IADIS International Journal on Computer Science & Information Systems

Hyperspectral imaging (HSI) classification has recently become a field of interest in the remote sensing (RS) community.However, such data contain multidimensional dynamic features that make it difficult for precise identification.Also, it covers structurally nonlinear affinity within the gathered spectral bands and the related materials.To systematically facilitate the HSI categorization, we propose a spectral-spatial classification of HSI data using a 3D-2D convolutional neural network and inception network to extract and learn the in-depth spectral-spatial feature vectors.We first applied the principal component analysis (PCA) on the entire HSI image to reduce the original space dimensionality.Second, the exploitation of the spatial hyperspectral input features contiguous information by 2-D CNN.Besides, we used 3-D CNN without relying on any preprocessing to extract deep spectral-spatial fused features efficiently.The learned spectral-spatial characteristics are concatenated and fed to the inception network layer for joint spectral-spatial learning.Furthermore, we learned and achieved the correct classification with a softmax regression classifier.Finally, we evaluated our model performance on different training set sizes of two hyperspectral remote sensing data sets (HSRSI), namely Botswana (BT) and Kennedy Space Center (KSC), and compared the experimental results with deep learning-based and state-of-the-art (SOTA) classification methods.The experiment results show that our model provides competitive classification results with state-of-the-art techniques, demonstrating the considerable potential for HSRSI classification.

Douglas Nyabuga

Guohua Liu

IADIS INTERNATIONAL JOURNAL ON COMPUTER SCIENCE AND INFORMATION SYSTEMS

SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL DATA USING 3D-2D CONVOLUTIONAL NEURAL NETWORK AND INCEPTION NETWORK

基于3D-2D卷积神经网络和Inception网络的高光谱数据光谱-空间分类

Augmented reality (AR) and virtual reality (VR) applications can take advantage of efficient digitalization of real objects as reconstructed elements can allow users a better connection between real and virtual worlds than using pre-set 3D CAD models.Technology advances contribute to the spread of AR and VR technologies, which are always more diffuse and popular.On the other hand, the design and implementation of virtual and extended worlds is still an open problem; affordable and robust solutions to support 3D object digitalization is still missing.This work proposes a reconstruction system that allows users to receive a 3D CAD model starting from a single image of the object to be digitalized and reconstructed.A smartphone can be used to take a photo of the object under analysis and a remote server performs the reconstruction process by exploiting a pipeline of three Deep Learning methods.Accuracy and robustness of the system have been assessed by several experiments and the main outcomes show how the proposed solution has a comparable accuracy (chamfer distance) with the state-of-the-art methods for 3D object reconstruction.

Damiano Oriti

Andrea Sanna

Francesco De Pace

Federico Manuri

Francesco Tamburello

Fabrizio Ronzino

3D SCENE RECONSTRUCTION SYSTEM BASED ON A MOBILE DEVICE

基于移动设备的3D场景重建系统

Our transport system is currently undergoing fundamental change due to increasing use of automation.New automation solutions are introduced in all sectors of transportation, for example automated metros and autonomous ships are in the visions of technology developers.There are many reasons for this ongoing trend of higher use of automation such as demands for sustainability and efficiency to mention some.In this paper, we present a research and development effort aiming at introducing an automatic tram, that is to say SmartTram.In particular, we concentrate on how the changing role of human (as driver, passenger and member of other user groups) is acknowledged in the design of a new automatic tram.For this reason, we present a human factors engineering program for automated trams.The special focus is on how the relevant user groups may be involved in design within the defined program.This approach can be utilized also in other sectors when increasing automation.

Hanna Koskinen

Susanna Aromaa

Vladimir Goriachev

HUMAN FACTORS ENGINEERING PROGRAM DEVELOPMENT AND USER INVOLVEMENT IN DESIGN OF AUTOMATIC TRAM

自动有轨电车设计中的人因工程项目开发与用户参与

Literature reviews are essential for any scientific work, both as part of a dissertation or as a stand-alone work.Scientists benefit from the fact that more and more literature is available in electronic form, and finding and accessing relevant literature has become more accessible through scientific databases.However, a traditional literature review method is characterized by a highly manual process, while technologies and methods in big data, machine learning, and text mining have advanced.Especially in areas where research streams are rapidly evolving, and topics are becoming more comprehensive, complex, and heterogeneous, it is challenging to provide a holistic overview and identify research gaps manually.Therefore, we have developed a framework that supports the traditional approach of conducting a literature review using machine learning and text mining methods.The framework is particularly suitable in cases where a large amount of literature is available, and a holistic understanding of the research area is needed.The framework consists of several steps in which the critical mind of the scientist is supported by machine learning.The unstructured text data is transformed into a structured form through data preparation realized with text mining, making it applicable for various machine learning techniques.A concrete example in the field of smart cities makes the framework tangible.

Yusuf Bozkurt

Reiner Braun

Alexander Rossmann

THE APPLICATION OF MACHINE LEARNING IN LITERATURE REVIEWS: A FRAMEWORK

机器学习在文献综述中的应用：一个框架

This paper describes the temporal progression of human and social dimensions that undergraduate information and communications technology (ICT) students realized during an experiential learning externship where they explored digital divide technology solutions for low-income neighborhoods in the surrounding urban community.The described research represents significant adaptation and use of socio-technical integration research (STIR) with undergraduate ICT students engaged in work based experiential learning to promote equity in STEM education, instill a sense of civic responsibility, and practice approaches to tackling complex societal problems.Methods used for the research study included: STIR, semi-structured interviews, and on-site group observations.Using STIR, an embedded social scientist conducted regular one-on-one dialogs with three of four student externs, to collaboratively describe each student's consideration of human and social dimensions as part of their technical work, explore alternative choices and their potential outcomes, and engage in reflexive learning that in some cases, influenced deliberate changes to material and behavioral practices.The on-site observation of group activities within the ICT innovation center situated in the local urban community provided additional ecosystem context during technical solution design and development of the digital divide solution for local high schools and feeder schools.Outcomes for participating undergraduate ICT students showed: 1) Technology learning improvements for all students; 2) Capacity building to reflect, anticipate and respond to sociotechnical interactions for some students; and 3) Each student was able to progress to a new level of socio-technical learning and decision making.Reflexive discourse with participants surfaced cultural assets and consideration of alternative knowledges in collaborative technology design, development, and implementation that can potentially lead to solutions that are more community centered now and in the future as the ICT students transition to the workforce.

Cynthia Pickering

Erik Fisher

Paul Ross

SOCIO-TECHNICAL LEARNING: CONTEXTUALIZING UNDERGRADUATE EXTERNSHIPS TO BRIDGE THE DIGITAL DIVIDE

社会技术学习：将本科实习情境化以弥合数字鸿沟

Jean-Christophe Sakdavong

Pierre Puigpinos

Nicolas Loiseau

Adrien Bruni

HOW SELF-EFFICACY EVOLUTION COMBINED WITH HELP SEEKING CHOICES IMPACTS ON LEARNING PERFORMANCE ON A MOBILE LEARNING APPLICATION

自我效能演化与求助选择如何影响移动学习应用中的学习表现

Creating seamless textures is crucial to attain realistic 3D virtual objects and environments.This is because when stochastic textures are tiled in a straightforward manner, they produce cluttered visuals with noticeable seams that lack authenticity.This paper proposes GAN-based method for automatic seamless texture synthesis by designing three main components in generator block: (i) the texture style encoder, (ii) residual tiling blocks and (iii) the BRDFs tileable decoder in the generator of an adversarial expansion network, resulting in a continuous texture output at the seam intersection area.In addition, considering the different properties of virtual environment rendering materials, the spatially varying BRDFs (albedo, normal, roughness and displacement map) are all designed in the proposed model to handle multi-layer texture representation.Furthermore, the proposed method for generating seamless multi-layer texture maps that incorporates different loss functions, allowing us to control both the geometric shape and visual fidelity of the synthesized textures.Qualitative and quantitative experiments on the describable textures dataset (DTD) show that the generated texture maps are not only seamlessly tiled but also exhibit superior visual quality in preserving details compared to previous deep texture synthesis methods.

Honghong He

Zhengwentai Sun

Jintu Fan

Pik Mok

SP3F-GAN: GENERATING SEAMLESS TEXTURE MAPS FOR FASHION

SP3F-GAN：生成无缝纹理图用于时尚

We introduce a surface streamline generation approach for visualizing vector fields defined on curved surfaces.This approach performs the intersection calculation on curved surfaces with complex topology to achieve the highly detailed underlying vector.Then, an extended Runge-Kutta streamline integration technology is applied for performing streamline tracing on an unstructured mesh, where the adaptive stepsize strategy and intersection acceleration structure are presented for sake of simplicity and efficiency.Finally, this algorithm applies the ball feature to improve its visual intuitiveness and is integrated into the general visual analysis platform.Experimental results show that our method can generate continuous and consistent geometric surface streamlines by tracing streamlines on curved surfaces.

Fukun Wu

Yi Cao

Qingli Dong

A VISUAL ANALYSIS METHOD FOR VECTOR FIELDS DEFINED ON CURVED SURFACES

曲面上矢量场的可视化分析方法

For several years now, the literature has been reporting an increase in aggression via the Internet among young people living in developed countries.Despite the financial and technical difficulties due to the situation in the country, young Congolese are also very open to ICTs and fun of all kinds of online applications that make them vulnerable to cyber-attacks.In this context, this study aims to examine the prevalence and factors affecting online aggression in Congolese academia.Indeed, with a field survey of 1500 students, we found that students who engage in high-risk online behaviors, such as sharing the Internet connection with others, posting content online, or dating virtual friends, are among those who have a higher probability of being victims and/or perpetrators of online assault.Based on the findings we formulated some recommendations that can help reduce the prevalence of cyberaggression.

Efrem Luzayisu

Jean-Pierre Zamwangana Tungu

STUDY OF CYBER AGGRESSION FACTORS AMONG YOUNG CONGOLESE STUDENTS

刚果青年学生网络攻击因素研究

Most of the studies in identifying the factors contributing to high academic performance of students focus on both traditional and blended learning environments.This study explores the online engagement behaviours of high-performing online students.Three years of data derived from students' online activities and academic performance across six computing courses was analysed.Our findings reveal a continuity of high-performance among students who excel in online introductory programming courses, extending their success to subsequent online computing courses.Furthermore, we establish a positive association between programming experience and improved performance.High-performing students exhibit engagement levels that exceed their peers by at least 100% in online formative learning activities, with particular emphasis on forum participation and quiz contribution.This study also looked into the predictive potential of past academic performances in anticipating future achievements.It demonstrated a predictive accuracy of 75% for programming courses and 91% for non-programming ones.When combined with student engagement data, the predictive accuracy for programming courses increases to 81%.This approach requires substantial data until at least week 7 or 8 of a 10-week course, potentially delaying intervention until the latter stage of the course.To address this, exploring models exclusively reliant on engagement data is recommended.Our research offers actionable insights for educators, enabling them to identify critical content design elements that enhance academic performance across diverse student profiles, fostering improved online engagement and narrowing performance gaps.Moreover, this study calls for a re-evaluation of learning analytics tools within educational institutions to better understand and enhance student behaviours and patters, ultimately improving the overall online learning experience.

Rhodora Abadia

Sisi Liu

Qiaoling Sun

HIGH ACADEMIC PERFORMANCE AND ENGAGEMENT BEHAVIOURS IN ONLINE LEARNING ENVIRONMENTS

在线学习环境中高学术表现与参与行为

Abbreviation
Journal Impact	0.31
Quartiles(Global)	COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS(Q4)

Publication Information	Publisher: ，Publishing cycle: ，Journal Type: journal，Open Access Journals: No
Basic data	Year of publication: ，Proportion of original research papers: 100.00%，Self Citation Rate:0.00%， Gold OA Rate: 0.00%

IADIS International Journal on Computer Science & Information Systems

Journal Citation Format

A journal article with 1 author

A journal article with 2 authors

A journal article with 3 authors

A journal article with 5 or more authors

Books Citation Format

Thesis Citation Format

Web sites Citation Format

Patent Citation Format

Staying up late manually editing references? ivySCI automatically matches journals and helps you generate references with a single click.

Share Submission Experience