Neuroanatomical Research Articles

Deep reinforcement learning for collision avoidance of autonomous ships in inland river

Due to the characteristics of large inertia, large time delay, and nonlinearity in ship motion, the maneuverability of ships is an important issue related to the safety of ship navigation. The manipulation of ships significantly affects the safety of ship navigation, and its importance will gradually increase with the development of autonomous ships. Collision accidents are common due to the complexity of inland waterways and density of the ships. Herein, an autonomous learning framework with deep reinforcement learning (DRL) is constructed for autonomous driving tasks. The state space, action space, reward function and neural network structure of DRL are designed based on the ship’s maneuvering characteristics and control requirements. A DDPG algorithm is then used to implement the controller. Finally, some representative route segments of the inland waterway is selected for simulation research based on the virtual simulation environment. The designed DRL controller can quickly converge from the training and learning process to meet the control requirements. By comparing with the previous experimental results, the effectiveness of this algorithm is verified. Therefore, this study provides a reference for future research on the collision avoidance technology of autonomous ships in inland rivers.

Exposure to the antiretroviral drug dolutegravir impairs structure and neurogenesis in a forebrain organoid model of human embryonic cortical development

IntroductionFor many therapeutic drugs, including antiretroviral drugs used to treat people living with HIV-1 (PLWH), we have little data on the potential effects on the developing human brain due to limited access to tissue and historical constraints on the inclusion of pregnant populations in clinical trials. Human induced pluripotent stem cells (iPSCs) offer a new avenue to gain insight on how drugs may impact human cell types representative of the developing central nervous system. To prevent vertical transmission of HIV and promote the health of pregnant PLWH, antiretroviral therapy must be initiated and/or maintained throughout pregnancy. However, many antiretroviral drugs are approved for widespread use following clinical testing only in non-pregnant populations and there may be limited information on potential teratogenicity until pregnancy outcomes are evaluated. The integrase strand transfer inhibitor dolutegravir (DTG) is a frontline antiretroviral drug that is effective in viral suppression of HIV but was previously reported to be associated with a slight increase in the risk for neural tube defects in one study, although this has not been replicated in other cohorts.MethodsTo directly investigate the potential impact of DTG on human cortical neurogenesis, we measured the effects of daily drug exposure on the early stages of corticogenesis in a human iPSC-based forebrain organoid model. We quantified organoid size and structure and analyzed gene and protein expression to evaluate the impact of several doses of DTG on organoid development.ResultsWe observed deficits in organoid structure and impaired neurogenesis in DTG-treated organoids compared to vehicle-treated control organoids after 20 or 40 days in culture. Our highest dose of DTG (10 μM) resulted in significantly smaller organoids with a reduced density of neural rosette structures compared to vehicle-treated controls. Mechanistically, RNA-sequencing and immunohistological analysis suggests dysregulated amino acid transport and activation of the integrated stress response in the DTG-treated organoids, and functionally, a small molecule integrated stress response inhibitor (ISRIB) could partially rescue increased expression of proteins related to cell cycle regulation.DiscussionTogether, these results illustrate the potential for human iPSC-based strategies to reveal biological processes during neurogenesis that may be affected by therapeutic drugs and provide complementary data in relevant human cell types to augment preclinical investigations of drug safety during pregnancy.

Scalable parallel photonic processing unit for various neural network accelerations

In recent years, integrated optical processing units (IOPUs) have demonstrated advantages in energy efficiency and computational speed for neural network inference applications. However, limited by optical integration technology, the practicality and versatility of IOPU face serious challenges. In this work, a scalable parallel photonic processing unit (SPPU) for various neural network accelerations based on high-speed phase modulation is proposed and implemented on a silicon-on-insulator platform, which supports parallel processing and can switch between multiple computational paradigms simply and without latency to infer different neural network structures, enabling to maximize the utility of on-chip components. The SPPU adopts a scalable and process-friendly architecture design, with a preeminent photonic-core energy efficiency of 0.83 TOPS/W, two to ten times higher than existing integrated solutions. In the proof-of-concept experiment, a convolutional neural network (CNN), a residual CNN, and a recurrent neural network (RNN) are all implemented on our photonic processor to handle multiple tasks of handwritten digit classification, signal modulation format recognition, and review emotion recognition. The SPPU achieves multi-task parallel processing capability, serving as a promising and attractive research route to maximize the utility of on-chip components under the constraints of integrated technology, which helps to make IOPU more practical and universal.

Investigating neural networks with groundwater flow equation loss

Physics-Informed Neural Networks (PINNs) are considered a powerful tool for solving partial differential equations (PDEs), particularly for the groundwater flow (GF) problem. In this paper, we investigate how the deep learning (DL) architecture, within the PINN framework, is connected to the ability to compute a more or less accurate numerical GF solution, so the link ‘PINN architecture - numerical performance’ is explored. Specifically, this paper explores the effect of various DL components, such as different activation functions and neural network structures, on the computational framework. Through numerical results and on the basis of some theoretical foundations of PINNs, this research aims to improve the explicability of PINNs to resolve, in this case, the one-dimensional GF equation. Moreover, our problem involves source terms described by a Dirac delta function, providing insights into the role of DL architecture in solving complex PDEs.

Split tensile strength of fiber-reinforced coral aggregate concrete: Deep learning model and experimental validation

Machine learning methods are increasingly becoming an important research field for solving the complex mechanical behavior of concrete materials. A reliable deep learning model was developed based on a dataset consisting of 319 experimental data points to predict the split tensile strength of fiber-reinforced coral aggregate concrete (FRCAC). The feature selection was carried out using correlation analysis, and the neural network structure was optimized by adjusting hyperparameters based on the 10-fold cross-validation (CV). Subsequently, six statistical indicators were employed to evaluate the accuracy and generalization ability of the model. The deep neural network (DNN) model demonstrates excellent performance, with R2, MAE, and MAPE of 0.98, 0.181 MPa, and 0.037 for the training dataset and 0.95, 0.286 MPa, and 0.074 for the test dataset, respectively. Additionally, 24 sets of concrete proportions are designed using the trained DNN model, and the results indicate that the absolute error and relative error between predicted and experimental values are less than 0.4 MPa and 6.8 %, respectively. The feature analysis based on SHapley Additive exPlanations (SHAP) reveals that volume fraction, curing age, water-binder ratio, and the tensile strength of fiber have the highest contribution in estimating the split tensile strength of FRCAC. This research can provide a reference for optimizing the design of FRCAC.

Wheat Flour Discrimination Using Two-Dimensional Correlation Spectroscopy and Deep Learning.

The continuous evolution of deep learning has garnered significant attention in spectroscopy. This study focuses on identifying wheat flour, presenting a more efficient and accurate method by combining two-dimensional correlation spectroscopy (2D-COS) and deep learning techniques. A data set of 316 near-infrared (NIR) spectral samples of four types of wheat flour was collected. By applying three disparate 2D-COS techniques, i.e., synchronous, asynchronous, and integrated, we crafted 948 2D-COS images. These images, obtained by transforming the original one-dimensional spectra into 2D representations, offer richer information for deep learning analysis. The study introduced an 18-layer residual network incorporating a convolutional attention mechanism, specifically tailored for the 2D-COS analysis of wheat flour, aimed at enhancing the model's discriminative capabilities by refining the residual neural network's structure. Achieving an unprecedented recognition accuracy of 100% through methodical optimization and rigorous training on the synchronous 2D-COS data set of wheat flour, the proposed model is a testament to the efficacy of deep learning in spectroscopic analysis. To further exhibit the confluence of 2D-COS with deep learning, t-distributed stochastic neighbor embedding was employed to visualize the distinctive 2D-COS features within the deep learning architecture. Additionally, the model's performance was juxtaposed with prevailing NIR spectral recognition methods, including random forest, gradient boosting decision tree, and artificial neural network. This comparison cemented the proposed approach's superiority in wheat flour categorization. The findings of this study not only introduce a novel and efficient solution for wheat flour quality analysis but also underscore the significant potential of deep learning techniques in spectroscopy applications.

Numerical investigation of the effective receptive field and its relationship with convolutional kernels and layers in convolutional neural network

The receptive field (RF) plays a crucial role in convolutional neural networks (CNNs) because it determines the amount of input information that each neuron in a CNN can perceive, which directly affects the feature extraction ability. As the number of convolutional layers in CNNs increases, there is a decay of the RF according to the two-dimensional Gaussian distribution. Thus, an effective receptive field (ERF) can be used to characterize the available part of the RF. The ERF is calculated by the kernel size and layer number within the neural network architecture. Currently, ERF calculation methods are typically applied to single-channel input data that are both independent and identically distributed. However, such methods may result in a loss of effective information if they are applied to more general (i.e., multi-channel) datasets. Therefore, we proposed a multi-channel ERF calculation method. By conducting a series of numerical experiments, we determined the relationship between the ERF and the convolutional kernel size in conjunction with the layer number. To validate the new method, we used the recently published global wave surrogate model for climate simulation (GWSM4C) and its accompanying dataset. According to the newly established relationship, we refined the kernel size and layer number in each neural network of the GWSM4C to produce the same ERF but lower RF attenuation rates than those of the original version. By visualizing the gradient map at several points in West African and East Pacific areas, the high gradient value regions confirmed the known swell sources, which indicated effective feature extraction in these areas. Furthermore, the new version of the GWSM4C yielded better prediction accuracy for significant wave height in global swell pools. The root mean square errors in the West African and East Pacific regions reduced from approximately 0.3 m, in the original model to about 0.15 m, in the new model. Moreover, these improvements were attributed to the higher efficiency of the newly modified neural network structure that allows the inclusion of more historical winds while maintaining acceptable computational consumption.

Comparison of transformer, LSTM and coupled algorithms for soil moisture prediction in shallow-groundwater-level areas with interpretability analysis

Accurate quantification of soil moisture is essential for understanding water and energy exchanges between the atmosphere and the Earth’s surface, as well as for agricultural applications. Predicting soil moisture content is vital for efficient water management, irrigation scheduling, and drought monitoring. Traditional forecasting methods, such as numerical regression models, often struggle due to various influencing factors and poor observation data quality. In contrast, deep learning algorithms, particularly recurrent and convolutional neural networks, show promise in predicting nonlinear data like soil moisture. This study focuses on shallow groundwater regions, using groundwater levels and meteorological data as features while coupling the Transformer model with other neural network structures. We investigate the potential of attention-based neural networks for soil moisture time series prediction. Our findings demonstrate that the Transformer model achieves an average R2 of 0.523 across different time lags, outperforming the LSTM model with an R2 of 0.485. The introduction of LSTM enhances the Transformer’s stability in handling temporal changes. Additionally, we verified the importance of groundwater for soil moisture prediction. This study introduces new methods for soil moisture prediction and offers new insights and recommendations for the development of artificial intelligence technology for soil moisture prediction.

Crossmodal correspondence of elevation/pitch and size/pitch is driven by real-world features.

Crossmodal correspondences are consistent associations between sensory features from different modalities, with some theories suggesting they may either reflect environmental correlations or stem from innate neural structures. This study investigates this question by examining whether retinotopic or representational features of stimuli induce crossmodal congruency effects. Participants completed an auditory pitch discrimination task paired with visual stimuli varying in their sensory (retinotopic) or representational (scene integrated) nature, for both the elevation/pitch and size/pitch correspondences. Results show that only representational visual stimuli produced crossmodal congruency effects on pitch discrimination. These results support an environmental statistics hypothesis, suggesting crossmodal correspondences rely on real-world features rather than on sensory representations.

Physics-Driven Image Dehazing from the Perspective of Unmanned Aerial Vehicles

Drone vision is widely used in change detection, disaster response, and military reconnaissance due to its wide field of view and flexibility. However, under haze and thin cloud conditions, image quality is usually degraded due to atmospheric scattering. This results in issues like color distortion, reduced contrast, and lower clarity, which negatively impact the performance of subsequent advanced visual tasks. To improve the quality of unmanned aerial vehicle (UAV) images, we propose a dehazing method based on calibration of the atmospheric scattering model. We designed two specialized neural network structures to estimate the two unknown parameters in the atmospheric scattering model: the atmospheric light intensity A and medium transmission t. However, calculation errors always occur in both processes for estimating the two unknown parameters. The error accumulation for atmospheric light and medium transmission will cause the deviation in color fidelity and brightness. Therefore, we designed an encoder-decoder structure for irradiance guidance, which not only eliminates error accumulation but also enhances the detail in the restored image, achieving higher-quality dehazing results. Quantitative and qualitative evaluations indicate that our dehazing method outperforms existing techniques, effectively eliminating haze from drone images and significantly enhancing image clarity and quality in hazy conditions. Specifically, the compared experiment on the R100 dataset demonstrates that the proposed method improved the peak signal-to-noise ratio (PSNR) and structure similarity index measure (SSIM) metrics by 6.9 dB and 0.08 over the second-best method, respectively. On the N100 dataset, the method improved the PSNR and SSIM metrics by 8.7 dB and 0.05 over the second-best method, respectively.

Multimodal Connectivity‐Guided Glioma Segmentation From Magnetic Resonance Images via Cascaded 3D Residual U‐Net

ABSTRACTGlioma is a type of brain tumor with a high mortality rate. Magnetic resonance imaging (MRI) is commonly used for examination, and the accurate segmentation of tumor regions from MR images is essential to computer‐aided diagnosis. However, due to the intrinsic heterogeneity of brain glioma, precise segmentation is very challenging, especially for tumor subregions. This article proposed a two‐stage cascaded method for brain tumor segmentation that considers the hierarchical structure of the target tumor subregions. The first stage aims to identify the whole tumor (WT) from the background area; and the second stage aims to achieve fine‐grained segmentation of the subregions, including enhanced tumor (ET) region and tumor core (TC) region. Both stages apply a deep neural network structure combining modified 3D U‐Net with a residual connection scheme to tumor region and subregion segmentation. Moreover, in the training phase, the 3D masks generation of subregions with potential incomplete connectivity are guided by the completely connected regions. Experiments were performed to evaluate the performance of the methods on both area and boundary accuracy. The average dice score of the WT, TC, and ET regions on BraTS 2020 dataset is 0.9168, 0.0.8992, 0.8489, and the Hausdorff distance is 6.021, 9.203, 12.171, respectively. The proposed method outperforms current works, especially in segmenting fine‐grained tumor subregions.

Neuroimaging Findings for the Overnight Consolidation of Learned Non-native Speech Sounds

Abstract Research over the past two decades has documented the importance of sleep to language learning. Sleep has been suggested to play a role in establishing new speech representations as well; however, the neural mechanisms corresponding to sleep-mediated effects on speech perception behavior are unknown. In this study, we trained monolingual English-speaking adults to perceive differences between the Hindi dental vs. retroflex speech contrast in the evening. We examined the blood oxygen level dependent signal using functional magnetic resonance imaging during perceptual tasks on both the trained talker and on an untrained talker shortly after training, and again the next morning. We also employed diffusion tensor imaging to determine if individual differences in white matter structure could predict variability in overnight consolidation. We found greater activity in cortical regions associated with language processing (e.g., left insula) on the second day. Fractional anisotropy values in the anterior thalamic radiation and the uncinate fasciculus was associated with the magnitude of overnight change in perceptual behavior on the generalization (untrained) talker, after controlling for differences in sleep duration and initial learning. Our findings suggest that speech-perceptual information is subject to an overnight transfer of information to the cortex. Moreover, neural structure appears to be linked to individual differences in efficiency of overnight consolidation.

Metabolomics Reveal Key Metabolic Pathway Responses to Anxiety State Regulated by Serotonin in Portunus trituberculatus.

Anxiety refers to the pathological persistence and intensification of emotional responses to danger, affecting health from psychological and physical aspects. Serotonin is an important neurotransmitter involved in the onset of anxiety. To explore the biological changes in the formation of anxiety in crustaceans under the regulation of serotonin, we applied the open field-like test method for assessing anxiety states of larval Portunus trituberculatus, a highly aggressive crustacean species with a more simple neural structure compared with rodents and mammals. Compared with the control group, serotonin treatment resulted in a significant decrease in the time spent by the larvae in the central zone, suggesting anxiety-like behavior. Clonazepam treatment reversed this result and provided further evidence that the behavior of larval P. trituberculatus displayed anxiety. Moreover, a non-targeted metabolomic analysis found a significant alteration in the metabolites involved in tryptophan metabolism pathways associated with anxiety, including L-kynurenine, N-acetyl serotonin, and serotonin. These metabolites are involved in the serotonin pathway, the kynurenine pathway, and other pathways that affect anxiety through tryptophan metabolism. There were no significant differences in tryptophan metabolism levels between the control and clonazepam treatment groups. Our results demonstrate the possible existence of anxiety-like behavior in the larvae of P. trituberculatus from two perspectives. Being a species with a simpler neural structure than that of mammals, the larvae of P. trituberculatus offer a convenient model for studying the mechanisms of anxiety in crustaceans.

Hybrid wind speed optimization forecasting system based on linear and nonlinear deep neural network structure and data preprocessing fusion

Wind speed time series forecasting has been widely used in wind power generation. However, the nonlinear and non-stationary characteristics of wind speed make accurate wind speed forecasting a difficult task. In recent years, the rapid development of artificial intelligence and machine learning technology provides a new solution to the problem of wind speed forecasting. Combining the advance of artificial intelligence and data analysis strategy, this paper proposes a wind speed forecasting system based on multi-model fusion and integrated learning. Considering the differences in data observation and training principles of various algorithms and exploiting the advantages of each model, a wind speed forecasting system with multiple machine learning algorithms embedded in integrated learning is constructed, which includes three modules: data preprocessing, optimization and forecasting. The data preprocessing module can conduct quantitative analysis through input data decomposition and feature extraction, and the combination of multi-objective intelligent optimization algorithm and combined forecasting method can effectively forecast the wind speed time series. The validity of the algorithm is verified using the data of Shandong wind farm in China. The forecasting results show that compared with the traditional single model forecasting, the proposed integrated wind speed forecasting system based on the fusion of multiple models has higher forecasting accuracy.

Changes in the Cyto- and Fibroarchitectonics of the Cerebellar Cortex in Rats Subjected to Extreme Physical Activity.

Physical overexertion surpassing the functional capacity of the nervous system causes the hyperactivation of the neural structures of the cerebellum. In turn, it causes the depletion of intracellular resources and progressive structural changes in cerebellar cells and fibers. These degenerative changes may lead to cerebellar dysfunction, including the worsening of coordination, balance, and motor functions. In order to maintain the health and functioning of the cerebellum and the nervous system in general, one needs to avoid physical overexertion and have enough time to recover. Three major types of Purkinje cells were identified in control group animals. After the forced swimming test, animals had significant morphological changes in pyriform cells, granule cells, internuncial neurons, and neuroglial cells. In particular, the extreme degeneration of granule cells was manifested via their fusion into conglomerates. These changes demonstrate that neurodegeneration in the cerebellum takes place in response to physical overexertion.

Enhanced Speech Processing for Air Traffic Control Using an Optimized Generative Adversarial Network

In order to improve the quality of voice calls during air traffic control, an improved SEGAN air traffic control speech enhancement algorithm is proposed. Aiming at the problem that the traditional speech enhancement algorithm based on generative adversarial network (SEGAN) is drowned under low signal-to-noise ratio conditions, a multi-stage, multi-mapping, multi-dimensional output generator and a multi-scale, multi-discriminator network model are proposed based on the SEGAN network model. First, the speech semantic features are extracted based on the deep neural network structure to complete the semantic segmentation of air traffic control speech. Secondly, multiple generators are set to further optimize the speech signal. Then, a downsampling module is added to the convolution layer to improve the model's utilization of speech information and reduce the loss of speech information. Finally, multi-scale, multiple discriminators are used to learn the distribution law and information of speech samples in multiple directions. The results show that under low signal-to-noise ratio conditions, the improved SEGAN model improves the short-term objective intelligibility (STOI) and the perceptual evaluation of speech quality (PESQ) by and respectively , which can quickly and effectively perform air traffic control speech enhancement and provide preparation for subsequent air traffic control speech recognition.

A novel deep neural network structure for software fault prediction

A novel deep neural network structure for software fault prediction

Brachial and Lumbosacral Plexopathies.

The brachial and lumbosacral plexuses are complex neural structures that transmit sensory, motor, and autonomic information between the spinal cord and the extremities. Plexus disorders can be particularly disabling because lesions in the plexus usually affect large groups of nerve fibers originating from several spinal levels. Electrodiagnostic studies are often required to confirm a plexus lesion and determine the extent of injury and prognosis. Magnetic resonance is the imaging modality of choice for detecting intrinsic nerve abnormalities; recently, high-resolution ultrasound has emerged as an alternative method for dynamic evaluation and visualization of internal nerve architecture. Once a plexopathy is confirmed, the list of possible etiologies is relatively limited and includes traumatic and nontraumatic causes. Treatment relies on symptom management and physical rehabilitation unless a treatable underlying condition is found. Surgical approaches, including nerve grafts or tendon transfers, may improve limb function when spontaneous recovery is suboptimal.

Plastic Constitutive Training Method for Steel Based on a Recurrent Neural Network

The deep learning steel plastic constitutive model training method was studied based on the recurrent neural network (RNN) model to improve the allocative efficiency of the deep learning steel plastic constitutive model and promote its application in practical engineering. Two linear hardening constitutive datasets of steel were constructed using the Gaussian stochastic process. The RNN, long short-term memory (LSTM), and gated recurrent unit (GRU) were used as models for training. The effects of the data pre-processing method, neural network structure, and training method on the model training were analyzed. The prediction ability of the model for different scale series and the corresponding data demand were evaluated. The results show that LSTM and the GRU are more suitable for stress–strain prediction. The marginal effect of the stacked neural network depth and number gradually decreases, and the hysteresis curve can be accurately predicted by a two-layer RNN. The optimal structure of the two models is A50-100 and B150-150. The prediction accuracy of the models increased with the decrease in batch size and the increase in training batch, and the training time also increased significantly. The decay learning rate method could balance the prediction accuracy and training time, and the optimal initial learning rate, batch size, and training batch were 0.001, 60, and 100, respectively. The deep learning plastic constitutive model based on the optimal parameters can accurately predict the hysteresis curve of steel, and the prediction abilities of the GRU are 6.13, 6.7, and 3.3 times those of LSTM in short, medium, and long sequences, respectively.

Aesthete Pattern Diversity in Chiton Clades (Mollusca: Polyplacophora): Balancing Sensory Structures and Strength in Valve Architecture.

Chitons possess the most elaborate system of shell pores found in any hard-shelled invertebrate. Although chitons possess some anteriorly located sense organs, they lack true cephalization, as their major sensory systems are not concentrated in a distinct head region. Instead, the aesthete system within their shells forms a dense sensory network that overcomes the barrier of their hard dorsal armour. The basic arrangement of neural structures embedded within a solid, opaque matrix, has confounded understanding of the overall network. In this study, we use synchrotron X-ray μCT to visualise the aesthete canal networks inside chiton valves. We selected representatives from all three major chiton clades: Lepidopleurida, the basal branching clade, and Callochitonida and Chitonida, which both havemore complex shell morphology, to compare internal structure. Lepidopleurida aesthete canals are oriented vertically and pass directly through the shell to connect with the body. By contrast, aesthetes canals in Callochitonida and Chitonida have complex internal structures with extended horizontal passages, coalescing at the shell diagonal that corresponds to the valve insertion slits. This represents a stepwise evolution of chiton shell form, where thicker and more complex valves require a diverting and rewiring of the entire sensorynetwork. Aspects of the aesthete system, such as the microscopic arrangement of surface pores, have long been used in chiton taxonomy for species diagnoses; insertion slits should also be understood as a secondary feature of the aesthete system. Chiton shell structures that are used for morphological systematics are driven by sensory adaptations.