Classification of mental workload with EEG analysis by using effective connectivity and a hybrid model of CNN and LSTM.

Estimation of mental workload from electroencephalogram (EEG) signals aims to accurately measure the cognitive demands placed on an individual during multitasking mental activities. By analyzing the brain activity of the subject, we can determine the level of mental effort required to perform a task and optimize the workload to prevent cognitive overload or underload. This information can be used to enhance performance and productivity in various fields such as healthcare, education, and aviation. In this paper, we propose a method that uses EEG and deep neural networks to estimate the mental workload of human subjects during multitasking mental activities. Notably, our proposed method employs subject-independent classification. We use the "STEW" dataset, which consists of two tasks, namely "No task" and "simultaneous capacity (SIMKAP)-based multitasking activity". We estimate the different workload levels of two tasks using a composite framework consisting of brain connectivity and deep neural networks. After the initial preprocessing of EEG signals, an analysis of the relationships between the 14 EEG channels is conducted to evaluate effective brain connectivity. This assessment illustrates the information flow between various brain regions, utilizing the direct Directed Transfer Function (dDTF) method. Then, we propose a deep hybrid model based on pre-trained Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) for the classification of workload levels. The accuracy of the proposed deep model achieved 83.12% according to the subject-independent leave-subject-out (LSO) approach. The pre-trained CNN + LSTM approaches to EEG data have been found to be an accurate method for assessing the mental workload.

Classification of mental workload using brain connectivity and machine learning on electroencephalogram data.

Mental workload refers to the cognitive effort required to perform tasks, and it is an important factor in various fields, including system design, clinical medicine, and industrial applications. In this paper, we propose innovative methods to assess mental workload from EEG data that use effective brain connectivity for the purpose of extracting features, a hierarchical feature selection algorithm to select the most significant features, and finally machine learning models. We have used the Simultaneous Task EEG Workload (STEW) dataset, an open-access collection of raw EEG data from 48 subjects. We extracted brain-effective connectivities by the direct directed transfer function and then selected the top 30 connectivities for each standard frequency band. Then we applied three feature selection algorithms (forward feature selection, Relief-F, and minimum-redundancy-maximum-relevance) on the top 150 features from all frequencies. Finally, we applied sevenfold cross-validation on four machine learning models (support vector machine (SVM), linear discriminant analysis, random forest, and decision tree). The results revealed that SVM as the machine learning model and forward feature selection as the feature selection method work better than others and could classify the mental workload levels with accuracy equal to 89.53% (± 1.36).

Expression of Linear and Circular lncRNAs in Alzheimer's Disease.

Alzheimer's disease is a neurodegenerative disorder of the elderly described by progressive cognitive debility. Recent studies have displayed the significance of linear and circular long non-coding RNAs (lncRNAs) in the pathobiology of Alzheimer's disease. These studies have reported the downregulation of MALAT1, while the upregulation of NEAT1, RP11-543N12.1, SOX21-AS1, BDNF-AS, BACE1-AS, ANRIL, XIST, and some other linear lncRNAs in clinical samples are obtained from these patients or animal models of Alzheimer's disease. A number of circRNAs such as ciRS-7, ciRS-7, circNF1-419, circHDAC9, circ_0000950,and circAß-a have been shown to partake in the pathogenesis of this disorder. In the present manuscript, we provide a review of the impact of linear and circular lncRNAs in the pathobiology of Alzheimer's disease and their potential application as markers for this neurodegenerative condition.

The rs12826786 in HOTAIR lncRNA Is Associated with Risk of Autism Spectrum Disorder.

Autism spectrum disorder (ASD) encompasses a group of neurodevelopmental disorders with complex pattern of inheritance. Several single nucleotide polymorphisms (SNPs) within coding or non-coding regions of genome have been associated with risk of this disorder. In the current study, we genotyped rs12826786, rs1899663, and rs4759314 SNPs within HOX transcript antisense RNA (HOTAIR) in 427 ASD cases and 430 normally developed children. The rs12826786 was associated with ASD in allelic (T vs. C: OR (95% CI) = 1.29 (1.07-1.57), adjusted P value = 0.03) and recessive (TT vs. TC + CC: OR (95% CI) = 1.60 (1.10-2.32), adjusted P value = 0.04) models. However, the other SNPs were not associated with ASD in any inheritance model. No estimated haplotype within HOTAIR was associated with risk of ASD in the assessed population. Based on the results of the current investigation, the rs12826786 can be regarded as a risk locus for ASD in Iranian population.

Antioxidant Effects of Lycopene and Ubiquinol-10 on the Oxidative Stress in Rat Hepatocytes Induced by Tert-Buthyl Hydroperoxide.

Free radicals especially reactive oxygen metabolites can damage DNA, protein, enzymes, and membrane lipids. Lipid peroxidation in hepatocyte membrane may be involved in hepatic diseases. Antioxidants may inhibit this reaction. Due to oxidant-antioxidant imbalance, free radicals may cause destructive effects. For several years, scientists tried to find antioxidant compounds. In this study, the effects of lycopene and ubiquinol-10 on the oxidative stress in rat hepatocytes induced by t-buthyl hydroperoxide was determined. First, rat hepatocytes were isolated and then incubated in the presence of tert-buthyl hydroperoxide and the amount of malondialdehyde, as a marker of lipid peroxidation, was determined. Then, this reaction was performed in the presence of various concentrations of each lycopene and ubiquinol-10, and the malondialdehyde level was determined. The results of this study showed that in the presence of various concentrations of lycopene and ubiquinol-10 the levels of lipid peroxidation products significantly decreased (P<0.05). Thus, lycopene and ubiquinol-10 have inhibitory effects on lipid peroxidation reaction. This study showed the potential utility of lycopene and ubiquinol-10 in prevention of hepatic dysfunction.

The Study of Hemodialysis Effectiveness on the Change Rate of Lipid Peroxidation and L-Carnitine Level in Hemodialysis Patients.

Carnitine is a small molecule widely present in all cells from prokaryotic to eukaryotic. It is an important element in ß-oxidation of fatty acids. Carnitine is a scavenger of oxygen free radicals in mammalian tissues. Lack of carnitine in a hemodialysis patient can lead to carnitine deficiency. Oxidation of fatty acids and lipid metabolism are severly affected by carnitine deficiency. Oxidative stress is defined as imbalance between formation of free radicals and antioxidative defense mechanisms. It has been proposed to play a role in many disease states. In hemodialysis patients multiple factors can lead to a a high susceptibility to oxidative stress. The aim of this study was to determine hemodialysis effectiveness on the change rate of serum L-carnitine and lipid peroxidation. 27 patients with chronic renal failure (24-80 yrs) who undergo hemodialysis for 6-12 months were selected (M= 17, F= 10). Malondialdehyde (MDA), as an indicator of lipid peroxidation was measured colorimetrically with a standard thiobarbituric acid (TBA) method. L-carnitine was measured with enzymatic UV method (ROCHE, Spectronic Genesis 2, 340 nm). The weight mean of L-carnitine before and after hemodialysis was 7.67±3.6 mg/l and 2.07±1.6 mg/l, respectively (P<0.001). The weight mean of pre-hemodialysis MDA was 4.17±1.24 µmol/l, following hemodialysis -4.98±1.2 µmol/l (P<0.001). Results showed that 55.6% of patients suffered from carnitine defciency. Serum carnitine was found to be decreased markedly after hemodialysis (P<0.001). Our findings indicated that oxidative stress in these patients is further exacerbated by hemodialysis, as evidenced by increased lipid peroxidation. The relationship between serum L-carnitine and MDA before and after hemodialysis was observed (r=0.82; p<0.001; r=0.75; p<0.001).

Effects of some flavonoids on the susceptibility of low-density lipoprotein to oxidative modification.

The effects of six flavonoids viz., apigenin, genistein, morin, naringin, pelargonidin and quercetin on the susceptibility of low-density lipoprotein (LDL) to oxidative modification were investigated. Flavonoids were added to plasma and incubated for 3 hr at 37 degrees C, and the LDL fraction was separated by ultracentrifugation. Oxidizability of LDL was estimated by measuring conjugated diene (CD), lipid peroxides and thiobarbituric acid-reactive substances (TBARS), after cupric sulfate solution was added. Quercetin and morin significantly (P<0.01 by ANOVA) prolonged the lag time before initiation of oxidation reaction in dose-dependent manner. They also suppressed the formation of lipid peroxides and TBARS more markedly than other flavonoids. The ability to prolong lag time and suppression of lipid peroxides and TBARS formation was in the following order: quercetin >morin >pelargonidin >genistein >naringin >apigenin. LDL exposed to flavonoids reduced oxidizability. These findings suggest that flavonoids may have a role in ameliorating atherosclerosis.