A gradient-based automatic optimization CNN framework for EEG state recognition

The Electroencephalogram (EEG) signal, as a data carrier that can contain a large amount of information about the human brain in different states, is one of the most widely used metrics for assessing human psychophysiological states. Among a variety of analysis methods, deep learning, especially convolutional neural network (CNN), has achieved remarkable results in recent years as a method to effectively extract features from EEG signals. Although deep learning has the advantages of automatic feature extraction and effective classification, it also faces difficulties in network structure design and requires an army of prior knowledge. Automating the design of these hyperparameters can therefore save experts' time and manpower. Neural architecture search techniques have thus emerged. In this paper, based on an existing gradient-based NAS algorithm, PC-DARTS, with targeted improvements and optimizations for the characteristics of EEG signals. Specifically, we establish the model architecture step by step based on the manually designed deep learning models for EEG discrimination by retaining the framework of the search algorithm and performing targeted optimization of the model search space. Corresponding features are extracted separately according to the frequency domain, time domain characteristics of the EEG signal and the spatial position of the EEG electrode. The architecture was applied to EEG-based emotion recognition and driver drowsiness assessment tasks. The results illustrate that compared with the existing methods, the model architecture obtained in this paper can achieve competitive overall accuracy and better standard deviation in both tasks. Therefore, this approach is an effective migration of NAS technology into the field of EEG analysis and has great potential to provide high-performance results for other types of classification and prediction tasks. This can effectively reduce the time cost for researchers and facilitate the application of CNN in more areas.

Reproducible Neuroimaging Features for Diagnosis of Autism Spectrum Disorder with Machine Learning

Autism spectrum disorder (ASD) is the fourth most common neurodevelopmental disorder, with a prevalence of 1 in 160 children. Accurate diagnosis relies on experts, but such individuals are scarce. This has led to increasing interest in the development of machine learning (ML) models that can integrate neuroimaging features from functional and structural MRI (fMRI and sMRI) to measure alterations manifest in ASD. We optimized and compared the performance of 12 of the most popular and powerful ML models. Each was separately trained using 15 different combinations of fMRI and sMRI features and optimized with an unbiased model search. Deep learning models predicted ASD with the highest diagnostic accuracy and generalized well to other MRI datasets. Our model achieves state-of-the-art 80% area under the ROC curve (AUROC) in diagnosis on test data from the IMPAC dataset; and 86% and 79% AUROC on the external ABIDE I and ABIDE II datasets. The highest performing models identified reproducible putative biomarkers for accurate ASD diagnosis in accord with known ASD markers as well as novel cerebellar biomarkers. Such reproducibility lends credence to their tremendous potential for defining and using a set of truly generalizable ASD biomarkers that will advance scientific understanding of neuronal changes in ASD.

Reproducible neuroimaging features in Autism spectrum disorder that enable accurate diagnosis with machine learning models

Autism spectrum disorder (ASD) is the fourth most common neurodevelopmental disorder, with a prevalence of 1 in 160 children. Accurate diagnosis relies on experts, but such individuals are scarce. This has led to increasing interest in the development of machine learning (ML) models that can integrate neuroimaging features from functional and structural MRI (fMRI and sMRI) to measure alterations manifest in ASD. We optimized and compared the performance of 12 of the most popular and powerful ML models. Each was separately trained using 15 different combinations of fMRI and sMRI features and optimized with an unbiased model search. Deep learning models predicted ASD with the highest diagnostic accuracy and generalized well to other MRI datasets. Our model achieves state-of-the-art 80% area under the ROC curve (AUROC) in diagnosis on test data from the IMPAC dataset; and 86% and 79% AUROC on the external ABIDE I and ABIDE II datasets. The highest performing models identified reproducible putative biomarkers for accurate ASD diagnosis in accord with known ASD markers as well as novel cerebellum biomarkers. Such reproducibility lends credence to their tremendous potential for defining and using a set of truly generalizable ASD biomarkers that will advance scientific understanding of neuronal changes in ASD.

Model Pembelajaran Search, Solve, Create And Share (SSCS): Dampak Terhadap Kemampuan Penalaran Matematis Dan Motivasi Belajar Peserta Didik

Penelitian ini betujuan untuk mengetahui pengaruh model pembelajaran Search, Solve, Create and Share (SSCS) terhadap kemampuan penalaran matematis dan motivasi belajar peserta didik. Penelitian ini menggunakan jenis penelitian Quasy Experimental Desaign. Populasi dalam penelitian ini adalah seluruh siswa kelas VIII SMP Negeri 2 Belitang Mulya. Sampel diambil dua kelas yaitu kelas VIII A sebagai kelas eksperimen yang memperoleh pembelajaran menggunakan model Search, Solve, Create and Share (SSCS) dan kelas VIII B sebagai kelas kontrol yang memperoleh pembelajaran konvensional dengan menggunakan teknik simple random sampling. Analisis data pada penelitian ini menggunakan Uji Multivariate Analysis of Variance (Manova). Hasil analisis data menunjukkan menunjukkan bahwa: (1) terdapat pengaruh model pembelajaan Search, Solve, Create, and Share (SSCS) terhadap kemampuan penalaran matematis peserta didik, (2) terdapat pengaruh model pembelajaan Search, Solve, Create, and Share (SSCS) terhadap motivasi belajar peserta didik, (3) terdapat pengaruh model pembelajaan Search, Solve, Create, and Share (SSCS) terhadap kemampuan penalaran matematis dan motivasi belajar peserta didik.

Searching and Caring for the Sacred: Psychological Perspectives on Caring for People’s Spiritual Needs

We present knowledge from the field of psychology of religion for professional clinicians. The model “Search for the Sacred” and other concepts of psychology of religion are introduced: Sacred core and ring, sanctification, spiritual emotions, spiritual relationships, spiritual pathways, and sacred moments. These are discussed in relation to different concepts of theology for broadening the understanding and application of these concepts. Interviews with Danish Christians facing a crisis illustrate the application of the theoretical perspectives.

Dual Active Learning for Both Model and Data Selection

To learn an effective model with less training examples, existing active learning methods typically assume that there is a given target model, and try to fit it by selecting the most informative examples. However, it is less likely to determine the best target model in prior, and thus may get suboptimal performance even if the data is perfectly selected. To tackle with this practical challenge, this paper proposes a novel framework of dual active learning (DUAL) to simultaneously perform model search and data selection. Specifically, an effective method with truncated importance sampling is proposed for Combined Algorithm Selection and Hyperparameter optimization (CASH), which mitigates the model evaluation bias on the labeled data. Further, we propose an active query strategy to label the most valuable examples. The strategy on one hand favors discriminative data to help CASH search the best model, and on the other hand prefers informative examples to accelerate the convergence of winner models. Extensive experiments are conducted on 12 openML datasets. The results demonstrate the proposed method can effectively learn a superior model with less labeled examples.

Security Establishment In Cybersecurity Environment Using PSO Based Optimization

Cybersecurity based significant data context is considered a challenge in the research community. Machine Learning approaches are considered for dealing with the big data-based security problem. Here, Particle Swarm Optimization (PSO) is used for configuring a massive amount of data. This work formulates a solution for Multi-objective problems to fulfill accuracy, computational and model complexities. A novel Meta-heuristic framework for multi-objective optimization is developed for dealing with lower levels and higher-level heuristics. In the former group, various rules are generated for configuring PSO, and in the latter model, search performance to control the selection process is used for newer configurations of PSO, deal with this multi-objective function. Parento-Approximation (PA) approach is used for strengthening this framework. The proposed optimization approach can be used in cybersecurity problems like anomaly classification. The proposed model is expected to provide better results in contrast to other models.