How Best to Hunt a Mammoth - Toward Automated Knowledge Extraction From Graphical Research Models

2023 | International Conference on Business Informatics | Citations: 0

Authors: Huettemann, Sebastian; Mueller, Roland M.; Larsen, Kai R.; Dinter, Barbara; Chiny, Joshua Campos

Abstract: ... Expand

Abstract: Collapse

Topics: knowledge repository database system knowledge base application programming interface Python

Methods: design science metamodel computational algorithm machine learning literature study

Visualizing Convolutional Neural Network Models’ Sensitivity to Nonnatural Data Order

2023 | Information Systems Frontiers | Citations: 0

Authors: Klepetko, Randy; Krishnan, Ram

Abstract: Convolutional neural networks (CNN) have revolutionized image recognition techno ... Expand

Abstract: Convolutional neural networks (CNN) have revolutionized image recognition technology and found applications in various nonimage-related fields. For nonnatural data, such as cybersecurity packets, in which the data sample order is not defined by nature, some models trained on certain orderings of data perform better than when trained with other orderings. Some orderings create patterns from which the CNN extracts better features. Understanding how to best order the training data to improve CNN performance is not well-studied. In this study, we investigate this problem by examining malware infections using different CNN models and include visualization tools to enhance our analysis. We define a functional algorithm for ordering and show that order importance in CNNs is model dependent. In addition, we show that depending on the model, statistical relationships are crucial in establishing order with better performance. Collapse

Topics: malware mobile system cloud computing infrastructure as a service

Methods: experiment descriptive statistic machine learning computational algorithm Keras

Utilizing the omnipresent: Incorporating digital documents into predictive process monitoring using deep neural networks

2023 | Decision Support Systems | Citations: 0

Authors: Levich, Sergej; Lutz, Bernhard; Neumann, Dirk

Abstract: Predictive process monitoring (PPM) allows companies to improve the efficiency o ... Expand

Abstract: Predictive process monitoring (PPM) allows companies to improve the efficiency of their business processes by predicting aspects such as the process outcome, the next event, or the time until the next event. So far, existing studies have mainly focused on developing novel predictive models while using features solely from event logs. In this study, we aim to go beyond log data and increase the focus of PPM research towards external context information. To this end, we consider digital documents as they are omnipresent in many business processes and their inclusion can often be justified by a business rationale. However, incorporating digital documents into PPM models poses considerable challenges as they present unstructured data that can contain visual and textual cues of future process behavior, while manual feature extraction is generally not feasible. Therefore, we propose an approach that processes digital documents based on automated visual and textual feature extraction methods. Furthermore, we design a tailored integration module which transforms the extracted features from multiple document pages into a fixed-size representation that subsequently serves as input for the predictive models. Our evaluation, based on a real-world dataset of insurance claims from a mid-sized German insurance company, featuring 5131 process instances with 32,058 events and 39,242 document pages, shows that incorporating digital documents improves the performance by significant margins in predicting the damage type, the next event, and the time until the next event. Finally, we analyze how digital documents contribute to the model’s predictions in terms of Shapley additive explanations. Collapse

Topics: shapley additive explanation business process management artificial intelligence explainable artificial intelligence

Methods: BERT machine learning descriptive statistic artificial neural network business process modeling

Explanatory Interactive Machine Learning

2023 | Business & Information Systems Engineering | Citations: 1

Authors: Pfeuffer, Nicolas; Baum, Lorenz; Stammer, Wolfgang; Abdel-Karim, Benjamin M.; Schramowski, Patrick; Bucher, Andreas M.; Hügel, Christian; Rohde, Gernot; Kersting, Kristian; Hinz, Oliver

Abstract: The most promising standard machine learning methods can deliver highly accurate ... Expand

Abstract: The most promising standard machine learning methods can deliver highly accurate classification results, often outperforming standard white-box methods. However, it is hardly possible for humans to fully understand the rationale behind the black-box results, and thus, these powerful methods hamper the creation of new knowledge on the part of humans and the broader acceptance of this technology. Explainable Artificial Intelligence attempts to overcome this problem by making the results more interpretable, while Interactive Machine Learning integrates humans into the process of insight discovery. The paper builds on recent successes in combining these two cutting-edge technologies and proposes how Explanatory Interactive Machine Learning (XIL) is embedded in a generalizable Action Design Research (ADR) process – called XIL-ADR. This approach can be used to analyze data, inspect models, and iteratively improve them. The paper shows the application of this process using the diagnosis of viral pneumonia, e.g., Covid-19, as an illustrative example. By these means, the paper also illustrates how XIL-ADR can help identify shortcomings of standard machine learning projects, gain new insights on the part of the human user, and thereby can help to unlock the full potential of AI-based systems for organizations and research. Collapse

Topics: explainable artificial intelligence database system crowdsourcing artificial intelligence cloud computing

Methods: machine learning action design research case study computational algorithm design science

Deep Neural Network at Edge: An Exploration of Hyper Parameter Tuning on Plant Seedling Dataset

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Shaheen, Ali; El-Gayar, Omar

Abstract: This study explored different hyperparameters and their outcomes on multiple DN ... Expand

Abstract: This study explored different hyperparameters and their outcomes on multiple DNN architectures by incorporating transfer learning technique on the plant seedling dataset. Optimizers can have different strengths and weaknesses, and their performance may depend on the specific characteristics of the model and the dataset being used. We have observed that the choice of the optimizer is just one of many hyperparameters that can affect the performance of deep neural network (DNN) models. Other hyperparameters, such as the droprate, number of epochs, and batch size, can also have a significant impact. MobileNetV2 demonstrated superior performance while maintaining a smaller model size, making it a highly valuable option for edge devices where size is a crucial factor. Collapse

Topics: Google+ information system use data visualization Python

Methods: experiment deep learning optimization model Keras machine learning

A Light in the Dark: Deep Learning Practices for Industrial Computer Vision

2022 | International Conference on Business Informatics | Citations: 0

Authors: Harl, Maximilian V; Herchenbach, Marvin; Kruschel, Sven; Hambauer, Nico; Zschech, Patrick; Kraus, Mathias

Abstract: In recent years, large pre-trained deep neural networks (DNNs) have revolutioniz ... Expand

Abstract: In recent years, large pre-trained deep neural networks (DNNs) have revolutionized the field of computer vision (CV). Although these DNNs have been shown to be very well suited for general image recognition tasks, application in industry is often precluded for three reasons: 1) large pre-trained DNNs are built on hundreds of millions of parameters, making deployment on many devices impossible, 2) the underlying dataset for pre-training consists of general objects, while industrial cases often consist of very specific objects, such as structures on solar wafers, 3) potentially biased pre-trained DNNs raise legal issues for companies. As a remedy, we study neural networks for CV that we train from scratch. For this purpose, we use a real-world case from a solar wafer manufacturer. We find that our neural networks achieve similar performances as pre-trained DNNs, even though they consist of far fewer parameters and do not rely on third-party datasets. Collapse

Topics: competitive advantage Google+ edge computing explainable artificial intelligence data quality

Methods: experiment artificial neural network descriptive statistic literature study computational algorithm

Instance Selection Mechanisms for Human-in-the-Loop Systems in Few-Shot Learning

2022 | International Conference on Business Informatics | Citations: 0

Authors: Jakubik, Johannes; Blumenstiel, Benedikt; Vössing, Michael; Hemmer, Patrick

Abstract: Business analytics and machine learning have become essential success factors fo ... Expand

Abstract: Business analytics and machine learning have become essential success factors for various industries—with the downside of cost-intensive gathering and labeling of data. Few-shot learning addresses this challenge and reduces data gathering and labeling costs by learning novel classes with very few labeled data. In this paper, we design a human-in-the-loop (HITL) system for few-shot learning and analyze an extensive range of mechanisms that can be used to acquire human expert knowledge for instances that have an uncertain prediction outcome. We show that the acquisition of human expert knowledge significantly accelerates the few-shot model performance given a negligible labeling effort. We validate our findings in various experiments on a benchmark dataset in computer vision and real-world datasets. We further demonstrate the cost-effectiveness of HITL systems for few-shot learning. Overall, our work aims at supporting researchers and practitioners in effectively adapting machine learning models to novel classes at reduced costs. Collapse

Topics: human in the loop human computer interaction artificial intelligence online learning system autonomous driving system

Methods: design artifact experiment ImageNet k-means clustering data transformation

Classification of COVID-19 Cases: The Customized Deep Convolutional Neural Network and Transfer Learning Approach

2022 | Americas Conference on Information Systems | Citations: 0

Authors: Vyas, Piyush; Ragothaman, Kaushik Nagarajan Muthusamy; Chauhan, Akhilesh; Rimal, Bhaskar P.

Abstract: The recent advancements under the umbrella of artificial intelligence (AI) open ... Expand

Abstract: The recent advancements under the umbrella of artificial intelligence (AI) open opportunities to tackle complex problems related to image analysis. Recently, the proliferation of COVID-19 brought multiple challenges to medical practitioners, such as precise analysis and classification of COVID-19 cases. Deep learning (DL) and transfer learning (TL) techniques appear to be attractive solutions. To provide the precise classification of COVID-19 cases, this article presents a customized Deep Convolutional Neural Network (DCNN) and pre-trained TL model approach. Our pipeline accommodated several popular pre-trained TL models, namely DenseNet121, ResNet50, InceptionV3, EfficientNetB0, and VGG16, to classify COVID-19 positive and negative cases. We evaluated and compared the performance of these models with a wide range of measures, including accuracy, precision, recall, and F1 score for classifying COVID-19 cases based on chest X-rays. The results demonstrate that our customized DCNN model performed well with randomly assigned weights, achieving 98.5% recall and 97.0% accuracy. KeywordsCovid19, transfer learning, deep convolutional neural network, medical imaging. Collapse

Topics: Google Cloud Platform Google+ covid 19

Methods: machine learning ImageNet deep learning convolutional neural network literature study

Model identification for ARMA time series through convolutional neural networks

2021 | Decision Support Systems | Citations: 0

Authors: Tang, Wai Hoh; Röllin, Adrian

Abstract: We use convolutional neural networks for model identification in ARMA time serie ... Expand

Abstract: We use convolutional neural networks for model identification in ARMA time series models, where our networks are trained on synthetic data with known ground truths. Comparing the performance of these networks with traditional likelihood-based methods, in particular the Akaike and Bayesian Information Criteria, we are able to show that when it comes to statistical inference on ARMA orders, neural networks can significantly outperform likelihood-based methods in terms of accuracy and, by orders of magnitude, in terms of speed. We also observe improvements in terms of time series forecasting. Our approach shows the feasibility of using artificial neural networks for statistical inference in situations where classical likelihood-based methods are difficult or costly to implement. Collapse

Methods: time series analysis longitudinal research autoregressive moving average model artificial neural network residual neural network

Theories: mathematical theory

Enhancing Social Media Analysis with Visual Data Analytics: A Deep Learning Approach

2020 | Management Information Systems Quarterly | Citations: 0

Authors: Donghyuk Shin; Shu He; Gene Moo Lee; Whinston, Andrew B.; Cetintas, Suleyman; Kuang-Chih Lee

Abstract: This research methods article proposes a visual data analytics framework to enha ... Expand

Abstract: This research methods article proposes a visual data analytics framework to enhance social media research using deep learning models. Drawing on the literature of information systems and marketing, complemented with data-driven methods, we propose a number of visual and textual content features including complexity, similarity, and consistency measures that can play important roles in the persuasiveness of social media content. We then employ state-of-the-art machine learning approaches such as deep learning and text mining to operationalize these new content features in a scalable and systematic manner. For the newly developed features, we validate them against human coders on Amazon Mechanical Turk. Furthermore, we conduct two case studies with a large social media dataset from Tumblr to show the effectiveness of the proposed content features. The first case study demonstrates that both theoretically motivated and data-driven features significantly improve the model’s power to predict the popularity of a post, and the second one highlights the relationships between content features and consumer evaluations of the corresponding posts. The proposed research framework illustrates how deep learning methods can enhance the analysis of unstructured visual and textual data for social media research. Collapse

Topics: social media Tumblr blog analytical information system Flickr

Methods: deep learning case study word2vec machine learning experiment

Theories: elaboration likelihood model