Single image haze removal is a challenging ill-posed problem. Existing methods use various constraints/priors to get plausible dehazing solutions. The key to achieve haze removal is to estimate a ...medium transmission map for an input hazy image. In this paper, we propose a trainable end-to-end system called DehazeNet, for medium transmission estimation. DehazeNet takes a hazy image as input, and outputs its medium transmission map that is subsequently used to recover a haze-free image via atmospheric scattering model. DehazeNet adopts convolutional neural network-based deep architecture, whose layers are specially designed to embody the established assumptions/priors in image dehazing. Specifically, the layers of Maxout units are used for feature extraction, which can generate almost all haze-relevant features. We also propose a novel nonlinear activation function in DehazeNet, called bilateral rectified linear unit, which is able to improve the quality of recovered haze-free image. We establish connections between the components of the proposed DehazeNet and those used in existing methods. Experiments on benchmark images show that DehazeNet achieves superior performance over existing methods, yet keeps efficient and easy to use.
In recent years, emotion recognition has become a research focus in the area of artificial intelligence. Due to its irregular structure, EEG data can be analyzed by applying graphical based ...algorithms or models much more efficiently. In this work, a Graph Convolutional Broad Network (GCB-net) was designed for exploring the deeper-level information of graph-structured data. It used the graph convolutional layer to extract features of graph-structured input and stacks multiple regular convolutional layers to extract relatively abstract features. The final concatenation utilized the broad concept, which preserves the outputs of all hierarchical layers, allowing the model to search features in broad spaces. To improve the performance of the proposed GCB-net, the broad learning system (BLS) was applied to enhance its features. For comparison, two individual experiments were conducted to examine the efficiency of the proposed GCB-net based on the SJTU emotion EEG dataset (SEED) and DREAMER dataset respectively. In SEED, compared with other state-of-art methods, the GCB-net could better promote the accuracy (reaching 94.24 percent) on the DE feature of the all-frequency band. In DREAMER dataset, GCB-net performed better than other models with the same setting. Furthermore, the GCB-net reached high accuracies of 86.99, 89.32 and 89.20 percent on dimensions of Valence, Arousal and Dominance respectively. The experimental results showed the robust classifying ability of the GCB-net and BLS in EEG emotion recognition.
Emotion recognition based on physiological signals has been a hot topic and applied in many areas such as safe driving, health care and social security. In this paper, we present a comprehensive ...review on physiological signal-based emotion recognition, including emotion models, emotion elicitation methods, the published emotional physiological datasets, features, classifiers, and the whole framework for emotion recognition based on the physiological signals. A summary and comparation among the recent studies has been conducted, which reveals the current existing problems and the future work has been discussed.
Electroencephalogram (EEG) signal-based emotion recognition has attracted wide interests in recent years and has been broadly adopted in medical, affective computing, and other relevant fields. ...However, the majority of the research reported in this field tends to focus on the accuracy of classification whilst neglecting the interpretability of emotion progression. In this paper, we propose a new interpretable emotion recognition approach with the activation mechanism by using machine learning and EEG signals. This paper innovatively proposes the emotional activation curve to demonstrate the activation process of emotions. The algorithm first extracts features from EEG signals and classifies emotions using machine learning techniques, in which different parts of a trial are used to train the proposed model and assess its impact on emotion recognition results. Second, novel activation curves of emotions are constructed based on the classification results, and two emotion coefficients, i.e., the correlation coefficients and entropy coefficients. The activation curve can not only classify emotions but also reveals to a certain extent the emotional activation mechanism. Finally, a weight coefficient is obtained from the two coefficients to improve the accuracy of emotion recognition. To validate the proposed method, experiments have been carried out on the DEAP and SEED dataset. The results support the point that emotions are progressively activated throughout the experiment, and the weighting coefficients based on the correlation coefficient and the entropy coefficient can effectively improve the EEG-based emotion recognition accuracy.
EEG-based automatic emotion recognition can help brain-inspired robots in improving their interactions with humans. This paper presents a novel framework for emotion recognition using multi-channel ...electroencephalogram (EEG). The framework consists of a linear EEG mixing model and an emotion timing model. Our proposed framework considerably decomposes the EEG source signals from the collected EEG signals and improves classification accuracy by using the context correlations of the EEG feature sequences. Specially, Stack AutoEncoder (SAE) is used to build and solve the linear EEG mixing model and the emotion timing model is based on the Long Short-Term Memory Recurrent Neural Network (LSTM-RNN). The framework was implemented on the DEAP dataset for an emotion recognition experiment, where the mean accuracy of emotion recognition achieved 81.10% in valence and 74.38% in arousal, and the effectiveness of our framework was verified. Our framework exhibited a better performance in emotion recognition using multi-channel EEG than the compared conventional approaches in the experiments.
Early sensory experience instructs the maturation of neural circuitry in the cortex. This has been studied extensively in the primary visual cortex, in which loss of vision to one eye permanently ...degrades cortical responsiveness to that eye, a phenomenon known as ocular dominance plasticity (ODP). Cortical inhibition mediates this process, but the precise role of specific classes of inhibitory neurons in ODP is controversial. Here we report that evoked firing rates of binocular excitatory neurons in the primary visual cortex immediately drop by half when vision is restricted to one eye, but gradually return to normal over the following twenty-four hours, despite the fact that vision remains restricted to one eye. This restoration of binocular-like excitatory firing rates after monocular deprivation results from a rapid, although transient, reduction in the firing rates of fast-spiking, parvalbumin-positive (PV) interneurons, which in turn can be attributed to a decrease in local excitatory circuit input onto PV interneurons. This reduction in PV-cell-evoked responses after monocular lid suture is restricted to the critical period for ODP and appears to be necessary for subsequent shifts in excitatory ODP. Pharmacologically enhancing inhibition at the time of sight deprivation blocks ODP and, conversely, pharmacogenetic reduction of PV cell firing rates can extend the critical period for ODP. These findings define the microcircuit changes initiating competitive plasticity during critical periods of cortical development. Moreover, they show that the restoration of evoked firing rates of layer 2/3 pyramidal neurons by PV-specific disinhibition is a key step in the progression of ODP.
This paper is to design substitution boxes (S-Boxes) using innovative I-Ching operators (ICOs) that have evolved from ancient Chinese I-Ching philosophy. These three operators-intrication, turnover, ...and mutual- inherited from I-Ching are specifically designed to generate S-Boxes in cryptography. In order to analyze these three operators, identity, compositionality, and periodicity measures are developed. All three operators are only applied to change the output positions of Boolean functions. Therefore, the bijection property of S-Box is satisfied automatically. It means that our approach can avoid singular values, which is very important to generate S-Boxes. Based on the periodicity property of the ICOs, a new network is constructed, thus to be applied in the algorithm for designing S-Boxes. To examine the efficiency of our proposed approach, some commonly used criteria are adopted, such as nonlinearity, strict avalanche criterion, differential approximation probability, and linear approximation probability. The comparison results show that S-Boxes designed by applying ICOs have a higher security and better performance compared with other schemes. Furthermore, the proposed approach can also be used to other practice problems in a similar way.
The hippocampal formation (HF) is well documented as having a feedforward, unidirectional circuit organization termed the trisynaptic pathway. This circuit organization exists along the septotemporal ...axis of the HF, but the circuit connectivity across septal to temporal regions is less well described. The emergence of viral genetic mapping techniques enhances our ability to determine the detailed complexity of HF circuitry. In earlier work, we mapped a subiculum (SUB) back projection to CA1 prompted by the discovery of theta wave back propagation from the SUB to CA1 and CA3. We reason that this circuitry may represent multiple extended noncanonical pathways involving the subicular complex and hippocampal subregions CA1 and CA3. In the present study, multiple retrograde viral tracing approaches produced robust mapping results, which supports this prediction. We find significant noncanonical synaptic inputs to dorsal hippocampal CA3 from ventral CA1 (vCA1), perirhinal cortex (Prh), and the subicular complex. Thus, CA1 inputs to CA3 run opposite the trisynaptic pathway and in a temporal to septal direction. Our retrograde viral tracing results are confirmed by anterograde-directed viral mapping of projections from input mapped regions to hippocampal dorsal CA3 (dCA3). We find that genetic inactivation of the projection of vCA1 to dCA3 impairs object-related spatial learning and memory but does not modulate anxiety-related behaviors. Our data provide a circuit foundation to explore novel functional roles contributed by these noncanonical hippocampal circuit connections to hippocampal circuit dynamics and learning and memory behaviors.
Microglia have crucial roles in sculpting synapses and maintaining neural circuits during development. To test the hypothesis that microglia continue to regulate neural circuit connectivity in adult ...brain, we have investigated the effects of chronic microglial depletion, via CSF1R inhibition, on synaptic connectivity in the visual cortex in adult mice of both sexes. We find that the absence of microglia dramatically increases both excitatory and inhibitory synaptic connections to excitatory cortical neurons assessed with functional circuit mapping experiments in acutely prepared adult brain slices. Microglia depletion leads to increased densities and intensities of perineuronal nets. Furthermore,
calcium imaging across large populations of visual cortical neurons reveals enhanced neural activities of both excitatory neurons and parvalbumin-expressing interneurons in the visual cortex following microglia depletion. These changes recover following adult microglia repopulation. In summary, our new results demonstrate a prominent role of microglia in sculpting neuronal circuit connectivity and regulating subsequent functional activity in adult cortex.
Microglia are the primary immune cell of the brain, but recent evidence supports that microglia play an important role in synaptic sculpting during development. However, it remains unknown whether and how microglia regulate synaptic connectivity in adult brain. Our present work shows chronic microglia depletion in adult visual cortex induces robust increases in perineuronal nets, and enhances local excitatory and inhibitory circuit connectivity to excitatory neurons. Microglia depletion increases
neural activities of both excitatory neurons and parvalbumin inhibitory neurons. Our new results reveal new potential avenues to modulate adult neural plasticity by microglia manipulation to better treat brain disorders, such as Alzheimer's disease.
Sharing our feelings through content with images and short videos is one main way of expression on social networks. Visual content can affect people's emotions, which makes the task of analyzing the ...sentimental information of visual content more and more concerned. Most of the current methods focus on how to improve the local emotional representations to get better performance of sentiment analysis and ignore the problem of how to perceive objects of different scales and different emotional intensity in complex scenes. In this paper, based on the alterable scale and multi-level local regional emotional affinity analysis under the global perspective, we propose a multi-level context pyramid network (MCPNet) for visual sentiment analysis by combining local and global representations to improve the classification performance. Firstly, Resnet101 is employed as backbone to obtain multi-level emotional representation representing different degrees of semantic information and detailed information. Next, the multi-scale adaptive context modules (MACM) are proposed to learn the sentiment correlation degree of different regions for different scale in the image, and to extract the multi-scale context features for each level deep representation. Finally, different levels of context features are combined to obtain the multi-cue sentimental feature for image sentiment classification. Extensive experimental results on seven commonly used visual sentiment datasets illustrate that our method outperforms the state-of-the-art methods, especially the accuracy on the FI dataset exceeds 90%.
PDF
