Schizophrenia (SZ), major depressive disorder (MDD), and bipolar disorder (BD) are severe psychiatric disorders and share common characteristics not only in clinical symptoms but also in neuroimaging. The purpose of this study was to examine common and specific neuroanatomical features in individuals with these three psychiatric conditions. In this study, 70 patients with SZ, 85 patients with MDD, 42 patients with BD, and 95 healthy controls (HCs) were recruited. Voxel-based morphometry (VBM) analysis was used to explore brain imaging characteristics. Psychopathology was assessed using the Beck Depression Inventory (BDI), the Beck Anxiety Inventory (BAI), the Young Mania Rating Scale (YMRS), and the Positive and Negative Syndrome Scale (PANSS). Cognition was assessed using the digit symbol substitution test (DSST), forward-digital span (DS), backward-DS, and semantic fluency. Common reduced gray matter volume (GMV) in the orbitofrontal cortex (OFC) region was found across the SZ, MDD, and BD. Specific reduced GMV of brain regions was also found. For patients with SZ, we found reduced GMV in the frontal lobe, temporal pole, occipital lobe, thalamus, hippocampus, and cerebellum. For patients with MDD, we found reduced GMV in the frontal and temporal lobes, insular cortex, and occipital regions. Patients with BD had reduced GMV in the medial OFC, inferior temporal and fusiform regions, insular cortex, hippocampus, and cerebellum. Furthermore, the OFC GMV was correlated with processing speed as assessed with the DSST across four groups (r = 0.17, p = 0.004) and correlated with the PANSS positive symptoms sub-score in patients with SZ (r = - 0.27, p = 0.026). In conclusion, common OFC alterations in SZ, MDD, and BD provided evidence that this region dysregulation may play a critical role in the pathophysiology of these three psychiatric disorders.
Distributed training of graph neural networks (GNNs) has become a crucial technique for processing large graphs. Prevalent GNN frameworks are model-centric, necessitating the transfer of massive graph vertex features to GNN models, which leads to a significant communication bottleneck. Recognizing that the model size is often significantly smaller than the feature size, we propose LeapGNN, a feature-centric framework that reverses this paradigm by bringing GNN models to vertex features. To make it truly effective, we first propose a micrograph-based training strategy that trains the model using a refined structure with superior locality to reduce remote feature retrieval. Then, we devise a feature pre-gathering approach that merges multiple fetch operations into a single one to eliminate redundant feature transmissions. Finally, we employ a micrograph-based merging method that adjusts the number of micrographs for each worker to minimize kernel switches and synchronization overhead. Our experimental results demonstrate that LeapGNN achieves a performance speedup of up to 4.2x compared to the state-of-the-art method, namely P3.
Abstract The rolling bearing is a widely-used component in engineering. The fault diagnosis of rolling bearings is key to ensuring the normal operation of equipment. At present, research into the fault diagnosis of rolling bearings mainly focuses on the analysis of vibration data under constant working conditions. However, when dealing with practical engineering problems, equipment frequently operates at variable speed. To analyse the vibration data in the case of frequency conversion and accurately extract the fault characteristic frequency is a challenge, especially when the fault characteristics are weak. In addition, traditional vibration characteristic analysis requires professional technicians to supervise the operation of the equipment, which requires a certain professional ability of the staff. Based on the above two problems, this paper proposes a rolling bearing fault diagnosis model under time-varying speed working conditions, based on the EfficientNetv2 network. This method uses a short-time Fourier transform to convert a one-dimensional vibration signal into a two-dimensional image signal, and uses the advantages of an image recognition network to realize the fault diagnosis under time-varying speed conditions. After training the network, based on transfer learning, the experimental data verify that the accuracy of the results reaches 99.9 ± 0.1%, even in the case of weak fault characteristics, and there is no need for professional technicians to supervise and diagnose once the model is trained, which is conducive to practical application.
In mammalian testes, the apical cytoplasm of each Sertoli cell holds up to several dozens of germ cells, especially spermatids that are transported up and down the seminiferous epithelium. The blood-testis barrier (BTB) established by neighboring Sertoli cells in the basal compartment restructures on a regular basis to allow preleptotene/leptotene spermatocytes to pass through. The timely transfer of germ cells and other cellular organelles such as residual bodies, phagosomes, and lysosomes across the epithelium to facilitate spermatogenesis is important and requires the microtubule-based cytoskeleton in Sertoli cells. Kinesins, a superfamily of the microtubule-dependent motor proteins, are abundantly and preferentially expressed in the testis, but their functions are poorly understood. This review summarizes recent findings on kinesins in mammalian spermatogenesis, highlighting their potential role in germ cell traversing through the BTB and the remodeling of Sertoli cell-spermatid junctions to advance spermatid transport. The possibility of kinesins acting as a mediator and/or synchronizer for cell cycle progression, germ cell transit, and junctional rearrangement and turnover is also discussed. We mostly cover findings in rodents, but we also make special remarks regarding humans. We anticipate that this information will provide a framework for future research in the field.
Abstract Magnetic flux leakage (MFL) testing, non-destructive testing, can prevent some major accidents of hoist equipment by identifying the damage of wire ropes. However, in harsh working conditions such as mines and oil wells, the inevitable vibration and swing of wire rope will generate noise and interfere with the MFL signal, which makes us difficult to identify the damage. As a classification network, Convolutional neural network (CNN) is positive in recognition accuracy and noise resistance, but it hardly uses in wire rope damage classification. To improve the accuracy of wire rope damage identification under noise background, we propose a method of wire rope damage identification via Light-EfficientNetV2 and MFL image. First, the MFL signal is segmented and rearranged to form the MFL image, and then the image is classified by Light-EfficientNetV2. To improve the classification efficiency, we reduce the layers of EfficientNetV2 to make it lighter. Finally, the availability of this method is proved by the validation set. Compared with four neural networks, the accuracy is the highest. Moreover, as the noise increased, the accuracy of Light-EfficientNetV2 is higher than EfficientNetV2, which has application value in the wire rope damage identification under noise background.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'/%3e%3cuse xlink:href='%23a' transform='rotate(144 450 300)'/%3e%3cuse xlink:href='%23a' transform='rotate(216 450 300)'/%3e%3cuse xlink:href='%23a' transform='rotate(288 450 300)'/%3e%3c/svg%3e)