Search

This paper introduces a framework that integrates smart production logistics (SPL) with network diagrams. This integration enhances visibility in the material and information flow within the manufacturing sector, thereby adding value through data visualization. Drawing from a detailed case study in the automotive industry, we outline the essential components of network diagrams that are tailored to depict spatial-temporal data linked with material handling processes in an SPL context. This integrated approach presents managers with a new tool for optimizing planning and executing tasks related to the transport of materials and information. Furthermore, while the framework brings about significant technological progress, it also emphasizes the managerial implications of SPL data visualization. In particular, it highlights its potential to foster informed decision-making, resource optimization, and strategic forecasting. The paper also discusses prospective research avenues, stressing the importance of dynamic diagrams that decode complex patterns from digital data and the incorporation of sustainability metrics in SPL assessments., QC 20240522Part of ISBN 978-164368510-6

Climate change has impacted global temperatures, triggering extreme weather and adverse environmental effects. In Sweden, these changes have caused shifts in weather patterns, leading to disruptions in infrastructure. This, in turn, has influenced water turbidity levels, negatively impacting water quality. To tackle these issues, a study was conducted using machine learning to predict turbidity with six meteorological variables collected for two years. Our preliminary research showed a substantial influence of seasonal changes on water turbidity, especially air temperature. Identifying supporting indicators such as lagged features is crucial and considerably improved the turbidity prediction performance for two of the machine learning models used. However, the study also identified challenges like data collection and uncertainty issues. We recommend improving data collection quality with higher frequency, minimizing geographical gaps between data collection points, sharing calibration assumptions, checking the sensors regularly, and accounting for data anomalies. Understanding these challenges and their potential implications could lead to more methodological enhancements., Corresponding author: juhee.bae@his.seThis project has been funded by VINNOVA, the Swedish Government Agency for Innovation Systems, “AI för klimatanpassning - metoder för att skapa en mer resilient dricksvattenproduktion och leverans” (DNR 2021-02460) and was conducted in cooperation with IVL Svenska Miljöinstitutet AB.

The problem of using machine learning (ML) to predict the process endpoint for a Basic Oxygen Furnace (BOF) process used for steelmaking has been largely studied. However, current research often lacks both the usage of a rich dataset and does not address revealing influential factors that explain the process. The process is complex and difficult to control and has a multi-objective target endpoint with a proper range of heat temperature combined with sufficiently low levels of carbon and phosphorus. Reaching this endpoint requires skilled process operators, who are manually controlling the heat throughout the process by using both implicit and explicit control variables in their decisions. Trained ML models can reach good BOF target prediction results, but it is still a challenge to extract the influential factors that are significant to the ML prediction accuracy. Thus, it becomes a challenge to explain and validate an ML prediction model that claims to capture the process well. This paper makes use of a complex and full production dataset to evaluate and compare different approaches for understanding how the data can determine the process target prediction. One approach is based on the collected process data and the other on the ML approach trained on that data to find the influential factors. These complementary approaches aim to explain the BOF process to reveal actionable information on how to improve process control., © 2021 Copyright held by the owner/author(s). Publication rights licensed to ACM.We would like to thank Carl Ellström, Patrik Wikström, and Lennart Gustavsson at SSAB for their close collaboration in this project. This project is funded by the Knowledge Foundation in Sweden, under grant number 20170297.

This paper aims to analyze international migrations in western African countries using irregular multivariate monthly time series containing a few values. Existing methods of filling in missing values have limitations because there are not enough values to infer them. In this study, we explore two approaches to solve this problem. One approach is to aggregate the values annually to eliminate missing values. The other is to use the Random Forest (RF) based approach to fill in the missing values. Then, we predict the international migration intentions using deep learning approaches and time series dataset. We demonstrate that a RF-based imputation outperforms a zero filling approach (used as the baseline) with Long Short-Term Memory (LSTM) method. Moreover, we show that analyzing the monthly subregion-based time series provides better insights than the yearly country-based time series., © 2020 ACM.Article No.: 37

This paper demonstrates how to explore and visualize different types of structure in data, including clusters, anomalies, causal relations, and higher order relations. The methods are developed with the goal of being as automatic as possible and applicable to massive, streaming, and distributed data. Finally, a decentralized learning scheme is discussed, enabling finding structure in the data without collecting the data centrally., BIDAF

Discovering causal relations from limited amounts of data can be useful for many applications. However, all causal discovery algorithms need huge amounts of data to estimate the underlying causal graph. To alleviate this gap, this paper proposes a novel visualization tool which incrementally discovers causal relations as more data becomes available. That is, we assume that stronger causal links will be detected quickly and weaker links revealed when enough data is available. In addition to causal links, the correlation between variables and the uncertainty of the strength of causal links are visualized in the same graph. The tool is illustrated on three example causal graphs, and results show that incremental discovery works and that the causal structure converges as more data becomes available. © 2019 Copyright held by the owner/author(s). Publication rights licensed to ACM.

The first Workshop on Interactive Data Mining is held in Melbourne, Australia, on February 15, 2019 and is co-located with 12th ACM International Conference on Web Search and Data Mining (WSDM 2019). The goal of this workshop is to share and discuss research and projects that focus on interaction with and interactivity of data mining systems. The program includes invited speaker, presentation of research papers, and a discussion session.

We approach the problem of identifying and interpreting clusters over different time scales and granularity in multivariate time series data. We extract statistical features over a sliding window of each time series, and then use a Gaussian mixture model to identify clusters which are then projected back on the data streams. The human analyst can then further analyze this projection and adjust the size of the sliding window and the number of clusters in order to capture the different types of clusters over different time scales. We demonstrate the effectiveness of our approach in two different application scenarios: (1) fleet management and (2) district heating, wherein each scenario, several different types of meaningful clusters can be identified when varying over these dimensions. © 2019 Copyright held by the owner/author(s). Publication rights licensed to ACM.

This half-day workshop seeks to bring together practitioners and academics interested in the challenges of structuring interactions for subject matter experts (SMEs) who are providing knowledge and/or feedback to an AI system, but are not well-versed in the underlying algorithms. Since the information provided by SMEs directly effects the efficacy of the final system, collecting the correct data is a problem that navigates issues ranging from curating data that may be tainted to structuring data collection tasks in such a way as to mitigate user boredom. The goal of this workshop is to discuss methods and new paradigms for productively interacting with users while collecting knowledge.

The technology and techniques for bio-sensors are rapidly evolving. Accordingly, there is significant business interest to identify upcoming technologies and new targets for the near future. Text information from internet reflects much of the recent information and public interests that help to understand the trend of a certain field. Thus, we utilize Dirichlet process topic modeling on different media sources containing short text (e.g., blogs, news) which is able to self-adapt the learned topic space to the data. We share the observations from the domain experts on the results derived from topic modeling on wearable biosensors from multiple media sources over more than eight years. We analyze the topics on wearable devices, forecast and market analysis, and bio-sensing techniques found from our method.

Social media plays a critical role in propagating emergency information during disasters. Governmental agencies have opened social media accounts for emergency communication channels. To understand the underlying mechanism of user behaviors and engagement, this study employs social network analysis to investigate information network and diffusion across news, weather agencies, governmental agencies, organizations and the public during the 2017 Storm Cindy in the U.S. This study identified certain types of Twitter users (news and weather agencies) were dominant as information sources and information diffusers (the public and organizations). However, the information flow in the network was controlled by numerous types of users including news, agency, weather agencies and the public. The results highlighted the importance of understanding the unique characteristics of social media and networks for better emergency communication system. © 2018 Elsevier Ltd, © 2018 Elsevier Ltd. All rights reserved. The RightsLink Digital Licensing and Rights Management Service (including RightsLink for Open Access) is available (A) to users of copyrighted works found at the websites of participating publishers who are seeking permissions or licenses to use those works, and (B) to authors of articles and other manuscripts who are seeking to pay author publication charges in connection with the submission of their works to publishers.

Fast-moving trends, both in society and in highly competitive business areas, call for effective methods for automatic analysis. The availability of fast-moving sources in the form of short texts, such as social media and blogs, allows aggregation from a vast number of text sources, for an up to date view of trends and business insights. Topic modeling is established as an approach for analysis of large amounts of texts, but the scarcity of statistical information in short texts is considered to be a major problem for obtaining reliable topics from traditional models such as LDA. A range of different specialized topic models have been proposed, but a majority of these approaches rely on rather strong parametric assumptions, such as setting a fixed number of topics. In contrast, recent advances in the field of Bayesian non-parametrics suggest the Dirichlet process as a method that, given certain hyper-parameters, can self-adapt to the number of topics of the data at hand. We perform an empirical evaluation of the Dirichlet process multinomial (unigram) mixture model against several parametric topic models, initialized with different number of topics. The resulting models are evaluated, using both direct and indirect measures that have been found to correlate well with human topic rankings. We show that the Dirichlet Process Multinomial Mixture model is a viable option for short text topic modeling since it on average performs better, or nearly as good, compared to the parametric alternatives, while reducing parameter setting requirements and thereby eliminates the need of expensive preprocessing.

This paper presents findings about visual representations of cause and effect relationship's direction, strength, and uncertainty based on an online user study. While previous researches focus on accuracy and few attributes, our empirical user study examines accuracy and the subjective ratings on three different attributes of a cause and effect relationship edge. The cause and effect direction was depicted by arrows and tapered lines; causal strength by hue, width, and a numeric value; and certainty by granularity, brightness, fuzziness, and a numeric value. Our findings point out that both arrows and tapered cues work well to represent causal direction. Depictions with width showed higher conjunct accuracy and were more preferred than that with hue. Depictions with brightness and fuzziness showed higher accuracy and were marked more understandable than granularity. In general, depictions with hue and granularity performed less accurately and were not preferred compared to the ones with numbers or with width and brightness.

Exploring and revealing relations between the elements is a fre-quent task in exploratory analysis and search. Examples includethat of correlations of attributes in complex data sets, or facetedsearch. Common visual representations for such relations are di-rected graphs or correlation matrices. These types of visual encod-ings are often - if not always - fully constructed before being shownto the user. This can be thought of as a top-down approach, whereusers are presented with a full picture for them to interpret andunderstand. Such a way of presenting data could lead to a visualoverload, specially when it results in complex graphs with highdegrees of nodes and edges. We propose a bottom-up alternativecalled Billiard where few elements are presented at rst and fromwhich a user can interactively construct the rest based on whats/he nds of interest. The concept is based on a billiard metaphorwhere a cue ball (node) has an eect on other elements (associatednodes) when stroke against them.