A Multi-Label Classification with an Adversarial-Based Denoising Autoencoder for Medical Image Annotation

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

Authors: Chai, Yidong; Liu, Hongyan; Xu, Jie; Samtani, Sagar; Jiang, Yuanchun; Liu, Haoxin

Abstract: Medical image annotation aims to automatically describe the content of medical i ... Expand

Abstract: Medical image annotation aims to automatically describe the content of medical images. It helps doctors to understand the content of medical images and make better informed decisions like diagnoses. Existing methods mainly follow the approach for natural images and fail to emphasize the object abnormalities, which is the essence of medical images annotation. In light of this, we propose to transform the medical image annotation to a multi-label classification problem, where object abnormalities are focused directly. However, extant multi-label classification studies rely on arduous feature engineering, or do not solve label correlation issues well in medical images. To solve these problems, we propose a novel deep learning model where a frequent pattern mining component and an adversarial-based denoising autoencoder component are introduced. Extensive experiments are conducted on a real retinal image dataset to evaluate the performance of the proposed model. Results indicate that the proposed model significantly outperforms image captioning baselines and multi-label classification baselines. Collapse

Topics: workstation

Methods: data transformation autoencoder experiment deep learning literature study

Conversation Analytics: Can Machines Read between the Lines in Real-Time Strategic Conversations?

2023 | HICSS | Citations: 0

Authors: Chen, Y.; Rui, H.; Whinston, A.

Abstract: Strategic conversations involve one party with an informational advantage and t ... Expand

Abstract: Strategic conversations involve one party with an informational advantage and the other with an interest in the information. This paper proposes machinelearning based measures to quantify the degrees of evasiveness and incoherence of the informed party during real-time strategic conversations. The specific empirical context is the questions and answers (Q&A) part of earnings conference calls during which managers endure high pressure as they face analysts' scrutinizing questions. Being reluctant to disclose adverse information, managers may resort to evasive answers and sometimes respond less coherently due to increased cognitive load. Using data from the earnings calls of the S&P 500 companies from 2006 to 2018, we show that the proposed measures predict worse nextquarter earnings. Moreover, the stock market perceives incoherence as a negative signal. This paper contributes methodologically by developing two novel machinepowered measures to automatically evaluate behavioral cues during real-time strategic conversations. The proposed analytical tools are particularly beneficial to resource-constrained and informationally disadvantaged parties such as retail investors who may not be able to effectively trade on signals buried deep in unstructured conversational data. Collapse

Topics: database system artificial intelligence electronic finance missing data accounting

Methods: computational algorithm BERT deep learning machine learning next sentence prediction

Theories: theory of economic growth

Improved learning performance for small datasets in high dimensions by new dual-net model for non-linear interpolation virtual sample generation

2023 | Decision Support Systems | Citations: 0

Authors: Lin, Liang-Sian; Lin, Yao-San; Li, Der-Chiang; Liu, Yun-Hsuan

Abstract: The number of reliable samples obtained in early decision-making activity is usu ... Expand

Abstract: The number of reliable samples obtained in early decision-making activity is usually relatively small. Due to variable distribution and incomplete structure of tiny datasets, it is challenging to create reliable and robust predictive modeling using classic statistical and machine learning models in small sample settings. The virtual sample generation (VSG) technique improves model learning accuracies for minimal datasets across diverse applications. Virtual samples on independent variables were generated using established VSG methods predi­ cated on the assumption of a probability distribution or a membership function to fill data gaps. However, in the actual world, non-linear function interactions between variables are common. To address this issue, this paper developed a novel VSG method called Dual-VSG, which generates non-linear interpolation virtual samples using a self-supervised learning (SSL) framework to improve learning performance on small datasets. We generated non-linear interpolation virtual samples without labels by estimating non-linear functions and transforming them into a high-dimensional space using the proposed dual-net model. The weights of the dual-net model are transferred to a downstream task to generate virtual sample labels. To demonstrate the effectiveness of the suggested strategy, this research employed five datasets. On the Backpropagation Neural Networks (BPNN) predictive model, we compared the suggested method’s prediction performance to two state-of-the-art VSG approaches. To assess prediction performance on a regression dataset, the Mean Absolute Percentage Error (MAPE) and the Root Mean Square Error (RMSE) are used. Furthermore, the classification accuracy (ACC) and the Fl measure are used to assess classification capability on classification datasets. In addition, the paired t-test was utilized to see if the suggested Dual-VSG approach differed significantly from the other VSG methods in terms of RMSE, MAPE, accuracy (ACC), or F1 score. For short datasets, the suggested Dual-VSG method out­ performs those VSG methods, according to our experimental results. Collapse

Topics: Python programming language

Methods: data transformation t-distributed stochastic neighbor embedding experiment machine learning parametric test

Semi-Supervised Discovery of DNN-Based Outcome Predictors from Scarcely-Labeled Process Logs

2022 | Business & Information Systems Engineering | Citations: 0

Authors: Folino, Francesco; Folino, Gianluigi; Guarascio, Massimo; Pontieri, Luigi

Abstract: Predicting the final outcome of an ongoing process instance is a key problem in ... Expand

Abstract: Predicting the final outcome of an ongoing process instance is a key problem in many real-life contexts. This problem has been addressed mainly by discovering a prediction model by using traditional machine learning methods and, more recently, deep learning methods, exploiting the supervision coming from outcome-class labels associated with historical log traces. However, a supervised learning strategy is unsuitable for important application scenarios where the outcome labels are known only for a small fraction of log traces. In order to address these challenging scenarios, a semi-supervised learning approach is proposed here, which leverages a multi-target DNN model supporting both outcome prediction and the additional auxiliary task of next-activity prediction. The latter task helps the DNN model avoid spurious trace embeddings and overfitting behaviors. In extensive experimentation, this approach is shown to outperform both fully-supervised and semi-supervised discovery methods using similar DNN architectures across different real-life datasets and label-scarce settings. Collapse

Topics: application programming interface Python business process management data breach database system

Methods: machine learning semi-supervised learning experiment computational algorithm statistical hypothesis test

A Novel Business Process Prediction Model Using a Deep Learning Method

2020 | Business & Information Systems Engineering | Citations: 6

Authors: Mehdiyev, Nijat; Evermann, Joerg; Fettke, Peter

Abstract: The ability to proactively monitor business processes is a main competitive diff ... Expand

Abstract: The ability to proactively monitor business processes is a main competitive differentiator for firms. Process execution logs generated by process aware information systems help to make process specific predictions for enabling a proactive situational awareness. The goal of the proposed approach is to predict the next process event from the completed activities of the running process instance, based on the execution log data from previously completed process instances. By predicting process events, companies can initiate timely interventions to address undesired deviations from the desired workflow. The paper proposes a multi-stage deep learning approach that formulates the next event prediction problem as a classification problem. Following a feature pre-processing stage with n-grams and feature hashing, a deep learning model consisting of an unsupervised pre-training component with stacked autoencoders and a supervised fine-tuning component is applied. Experiments on a variety of business process log datasets show that the multi-stage deep learning approach provides promising results. The study also compared the results to existing deep recurrent neural networks and conventional classification approaches. Furthermore, the paper addresses the identification of suitable hyperparameters for the proposed approach, and the handling of the imbalanced nature of business process event datasets. Collapse

Topics: business process management open source Microsoft Azure Java information retrieval

Methods: deep learning experiment machine learning autoencoder classification method

Beyond search: Retrieving complete tuples from a text-database

2013 | Information Systems Frontiers | Citations: 0

Authors: Löser, Alexander; Nagel, Christoph; Pieper, Stephan; Boden, Christoph

Abstract: A common task of Web users is querying structured information from Web pages. Fo ... Expand

Abstract: A common task of Web users is querying structured information from Web pages. For realizing this interesting scenario we propose a novel query processor for systematically discovering instances of semantic relations in Web search results and joining these relation instances into complex result tuples with conjunctive queries. Our query processor transforms a structured user query into keyword queries that are submitted to a search engine, forwards search results to a relation extractor, and then combines relations into complex result tuples. The processor automatically learns discriminative and effective keywords for different types of semantic relations. Thereby, our query processor leverages the index of a search engine to query potentially billions of pages. Unfortunately, relation extractors may fail to return a relation for a result tuple. Moreover, user defined data sources may not return at least k complete result tuples. Therefore we propose an adaptive routing model based on information theory for retrieving missing attributes of incomplete result tuples. The model determines the most promising next incomplete tuple and attribute type for returning any-k complete result tuples at any point during the query execution process. We report a thorough experimental evaluation over multiple relation extractors. Our query processor returns complete result tuples while processing only very few Web pages. Collapse

Topics: web page search engine database system web search engine laptop computer

Methods: experiment computational algorithm literature study self-supervised learning natural language processing

Theories: information theory