Graph-based EEG approach for depression prediction: integrating time-frequency complexity and spatial topology.

Depression has become the prevailing global mental health concern. The accuracy of traditional depression diagnosis methods faces challenges due to diverse factors, making primary identification a complex task. Thus, the imperative lies in developing a method that fulfills objectivity and effectiveness criteria for depression identification. Current research underscores notable disparities in brain activity between individuals with depression and those without. The Electroencephalogram (EEG), as a biologically reflective and easily accessible signal, is widely used to diagnose depression. This article introduces an innovative depression prediction strategy that merges time-frequency complexity and electrode spatial topology to aid in depression diagnosis. Initially, time-frequency complexity and temporal features of the EEG signal are extracted to generate node features for a graph convolutional network. Subsequently, leveraging channel correlation, the brain network adjacency matrix is employed and calculated. The final depression classification is achieved by training and validating a graph convolutional network with graph node features and a brain network adjacency matrix based on channel correlation. The proposed strategy has been validated using two publicly available EEG datasets, MODMA and PRED+CT, achieving notable accuracy rates of 98.30 and 96.51%, respectively. These outcomes affirm the reliability and utility of our proposed strategy in predicting depression using EEG signals. Additionally, the findings substantiate the effectiveness of EEG time-frequency complexity characteristics as valuable biomarkers for depression prediction.

Data-Driven Discovery of Gas-Selective Organic Linkers in Metal-Organic Frameworks for the Separation of Ethylene and Ethane.

Metal-organic frameworks (MOFs) are potential candidates for gas-selective adsorbents for the separation of an ethylene/ethane mixture. To accelerate material discovery, high-throughput computational screening is a viable solution. However, classical force fields, which were widely employed in recent studies of MOF adsorbents, have been criticized for their failure to cover complicated interactions such as those involving π electrons. Herein, we demonstrate that machine learning force fields (MLFFs) trained on quantum-chemical reference data can overcome this difficulty. We have constructed a MLFF to accurately predict the adsorption energies of ethylene and ethane on the organic linkers of MOFs and discovered that the π electrons from both the ethylene molecule and the aromatic rings in the linkers could substantially influence the selectivity for gas adsorption. Four kinds of MOF linkers are identified as having promise for the separation of ethylene and ethane, and our results could also offer a new perspective on the design of MOF building blocks for diverse applications.

Unravelling the Impact of Metal Dopants and Oxygen Vacancies on Syngas Conversion over Oxides: A Machine Learning-Accelerated Study of CO Activation on Cr-Doped ZnO Surfaces.

As a critical component of the OX-ZEO composite catalysts toward syngas conversion, the Cr-doped ZnO ternary system can be considered as a model system for understanding oxide catalysts. However, due to the complexity of its structures, traditional approaches, both experimental and theoretical, encounter significant challenges. Herein, we employ machine learning-accelerated methods, including grand canonical Monte Carlo and genetic algorithm, to explore the ZnO(1010) surface with various Cr and oxygen vacancy (OV) concentrations. Stable surfaces with varied Cr and OV concentrations were then systematically investigated to examine their influence on the CO activation via density functional theory calculations. We observe that Cr tends to preferentially appear on the surface of ZnO(1010) rather than in its interior regions and Cr-doped structures incline to form rectangular islands along the [0001] direction at high Cr and OV concentrations. Additionally, detailed calculations of CO reactivity unveil an inverse relationship between the reaction barrier (Ea) for C-O bond dissociation and the Cr and OV concentrations, and a linear relationship is observed between OV formation energy and Ea for CO activation. Further analyses indicate that the C-O bond dissociation is much more favored when the adjacent OVs are geometrically aligned in the [1210] direction, and Cr is doped around the reactive sites. These findings provide a deeper insight into CO activation over the Cr-doped ZnO surface and offer valuable guidance for the rational design of effective catalysts for syngas conversion.

Mechanistic Studies on Aluminum-Catalyzed Ring-Opening Alternating Copolymerization of Maleic Anhydride with Epoxides: Ligand Effects and Quantitative Structure-Activity Relationship Model.

Previous work has indicated that aluminum (Al) complexes supported by a bipyridine bisphenolate (BpyBph) ligand exhibit higher activity in the ring-opening copolymerization (ROCOP) of maleic anhydride (MAH) and propylene oxide (PO) than their salen counterparts. Such a ligand effect in Al-catalyzed MAH-PO copolymerization reactions has yet to be clarified. Herein, the origin and applicability of the ligand effect have been explored by density functional theory, based on the mechanistic analysis for chain initiation and propagation. We found that the lower LUMO energy of the (BpyBph)AlCl complex accounts for its higher activity than the (salen)AlCl counterpart in MAH/epoxide copolymerizations. Inspired by the ligand effect, a structure-energy model was further established for catalytic activity (TOF value) predictions. It is found that the LUMO energies of aluminum chloride complexes and their average NBO charges of coordinating oxygen atoms correlate with the catalytic activity (TOF value) of Al complexes (R2 value of 0.98 and '3-fold' cross-validation Q2 value of 0.88). This verified that such a ligand effect is generally applicable in anhydride/epoxide ROCOP catalyzed by aluminum complex and provides hints for future catalyst design.

Exquisitely Constructing a Robust MOF with Dual Pore Sizes for Efficient CO2 Capture.

Developing metal-organic framework (MOF) adsorbents with excellent performance and robust stability is of critical importance to reduce CO2 emissions yet challenging. Herein, a robust ultra-microporous MOF, Cu(bpfb)(bdc), with mixed ligands of N, N'-(1,4-phenylene)diisonicotinamide (bpfb), and 1,4-dicarboxybenzene (bdc) was delicately constructed. Structurally, this material possesses double-interpenetrated frameworks formed by two staggered, independent frameworks, resulting in two types of narrow ultra-micropores of 3.4 × 5.0 and 4.2 × 12.8 Å2, respectively. The above structural properties make its highly selective separation at 273~298 K with a CO2 capacity of 71.0~86.2 mg/g. Its adsorption heat over CO2 and IAST selectivity were calculated to be 27 kJ/mol and 52.2, respectively. Remarkably, cyclic breakthrough experiments corroborate its impressive performance in CO2/N2 separation in not only dry but also 75% RH humid conditions. Molecular simulation reveals that C-H···OCO2 in the pores plays a pivotal role in the high selectivity of CO2 adsorption. These results point out the huge potential application of this material for CO2/N2 separation.

Comprehensive Study of Oxygen Vacancies on the Catalytic Performance of ZnO for CO/H2 Activation Using Machine Learning-Accelerated First-Principles Simulations.

Oxygen vacancies (OVs) play important roles on any oxide catalysts. In this work, using an investigation of the OV effects on ZnO(101̅0) for CO and H2 activation as an example, we demonstrate, via machine learning potentials (MLPs), genetic algorithm (GA)-based global optimization, and density functional theory (DFT) validations, that the ZnO(101̅0) surface with 0.33 ML OVs is the most likely surface configuration under experimental conditions (673 K and 2.5 MPa syngas (H2:CO = 1.5)). It is found that a surface reconstruction from the wurtzite structure to a body-centered-tetragonal one would occur in the presence of OVs. We show that the OVs create a Zn3 cluster site, allowing H2 homolysis and C-O bond cleavage to occur. Furthermore, the activity of intrinsic sites (Zn3c and O3c sites) is almost invariable, while the activity of the generated OV sites is strongly dependent on the concentration of the OVs. It is also found that OV distributions on the surface can considerably affect the reactions; the barrier of C-O bond dissociation is significantly reduced when the OVs are aligned along the [12̅10] direction. These findings may be general in the systems with metal oxides in heterogeneous catalysis and may have significant impacts on the field of catalyst design by regulating the concentration and distribution of the OVs.

EEG-based high-performance depression state recognition.

Depression is a global disease that is harmful to people. Traditional identification methods based on various scales are not objective and accurate enough. Electroencephalogram (EEG) contains abundant physiological information, which makes it a new research direction to identify depression state. However, most EEG-based algorithms only extract the original EEG features and ignore the complex spatiotemporal information interactions, which will reduce performance. Thus, a more accurate and objective method for depression identification is urgently needed. In this work, we propose a novel depression identification model: W-GCN-GRU. In our proposed method, we censored six sensitive features based on Spearman's rank correlation coefficient and assigned different weight coefficients to each sensitive feature by AUC for the weighted fusion of sensitive features. In particular, we use the GCN and GRU cascade networks based on weighted sensitive features as depression recognition models. For the GCN, we creatively took the brain function network based on the correlation coefficient matrix as the adjacency matrix input and the weighted fused sensitive features were used as the node feature matrix input. Our proposed model performed well on our self-collected dataset and the MODMA datasets with a accuracy of 94.72%, outperforming other methods. Our findings showed that feature dimensionality reduction, weighted fusion, and EEG spatial information all had great effects on depression recognition.

A Depression Diagnosis Method Based on the Hybrid Neural Network and Attention Mechanism.

Depression is a common but easily misdiagnosed disease when using a self-assessment scale. Electroencephalograms (EEGs) provide an important reference and objective basis for the identification and diagnosis of depression. In order to improve the accuracy of the diagnosis of depression by using mainstream algorithms, a high-performance hybrid neural network depression detection method is proposed in this paper combined with deep learning technology. Firstly, a concatenating one-dimensional convolutional neural network (1D-CNN) and gated recurrent unit (GRU) are employed to extract the local features and to determine the global features of the EEG signal. Secondly, the attention mechanism is introduced to form the hybrid neural network. The attention mechanism assigns different weights to the multi-dimensional features extracted by the network, so as to screen out more representative features, which can reduce the computational complexity of the network and save the training time of the model while ensuring high precision. Moreover, dropout is applied to accelerate network training and address the over-fitting problem. Experiments reveal that the 1D-CNN-GRU-ATTN model has more effectiveness and a better generalization ability compared with traditional algorithms. The accuracy of the proposed method in this paper reaches 99.33% in a public dataset and 97.98% in a private dataset, respectively.

A Depression Prediction Algorithm Based on Spatiotemporal Feature of EEG Signal.

Depression has gradually become the most common mental disorder in the world. The accuracy of its diagnosis may be affected by many factors, while the primary diagnosis seems to be difficult to define. Finding a way to identify depression by satisfying both objective and effective conditions is an urgent issue. In this paper, a strategy for predicting depression based on spatiotemporal features is proposed, and is expected to be used in the auxiliary diagnosis of depression. Firstly, electroencephalogram (EEG) signals were denoised through the filter to obtain the power spectra of the three corresponding frequency ranges, Theta, Alpha and Beta. Using orthogonal projection, the spatial positions of the electrodes were mapped to the brainpower spectrum, thereby obtaining three brain maps with spatial information. Then, the three brain maps were superimposed on a new brain map with frequency domain and spatial characteristics. A Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) were applied to extract the sequential feature. The proposed strategy was validated with a public EEG dataset, achieving an accuracy of 89.63% and an accuracy of 88.56% with the private dataset. The network had less complexity with only six layers. The results show that our strategy is credible, less complex and useful in predicting depression using EEG signals.

A Novel Fault Diagnosis Approach for Chillers Based on 1-D Convolutional Neural Network and Gated Recurrent Unit.

The safety of an Internet Data Center (IDC) is directly determined by the reliability and stability of its chiller system. Thus, combined with deep learning technology, an innovative hybrid fault diagnosis approach (1D-CNN_GRU) based on the time-series sequences is proposed in this study for the chiller system using 1-Dimensional Convolutional Neural Network (1D-CNN) and Gated Recurrent Unit (GRU). Firstly, 1D-CNN is applied to automatically extract the local abstract features of the sensor sequence data. Secondly, GRU with long and short term memory characteristics is applied to capture the global features, as well as the dynamic information of the sequence. Moreover, batch normalization and dropout are introduced to accelerate network training and address the overfitting issue. The effectiveness and reliability of the proposed hybrid algorithm are assessed on the RP-1043 dataset; based on the experimental results, 1D-CNN_GRU displays the best performance compared with the other state-of-the-art algorithms. Further, the experimental results reveal that 1D-CNN_GRU has a superior identification rate for minor faults.