Near-Infrared Spectroscopy for Bladder Monitoring: A Machine Learning Approach

2023 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Fechner, Pascal; König, Fabian; Kratsch, Wolfgang; Lockl, Jannik; Röglinger, Maximilian

Abstract: Patients living with neurogenic bladder dysfunction can lose the sensation of th ... Expand

Abstract: Patients living with neurogenic bladder dysfunction can lose the sensation of their bladder filling. To avoid over-distension of the urinary bladder and prevent long-term damage to the urinary tract, the gold standard treatment is clean intermittent catheterization at predefined time intervals. However, the emptying schedule does not consider actual bladder volume, meaning that catheterization is performed more often than necessary, which can lead to complications such as urinary tract infections. Time-consuming catheterization also interferes with patients' daily routines and, in the case of an empty bladder, uses human and material resources unnecessarily. To enable individually tailored and volume-responsive bladder management, we design a model for the continuous monitoring of bladder volume. During our design science research process, we evaluate the model's applicability and usefulness through interviews with affected patients, prototyping, and application to a real-world in vivo dataset. The developed prototype predicts bladder volume based on relevant sensor data (i.e., near-infrared spectroscopy and acceleration) and the time elapsed since the previous micturition. Our comparison of several supervised state-of-the-art machine and deep learning models reveals that a long short-term memory network architecture achieves a mean absolute error of 116.7 ml that can improve bladder management for patients. Collapse

Topics: computer hardware open source mobile application user interface programming language

Methods: design artifact qualitative interview design process support vector machine computational algorithm

Decoding the Mindset: A Neural Network Approach for Analyzing CEO’s Digital Strategy and Its Innovation Implications

2023 | International Conference on Information Systems | Citations: 0

Authors: Schaeper, Thomas; Maibaum, Frederik; Schulz, Colin; Foege, Johann Nils

Abstract: The swift advancement of digital technologies demands CEOs to prioritize digita ... Expand

Abstract: The swift advancement of digital technologies demands CEOs to prioritize digital innovation strategies to stay competitive. However, an overemphasis on digitality, neglecting aspects like customer focus, operations, and collaboration, can hinder innovation. Using a neural network, we evaluated CEOs' digital strategies by training on 1,000 company pitches and applying this to S&P 500 CEOs ' Shareholder Letters (2001-2018. We discovered an inverted U relationship between digital strategy intensity and innovation performance. This stresses the need for a balanced strategy with the right digital focus. Our research illuminates top executives' digital mindset in driving innovation, emphasizing the potential pitfalls of a purely digital approach. Furthermore, our machine-learning method offers a novel, scalable way to quantify digital strategy, paving the way for subsequent research. Collapse

Topics: information systems strategy innovation management database system accounting decision making

Methods: artificial neural network machine learning deep learning computational algorithm Keras

Theories: upper echelons theory

Deep Learning in Predicting Real Estate Property Prices: A Comparative Study

2023 | HICSS | Citations: 0

Authors: Shi, D.; Zhang, H.; Guan, J.; Zurada, J.; Chen, Z.; Li, X.

Abstract: The dominant methods for real estate property price prediction or valuation are ... Expand

Abstract: The dominant methods for real estate property price prediction or valuation are multi-regression based. Regression-based methods are, however, imperfect because they suffer from issues such as multicollinearity and heteroscedasticity. Recent years have witnessed the use of machine learning methods but the results are mixed. This paper introduces the application of a new approach using deep learning models to real estate property price prediction. The paper uses a deep learning approach for modeling to improve the accuracy of real estate property price prediction with data representing sales transactions in a large metropolitan area. Three deep learning models, LSTM, GRU and Transformer, are created and compared with other machine learning and traditional models. The results obtained for the data set with all features clearly show that the RF and Transformer models outperformed the other models. LSTM and GRU models produced the worst results, suggesting that they are perhaps not suitable to predict the real estate price. Furthermore, the implementations of Transformer and RF on a data set with feature reduction produced even more accurate prediction results. In conclusion, our research shows that the performance of the Transformer model is close to the RF model. Both models produce significantly better prediction results than existing approaches in terms of accuracy. Collapse

Topics: Python open source

Methods: deep learning transformer model machine learning autoregressive moving average model experiment

Novel role-wise attention mechanism for predicting purchases made through chat-based online customer services

2023 | Decision Support Systems | Citations: 0

Authors: Wang, Yajing; Chen, Gang; Xu, Yunjie (Calvin); Lu, Xianghua

Abstract: Online chat has become a key channel for firms to provide pre-purchase customer ... Expand

Abstract: Online chat has become a key channel for firms to provide pre-purchase customer services and generate pur­ chases. Firms must deploy their service personnel based on the customers' purchase probability. Conversational contingency is indicative of purchase probability. However, the unstructured nature of textual data hinders the use of interaction information. We develop a novel role-wise attention mechanism to capture the conversational contingency among customers and service agents. Our results reveal that the role-wise attention mechanism is effective for measuring service interaction quality. When the mechanism is combined with a deep-learning model, it outperforms traditional self-attention mechanisms for predicting customer purchases. The area under the curve of the model is 0.85. Ablation studies indicate that external attention, a core element of the role-wise attention mechanism, substantially improves prediction performance by capturing the conversational contin­ gency between communicators. Collapse

Topics: customer service social media online chat Python service-support information system

Methods: machine learning BERT deep learning design artifact ablation analysis

Social Media and Fake News Detection using Adversarial Collaboration

2022 | HICSS | Citations: 0

Authors: Dsouza, Karen; French, Aaron

Abstract: The diffusion of fake information on social media networks obscures public perce ... Expand

Abstract: The diffusion of fake information on social media networks obscures public perception of events, news, and relevant content. Intentional misleading news may promote negative online experiences and influence societal behavioral changes such as increased anxiety, loneliness, and inadequacy. Adversarial attacks target creating misinformation in online information systems. This behavior can be viewed as an instrument to manipulate the online social media networks for cultural, social, economic, and political gains. A method to test a deep learning model- long short-term memory (LSTM) using adversarial examples generated from a transformer model has been presented. The paper attempts to examine features in machine learning algorithms that propagate fake news. Another goal is to evaluate and compare the usefulness of generative adversarial networks with long-term short-term recurrent neural network algorithms in identifying fake news. A closer look at the mechanisms of implementing adversarial attacks in social media systems helps build robust intelligent systems that can withstand future vulnerabilities. Collapse

Topics: fake news social media Python database system web page

Methods: computational algorithm experiment machine learning deep learning artificial neural network

A Multi-attention Collaborative Deep Learning Approach for Blood Pressure Prediction

2022 | ACM Transactions on Management Information Systems | Citations: 0

Authors: He, Luo; Liu, Hongyan; Yang, Yinghui; Wang, Bei

Abstract: We develop a deep learning model based on Long Short-term Memory (LSTM) to predi ... Expand

Abstract: We develop a deep learning model based on Long Short-term Memory (LSTM) to predict blood pressure based on a unique data set collected from physical examination centers capturing comprehensive multi-year physical examination and lab results. In the Multi-attention Collaborative Deep Learning model (MAC-LSTM) we developed for this type of data, we incorporate three types of attention to generate more explainable and accurate results. In addition, we leverage information from similar users to enhance the predictive power of the model due to the challenges with short examination history. Our model significantly reduces predictive errors compared to several state-of-the-art baseline models. Experimental results not only demonstrate our model’s superiority but also provide us with new insights about factors influencing blood pressure. Our data is collected in a natural setting instead of a setting designed specifically to study blood pressure, and the physical examination items used to predict blood pressure are common items included in regular physical examinations for all the users. Therefore, our blood pressure prediction results can be easily used in an alert system for patients and doctors to plan prevention or intervention. The same approach can be used to predict other health-related indexes such as BMI. Collapse

Topics: health information system decision making

Methods: blood pressure deep learning time series analysis longitudinal research experiment

Predicting Stages in Omnichannel Path to Purchase: A Deep Learning Model

2022 | Information Systems Research | Citations: 1

Authors: Sun, Chenshuo; Adamopoulos, Panagiotis; Ghose, Anindya; Luo, Xueming

Abstract: The proliferation of omnichannel practices and emerging technologies opens up ne ... Expand

Abstract: The proliferation of omnichannel practices and emerging technologies opens up new opportunities for companies to collect voluminous data across multiple channels. This study examines whether leveraging omnichannel data can lead to, statistically and economically, significantly better predictions on consumers’ online path-to-purchase journeys, given the intrinsic fluidity in and heterogeneity brought forth by the digital transformation of traditional marketing. Using an omnichannel data set that captures consumers’ online behavior in terms of their website browsing trajectories and their offline behavior in terms of physical location trajectories, we predict consumers’ future path-to-purchase journeys based on their historical omnichannel behaviors. Using a state-of-the-art deep-learning algorithm, we find that using omnichannel data can significantly improve our model’s predictive power. The lift curve analysis reveals that the omnichannel model outperforms the corresponding single-channel model by 7.38%. This enhanced predictive power benefits various heterogeneous online firms, regardless of their size, offline presence, mobile app availability, or whether they are selling single- or multicategory products. Using an illustrative example of targeted marketing, we further quantify the economic value of the improved predictive power using a cost-revenue analysis. Our paper contributes to the emerging literature on omnichannel marketing and sheds light on the inherent dynamics and fluidity in consumers’ online path-to-purchase journeys. Collapse

Topics: marketing management website electronic commerce mobile application advertising management

Methods: machine learning deep learning computational algorithm descriptive statistic logistic regression

Combining Crowd and Machine Intelligence to Detect False News on Social Media

2022 | Management Information Systems Quarterly | Citations: 1

Authors: Wei, Xuan; Zhang, Zhu; Zhang, Mingyue; Chen, Weiyun; Zeng, Daniel

Abstract: The explosive spread of false news on social media has severely affected many ar ... Expand

Abstract: The explosive spread of false news on social media has severely affected many areas such as news ecosystems, politics, economics, and public trust, especially amid the COVID-19 infodemic. Machine intelligence has met with limited success in detecting and curbing false news. Human knowledge and intelligence hold great potential to complement machine-based methods. Yet they are largely underexplored in current false news detection research, especially in terms of how to efficiently utilize such information. We observe that the crowd contributes to the challenging task of assessing the veracity of news by posting responses or reporting. We propose combining these two types of scalable crowd judgments with machine intelligence to tackle the false news crisis. Specifically, we design a novel framework called CAND, which first extracts relevant human and machine judgments from data sources including news features and scalable crowd intelligence. The extracted information is then aggregated by an unsupervised Bayesian aggregation model. Evaluation based on Weibo and Twitter datasets demonstrates the effectiveness of crowd intelligence and the superior performance of the proposed framework in comparison with the benchmark methods. The results also generate many valuable insights, such as the complementary value of human and machine intelligence, the possibility of using human intelligence for early detection, and the robustness of our approach to intentional manipulation. This research significantly contributes to relevant literature on false news detection and crowd intelligence. In practice, our proposed framework serves as a feasible and effective approach for false news detection. Collapse

Topics: fake news Twitter logistics management social media Python

Methods: computational algorithm machine learning experiment support vector machine BERT

Applied machine learning for a zero defect tolerance system in the automated assembly of pharmaceutical devices

2021 | Decision Support Systems | Citations: 0

Authors: Dengler, Sebastian; Lahriri, Said; Trunzer, Emanuel; Vogel-Heuser, Birgit

Abstract: Creating reliable and robust quality control systems that identify process error ... Expand

Abstract: Creating reliable and robust quality control systems that identify process errors while having a low number of false rejects is a considerable challenge in the automated manufacturing industry. Especially in the pharma­ ceutical industry, where a product’s quality has to be ensured at all costs, a large amount of false rejects is acceptable to guarantee the integrity of all released products. As standard quality control systems mainly perform a binary classification, most of them do not provide insights about the reason behind rejections. As a result, the underlying reason for the rejects, such as degradation in equipment or wrong settings in process parameters, often goes unnoticed. Yet, these systems are based on conservative approaches that incorporate the uncertainties related to the measurement system and process variation such as batch-to-batch variations and assembly tol­ erances. In this contribution, a new data-driven quality control system is suggested. The system is based on wellestablished machine learning methods that differentiate multiple types of errors in the assembly processes of medical products. Trained on process data, the system’s functionality is demonstrated in a pre-study and two real industrial use cases. Moreover, application-specific differences are discussed. It is shown that for the two use cases and a limited number of batches the system not only detects 100% of all defective products but also limits the number of false rejects to an acceptable amount. In all of the application examples, the system has the po­ tential to be executed as a soft real-time system that allows integration into industrial processes. Moreover, it is shown that the algorithm can present the extracted knowledge in various forms understandable for humans, allowing for more informed decision making. Collapse

Topics: application programming interface Python source code decision making computer hardware

Methods: computational algorithm support vector machine time series analysis longitudinal research experiment

Transfer Learning to enable Flexibility of Demand Forecasting: Dropout Profiles to protect from Negative Transfer

2021 | European Conference On Information Systems | Citations: 3

Authors: Hütsch, Marek

Abstract: One of the largest investments of a company is its implementation of an enterpr ... Expand

Abstract: One of the largest investments of a company is its implementation of an enterprise system. Sometimes, companies, and thus their enterprise systems, face changes that were not foreseen at the time the system was implemented. One example can be found in the COVID-19 pandemic in which retailers are facing the huge problem that current forecasting models no longer produce accurate forecasts and changes in feature spaces are needed. In this paper transfer learning and a proposed method, called dropout profiles, are used to react faster to changes in feature space. This method is implemented in a case study with changes in the feature space of a demand forecast. It is shown that the proposed method performs significantly better than traditional methods. In practice, this means that neural networks can expect a longer life cycle and companies can react faster to changes in the market. Collapse

Topics: enterprise information system knowledge sharing Python logistics management pandemic

Methods: artificial neural network case study simulation computational algorithm design science