Sparse Logistic Regression With L 1/2 Penalty for Emotion Recognition in Electroencephalography Classification.

Emotion recognition based on electroencephalography (EEG) signals is a current focus in brain-computer interface research. However, the classification of EEG is difficult owing to large amounts of data and high levels of noise. Therefore, it is important to determine how to effectively extract features that include important information. Regularization, one of the effective methods for EEG signal processing, can effectively extract important features from the signal and has potential applications in EEG emotion recognition. Currently, the most popular regularization technique is Lasso (L 1) and Ridge Regression (L 2). In recent years, researchers have proposed many other regularization terms. In theory, L q -type regularization has a lower q value, which means that it can be used to find solutions with better sparsity. L 1/2 regularization is of L q type (0 < q < 1) and has been shown to have many attractive properties. In this work, we studied the L 1/2 penalty in sparse logistic regression for three-classification EEG emotion recognition, and used a coordinate descent algorithm and a univariate semi-threshold operator to implement L 1/2 penalty logistic regression. The experimental results on simulation and real data demonstrate that our proposed method is better than other existing regularization methods. Sparse logistic regression with L 1/2 penalty achieves higher classification accuracy than the conventional L 1, Ridge Regression, and Elastic Net regularization methods, using fewer but more informative EEG signals. This is very important for high-dimensional small-sample EEG data and can help researchers to reduce computational complexity and improve computational accuracy. Therefore, we propose that sparse logistic regression with the L 1/2 penalty is an effective technique for emotion recognition in practical classification problems.

A Feature Extraction Method Based on Differential Entropy and Linear Discriminant Analysis for Emotion Recognition.

Feature extraction of electroencephalography (EEG) signals plays a significant role in the wearable computing field. Due to the practical applications of EEG emotion calculation, researchers often use edge calculation to reduce data transmission times, however, as EEG involves a large amount of data, determining how to effectively extract features and reduce the amount of calculation is still the focus of abundant research. Researchers have proposed many EEG feature extraction methods. However, these methods have problems such as high time complexity and insufficient precision. The main purpose of this paper is to introduce an innovative method for obtaining reliable distinguishing features from EEG signals. This feature extraction method combines differential entropy with Linear Discriminant Analysis (LDA) that can be applied in feature extraction of emotional EEG signals. We use a three-category sentiment EEG dataset to conduct experiments. The experimental results show that the proposed feature extraction method can significantly improve the performance of the EEG classification: Compared with the result of the original dataset, the average accuracy increases by 68%, which is 7% higher than the result obtained when only using differential entropy in feature extraction. The total execution time shows that the proposed method has a lower time complexity.

Harnessing microfluidic streak plate technique to investigate the gut microbiome of Reticulitermes chinensis.

The termite gut microbiome is a model system to investigate microbial interactions and their associations with host. For decades, extensive research with molecular tools and conventional cultivation method has been carried out to define the microbial diversity in termite gut. Yet, many bacterial groups of the termite gut microbiome have not been successfully cultivated in laboratory. In this study, we adapted the recently developed microfluidic streak plate (MSP) technique for cultivation of termite gut microbial communities at both aerobic and anaerobic conditions. We found that 99 operational taxonomic units (OTUs) were cultivable by MSP approach and 18 OTUs were documented first time for termite gut microbiota. Further analysis of the bacterial diversities derived by culture-dependent MSP approach and culture-independent 16S rRNA gene typing revealed that both methods have bias in recovery of gut microbiota. In total 396 strains were isolated with MSP technique, and potential new taxa at species and/or genus levels were obtained that were phylogenetically related to Burkholderia, Micrococcus, and Dysgonomonas. Results from this study indicate that MSP technique is applicable for cultivating previously unknown and new microbial groups of termite gut microbiota.

Automated Chemotactic Sorting and Single-cell Cultivation of Microbes using Droplet Microfluidics.

We report a microfluidic device for automated sorting and cultivation of chemotactic microbes from pure cultures or mixtures. The device consists of two parts: in the first part, a concentration gradient of the chemoeffector was built across the channel for inducing chemotaxis of motile cells; in the second part, chemotactic cells from the sample were separated, and mixed with culture media to form nanoliter droplets for encapsulation, cultivation, enumeration, and recovery of single cells. Chemotactic responses were assessed by imaging and statistical analysis of droplets based on Poisson distribution. An automated procedure was developed for rapid enumeration of droplets with cell growth, following with scale-up cultivation on agar plates. The performance of the device was evaluated by the chemotaxis assays of Escherichia coli (E. coli) RP437 and E. coli RP1616. Moreover, enrichment and isolation of non-labelled Comamonas testosteroni CNB-1 from its 1:10 mixture with E. coli RP437 was demonstrated. The enrichment factor reached 36.7 for CNB-1, based on its distinctive chemotaxis toward 4-hydroxybenzoic acid. We believe that this device can be widely used in chemotaxis studies without necessarily relying on fluorescent labelling, and isolation of functional microbial species from various environments.

Benzoate metabolism intermediate benzoyl coenzyme A affects gentisate pathway regulation in Comamonas testosteroni.

A previous study showed that benzoate was catabolized via a coenzyme A (CoA)-dependent epoxide pathway in Azoarcus evansii (R. Niemetz, U. Altenschmidt, S. Brucker, and G. Fuchs, Eur. J. Biochem. 227:161-168, 1995), but gentisate 1,2-dioxygenase was induced. Similarly, we found that the Comamonas testosteroni strain CNB-1 degraded benzoate via a CoA-dependent epoxide pathway and that gentisate 1,2-dioxygenase (GenA) was also induced when benzoate or 3-hydroxybenzoate served as a carbon source for growth. Genes encoding the CoA-dependent epoxide (box genes) and gentisate (gen genes) pathways were identified. Genetic disruption revealed that the gen genes were not involved in benzoate and 3-hydroxybenzoate degradation. Hence, we investigated gen gene regulation in the CNB-1 strain. The PgenA promoter, a MarR-type regulator (GenR), and the GenR binding site were identified. We found that GenR took gentisate, 3-hydroxybenzoate, and benzoyl-CoA as effectors and that binding of GenR to its target DNA sequence was prohibited when these effectors were present. In vivo studies showed that the CNB-1 mutant that lost benzoyl-CoA synthesis was not able to activate PgenA promoter, while transcription of genA was upregulated in another CNB-1 mutant that lost the ability to degrade benzoyl-CoA. The finding that benzoyl-CoA (a metabolic intermediate of benzoate degradation) and 3-hydroxybenzoate function as GenR effectors explains why GenA was induced when CNB-1 grew on benzoate or 3-hydroxybenzoate. Regulation of gentisate pathways by MarR-, LysR-, and IclR-type regulators in diverse bacterial groups is discussed in detail.

Assimilation of aromatic compounds by Comamonas testosteroni: characterization and spreadability of protocatechuate 4,5-cleavage pathway in bacteria.

Comamonas testosteroni strain CNB-1 was isolated from activated sludge and has been investigated for its ability to degrade 4-chloronitrobenzene. Results from this study showed that strain CNB-1 grew on phenol, gentisate, vanillate, 3-hydroxybenzoate (3HB), and 4-hydroxybenzoate (4HB) as carbon and energy sources. Proteomic data and enzyme activity assays suggested that vanillate, 3HB, and 4HB were degraded in strain CNB-1 via protocatechuate (PCA) 4,5-cleavage pathway. The genetics and biochemistry of the PCA 4,5-cleavage pathway were investigated. Results showed that the 4-oxalomesaconate (OMA) hydratase from C. testosteroni takes only enol-OMA as substrate. A previously functionally unknown gene pmdU encodes an OMA tautomerase and catalyzes conversion of OMAketo into OMAenol. The 4-carboxy-4-hydroxy-2-oxoadipate (CHA) aldolase is encoded by pmdF and catalyzes the last step of the PCA 4,5-cleavage pathway. We explored the 1,183 microbial genomes at GenBank for potential PCA 4,5-cleavage pathways, and 33 putative pmd clusters were found. Results suggest that PCA 4,5-cleavage pathways are mainly distributed in α- and ß-Proteobacteria.

The complete genome of Comamonas testosteroni reveals its genetic adaptations to changing environments.

Members of the gram-negative, strictly aerobic genus Comamonas occur in various environments. Here we report the complete genome of Comamonas testosteroni strain CNB-2. Strain CNB-2 has a circular chromosome that is 5,373,643 bp long and has a G+C content of 61.4%. A total of 4,803 open reading frames (ORFs) were identified; 3,514 of these ORFs are functionally assigned to energy production, cell growth, signal transduction, or transportation, while 866 ORFs encode hypothetical proteins and 423 ORFs encode purely hypothetical proteins. The CNB-2 genome has many genes for transportation (22%) and signal transduction (6%), which allows the cells to respond and adapt to changing environments. Strain CNB-2 does not assimilate carbohydrates due to the lack of genes encoding proteins involved in glycolysis and pentose phosphate pathways, and it contains many genes encoding proteins involved in degradation of aromatic compounds. We identified 66 Tct and nine TRAP-T systems and a complete tricarboxylic acid cycle, which may allow CNB-2 to take up and metabolize a range of carboxylic acids. This nutritional bias for carboxylic acids and aromatic compounds enables strain CNB-2 to occupy unique niches in environments. Four different sets of terminal oxidases for the respiratory system were identified, and they putatively functioned at different oxygen concentrations. This study conclusively revealed at the genomic level that the genetic versatility of C. testosteroni is vital for competition with other bacteria in its special niches.