Patients suffering from Parkinson’s disease suffer from voice impairment. In this study, we introduce models to classify normal and Parkinson’s patients using their speech. We used an AST (audio spectrogram transformer), a transformer-based speech classification model that has recently outperformed CNN-based models in many fields, and a CNN-based PSLA (pretraining, sampling, labeling, and aggregation), a high-performance model in the existing speech classification field, for the study. This study compares and analyzes the models from both quantitative and qualitative perspectives. First, qualitatively, PSLA outperformed AST by more than 4% in accuracy, and the AUC was also higher, with 94.16% for AST and 97.43% for PSLA. Furthermore, we qualitatively evaluated the ability of the models to capture the acoustic features of Parkinson’s through various CAM (class activation map)-based XAI (eXplainable AI) models such as GradCAM and EigenCAM. Based on PSLA, we found that the model focuses well on the muffled frequency band of Parkinson’s speech, and the heatmap analysis of false positives and false negatives shows that the speech features are also visually represented when the model actually makes incorrect predictions. The contribution of this paper is that we not only found a suitable model for diagnosing Parkinson’s through speech using two different types of models but also validated the predictions of the model in practice.

In colonoscopy, computer vision and artificial intelligence technology have enabled the automatic detection of the location of polyps and their visualization. These advancements have facilitated considerable research in the field. However, deep learning models used in the segmentation problem for capturing various patterns of polyps are becoming increasingly complex, which has rendered their operation in real time difficult. To identify and overcome this problem, a study was conducted on a model capable of precise polyp segmentation while increasing its processing speed. First, an efficient, high-performance, and lightweight model suitable for the segmentation of polyps was sought; the performance of existing segmentation models was compared and combined to obtain a learning model that exhibited good accuracy and speed. Next, hyperparameters were found for the MobileNetV3-encoder-based DeepLabV3+ model and, after tuning the hyperparameters, quantitative and qualitative results were compared, and the final model was selected. The experimental results showed that this model achieved high accuracy, with a Dice coefficient of 93.79%, while using a limited number of parameters and computational resources. Specifically, the model used 6.18 million parameters and 1.623 giga floating point operations for the CVC-ClinicDB dataset. This study revealed that increasing the amount of computation and parameters of the model did not guarantee unconditional performance. Furthermore, for the search and removal of polyps in cases in which morphological information is critical, an efficient model with low model complexity and high accuracy was proposed for real-time segmentation.

Despite major breakthroughs in facial recognition technology, problems with bias and a lack of diversity still plague face recognition systems today. To address these issues, we created synthetic face data using a diffusion-based generative model and fine-tuned already-high-performing models. To achieve a more balanced overall performance across various races, the synthetic dataset was created by following the dual-condition face generator (DCFace) resolution and using race-varied data from BUPT-BalancedFace as well as FairFace. To verify the proposed method, we fine-tuned a pre-trained improved residual networks (IResnet)-100 model with additive angular margin (ArcFace) loss using the synthetic dataset. The results show that the racial gap in performance is reduced from 0.0107 to 0.0098 in standard deviation terms, while the overall accuracy increases from 96.125% to 96.1625%. The improved racial balance and diversity in the synthetic dataset led to an improvement in model fairness, demonstrating that this resource could facilitate more equitable face recognition systems. This method provides a low-cost way to address data diversity challenges and help make face recognition more accurate across different demographic groups. The results of the study highlighted that more advanced synthesized datasets, created through diffusion-based models, can also result in increased facial recognition accuracy with greater fairness, emphasizing that these should not be ignored by developers aiming to create artificial intelligence (AI) systems.

Smart-diaper signals collected during routine care are affected by sensor noise, transmission gaps, variable event durations, and limited labels, making normal voiding (NV) and urinary incontinence (UI) difficult to distinguish using threshold-based detection alone. We developed a label-efficient time-series classification framework based on Context-Aware Temporal Contrastive Coding (CA-TCC) using the resistance ($R_{\mathrm{VAL}}$) channel of a smart-diaper sensor. Recordings from 97 older residents across three long-term care facilities were quality-filtered, aggregated at 3 min intervals, screened for candidate events, and interpolated to fixed-length inputs. CA-TCC was pre-trained on an unlabeled candidate-event pool and adapted using 4877 manually labeled events. The linear-probe, full fine-tuning, and class-aware pseudo-label retraining configurations were evaluated using participant-grouped five-fold cross-validation. The selected semi-supervised configuration achieved $82.12\pm 2.33$% accuracy, $82.12\pm 2.32$% macro-F1, and an AUC of $0.895\pm 0.018$ (mean ± 95% confidence interval), exceeding the strongest classical baseline by 4.80 macro-F1 percentage points. Its macro-F1 increased from $79.22\pm 1.84$% with 1000 labeled events to $81.97\pm 1.82$% with the full labeled set, whereas full fine-tuning showed greater fold-to-fold variability. Aggregated LIME analysis over 300 held-out events did not support localization of the model’s evidence to the event onset. These results indicate that contrastive pre-training can support smart-diaper voiding-pattern classification when labeled data are limited.