results in a suboptimal latency and accuracy trade-off. To this end, we propose a novel architecture, termed Feature Aggregating Network with Inter-frame Interaction (FANI), a lightweight yet considering frame-wise correlation VSR network, which could achieve real-time inference while maintaining superior performance. Our FANI accepts adjacent multi-frame low-resolution images as input and generally consists of several fully-connection-embedded modules, i.e., Multi-stage Partial Feature Distillation (MPFD) for capturing multi-level feature representations. Moreover, considering the importance of inter-frame alignment, we further employ a tiny Attention-based Frame Alignment (AFA) module to promote inter-frame information flow and aggregation efficiently. Extensive experiments on the well-known dataset and real-world mobile device demonstrate the superiority of our proposed FANI, which means that our FANI could be well adapted to mobile devices and produce visually pleasing results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Empirical Analysis on Productivity Prediction and Locality for Use Case Points Method

arXiv

引用

arXiv 2021年

作者： Azzeh, Mohammad Nassif, Ali Bou Martín, Cuauhtémoc López Department of Software Engineering Applied Science Private University Jordan Department of Computer Engineering University of Sharjah UAE United Arab Emirates Department of Information Systems Universidad de Guadalajara ZapopanJalisco Mexico

Use Case Points (UCP) method has been around for over two decades. Although, there was a substantial criticism concerning the algebraic construction and factors assessment of UCP, it remains an efficient early size estimation method. Predicting software effort from UCP is still an ever-present challenge. The earlier version of UCP method suggested using productivity as a cost driver, where fixed or a few pre-defined productivity ratios have been widely agreed. While this approach was successful when no enough historical data is available, it is no longer acceptable because software projects are different in terms of development aspects. Therefore, it is better to understand the relationship between productivity and other UCP variables. This paper examines the impact of data locality approaches on productivity and effort prediction from multiple UCP variables. The environmental factors are used as partitioning factors to produce local homogeneous data either based on their influential levels or using clustering algorithms. Different machine learning methods, including solo and ensemble methods, are used to construct productivity and effort prediction models based on the local data. The results demonstrate that the prediction models that are created based on local data surpass models that use entire data. Also, the results show that conforming the hypothetical assumption between productivity and environmental factors is not necessarily a requirement for success of locality. © 2021, CC BY.

关键词： Productivity

来源：评论

学校读者我要写书评

暂无评论

Pl-Densenet: Enhancing Disease Classification in Pear Leaves Using Deep Learning

SSRN

引用

SSRN 2023年

作者： Gulzar, Yonis Ünal, Zeynep Ayoub, Shahnawaz Wani, Sharyar Mir, Mohammad Shuaib Soomro, Arjumand Bano Department of Management Information Systems College of Business Administration King Faisal University Al-Ahsa31982 Saudi Arabia Department of Biosystem Engineering Niğde Ömer Halisdemir University Central Campus Türkiye Niğde51240 Turkey Mirzapur Pole U.P. Saharanpur247121 India Department of Computer Science Kulliyyah of Information and Communication Technology International Islamic University Malaysia Kuala Lumpur53100 Malaysia Department of Software Engineering Faculty of Engineering and Technology University of Sindh Sindh Pakistan

Over the past two decades, climate changes have negatively impacted agriculture. It hasn’t left any stage of production unaffected. These noticeable changes have left formers no choice but to adopt new technological measures to tackle such changes. Deep learning has played a great role in improving decision-making in agriculture. This research introduces a novel deep learning model, PL-DenseNet, designed to accurately identify various disease types present in pear leaves. The PL-DenseNet model is an adaptation of the original DenseNet architecture, incorporating significant modifications to enhance its disease classification capabilities. The modifications involve replacing the classification layer of the DenseNet with three additional layers: Global Average Pooling 2D, Batch Normalization, and Dropout layers. Moreover, the final layer of the PL-DenseNet model comprises four nodes dedicated to classifying pear leaf diseases. The integration of these modifications aims to improve disease identification accuracy and enhance overall classification performance within the context of pear leaf diseases. The PL-DenseNet model also incorporated transfer learning and data augmentation to increase the variety and quantity of training data. The model's performance was evaluated on the DiaMOS Plant dataset, which comprises four different pear leaf diseases under real field conditions with varying brightness, disease similarity, complex background, and multiple leaves. Experimental evaluation reveals that the proposed PL-DenseNet model achieves notable advancements compared to the baseline model. It demonstrates higher accuracy (99.18%), precision (98.83), recall (99.06), and F1-score (93.58). Additionally, the proposed model surpasses other state-of-the-art models, including EfficientNetB0, InceptionV2, MobileNetV2, ResNet50, and VGG16, underscoring its superior performance in disease classification. Moreover, this research demonstrates how transfer learning and data augmentati

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Systematic Literature Review on Agile, Cloud, and Devops Integration: Challenges, Benefits

SSRN

引用

SSRN 2024年

作者： El Aouni, Fatiha Moumane, Karima Idri, Ali Najib, Mehdi Jan, Saeed Ullah Software Project Management Research Team National School of Computer Science and Systems Analysis Mohammed V University in Rabat Rabat10112 Morocco MSDA University Mohamed VI Polytechnic Ben Guerir Morocco TICLab College of Engineering and Architecture International University of Rabat Sala Al Jadida Morocco Higher Education Department Govt Degree College Wari Dir Upper 18200 Pakistan

Context : In today’s fast-paced digital landscape, integrating DevOps, cloud, and agile methodologies is crucial for meeting software demands. However, this integration remains *** : This study explores the integration of Agile, Cloud, and DevOps in today’s software development landscape. It aims to analyze the challenges and benefits associated with merging these three approaches, focusing on its impact on software testing and the role of mindset in successful implementation and identifying the most suitable Agile *** : This investigation utilizes a Systematic Literature Review(SLR) to enrich comprehension of these integrations in current software development *** : The analysis of 31 articles highlights benefits such as improved collaboration and accelerated development, despite challenges with tool proliferation. Platforms like Jenkins, GitLab, Kubernetes, and Docker show promise in addressing these complexities. Our study examines the advantages and challenges of this integration, focusing on its impact on software testing and the role of mindset in successful implementation and identifyingthe most suitable Agile *** : The integration of Agile, DevOps, and Cloud signifies a vital move towards collaborative, scalable, and automated methods, crucial for swift delivery, enhanced quality, and ongoing competitiveness. This unified approach is fundamental for organizational advancement and innovation in the ever-evolving software development realm. Further research should tackle challenges in merging these methods and delve into their interactions with emerging technologies to refine practices for increased efficiency. © 2024, The Authors. All rights reserved.

关键词： Integration

来源：评论

学校读者我要写书评

暂无评论

Learning assistant to acquire the fundamental language skills for non-native learners using AI 2

Learning assistant to acquire the fundamental language skill...

引用

2nd International Conference on Advancements in Computing, ICAC 2020

作者： Srikanthan, Praveenkumar Nizar, Roshan Ravikumar, Abishaan Lalitharan, Keerthigan Harshanath, S.M.B. Alosius, Jesuthasan Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer Systems Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka

ISBN: (纸本)9781728184128

The ability to speak and learn a language properly requires good practice, experience and good learning strategies but the existing solutions do not provide proper guidance to learn a language with instant feedback. This research is an approach to devise an improved language learning assistant with practices that will help to improve the fundamental language skills for non-native learners and children who are in the early stage of their education. The four main skills focused on this application will be conversation, pronunciation, listening and grammatical skills. The implementation of this research is done by using technologies like natural language processing, machine learning, and deep learning approaches to come up with components to train the learner. The solution of this research is delivered by using a cross-platform application called GLIB which facilities to improve all the English language skills mentioned above along with guides, tips, practices, and feedback based on an evaluation to improve the English language. © 2020 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Optimizations of friction stir welding process parameters of AA6063 Aluminium alloy by Taguchi technique

引用

Materials Today: Proceedings 2021年 46卷 4008-4013页

作者： K. Umanath K. Palanikumar Veeramalai Sankaradass K. Uma Department of Mechanical Engineering Academy of Maritime Education and Training AMET University Chennai 603112 India Sri Sairam Institute of Technology Chennai 600044 India Department of Computer Science and Engineering ISL Engineering College Hyderabad Telangana 500005 India Department of Software and Systems Engineering School of Information Technology and Engineering VIT University Vellore 632014 India

The effects of axial force, rotational speed, welding speed, and shoulder penetration on various Process parameters of Aluminium alloy 6063 butt joint produced by Friction Stir Welding have been analyzed. The mechanical properties like tensile strength , Yield strength, and % Elongation have been tested using a 6 mm thickness plate. The tool used for experimenting was Hot Die Steel (HDS). The welding quality can be improved by enhancing the mechanical properties and minimizing the defects. Hence, analyzing & examining the mechanical or physical properties and other relevant significant factors would enhance the weldability . Tensile Strength (T.S.), Percentage of Elongation & Yield Strength (Y.S.) of FSW Al 6063 alloy has been carried out under different processing conditions using Taguchi's experimental design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A performance comparison of graph analytic methods for supporting enterprise architecture model maintenance

A performance comparison of graph analytic methods for suppo...

引用

2019 Practice of Enterprise Modelling Conference Forum, PoEM 2019 Forum

作者： Rajashekar, Nikhitha Hacks, Simon Silva, Nuno Research Group Software Construction RWTH Aachen University Germany Division of Network and Systems Engineering KTH Royal Institute of Technology Sweden Department of Computer Science and Engineering Technical University of Lisbon Lisbon Portugal

Enterprise Architecture (EA) models help enterprise architects to make business decisions and to support organisations to understand and analyse its structure. Creating and maintaining such an EA model is expensive and time-consuming in large organisations. In this paper, the authors provide a review of how graph analytic methods can be used to support EA model maintenance. To achieve the best results for the duplicate identification, it is necessary to evaluate and optimise different graph analytic and Machine Learning (ML) algorithms to support the maintenance process. Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Reinforcement-Learning Based Method for Accelerating Functional Coverage Closure of Traffic Light Controller Dynamic Digital Design

Reinforcement-Learning Based Method for Accelerating Functio...

引用

International Conference on computer Theory and Applications (ICCTA)

作者： Youstina M. Halim Khaled A. Ismail Mohamed A. Abd El Ghany Sameh A. Ibrahim Youssef M. Halim Mixel Egypt. Electronics and Communications Engineering Dept. Faculty of Engineering Ain Shams University Cairo Egypt GSI Helmholtz Center for Heavy-Ion Research GmbH (GSI) Germany Electronics Department German University in Cairo Egypt. Integrated Electronic Systems Lab TU Darmstadt Germany Electronics and Communications Engineering Department Faculty of Engineering Ain Shams University Cairo Egypt Computer Engineering and Software Systems Dept. Faculty of Engineering Ain Shams University Cairo Egypt

Functional verification of digital designs is an increasingly complex and time-consuming endeavor. One of the major challenges in functional verification is achieving functional coverage closure in a timely manner. Verification experts have moved from using directed stimulus, towards constrained random stimulus and finally, towards using machine learning to direct stimulus. In this work, reinforcement learning (RL) was used, incorporating three different kinds of RL agents to direct stimulus generation for a traffic light controller system. Two of the agents are based on Q-learning (DQN and SARSA), and one is based on Monte-Carlo method (CEM). The maximum reduction in simulation time needed to achieve a targeted percent of coverage was 97%. The average reduction of simulation time across all testcases and agents used was 70%. The solution is highly reusable, the architecture was integrated with different agents and testcases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimization of wear properties on AA7075/Sic/Mos 2 hybrid metal matrix composite by response surface methodology

引用

Materials Today: Proceedings 2021年 46卷 4019-4024页

作者： K. Umanath K. Palanikumar Veeramalai Sankaradass K. Uma Deaprtment of Mechanical Engineering Acadamy of Maritime Education and Training Chennai 603112 India Sri SairamInstitute of Technology Chennai 600044 India Department of Computer Science and Engineering ISL Engineering College Hyderabad Telangana 500005 India Department of Software and Systems Engineering School of Information Technology and Engineering VIT University Vellore 632014 India

Nowadays, composites are profoundly thriving as the replacement of ferrous alloys . The Aluminum manifested into a great substitute due to its properties like lightweight, low density, high strength, and corrosion resistance . The process of fusing the non-ceramics reinforcement like Silicon carbide , Boron carbide , Aluminum oxide , Titanium diboride with a non-metal like Graphite, Molybdenum disulfide or with other non-ceramic to form a hybrid metal matrix composite . In the present paper, an investigation carried out on Aluminum 7075 material by the process of stir casting where the Silicon Carbide (SiC) with three different weight % (i.e., 3%, 6%, 9%) and Molybdenum Disulphide (MoS 2 ) with 1% constant weight % added to the base material. The tensile test and hardness test were then done on a UTM and Rockwell Hardness testing machine, respectively, for all three prepared materials. As the percentage of SiC increases in the material, the hardness value and tensile strength are increasing. The Al7075 + 9%SiC + 1%MoS 2 is the highest of all.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Subsentence extraction from text using coverage-based deep learning language models

arXiv

引用

arXiv 2021年

作者： Lim, JongYoon Sa, Inkyu Ahn, Ho Seok Gasteiger, Norina Lee, Sanghyub John MacDonald, Bruce CARES Department of Electrical Computer and Software Engineering University of Auckland New Zealand CSIRO Data61 Robotics and Autonomous Systems Group Dynamic Platforms

Sentiment prediction remains a challenging and unresolved task in various research fields, including psychology, neuroscience and computer science. This stems from its high-degree of subjectivity and limited input sources that can effectively capture the actual sentiment. This can be even more challenging with only text-based input. Meanwhile, the rise of deep learning and an unprecedented large volume of data have paved the way for artificial intelligence to perform impressively accurate predictions or even human-level reasoning. Drawing inspiration from this, we propose a coverage-based sentiment and subsentence extraction system that estimates a span of input text and recursively feeds this information back to the networks. The predicted subsentence consists of auxiliary information expressing a sentiment. This is an important building block for enabling vivid and epic sentiment delivery (within the scope of this paper) and for other natural language processing tasks such as text summarisation and Q&A. Our approach outperforms the state-of-the-art approaches by a large margin in subsentence prediction (i.e., Average Jaccard scores from 0.72 to 0.89). For the evaluation, we designed rigorous experiments consisting of 24 ablation studies. Finally, our learned lessons are returned to the community by sharing software packages and a public dataset that can reproduce the results presented in this paper. © 2021, CC BY.

关键词： Sentiment analysis

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：