工程技术最新文献

Cross subject Electroencephalogram (EEG) emotion recognition refers to the process of utilizing electroencephalogram signals to recognize and classify emotions across different individuals. It tracks neural electrical patterns, and by analyzing these signals, it's possible to infer a person's emotional state. The objective of cross-subject recognition is to create models or algorithms that can reliably detect emotions in both the same person and several other people. Accurately predicting emotions poses challenges due to dynamic traits. Models struggle with feature extraction, convergence, and negative transfer issues, hindering cross subject emotion recognition. The proposed model employs thorough signal preprocessing, Short-Time Geodesic Flow Kernel Fourier Transform (STGFKFT) for feature extraction, enhancing classifiers' accuracy. Multi-view sheaf attention improves feature discrimination, while the Multi-Scale Convolutional Conditional Invertible Puma Discriminator Neural Network (MSCCIPDNN) framework ensures generalization. Efficient computational techniques and the puma optimization algorithm enhance model robustness and convergence. The suggested framework demonstrates extraordinary success with high accuracy, of 99.5%, 99% and 99.50% for SEED, SEED-IV, and DEAP dataset sequentially. By incorporating these techniques, the proposed method aims to precisely recognition emotions, and accurately captures the features, thereby overcoming the limitations of existing methodologies.

Autism spectrum disorder (ASD) is one of the complicated neurodevelopmental disorders that impacts the daily functioning and social interactions of individuals. It includes diverse symptoms and severity levels, making it challenging to diagnose and treat efficiently. Various deep learning (DL) based methods have been developed for diagnosing ASD, which rely heavily on behavioral assessment. However, existing techniques have suffered from poor diagnostic outcomes, higher computational complexity, and overfitting issues. To address these challenges, this research work introduces an innovative framework called 3T Dilated Inception Network (3T-DINet) for effective ASD diagnosis using resting-state functional Magnetic Resonance Imaging (rs-fMRI) images. The proposed 3T-DINet technique designs a 3T dilated inception module that incorporates dilated convolutions along with the inception module, allowing it to extract multi-scale features from brain connectivity patterns. The 3T dilated inception module uses three distinct dilation rates (low, medium, and high) in parallel to determine local, mid-level, and global features from the brain. In addition, the proposed approach implements Residual networks (ResNet) to avoid the vanishing gradient problem and enhance the feature extraction ability. The model is further optimized using a Crossover-based Black Widow Optimization (CBWO) algorithm that fine-tunes the hyperparameters thereby enhancing the overall performance of the model. Further, the performance of the 3T-DINet model is evaluated using the five ASD datasets with distinct evaluation parameters. The proposed 3T-DINet technique achieved superior diagnosis results compared to recent previous works. From this simulation validation, it's clear that the 3T-DINet provides an excellent contribution to early ASD diagnosis and enhances patient treatment outcomes.

Psychological studies have demonstrated that the music can affect memory by triggering different emotions. Building on the relationships among music, emotion, and memory, a memristor-based emotion associative learning circuit is designed by utilizing the nonlinear and non-volatile characteristics of memristors, which includes a music judgment module, three emotion generation modules, three emotional homeostasis modules, and a memory module to implement functions such as learning, second learning, forgetting, emotion generation, and emotional homeostasis. The experimental results indicate that the proposed circuit can simulate the learning and forgetting processes of human under different music circumstances, demonstrate the feasibility of memristors in biomimetic circuits, verify the impact of music on memory, and provide a foundation for in-depth research and application development of the interaction mechanism between emotion and memory.

Alzheimer's disease (AD) is a chronic disability that occurs due to the loss of neurons. The traditional methods to detect AD involve questionnaires and expensive neuro-imaging tests, which are time-consuming, subjective, and inconvenient to the target population. To overcome these limitations, Electroencephalogram (EEG) based methods have been developed to classify AD patients from normal controlled (NC) and mild cognitive impairment (MCI) subjects. Most of the EEG-based methods involved entropy-based feature extraction and discrete wavelet transform. However, the existing AD classification methods failed to provide promising classification accuracy. Here, we proposed a wavelet-machine learning (ML) framework to detect AD using a newly designed biorthogonal filter bank by optimization of frequency and time localization of triplet halfband filter banks (OTFL-THFB). The OTFL-THFB decomposes EEG signals into various EEG sub- bands. Hjorth Parameters (HP) and Higuchi's Fractal Dimension (HFD) have been investigated to extract features from each EEG subband. Subsequently, ML models are trained and tested using different features such as OTFL-THFB with HFD, OTFL-THFB with HP, and OTFL-THFB with HFD and HP used for detecting AD with 10-fold cross-validation. This method was applied to two publicly available datasets. Our model achieved an accuracy of $98.91\%$ for AD versus NC and $98.65\%$ for AD versus MCI versus NC using the least square support vector machine. Results indicate that this framework surpassed existing state-of-the-art techniques for classifying AD from NC.

Parkinson's disease (PD) is a neurodegenerative disease with various clinical manifestations caused by multiple risk factors. However, the effect of different factors and relationships between different features related to PD and the extent of those factors leading to the incidence of PD remains unclear. we employed Bayesian network to construct a prediction model. The prediction system was trained on the data of 35 patients and 26 controls. The structure learning and parameter learning of Bayesian Network was completed through the tree-augmented network (TAN) and Netica software, respectively. We employed four Bayesian Networks in terms of the syllable, including monosyllables, disyllables, multisyllables and unsegmented syllables. The area under the curve (AUC) of monosyllabic, disyllabic, multisyllabic, and unsegmented-syllable models were 0.95, 0.83, 0.80 and 0.84, respectively. In the monosyllabic tests, the best predictor of PD was duration, the posterior probability of which was 92.70%. Meanwhile, minimum f0 (61.60%) predicted best in the disyllabic tests and the variables that predicted best in multisyllables and unsegmented syllables were end f0 (59.40%) and maximum f0 (58.40%). In the cross-sectional comparison, the prediction effect of each variable in the monosyllabic tests was generally higher than that of other test groups. The monosyllabic models had the highest predicted performance of PD. Among acoustic parameters, duration was the strongest feature in predicting the prevalence of PD in monosyllabic tests. We believe that this network methodology will be a useful tool for the clinical prediction of Parkinson's disease.

Supplementary information: The online version contains supplementary material available at 10.1007/s11571-024-10194-x.

The term "neuroenhancement" describes the enhancement of cognitive function associated with deficiencies resulting from a specific condition. Nevertheless, there is currently no agreed-upon definition for the term "neuroenhancement", and its meaning can change based on the specific research being discussed. As humans, our continual pursuit of expanding our capabilities, encompassing both cognitive and motor skills, has led us to explore various tools. Among these, repetitive Transcranial Magnetic Stimulation (rTMS) stands out, yet its potential remains underestimated. Historically, rTMS was predominantly employed in studies focused on rehabilitation objectives. A small amount of research has examined its use on healthy subjects with the goal of improving cognitive abilities like risk-seeking, working memory, attention, cognitive control, learning, computing speed, and decision-making. It appears that the insights gained in this domain largely stem from indirect outcomes of rehabilitation research. This review aims to scrutinize these studies, assessing the effectiveness of rTMS in enhancing cognitive skills in healthy subjects. Given that the dorsolateral prefrontal cortex (DLPFC) has become a popular focus for rTMS in treating psychiatric disorders, corresponding anatomically to Brodmann areas 9 and 46, and considering the documented success of rTMS stimulation on the DLPFC for cognitive improvement, our focus in this review article centers on the DLPFC as the focal point and region of interest. Additionally, recognizing the significance of theta burst magnetic stimulation protocols (TBS) in mimicking the natural firing patterns of the brain to modulate excitability in specific cortical areas with precision, we have incorporated Theta Burst Stimulation (TBS) wave patterns. This inclusion, mirroring brain patterns, is intended to enhance the efficacy of the rTMS method. To ascertain if brain magnetic stimulation consistently improves cognition, a thorough meta-analysis of the existing literature has been conducted. The findings indicate that, after excluding outlier studies, rTMS may improve cognition when compared to appropriate control circumstances. However, there is also a considerable degree of variation among the researches. The navigation strategy used to reach the stimulation site and the stimulation location are important factors that contribute to the variation between studies. The results of this study can provide professional athletes, firefighters, bodyguards, and therapists-among others in high-risk professions-with insightful information that can help them perform better on the job.

Genome editing tools have rapidly been adopted by plant scientists for crop improvement. Genome editing using a multiplex sgRNA-CRISPR/Cas9 genome editing system is a useful technique for crop improvement in monocot species. In this study, we utilized precise gene editing techniques to generate wheat 3'(2'), 5'-bisphosphate nucleotidase (TaSal1) mutants using a multiplex sgRNA-CRISPR/Cas9 genome editing system. Five active TaSal1 homologous genes were found in the genome of Giza168 in addition to another apparently inactive gene on chromosome 4A. Three gRNAs were designed and used to target exons 4, 5 and 7 of the five wheat TaSal1 genes. Among the 120 Giza168 transgenic plants, 41 lines exhibited mutations and produced heritable TaSal1 mutations in the M₁ progeny and 5 lines were full 5 gene knock-outs. These mutant plants exhibit a rolled-leaf phenotype in young leaves and bended stems, but there were no significant changes in the internode length and width, leaf morphology, and stem shape. Anatomical and scanning electron microscope studies of the young leaves of mutated TaSal1 lines showed closed stomata, increased stomata width and increase in the size of the bulliform cells. Sal1 mutant seedlings germinated and grew better on media containing polyethylene glycol than wildtype seedlings. Our results indicate that the application of the multiplex sgRNA-CRISPR/Cas9 genome editing is efficient tool for mutating more multiple TaSal1 loci in hexaploid wheat.

Herein, we investigated the phytochemical composition and antibacterial activities of the organic layers from biosynthesized silver nanoparticles (AgNPs). AgNPs were synthesized using Musa paradisiaca and Musa sapientum extracts. UV-vis absorption in the 400-450 nm range indicated surface plasmonic resonance peak of AgNPs. Samples analyses using dynamic light scattering and transmission electron microscopy revealed the presence of particles within nanometric ranges, with sizes of 30-140 nm and 8-40 nm, respectively. Fourier transform infrared (FTIR) unveiled the presence of several organic functional groups on the surface of AgNPs, indicating the presence of phytochemicals from plant extracts. Thin layer chromatography (TLC) of the phytochemicals (capping agents) from AgNPs identified multiple groups of secondary metabolites. These phytochemical capping agents exhibited antibacterial activities against Staphylococcus aureus, Escherichia coli, and Pseudomonas aeruginosa, with minimum inhibitory concentrations ranging from 62.5 to 1000 µg/mL. Regardless of the bacterial species or plant parts (leaves or pseudo-stems), capping agents from M. sapientum nanoparticles displayed significantly enhanced antibacterial effectiveness compared to all other samples, including the raw plant extracts and biosynthesized capped and uncapped AgNPs. These results suggest the presence of antimicrobial phytochemicals on biosynthesized AgNPs, highlighting the promise of green nanoparticle synthesis as a valuable approach in bioprospecting antimicrobial agents.

Objective: This trial probed the correlation between miR-31 expression and endometrial receptivity (ER) in patients with repeated implantation failure (RIF) of in vitro fertilization and embryo transfer (IVF-ET).

Methods: A retrospective study of 80 infertility patients who underwent IVF-ET assisted conception treatment were divided into RIF group and normal pregnancy group (control group) according to the pregnancy outcome after embryo transfer. General information of both groups was collected. Endometrial tissues were collected in the middle luteal phase of the menstrual cycle before IVF-ET. miR-31 levels in endometrial tissues were measured, and endometrial tolerance indicator pulsatility index (PI), resistance index (RI), and endometrial thickness (Em) were detected. The correlation between endometrial miR-31 levels and ER indices was evaluated by Pearson method. ROC curves were utilized to analyze the efficacy of miR-31 in predicting RIF occurrence. The influencing factors of RIF were analyzed by binary Logistic regression.

Results: RIF patients had increased miR-31 expression level and endometrial tolerance indicator PI, and RI while decreased Em (p < 0.05). miR-31 in RIF patients was positively correlated with PI and RI, and negatively correlated with Em (p < 0.05). The area under the curve for miR-31 to predict the occurrence of RIF was 0.899, with a sensitivity of 0.750 and a specificity of 0.950. PI, RI, and miR-31 were risk factors for developing RIF in IVF-ET women, and Em was a protective factor (p < 0.05).

Conclusion: miR-31 in RIF patients is positively correlated with PI and RI, and negatively correlated with Em.

Malic acid markedly affects watermelon flavor. Reducing the malic acid content can significantly increase the sweetness of watermelon. An effective solution strategy is to reduce watermelon malic acid content through molecular breeding technology. In this study, we measured the TSS and pH of six watermelon varieties at four growth nodes. The TSS content was very low at 10 DAP and accumulated rapidly at 18, 26, and 34 DAP. Three phosphoenolpyruvate carboxykinase (PEPCK) genes of watermelon were identified and analyzed. The ClaPEPCK4 expression was inversely proportional to malate content variations in fruits. In transgenic watermelon plants, overexpressing the ClaPEPCK4 gene, malic acid content markedly decreased. In the knockout transgenic watermelon plants, two SNP mutations and one base deletion occurred in the ClaPEPCK4 gene, with the malic acid content in the leaves increasing considerably and the PEPCK enzyme activity reduced to half of the wild-type. It is interesting that the ClaPEPCK4 gene triggered the closure of leaf stomata under dark conditions in the knockout transgenic plants, which indicated its involvement in stomatal movement. In conclusion, this study provides a gene target ClaPEPCK4 for creating innovative new high-sweetness watermelon varieties.