Ensemble method using real images, metadata and synthetic images for control of class imbalance in classification.

Binary classification and anomaly detection face the problem of class imbalance in data sets. The contribution of this paper is to provide an ensemble model that improves image binary classification by reducing the class imbalance between the minority and majority classes in a data set. The ensemble model is a classifier of real images, synthetic images, and metadata associated with the real images. First, we apply a generative model to synthesize images of the minority class from the real image data set. Secondly, we train the ensemble model jointly with synthesized images of the minority class, real images, and metadata. Finally, we evaluate the model performance using a sensitivity metric to observe the difference in classification resulting from the adjustment of class imbalance. Improving the imbalance of the minority class by adding half the size of the majority class we observe an improvement in the classifier's sensitivity by 12% and 24% for the benchmark pre-trained models of RESNET50 and DENSENet121 respectively.

Familiarity effects in EEG-based emotion recognition.

Although emotion detection using electroencephalogram (EEG) data has become a highly active area of research over the last decades, little attention has been paid to stimulus familiarity, a crucial subjectivity issue. Using both our experimental data and a sophisticated database (DEAP dataset), we investigated the effects of familiarity on brain activity based on EEG signals. Focusing on familiarity studies, we allowed subjects to select the same number of familiar and unfamiliar songs; both resulting datasets demonstrated the importance of reporting self-emotion based on the assumption that the emotional state when experiencing music is subjective. We found evidence that music familiarity influences both the power spectra of brainwaves and the brain functional connectivity to a certain level. We conducted an additional experiment using music familiarity in an attempt to recognize emotional states; our empirical results suggested that the use of only songs with low familiarity levels can enhance the performance of EEG-based emotion classification systems that adopt fractal dimension or power spectral density features and support vector machine, multilayer perceptron or C4.5 classifier. This suggests that unfamiliar songs are most appropriate for the construction of an emotion recognition system.

Effects of individual health topic familiarity on activity patterns during health information searches.

BACKGROUND: Non-medical professionals (consumers) are increasingly using the Internet to support their health information needs. However, the cognitive effort required to perform health information searches is affected by the consumer's familiarity with health topics. Consumers may have different levels of familiarity with individual health topics. This variation in familiarity may cause misunderstandings because the information presented by search engines may not be understood correctly by the consumers. OBJECTIVE: As a first step toward the improvement of the health information search process, we aimed to examine the effects of health topic familiarity on health information search behaviors by identifying the common search activity patterns exhibited by groups of consumers with different levels of familiarity. METHODS: Each participant completed a health terminology familiarity questionnaire and health information search tasks. The responses to the familiarity questionnaire were used to grade the familiarity of participants with predefined health topics. The search task data were transcribed into a sequence of search activities using a coding scheme. A computational model was constructed from the sequence data using a Markov chain model to identify the common search patterns in each familiarity group. RESULTS: Forty participants were classified into L1 (not familiar), L2 (somewhat familiar), and L3 (familiar) groups based on their questionnaire responses. They had different levels of familiarity with four health topics. The video data obtained from all of the participants were transcribed into 4595 search activities (mean 28.7, SD 23.27 per session). The most frequent search activities and transitions in all the familiarity groups were related to evaluations of the relevancy of selected web pages in the retrieval results. However, the next most frequent transitions differed in each group and a chi-squared test confirmed this finding (P<.001). Next, according to the results of a perplexity evaluation, the health information search patterns were best represented as a 5-gram sequence pattern. The most common patterns in group L1 were frequent query modifications, with relatively low search efficiency, and accessing and evaluating selected results from a health website. Group L2 performed frequent query modifications, but with better search efficiency, and accessed and evaluated selected results from a health website. Finally, the members of group L3 successfully discovered relevant results from the first query submission, performed verification by accessing several health websites after they discovered relevant results, and directly accessed consumer health information websites. CONCLUSIONS: Familiarity with health topics affects health information search behaviors. Our analysis of state transitions in search activities detected unique behaviors and common search activity patterns in each familiarity group during health information searches.