检索结果-内蒙古大学图书馆

Do humans and Convolutional Neural Networks attend to similar areas during scene classification: Effects of task and image type

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Müller, Romy Dürschmidt, Marcel Ullrich, Julian Knoll, Carsten Weber, Sascha Seitz, Steffen Faculty of Psychology Chair of Engineering Psychology and Applied Cognitive Research TUD Dresden University of Technology Dresden Germany Faculty of Electrical and Computer Engineering Chair of Fundamentals of Electrical Engineering TUD Dresden University of Technology Dresden Germany Faculty of Mathematics and Natural Sciences Department of Computer Science Machine Learning Group Heinrich-Heine-Universität Düsseldorf Düsseldorf Germany

Deep Learning models like Convolutional Neural Networks (CNN) are powerful image classifiers, but what factors determine whether they attend to similar image areas as humans do? While previous studies have focused on technological factors, little is known about the role of factors that affect human attention. In the present study, we investigated how the tasks used to elicit human attention maps interact with image characteristics in modulating the similarity between humans and CNN. We varied the intentionality of human tasks, ranging from spontaneous gaze during categorization over intentional gaze-pointing up to manual area selection. Moreover, we varied the type of image to be categorized, using either singular, salient objects, indoor scenes consisting of object arrangements, or landscapes without distinct objects defining the category. The human attention maps generated in this way were compared to the CNN attention maps revealed by explainable artificial intelligence (Grad-CAM). The influence of human tasks strongly depended on image type: For objects, human manual selection produced maps that were most similar to CNN, while the specific eye movement task has little impact. For indoor scenes, spontaneous gaze produced the least similarity, while for landscapes, similarity was equally low across all human tasks. To better understand these results, we also compared the different human attention maps to each other. Our results highlight the importance of taking human factors into account when comparing the attention of humans and CNN. © 2023, CC BY.

关键词： Eye movements

How to Identify Class Comment Types? A Multi-language Approach for Class Comment Classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Rani, Pooja Panichella, Sebastiano Leuenberger, Manuel Sorbo, Andrea Di Nierstrasz, Oscar Software Composition Group University of Bern Switzerland Zurich University of Applied Science Switzerland Department of Engineering University of Sannio Italy

Most software maintenance and evolution tasks require developers to understand the source code of their software systems. software developers usually inspect class comments to gain knowledge about program behavior, regardless of the programming language they are using. Unfortunately, (i) different programming languages present language-specific code commenting notations and guidelines;and (ii) the source code of software projects often lacks comments that adequately describe the class behavior, which complicates program comprehension and evolution activities. To handle these challenges, this paper investigates the different language-specific class commenting practices of three programming languages: Python, Java, and Smalltalk. In particular, we systematically analyze the similarities and differences of the information types found in class comments of projects developed in these languages. We propose an approach that leverages two techniques — namely Natural Language Processing and Text Analysis — to automatically identify class comment types, i.e., the specific types of semantic information found in class comments. To the best of our knowledge, no previous work has provided a comprehensive taxonomy of class comment types for these three programming languages with the help of a common automated approach. Our results confirm that our approach can classify frequent class comment information types with high accuracy for the Python, Java, and Smalltalk programming languages. We believe this work can help in monitoring and assessing the quality and evolution of code comments in different programming languages, and thus support maintenance and evolution tasks. © 2021, CC BY-NC-ND.

关键词： Semantics

Modeling of selected set of software requirements using UML class diagrams 17

学校读者我要写书评

暂无评论

Modeling of selected set of software requirements using UML ...

17th IEEE India Council International Conference, INDICON 2020

作者： Arif, Mohd. Mohammad, Chaudhary Wali Sadiq, Mohd. Faculty of Engineering and Technology Computer Science and Technology Research Group Department of Applied Sciences and Humanities New Delhi110025 India Indian Institute of Science Department of Computer Science and Automation Bangalore560012 India

ISBN: (纸本)9781728169163

Unified Modeling Language (UML) is used to model and design the software requirements. Among various components of UML, class diagram is employed to model the software requirements in terms of objects organized in classes and relationships between them. In real life applications, it has been observed that a system may have several requirements and it is not possible to model each and every requirement because of time, budget, and other constraints of an organization. Based on our review, we found that, in literature less attention is given to the modeling of the software requirements from the selected set of the requirements using UML class diagrams. Therefore, to address this issue, in this paper we present a method for modeling of the selected set of the software requirements using UML class diagrams. The applicability of the proposed method is discussed with the help of the software requirements of an institute examination system. © 2020 IEEE.

关键词： Budget control

Smart Soft Sensor for Froth flotation quality monitoring using pre-trained feature extractor and Vision Transformer ViT

学校读者我要写书评

暂无评论

Smart Soft Sensor for Froth flotation quality monitoring usi...

International IEEE Conference on Signal-Image Technologies and Internet-Based System

作者： Oussama Hasidi Ahmed Bendaouia El Hassan Abdelwahed El Alaoui-Chrifi Moulay Abdellah Abdelmalek Boussetta Intissar Benzakour François Bourzeix Kaotar Oubouhss LISI Laboratory Computer Science Departement UCA Analytics Lab Mohammed VI Polytechnic University Marrakech Morocco LISI Laboratory Computer Science Departement Cadi Ayyad University Marrakech Morocco R&D and Engineering center Reminex Managem Group Marrakech Morocco Analytics Lab Mohammed VI Polytechnic University Rabat Morocco Department of Electrical and Industrial Engineering National School of Applied Science UAE Tangier Morocco

Smart sensor technologies have gained prominence in the field of machine vision-based applications. Within this context, the utilization of machine vision systems for monitoring and controlling flotation plants has become increasingly prevalent. This paper addresses the critical need for accurate froth image classification in the development of an online machine vision-based control system. This paper explores the recent advancements in machine learning, with a focus on deep learning techniques. Specifically, it introduces the application of a Vision Transformer (VIT) model as an alternative to the traditional Convolutional Neural Network (CNN) for classifying froth images collected from an industrial lead flotation circuit. The results of this research demonstrate the remarkable performance of the ViT model, achieving an impressive overall accuracy rate of 96% when combined with pre-trained feature extractor models. This achievement surpasses the capabilities of conventional artificial neural network (CNN) classifiers of the state of art in terms of both accuracy and computational efficiency. These findings underscore the promising potential of deep learning neural networks in froth image analysis, highlighting their significance in the advancement of smart sensor-based machine vision systems within the field of flotation plant control.

关键词：

On the Complexity of the Storyplan Problem

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Binucci, Carla Di Giacomo, Emilio Lenhart, William J. Liotta, Giuseppe Montecchiani, Fabrizio Nöllenburg, Martin Symvonis, Antonios Department of Engineering University of Perugia Italy Department of Computer Science Williams College United States Algorithms and Complexity Group Tu Wien Vienna Austria School of Applied Mathematical & Physical Sciences Ntua Greece

Motivated by dynamic graph visualization, we study the problem of representing a graph G in the form of a storyplan, that is, a sequence of frames with the following properties. Each frame is a planar drawing of the subgraph of G induced by a suitably defined subset of its vertices. Between two consecutive frames, a new vertex appears while some other vertices may disappear, namely those whose incident edges have already been drawn in at least one frame. In a storyplan, each vertex appears and disappears exactly once. For a vertex (edge) visible in a sequence of consecutive frames, the point (curve) representing it does not change throughout the sequence. Note that the order in which the vertices of G appear in the sequence of frames is a total order. In the StoryPlan problem, we are given a graph and we want to decide whether there exists a total order of its vertices for which a storyplan exists. We prove that the problem is NP-complete, and complement this hardness with two parameterized algorithms, one in the vertex cover number and one in the feedback edge set number of G. Also, we prove that partial 3-trees always admit a storyplan, which can be computed in linear time. Finally, we show that the problem remains NP-complete in the case in which the total order of the vertices is given as part of the input and we have to choose how to draw the frames. © 2022, CC BY.

关键词： Hardness

Breamy: An augmented reality mHealth prototype for surgical decision-making in breast cancer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Najafi, Niki Addie, Miranda Meterissian, Sarkis Kersten-Oertel, Marta Applied Perception Lab Department of Computer Science and Software Engineering Concordia University Québec Canada Experimental Surgery Mcgill University Québec Canada Breast Center McGill University Health Centre Québec Canada Department of Surgery Faculty of Medicine McGill University Québec Canada

In 2020, according to WHO, breast cancer affected 2.3 million women worldwide, resulting in 685,000 fatalities. By the end of the year, approximately 7.8 million women worldwide had survived their breast cancer making it the most widespread form of cancer globally. Surgical treatment decisions, including choosing between oncoplastic options, often require quick decision-making within an 8-week time frame. However, many women lack the necessary knowledge and preparation for making such complex informed decisions. Anxiety and unsatisfactory outcomes can result from inadequate decision-making processes, leading to complications and the need for revision surgeries. Shared decision-making and personalized decision aids have shown positive effects on patient satisfaction and treatment outcomes. This paper introduces Breamy, a prototype mobile health (mHealth) application that utilizes augmented reality (AR) technology to assist breast cancer patients in making informed decisions. The app provides 3D visualizations of different oncoplastic procedures, aiming to improve confidence in surgical decision-making, reduce decisional regret, and enhance patient well-being after surgery. To determine the perception of the usefulness of Breamy, we collected data from 166 participants through an online survey. The results suggest that Breamy has the potential to reduce patient's anxiety levels and assist them during the decision-making process. Copyright © 2023, The Authors. All rights reserved.

关键词： Visualization

Keywords-driven web APIs group recommendation for automatic app service creation process

学校读者我要写书评

暂无评论

Keywords-driven web APIs group recommendation for automatic ...

作者： Gong, Wenwen Lv, Chao Duan, Yucong Liu, Zengguang Khosravi, Mohammad R. Qi, Lianyong Dou, Wanchun College of Information and Electrical Engineering China Agricultural University Beijing China China Telecom Smart Home Competence Center Nanjing China E-Surfing Smart Home Technology Co. Ltd Nanjing China School of Computer Science and Cyberspace Security Hainan University Haikou China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China Department of Computer Engineering Persian Gulf University Bushehr Iran Telecommunications Group Department of Electrical and Electronic Engineering Shiraz University of Technology Shiraz Iran School of Information Science and Engineering Qufu Normal University Rizhao China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

With the ever-increasing popularity of web application programming interfaces (APIs) sharing communities, it is becoming a promising way for software developers to design and create their interesting Apps through composing a set of selected web APIs that can collectively fulfill the App functions expected by the App developer. However, the App developer's web APIs selection decision-makings are often nontrivial due to the massive candidate APIs as well as their diverse functions. Furthermore, it is difficult to guarantee that the selected web APIs are compatible enough. Moreover, traditional web APIs recommendation approaches only return a recommended APIs list, which are often not sufficient to accommodate the App developer's undetermined and fuzzy personalized preferences. Considering the above challenges, a novel keywords-driven web APIs recommendation approach called keywords-driven and compatibility-aware multiple API group recommendation is proposed in this article for green and compatible software, which cannot only satisfy the App developer's functional requirements, but also return a group of web APIs recommended lists. Each returned list includes a set of compatible web APIs. Finally, we design a series of experiments based on a real-world web APIs dataset, that is, PW dataset crawled from ***. Experimental reports compared with other competitive approaches in existing literatures indicate the effectiveness and efficiency of our proposal in this work. © 2020 John Wiley & Sons Ltd

关键词： Application programs

A Glove CNN-Bilstm Sentiment Classification 18

学校读者我要写书评

暂无评论

A Glove CNN-Bilstm Sentiment Classification

18th International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2021

作者： Atandoh, Peter Feng, Zhang Adu-Gyamfi, Daniel Leka, Habte Lejebo Atandoh, Paul Hakeem University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu610054 China University of Technology and Applied Sciences School of Computing Information Sciences Department of Cyber Security and Computer Engineering CK Tedam Navrongo Ghana Western Michigan University Department of Statistics KalamazooMI49008-5278 United States

ISBN: (纸本)9781665413640

Reviewing products online has become an increasingly popular way for consumers to voice their opinions and feelings about a product or service. Analyzing this Big data of online reviews would help to discern and extract useful facts and information that could provide a competitive and economic advantage to merchants and other organizations that are interested. Text classification organizes documents according to a variety of predefined categories. In other to solve the aforementioned problems, we employed Glove embeddings for our review sentiment analysis. We further integrate this embedding layer into a deep convolutional neural network (CNN)-bidirectional LSTM model. We further train our model on the IMDB and movie review dataset to extract the polarity as positive or negative and subsequently compare our model with other state-of- the-art models. The aforementioned experiments validate the efficacy and superiority of our proposed approach. © 2021 IEEE.

关键词： Sentiment analysis

Investigating the effects of gamifying SQL-Tutor 28

学校读者我要写书评

暂无评论

Investigating the effects of gamifying SQL-Tutor

28th International Conference on computers in Education, ICCE 2020

作者： Tahir, Faiza Mitrovic, Antonija Sotardi, Valerie Intelligent Computer Tutoring Group Department of Computer Science and Software Engineering University of Canterbury New Zealand School of Educational Studies and Leadership University of Canterbury New Zealand

ISBN: (纸本)9789869721455

The practice of adding game elements to non-gaming educational environments has gained much popularity. Gamification has been found in some studies to increase learner engagement, motivation, and academic performance. However, there is a lack of empirical evidence to prove the effects of gamification in advanced learning technologies like Intelligent Tutoring Systems (ITS). This paper reports the results of an empirical study that included three categories of game elements (goals, assessment and challenges) implemented as badges in the context of SQL-Tutor. The study was conducted in a class under realistic conditions. SQL-Tutor was used voluntarily by 77 undergraduate students enrolled in a second-year database course. Although there were no differences between the experimental and control groups in terms of their interaction with SQL-Tutor and learning outcomes, we found a significant mediating effect of time-on-task on the direct relation between badges and achievement in the gamified condition. We also found evidence that not all students were interested in badges. © ICCE 2020 - 28th International Conference on computers in Education, Proceedings. All rights reserved.

关键词： Students