Quality of life (QoL) is one of the major issues for cancer patients. With the advent of medical databases containing large amounts of relevant QoL information it becomes possible to train predictive QoL models by machine learning (ML) techniques. However, the training of predictive QoL models poses several challenges mostly due to data privacy concerns and missing values in patient data. In this paper, we analyze several classification and regression ML models predicting QoL indicators for breast and prostate cancer patients. Two different approaches are employed for imputing missing values. The examined ML models are trained on datasets formed from two databases containing a large number of anonymized medical records of cancer patients from Sweden. Two learning scenarios are considered: centralized and federated learning. In the centralized learning scenario all patient data coming from different data sources is collected at a central location prior to model training. On the other hand, federated learning enables collective training of machine learning models without data sharing. The results of our experimental evaluation show that the predictive power of federated models is comparable to that of centrally trained models for short-term QoL predictions, whereas for long-term periods centralized models provide more accurate QoL predictions.

Human activities and behaviour in different domains are usually influenced by other people’s actions and opinion. Nowadays, it is evident that there is a growing research interest in sentiment analysis, evaluation and prediction. Content from web sources and social media is frequently used when people want to see others’ opinion about different things. Our research is focused on ML-based sentiment analysis of food services reviews data. The comparison of several regression models with regards to prediction of customer satisfaction of restaurant and food services is presented. The experimental data collected from food serving businesses located in Shanghai Lujiazui Commercial Zone includes keywords extracted from the customers’ written reviews. Additionally, the data are spatially labelled enabling to conduct separate analyses for different geographical regions. As a conclusion, the keywords extracted from the customer’s reviews were suitable for the prediction of three observed satisfaction criteria: food taste, service, and environment.

Improvement of prediction accuracy and early detection of the Alzheimer’s disease is becoming increasingly important for managing its impact on lives of affected patients. Many machine learning approaches have been applied to support the diagnosis and prediction of this illness. In this paper we propose an approach for improving the Alzheimer’s disease classification accuracy by using data fusion of several independent clinical datasets. Data fusion was performed twofold: 1) by enriching attributes of the base dataset with the attributes of the secondary dataset and 2) by enriching the examples set of the base dataset with the examples of the secondary dataset. In both cases the missing values (for newly added attributes and/or examples) were predicted by using linear regression for numeric and naive Bayes classifier for nominal attributes. We experimented on three data sources: on a dataset of Alzheimer’s disease-impaired patients, on a dataset of patients with vascular dementia, and on a dataset of patients who have been affected by a stroke. We fused these datasets with different data fusion approaches and analysed the improvement in classification accuracy as well as the quality of the fused attributes. The experiments indicated that we obtained an increase of classification accuracy on the fused dataset compared with the accuracy obtained from individual dataset.

The problem of time-series classification witnessed the application of many techniques for data mining and machine learning, including neural networks, support vector machines, and Bayesian approaches. Somewhat surprisingly, the simple 1-nearest neighbor (1NN) classifier, in combination with the Dynamic Time Warping (DTW) distance measure, is still competitive and not rarely superior to more advanced classification methods, which includes the majority-voting k-nearest neighbor (kNN) classifier. In this paper we focus on the kNN classifier combined with the inverse-squared weighting scheme, and its interaction with constrained DTW distance. By performing experiments on the entire UCR Time Series Classification Archive we show that with proper selection of the constraint parameter r and neighborhood size k, inverse-square weighted kNN consistently outperforms 1NN.

In the domain of time-series classification, one simple but persistently successful method is the 1-nearest neighbour (1NN) classifier coupled with an elastic distance measure such as Dynamic Time Warping (DTW). In this paper we evaluate the performance of DTW when constrained using the Itakura parallelogram, and compare it with the more commonly used Sakoe-Chiba band, as well as with the unconstrained DTW. Results show that although the Itakura parallelogram is generally inferior to the Sakoe-Chiba band, it is still superior to unconstrained DTW. Furthermore, on individual data sets the Itakura parallelogram can produce superior results, warranting further investigation into the merits of its use with DTW and other elastic distance measures for time-series classification.

This paper outlines the primary steps to investigate if artificial agents can be considered as true substitutes of humans. Based on a Socially augmented microworld (SAM) human tracking behavior was analyzed using time series. SAM involves a team of navigators jointly steering a driving object along different virtual tracks containing obstacles and forks. Speed and deviances from track are logged, producing high-resolution time series of individual (training) and cooperative tracking behavior. In the current study 52 time series of individual tracking behavior on training tracks were clustered according to different similarity measures. Resulting clusters were used to predict cooperative tracking behavior in fork situations. Results showed that prediction was well for tracking behavior shown at the first and, moderately well at the third fork of the cooperative track: navigators switched from their trained to a different tracking style and then back to their trained behavior. This matches with earlier identified navigator types, which were identified on visual examination. Our findings on navigator types will serve as a basis for the development of artificial agents, which can be compared later to behavior of human navigators.

Abstract Case‐based reasoning (CBR) is the area of artificial intelligence where problems are solved by adapting solutions that worked for similar problems from the past. This technique can be applied in different domains and with different problem representations. In this paper, a system curve base generator (CuBaGe) is presented. This framework is designed to be a domain‐independent prediction system for the analysis and prediction of curves and time‐series trends, based on the CBR technology.CuBaGeemploys a novel curve representation method based on splines and a corresponding similarity function based on definite integrals. This combination of curve representation and similarity measure showed excellent results with sparse and non‐equidistant time series, which is demonstrated through a set of experiments. Copyright © 2008 John Wiley & Sons, Ltd.

Case-based reasoning (CBR) is the area of the artificial intelligence in which the new problems are solved by adapting the solutions of the previously successfully solved similar problems. Medicine is a suitable domain for application of CBR because the knowledge of medical experts consists of mixture of textbook knowledge and experience, which consists of cases. Architecture of the system for the diagnoses of multiple sclerosis disease, based on CBR is proposed in this paper.