Wyniki wyszukiwania - BazTech

1

Semi-supervised vs. supervised learning for mental health monitoring: A case study on bipolar disorder

Casalino Gabriella, Castellano Giovanna, Hryniewicz Olgierd, Leite Daniel, Opara Karol, Radziszewska Weronika, Kaczmarek-Majer Katarzyna

International Journal of Applied Mathematics and Computer Science

|

2023

|

Vol. 33, no. 3

419--428

EN

Acoustic features of speech are promising as objective markers for mental health monitoring. Specialized smartphone apps can gather such acoustic data without disrupting the daily activities of patients. Nonetheless, the psychiatric assessment of the patient’s mental state is typically a sporadic occurrence that takes place every few months. Consequently, only a slight fraction of the acoustic data is labeled and applicable for supervised learning. The majority of the related work on mental health monitoring limits the considerations only to labeled data using a predefined ground-truth period. On the other hand, semi-supervised methods make it possible to utilize the entire dataset, exploiting the regularities in the unlabeled portion of the data to improve the predictive power of a model. To assess the applicability of semi-supervised learning approaches, we discuss selected state-of-the-art semi-supervised classifiers, namely, label spreading, label propagation, a semi-supervised support vector machine, and the self training classifier. We use real-world data obtained from a bipolar disorder patient to compare the performance of the different methods with that of baseline supervised learning methods. The experiment shows that semi-supervised learning algorithms can outperform supervised algorithms in predicting bipolar disorder episodes.

2

Semi-supervised structure attentive temporal mixup coherence for medical image segmentation

Pawan S.J., Jeevan Govind, Rajan Jeny

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 4

1149--1161

EN

Deep convolutional neural networks have shown eminent performance in medical image segmentation in supervised learning. However, this success is predicated on the availability of large volumes of pixel-level labeled data, making these approaches impractical when labeled data is scarce. On the other hand, semi-supervised learning utilizes pertinent information from unlabeled data along with minimal labeled data, alleviating the demand for labeled data. In this paper, we leverage the mixup-based risk minimization operator in a student-teacher-based semi-supervised paradigm along with structure-aware constraints to enforce consistency coherence among the student predictions for unlabeled samples and the teacher predictions for the corresponding mixup sample by significantly diminishing the need for labeled data. Besides, due to the intrinsic simplicity of the linear combination operation used for generating mixup samples, the proposed method stands at a computational advantage over existing consistency regularization-based SSL methods. We experimentally validate the performance of the proposed model on two public benchmark datasets, namely the Left Atrial (LA) and Automatic Cardiac Diagnosis Challenge (ACDC) datasets. Notably, on the LA dataset’s lowest labeled data set-up (5%), the proposed method significantly improved the Dice Similarity Coefficient and the Jaccard Similarity Coefficient by 1.08% and 1.46%, respectively. Furthermore, we demonstrate the efficacy of the proposed method with a consistent improvement across various labeled data proportions on the aforementioned datasets.

3

Classification of lung nodule malignancy in computed tomography imaging utilising generative adversarial networks and semi-supervised transfer learning

Apostolopoulos Ioannis D., Papathanasiou Nikolaos D., Panayiotakis George S.

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 4

1243--1257

EN

The pulmonary nodules’ malignancy rating is commonly confined in patient follow-up; examining the nodule’s activity is estimated with the Positron Emission Tomography (PET) system or biopsy. However, these strategies are usually after the initial detection of the malignant nodules acquired from the Computed Tomography (CT) scan. In this study, a Deep Learning methodology to address the challenge of the automatic characterisation of Solitary Pulmonary Nodules (SPN) detected in CT scans is proposed. The research methodology is based on Convolutional Neural Networks, which have proven to be excellent automatic feature extractors for medical images. The publicly available CT dataset, called Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI), and a small CT scan dataset derived from a PET/CT system, is considered the classification target. New, realistic nodule representations are generated employing Deep Convolutional Generative Adversarial Networks to circumvent the shortage of large-scale data to train robust CNNs. Besides, a hierarchical CNN called Feature Fusion VGG19 (FF-VGG19) was developed to enhance feature extraction of the CNN proposed by the Visual Geometry Group (VGG). Moreover, the generated nodule images are separated into two classes by utilising a semi-supervised approach, called self-training, to tackle weak labelling due to DC-GAN inefficiencies. The DC-GAN can generate realistic SPNs, as the experts could only distinguish 23% of the synthetic nodule images. As a result, the classification accuracy of FF-VGG19 on the LIDCIDRI dataset increases by +7%, reaching 92.07%, while the classification accuracy on the CT dataset is increased by 5%, reaching 84,3%.

4

Semi-supervised learning with the clustering and Decision Trees classifier for the task of cognitive workload study

Wawrzyk Martyna

Journal of Computer Sciences Institute

|

2020

|

Vol. 15

214--218

EN

The paper is focused on application of the clustering algorithm and Decision Tress classifier (DTs) as a semi-supervised method for the task of cognitive workload level classification. The analyzed data were collected during examination of Digit Symbol Substitution Test (DSST) with use of eye-tracker device. 26 participants took part in examination as vol-unteers. There were conducted three parts of DSST test with different levels of difficulty. As a results three versions were obtained of data: low, middle and high level of cognitive workload. The case study covered clustering of collected data by using k-means algorithm to detect three clusters or more. The obtained clusters were evaluated by three internal indices to measure the quality of clustering. The David-Boudin index detected the best results in case of four clusters. Based on this information it is possible to formulate the hypothesis of the existence of four clusters. The obtained clus-ters were adopted as classes in supervised learning and have been subjected to classification. The DTs was applied in classification. There were obtained the 0.85 mean accuracy for three-class classification and 0.73 mean accuracy for four-class classification.

PL

Celem artykułu było zastosowanie klasteryzacji wraz z klasyfikatorem Drzew Decyzyjnych jako częściowo nadzoro-wanej metody klasyfikacji poziomu obciążenia poznawczego. Dane przeznaczone do analizy zostały zebrane podczas badania DSST (z ang. Digit Symbol Substitution Test) z użyciem urządzenia eye-tracker. 26 wolontariuszów wzięło udział w badaniu. Zostały przeprowadzone trzy części testu DSST o różnych poziomach trudności. W wyniku tego, otrzymano trzy wersje danych: z niskim, średnim i wysokim poziomem obciążenia poznawczego. Do analizy danych został użyty algorytm klasteryzacji k-means do wyznaczenia trzech lub większej liczby klastrów. Uzyskane klastry zostały poddane ocenie przy użyciu trzech wewnętrznych indeksów w celu zmierzenia jakości klasteryzacji. Indeks David-Boudin’a wykazał najlepsze rezultaty w przypadku istnienia czterech klastrów. Na podstawie tej informacji można sformułować hipotezę, iż dane są podzielone na 4 klastry, co oznaczałoby istnienie dodatkowego poziomu poznawczego. Uzyskane klastry zostały zaadoptowane jako klasy w uczeniu pod nadzorem. Do klasyfikacji danych został użyty klasyfikator Drzew Decyzyjnych . Otrzymano średnią dokładność równą 0.85 w przypadku 3-klasowej klasyfikacji oraz 0.73 średnią dokładność dla 4-klasowej klasyfikacji.