Generalized discriminant orthogonal nonnegative tensor factorization for facial expression recognition.
Ontology highlight
ABSTRACT:
SUBMITTER: XiuJun Z
PROVIDER: S-EPMC3984787 | biostudies-other | 2014
REPOSITORIES: biostudies-other
Similar Datasets
Project description:Recent studies have indicated that facial electromyogram (fEMG)-based facial-expression recognition (FER) systems are promising alternatives to the conventional camera-based FER systems for virtual reality (VR) environments because they are economical, do not depend on the ambient lighting, and can be readily incorporated into existing VR headsets. In our previous study, we applied a Riemannian manifold-based feature extraction approach to fEMG signals recorded around the eyes and demonstrated that 11 facial expressions could be classified with a high accuracy of 85.01%, with only a single training session. However, the performance of the conventional fEMG-based FER system was not high enough to be applied in practical scenarios. In this study, we developed a new method for improving the FER performance by employing linear discriminant analysis (LDA) adaptation with labeled datasets of other users. Our results indicated that the mean classification accuracy could be increased to 89.40% by using the LDA adaptation method (p < .001, Wilcoxon signed-rank test). Additionally, we demonstrated the potential of a user-independent FER system that could classify 11 facial expressions with a classification accuracy of 82.02% without any training sessions. To the best of our knowledge, this was the first study in which the LDA adaptation approach was employed in a cross-subject manner. It is expected that the proposed LDA adaptation approach would be used as an important method to increase the usability of fEMG-based FER systems for social VR applications.
| S-EPMC8414465 | biostudies-literature
Project description:Factorization models express a statistical object of interest in terms of a collection of simpler objects. For example, a matrix or tensor can be expressed as a sum of rank-one components. However, in practice, it can be challenging to infer the relative impact of the different components as well as the number of components. A popular idea is to include infinitely many components having impact decreasing with the component index. This article is motivated by two limitations of existing methods: (1) lack of careful consideration of the within component sparsity structure; and (2) no accommodation for grouped variables and other non-exchangeable structures. We propose a general class of infinite factorization models that address these limitations. Theoretical support is provided, practical gains are shown in simulation studies, and an ecology application focusing on modelling bird species occurrence is discussed.
| S-EPMC9469809 | biostudies-literature
Project description:Excessive smartphone use causes personal and social problems. To address this issue, we sought to derive usage patterns that were directly correlated with smartphone dependence based on usage data. This study attempted to classify smartphone dependence using a data-driven prediction algorithm. We developed a mobile application to collect smartphone usage data. A total of 41,683 logs of 48 smartphone users were collected from March 8, 2015, to January 8, 2016. The participants were classified into the control group (SUC) or the addiction group (SUD) using the Korean Smartphone Addiction Proneness Scale for Adults (S-Scale) and a face-to-face offline interview by a psychiatrist and a clinical psychologist (SUC = 23 and SUD = 25). We derived usage patterns using tensor factorization and found the following six optimal usage patterns: 1) social networking services (SNS) during daytime, 2) web surfing, 3) SNS at night, 4) mobile shopping, 5) entertainment, and 6) gaming at night. The membership vectors of the six patterns obtained a significantly better prediction performance than the raw data. For all patterns, the usage times of the SUD were much longer than those of the SUC. From our findings, we concluded that usage patterns and membership vectors were effective tools to assess and predict smartphone dependence and could provide an intervention guideline to predict and treat smartphone dependence based on usage data.
| S-EPMC5479529 | biostudies-literature
Project description:Adoption of Electronic Health Record (EHR) systems has led to collection of massive healthcare data, which creates oppor- tunities and challenges to study them. Computational phenotyping offers a promising way to convert the sparse and complex data into meaningful concepts that are interpretable to healthcare givers to make use of them. We propose a novel su- pervised nonnegative tensor factorization methodology that derives discriminative and distinct phenotypes. We represented co-occurrence of diagnoses and prescriptions in EHRs as a third-order tensor, and decomposed it using the CP algorithm. We evaluated discriminative power of our models with an Intensive Care Unit database (MIMIC-III) and demonstrated superior performance than state-of-the-art ICU mortality calculators (e.g., APACHE II, SAPS II). Example of the resulted phenotypes are sepsis with acute kidney injury, cardiac surgery, anemia, respiratory failure, heart failure, cardiac arrest, metastatic cancer (requiring ICU), end-stage dementia (requiring ICU and transitioned to comfort-care), intraabdominal conditions, and alcohol abuse/withdrawal.
| S-EPMC5430728 | biostudies-literature
Project description:BackgroundDetermining which target to pursue is a challenging and error-prone first step in developing a therapeutic treatment for a disease, where missteps are potentially very costly given the long-time frames and high expenses of drug development. With current informatics technology and machine learning algorithms, it is now possible to computationally discover therapeutic hypotheses by predicting clinically promising drug targets based on the evidence associating drug targets with disease indications. We have collected this evidence from Open Targets and additional databases that covers 17 sources of evidence for target-indication association and represented the data as a tensor of 21,437 × 2211 × 17.ResultsAs a proof-of-concept, we identified examples of successes and failures of target-indication pairs in clinical trials across 875 targets and 574 disease indications to build a gold-standard data set of 6140 known clinical outcomes. We designed and executed three benchmarking strategies to examine the performance of multiple machine learning models: Logistic Regression, LASSO, Random Forest, Tensor Factorization and Gradient Boosting Machine. With 10-fold cross-validation, tensor factorization achieved AUROC = 0.82 ± 0.02 and AUPRC = 0.71 ± 0.03. Across multiple validation schemes, this was comparable or better than other methods.ConclusionIn this work, we benchmarked a machine learning technique called tensor factorization for the problem of predicting clinical outcomes of therapeutic hypotheses. Results have shown that this method can achieve equal or better prediction performance compared with a variety of baseline models. We demonstrate one application of the method to predict outcomes of trials on novel indications of approved drug targets. This work can be expanded to targets and indications that have never been clinically tested and proposing novel target-indication hypotheses. Our proposed biologically-motivated cross-validation schemes provide insight into the robustness of the prediction performance. This has significant implications for all future methods that try to address this seminal problem in drug discovery.
| S-EPMC6368709 | biostudies-literature
Project description:The rapidly increasing availability of electronic health records (EHRs) from multiple heterogeneous sources has spearheaded the adoption of data-driven approaches for improved clinical research, decision making, prognosis, and patient management. Unfortunately, EHR data do not always directly and reliably map to medical concepts that clinical researchers need or use. Some recent studies have focused on EHR-derived phenotyping, which aims at mapping the EHR data to specific medical concepts; however, most of these approaches require labor intensive supervision from experienced clinical professionals. Furthermore, existing approaches are often disease-centric and specialized to the idiosyncrasies of the information technology and/or business practices of a single healthcare organization. In this paper, we propose Limestone, a nonnegative tensor factorization method to derive phenotype candidates with virtually no human supervision. Limestone represents the data source interactions naturally using tensors (a generalization of matrices). In particular, we investigate the interaction of diagnoses and medications among patients. The resulting tensor factors are reported as phenotype candidates that automatically reveal patient clusters on specific diagnoses and medications. Using the proposed method, multiple phenotypes can be identified simultaneously from data. We demonstrate the capability of Limestone on a cohort of 31,815 patient records from the Geisinger Health System. The dataset spans 7years of longitudinal patient records and was initially constructed for a heart failure onset prediction study. Our experiments demonstrate the robustness, stability, and the conciseness of Limestone-derived phenotypes. Our results show that using only 40 phenotypes, we can outperform the original 640 features (169 diagnosis categories and 471 medication types) to achieve an area under the receiver operator characteristic curve (AUC) of 0.720 (95% CI 0.715 to 0.725). Moreover, in consultation with a medical expert, we confirmed 82% of the top 50 candidates automatically extracted by Limestone are clinically meaningful.
| S-EPMC6563906 | biostudies-literature
Project description:In recent years, convolutional neural networks (CNNs) have played a dominant role in facial expression recognition. While CNN-based methods have achieved remarkable success, they are notorious for having an excessive number of parameters, and they rely on a large amount of manually annotated data. To address this challenge, we expand the number of training samples by learning expressions from a face recognition dataset to reduce the impact of a small number of samples on the network training. In the proposed deep joint learning framework, the deep features of the face recognition dataset are clustered, and simultaneously, the parameters of an efficient CNN are learned, thereby marking the data for network training automatically and efficiently. Specifically, first, we develop a new efficient CNN based on the proposed affinity convolution module with much lower computational overhead for deep feature learning and expression classification. Then, we develop an expression-guided deep facial clustering approach to cluster the deep features and generate abundant expression labels from the face recognition dataset. Finally, the AC-based CNN is fine-tuned using an updated training set and a combined loss function. Our framework is evaluated on several challenging facial expression recognition datasets as well as a self-collected dataset. In the context of facial expression recognition applied to the field of education, our proposed method achieved an impressive accuracy of 95.87% on the self-collected dataset, surpassing other existing methods.
| S-EPMC10457757 | biostudies-literature
Project description:RNA-sequencing is rapidly becoming the method of choice for studying the full complexity of transcriptomes, however with increasing dimensionality, accurate gene ranking is becoming increasingly challenging. This paper proposes an accurate and sensitive gene ranking method that implements discriminant non-negative matrix factorization (DNMF) for RNA-seq data. To the best of our knowledge, this is the first work to explore the utility of DNMF for gene ranking. When incorporating Fisher's discriminant criteria and setting the reduced dimension as two, DNMF learns two factors to approximate the original gene expression data, abstracting the up-regulated or down-regulated metagene by using the sample label information. The first factor denotes all the genes' weights of two metagenes as the additive combination of all genes, while the second learned factor represents the expression values of two metagenes. In the gene ranking stage, all the genes are ranked as a descending sequence according to the differential values of the metagene weights. Leveraging the nature of NMF and Fisher's criterion, DNMF can robustly boost the gene ranking performance. The Area Under the Curve analysis of differential expression analysis on two benchmarking tests of four RNA-seq data sets with similar phenotypes showed that our proposed DNMF-based gene ranking method outperforms other widely used methods. Moreover, the Gene Set Enrichment Analysis also showed DNMF outweighs others. DNMF is also computationally efficient, substantially outperforming all other benchmarked methods. Consequently, we suggest DNMF is an effective method for the analysis of differential gene expression and gene ranking for RNA-seq data.
| S-EPMC4562600 | biostudies-literature
Project description:Recognition of pain in patients who are incapable of expressing themselves allows for several possibilities of improved diagnosis and treatment. Despite the advancements that have already been made in this field, research is still lacking with respect to the detection of pain in live videos, especially under unfavourable conditions. To address this gap in existing research, the current study proposed a hybrid model that allowed for efficient pain recognition. The hybrid, which consisted of a combination of the Constrained Local Model (CLM), Active Appearance Model (AAM), and Patch-Based Model, was applied in conjunction with image algebra. This contributed to a system that enabled the successful detection of pain from a live stream, even with poor lighting and a low-resolution recording device. The final process and output allowed for memory for storage that was reduced up to 40%-55% and an improved processing time of 20%-25%. The experimental system met with success and was able to detect pain for the 22 analysed videos with an accuracy of 55.75%-100.00%. To increase the fidelity of the proposed technique, the hybrid model was tested on UNBC-McMaster Shoulder Pain Database as well.
| S-EPMC6231392 | biostudies-literature
Project description: Not available
| S-EPMC7769577 | biostudies-literature