The proceedings contain 14 papers. The topics discussed include: a foundation for spatio-textual-temporal cube analytics;estimating the job’s pending time on a high-performance computing cluster through a hierarchica...
The proceedings contain 14 papers. The topics discussed include: a foundation for spatio-textual-temporal cube analytics;estimating the job’s pending time on a high-performance computing cluster through a hierarchical data-driven methodology;towards local post-hoc recommender systems explanations;learning analysis behavior in SQL workloads;an in-depth investigation of large-scale RDF relational schema optimizations using spark-SQL;MDORG: annotation assisted rule agents for metadata files;adaptive indexing for in-situ visualexploration and analytics;using fuzzy vaults for privacy preserving record linkage;and exploring data using patterns: a survey and open problems.
In recent years, the domain space interaction of subway stations based on computer-aided design has become a new trend. This article takes urban rail transit as an example to explain the importance of using computer t...
In recent years, the domain space interaction of subway stations based on computer-aided design has become a new trend. This article takes urban rail transit as an example to explain the importance of using computer to realize functions such as graphics and images. The system uses B/S structure to process graphic information, and stores the results in the server database for later analysis and feedback of changes in user needs. Through the simulation based on virtual sample technology, the effectiveness of the model and algorithm is verified. The visualization coefficient of the subway station domain space guidance system is between 0.7 and 0.9, the accuracy of landmarks is between 96% and 97%, the ease of use is between 84% and 89%, and the system operability is 80% above. Finally, in the computer environment, the interactive interface of the subway station domain space is designed to provide passengers with a better experience. This move means that the space interaction in the subway station has a higher technical level, and has played an important role in improving user satisfaction and convenience. In the research, it was found that the visual interaction method of the subway station spatial guidance system based on computer-aided design can be improved through the following aspects. These data may include passenger flow, train operation status, and safety information, and can be presented in the form of charts, heat maps, and animations. These research findings aim to continuously improve the spatial guidance system of subway station areas, enhance user experience and efficiency.
Machine learning and dataanalysis are becoming an essential part of the decision-making process in modern organizations. Even though new and improved analytics algorithms are developed frequently, organizations are s...
详细信息
ISBN:
(纸本)9781728191348
Machine learning and dataanalysis are becoming an essential part of the decision-making process in modern organizations. Even though new and improved analytics algorithms are developed frequently, organizations are struggling to develop analytics applications that can stay up-to-date with changing business requirements and technology innovations. The rapid development of ad-hoc programs to conduct machine learning tasks at hand has resulted in creating more expenses and efforts in the long term, a phenomenon referred to as technical debt in literature. This paper addresses the technical debt associated with data analytics applications by proposing a knowledge repository that captures analytics-related knowledge, which can be developed and maintained separately from the organization's IT infrastructure and used to design analytics applications with visual interfaces. This way, organizations can develop dynamic and adaptable analytics applications with easy-to-follow front-ends and can accommodate new data sources or machine learning models. We evaluate the proposed approach by conducting a case study that develops an application for the acquisition and management of high-frequency financial market data.
Applying machine learning techniques over streaming data is notoriously difficult as it involves the interplay of several technologies that need to be judiciously put together by IT experts. This has motivated the nee...
详细信息
ISBN:
(纸本)9781728191348
Applying machine learning techniques over streaming data is notoriously difficult as it involves the interplay of several technologies that need to be judiciously put together by IT experts. This has motivated the need to provide intuitive and easy to use interactive interfaces for financial experts to be able to leverage both Complex Event Processing (CEP) and Machine Learning (ML) technologies. The solution proposed in this paper is based on an open architecture that uses CEP engines as a pre-processing function for downstream ML training and prediction computations. We demonstrate this approach using a few scenarios involving the analysis of financial market data streams.
The proceedings contain 24 papers. The topics discussed include: using fast multidimensional projections to reveal band and circumplex patterns in reorderable matrices;a 3D spectral-spatial classification of hyperspec...
ISBN:
(纸本)9789898704320
The proceedings contain 24 papers. The topics discussed include: using fast multidimensional projections to reveal band and circumplex patterns in reorderable matrices;a 3D spectral-spatial classification of hyperspectral remote sensing imagery using inception based network;3D face reconstruction from hard blended edges;capsule neural networks in classification of skin lesions;a single RGB image based 3D object reconstruction system;face features-based personality assessment;analysis of capsule networks for image classification;analysis and visualexploration of prediction algorithms for public bicycle sharing systems;and hello, my name is smarttram, human factors is on board, enjoy the ride! developing a human factors program for automatic trams.
This research paper addresses the pivotal domain of image classification, a field with profound real-world applications. The significance of classifying hazy images into distinct categories lies in the ability to appl...
详细信息
ISBN:
(数字)9798350372847
ISBN:
(纸本)9798350372854
This research paper addresses the pivotal domain of image classification, a field with profound real-world applications. The significance of classifying hazy images into distinct categories lies in the ability to apply the most suitable dehazing algorithm for each class. Relying solely on human perception is deemed suboptimal due to its unpredictability and vulnerability to bias, underscoring the need for an algorithmic approach to image classification. The initial binary haze-clear classification is refined into six nuanced categories: dense fog, thick fog, moderate fog, light fog, thin fog, haze. While convolutional neural networks (CNNs) excel in image classification, manually constructing network structures for specific tasks requires numerous trials to fine-tune a multitude of hyperparameters. This process is time-consuming, and finding the fittest hyperparameters suitable for target data poses a challenge. This research paper introduces a Differential Evolution (DE) based automatic network evolution model, optimising hyper-parameters by exploring the fittest parameters. The proposed evolutionary algorithm identifies optimistic hyperparameters. By merging the capabilities of the Differential Evolution algorithm with a sophisticated classification system, this research promises to push the boundaries of hazy image classification. This approach enhances classification accuracy and empowers subsequent applications by delivering cleaner and more detailed images. The results showcase a more efficient and effective approach to tackle the challenges posed by atmospheric haze, ultimately contributing to advancements in computer vision, object recognition and various domains relying on visualdataanalysis.
The ability to see and find things is very important in our daily lives. For example, when looking for mistakes in debugging a program, or when looking for misspellings in documents, etc., the visual sense is mainly u...
详细信息
ISBN:
(纸本)9781665490085
The ability to see and find things is very important in our daily lives. For example, when looking for mistakes in debugging a program, or when looking for misspellings in documents, etc., the visual sense is mainly used. The search may or may not be successful. Is there any difference in the way of searching when the search is successful or unsuccessful? The aim of this study is to analyse the gaze while searching and to clarify the differences between successful and unsuccessful searches, using ‘spot the difference’ as a subject. We have developed an experimental application to measure people's gaze while they are looking ‘spot the difference'. In the experiment conducted in this study, 29 subjects have asked to perform ‘spot the difference’ of multiple problems and their gaze have been measured. analysis of the data obtained from this experiment shows that in many cases, subjects who could not find a difference were not looking at the location of the difference. On the other hand, the existence of ‘cases of looking but not finding’, in which the difference is not detected even though the difference is fully looked at, is also identified. In the present experiment, ‘looking but not finding’ cases account for 15% of all non-correct responses in all questions.
The FICA project - Tools for Identifying and Combating Dropout - started at the University of Aveiro in 2015 with the aim to help reduce and prevent dropouts and increase academic success among university students. Wi...
详细信息
ISBN:
(纸本)9781728191348
The FICA project - Tools for Identifying and Combating Dropout - started at the University of Aveiro in 2015 with the aim to help reduce and prevent dropouts and increase academic success among university students. Within the project a signicant amount of data is provided to different University stakeholders to monitor academic issues, however, these data are currently provided in large tables, a format difficult to analyze. In this paper, we present the main aspects of the data, the users and contexts of use. We also propose an approach to allow the visual and interactive exploration of the FICA project data to help monitor the path of the students and identify risk indicators and failure factors that can lead to critical situations such as dropout. A solution developed using the participatory design methodology is presented, detailing all stages of its creation process, from the requirements elicitation based on focus groups and interviews, design and prototype development in Power BI to its evaluation. Some suggestions for future work are also presented.
The overall scope and goal of the workshop is to bring together researchers active in the areas of Artificial Intelligence (AI), Big dataanalysis, and visualization to achieve a road map, which can support the accele...
详细信息
ISBN:
(纸本)9781450375351
The overall scope and goal of the workshop is to bring together researchers active in the areas of Artificial Intelligence (AI), Big dataanalysis, and visualization to achieve a road map, which can support the acceleration in research and data science activities by means of transforming, enriching, and deploying AI models and algorithms as well as intelligent advanced visual user interfaces supporting creation, configuration, management, and usage of distributed Big dataanalysis. Big dataanalysis and AI mutually support each other: AI-powered algorithms empower data scientists to analyze Big data and thereby exploit its full potential whereas Big data enables AI experts to comfortably design, validate, and deploy AI models. One of the workshop's objectives is the examination of the importance and necessity of a third, a more straightforward relationship of Big data and AI: AI supporting all user stereotypes and organizations involved in Big dataanalysis on their exploration journey from raw input data to insight and effectuation.
Massive data are surrounding us in our daily lives. Urban mobility generates a very high number of complex data reflecting the mobility of people, vehicles and objects. Transport operators are primary users who strive...
详细信息
暂无评论