Adaptive Gating Research Articles

The role of protein-membrane electrostatic interactions in the adaptive gating cycle of MscS.

Bacterial mechanosensitive channels MscS and MscL directly respond to tension in the cytoplasmic membrane. It appears not to be a coincidence that both channels are anchored to membrane lipids with positively charged residues primarily at the cytoplasmic interface of the inner membrane, leaving the periplasmic side of the barrel the freedom to move and tilt. The functional cycle of MscS involving opening ↔ closing and inactivation ↔ recovery transitions relies on two prominent anchors, R46 and R74, that reside at the level of cytoplasmic phosphates. WT MscS exhibits voltage-dependent inactivation and recovery, showing deeper inactivation and slower recovery under depolarizing voltages (+60 mV) compared to hyperpolarizations (−60 mV). Substitutions of both R46 and R74 with poor interfacial anchors (A or D) result in no expression, whereas G, I, L, or V substitutions express but produce non-functional channels. Patch-clamp experiments showed that polar substitutions in positions 46 and 74, which maintain H-bonding capability to lipid phosphate groups (N, Q, S), preserve expression, activation, voltage-dependence of inactivation and recovery, as well as osmotic rescuing. Aromatic (W, Y) substitutions produce channels that completely lack voltage sensitivity of inactivation and recovery, but are otherwise functional. Insertion of periplasmic anchors (R or W) in flexible N-terminal segments (positions 3-21) did not produce strong phenotypes, however, the A22R substitution, which faces outer-leaflet phosphates, abolishes inactivation without affecting opening. These data show that the inactivation and recovery transitions are sensitive to the polarity of the cytoplasmic ends of TM1 and TM2 and are likely associated with the change of hydration near these segments which can be altered by voltage. The insertion of a periplasmic anchor (R22) restrains the position of the TM1-TM2 pair of helices, which require a higher degree of freedom during inactivation.

Differential effects of executive load on automatic versus controlled semantic memory retrieval.

Growing evidence indicates that a domain-general executive control supports semantic memory retrieval, yet the nature of this interaction remains elusive. To shed light on such control mechanisms, we conducted two dual-task experiments loading distinct executive capacities (working memory maintenance, monitoring, and switching), while participants carried out automatic (free-associative) and controlled (dissociative) word retrieval tasks. We found that these forms of executive load interfered with retrieval fluency in both tasks, but these negative effects were more pronounced for the dissociative performance. Together, these findings indicate that the domain-general executive control supports accessing contextually relevant knowledge as well as the inhibition of automatically activated but task-inappropriate retrieval candidates, putatively via an adaptive gating of semantic activation and interference control. Moreover, the processing costs related to retrieval inhibition and switching were negatively correlated, suggesting a trade-off between the ability to constrain semantic activation (i.e., inhibition) and the ability to initiate flexible transitions between semantic sets (i.e., switching), which may thus represent two complementary control functions governing semantic memory retrieval.

Three‑Dimensional Lane Detection Algorithm of Lidar Based on Adaptive Gating and Dual Pathways

Three‑Dimensional Lane Detection Algorithm of Lidar Based on Adaptive Gating and Dual Pathways

Multimodal Sentiment Analysis With Image-Text Interaction Network

More and more users are getting used to posting images and text on social networks to share their emotions or opinions. Accordingly, multimodal sentiment analysis has become a research topic of increasing interest in recent years. Typically, there exist affective regions that evoke human sentiment in an image, which are usually manifested by corresponding words in peoples comments. Similarly, people also tend to portray the affective regions of an image when composing image descriptions. As a result, the relationship between image affective regions and the associated text is of great significance for multimodal sentiment analysis. However, most of the existing multimodal sentiment analysis approaches simply concatenate features from image and text, which could not fully explore the interaction between them, leading to suboptimal results. Motivated by this observation, we propose a new image-text interaction network (ITIN) to investigate the relationship between affective image regions and text for multimodal sentiment analysis. Specifically, we introduce a cross-modal alignment module to capture region-word correspondence, based on which multimodal features are fused through an adaptive cross-modal gating module. Moreover, considering the complementary role of context information on sentiment analysis, we integrate the individual-modal contextual feature representations for achieving more reliable prediction. Extensive experimental results and comparisons on public datasets demonstrate that the proposed model is superior to the state-of-the-art methods.

BCTNet: Bi-Branch Cross-Fusion Transformer for Building Footprint Extraction

Building footprint extraction in remote sensing remains challenging due to the diverse appearances of buildings and confusing scenarios. Recently, researchers have revealed that both the globality and locality are vitally important in building footprint extraction tasks and proposed to incorporate the local context and global long-range dependency in the segmentation models. However, the inadequate integration of the globality and locality still leads to incomplete, fake or missing extraction results. To alleviate these problems, a novel segmentation method named Bi-branch Cross-fusion Transformer Network (BCTNet) is proposed in this study. Two parallel branches of the convolutional encoder branch (CB) and the transformer encoder branch (TB) are designed to extract multi-scale feature maps. A concatenation-then-cross-fusion transformer block (CCTB) is put forward to integrate the locality from the CB and globality from the TB in a cross-fusion way at each stage of the encoding process. Then, an adaptive gating module (AGM) is proposed to gate the feature maps from the CCTB to strengthen the important features while suppressing the irrelevant interference information. After that, the segmentation results can be obtained through a simple decoding process. Comprehensive experiments on two benchmark datasets demonstrate that the proposed BCTNet can achieve superior performance compared to the current state-of-the-art (SOTA) segmentation methods.

Image Super-Resolution Reconstruction Method for Lung Cancer CT-Scanned Images Based on Neural Network.

The super-resolution (SR) reconstruction of a single image is an important image synthesis task especially for medical applications. This paper is studying the application of image segmentation for lung cancer images. This research work is utilizing the power of deep learning for resolution reconstruction for lung cancer-based images. At present, the neural networks utilized for image segmentation and classification are suffering from the loss of information where information passes through one layer to another deep layer. The commonly used loss functions include content-based reconstruction loss and generative confrontation network. The sparse coding single-image super-resolution reconstruction algorithm can easily lead to the phenomenon of incorrect geometric structure in the reconstructed image. In order to solve the problem of excessive smoothness and blurring of the reconstructed image edges caused by the introduction of this self-similarity constraint, a two-layer reconstruction framework based on a smooth layer and a texture layer is proposed for a medical application of lung cancer. This method uses a global nonzero gradient number constrained reconstruction model to reconstruct the smooth layer. The proposed sparse coding method is used to reconstruct high-resolution texture images. Finally, a global and local optimization models are used to further improve the quality of the reconstructed image. An adaptive multiscale remote sensing image super-division reconstruction network is designed. The selective core network and adaptive gating unit are integrated to extract and fuse features to obtain a preliminary reconstruction. Through the proposed dual-drive module, the feature prior drive loss and task drive loss are transmitted to the super-resolution network. The proposed work not only improves the subjective visual effect but the robustness has also been enhanced with more accurate construction of edges. The statistical evaluators are used to test the viability of the proposed scheme.

Two faces of perceptual awareness during the attentional blink: Gradual and discrete.

In a series of experiments, the nature of perceptual awareness during the attentional blink was investigated. Previous work has considered the attentional blink as a discrete, all-or-none phenomenon, indicative of general access to conscious awareness. Using continuous report measures in combination with mixture modeling, the outcomes showed that perceptual awareness during the attentional blink can be a gradual phenomenon. Awareness was not exclusively discrete, but also exhibited a gradual characteristic whenever the spatial extent of attention induced by the first target spanned more than a single location. Under these circumstances, mental representations of blinked targets were impoverished, but did approach the actual identities of the targets. Conversely, when the focus of attention covered only a single location, there was no evidence for any partial knowledge of blinked targets. These two different faces of awareness during the attentional blink challenge current theories of both awareness and temporal attention, which cannot explain the existence of gradual awareness of targets during the attentional blink. To account for the current outcomes, an adaptive gating model is proposed that casts awareness on a continuum between gradual and discrete, rather than as being of either single kind. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Make More Connections: Urban Traffic Flow Forecasting with Spatiotemporal Adaptive Gated Graph Convolution Network

Urban traffic flow forecasting is a critical issue in intelligent transportation systems. Due to the complexity and uncertainty of urban road conditions, how to capture the dynamic spatiotemporal correlation and make accurate predictions is very challenging. In most of existing works, urban road network is often modeled as a fixed graph based on local proximity. However, such modeling is not sufficient to describe the dynamics of the road network and capture the global contextual information. In this paper, we consider constructing the road network as a dynamic weighted graph through attention mechanism. Furthermore, we propose to seek both spatial neighbors and semantic neighbors to make more connections between road nodes. We propose a novel Spatiotemporal Adaptive Gated Graph Convolution Network ( STAG-GCN ) to predict traffic conditions for several time steps ahead. STAG-GCN mainly consists of two major components: (1) multivariate self-attention Temporal Convolution Network ( TCN ) is utilized to capture local and long-range temporal dependencies across recent, daily-periodic and weekly-periodic observations; (2) mix-hop AG-GCN extracts selective spatial and semantic dependencies within multi-layer stacking through adaptive graph gating mechanism and mix-hop propagation mechanism. The output of different components are weighted fused to generate the final prediction results. Extensive experiments on two real-world large scale urban traffic dataset have verified the effectiveness, and the multi-step forecasting performance of our proposed models outperforms the state-of-the-art baselines.

Noise reduction and 3D image restoration of single photon counting LiDAR using adaptive gating

Single photon LiDAR is considered as one of the most important tools in acquiring target information with high accuracy under extreme imaging conditions, as it offers single photon sensitivity and picosecond timing resolution. However, such technique sense the scene with the photons reflected by the target, thus resulting in severe degradation of image in presence of strong noise. Range gating with high-speed electronics is an effective way to suppress the noise, unfortunately, such technique suffers from manually selecting the parameters and limited gating width. This paper presents a target information extracting and image restoration method under large observation window, which first obtain the depth distribution of the target and extract the information within the range by analyzing the model of signal and noise, then further improve the image quality by adopting advanced image restoration algorithm and henceforth shows better results than those denoising method that purely relying on hardware. In the experiment, photon-per-pixel (PPP) was as low as 3.020 and signal-to-background ratio (SBR) was as low as 0.106, the proposed method is able to improve SBR with a factor of 19.330. Compared to classical algorithm named cross correlation, the reconstruction signal to noise ratio (RSNR) increased 33.520dB by further cooperating with advanced image restoration algorithm, thus improved the ability of sensing accurate target information under extreme cases.

High-resolution structural and functional deep brain imaging using adaptive optics three-photon microscopy

Multiphoton microscopy has become a powerful tool with which to visualize the morphology and function of neural cells and circuits in the intact mammalian brain. However, tissue scattering, optical aberrations and motion artifacts degrade the imaging performance at depth. Here we describe a minimally invasive intravital imaging methodology based on three-photon excitation, indirect adaptive optics (AO) and active electrocardiogram gating to advance deep-tissue imaging. Our modal-based, sensorless AO approach is robust to low signal-to-noise ratios as commonly encountered in deep scattering tissues such as the mouse brain, and permits AO correction over large axial fields of view. We demonstrate near-diffraction-limited imaging of deep cortical spines and (sub)cortical dendrites up to a depth of 1.4 mm (the edge of the mouse CA1 hippocampus). In addition, we show applications to deep-layer calcium imaging of astrocytes, including fibrous astrocytes that reside in the highly scattering corpus callosum.

Image-Guided Liver Stereotactic Body Radiotherapy Using VMAT and Real-Time Adaptive Tumor Gating: Evaluation of the Efficacy and Toxicity for Hepatocellular Carcinoma.

Liver SBRT is a therapeutic option for the treatment of HCC in patients not eligible for other local therapies. We retrospectively report the outcomes of a cohort of consecutive patients treated with SBRT for HCC at the Montpellier Cancer Institute. Between March 2013 and December 2018, 66 patients were treated with image-guided liver SBRT using VMAT and real-time adaptive tumor gating in our institute. The main endpoints considered in this study were local control, disease-free survival, overall survival, and toxicity. The median follow-up was 16.8 months. About 66.7% had prior liver treatment. Most patients received 50 Gy in five fractions of 10 Gy. No patient had local recurrence. Overall survival and disease-free survival were, respectively, 83.9% and 46.7% at one year. In multivariate analysis, the diameter of the lesions was a significant prognostic factor associated with disease-free survival (HR = 2.57 (1.19-5.53) p = 0.02). Regarding overall survival, the volume of PTV was associated with lower overall survival (HR = 2.84 (1.14-7.08) p = 0.025). No grade 3 toxicity was observed. One patient developed a grade 4 gastric ulcer, despite the dose constraints being respected. Image-guided liver SBRT with VMAT is an effective and safe treatment in patients with inoperable HCC, even in heavily pre-treated patients. Further prospective evaluation will help to clarify the role of SBRT in the management of HCC patients.

Few-Shot Learning in Spiking Neural Networks by Multi-Timescale Optimization.

Learning new concepts rapidly from a few examples is an open issue in spike-based machine learning. This few-shot learning imposes substantial challenges to the current learning methodologies of spiking neuron networks (SNNs) due to the lack of task-related priori knowledge. The recent learning-to-learn (L2L) approach allows SNNs to acquire priori knowledge through example-level learning and task-level optimization. However, existing L2L-based frameworks do not target the neural dynamics (i.e., neuronal and synaptic parameter changes) on different timescales. This diversity of temporal dynamics is an important attribute in spike-based learning, which facilitates the networks to rapidly acquire knowledge from very few examples and gradually integrate this knowledge. In this work, we consider the neural dynamics on various timescales and provide a multi-timescale optimization (MTSO) framework for SNNs. This framework introduces an adaptive-gated LSTM to accommodate two different timescales of neural dynamics: short-term learning and long-term evolution. Short-term learning is a fast knowledge acquisition process achieved by a novel surrogate gradient online learning (SGOL) algorithm, where the LSTM guides gradient updating of SNN on a short timescale through an adaptive learning rate and weight decay gating. The long-term evolution aims to slowly integrate acquired knowledge and form a priori, which can be achieved by optimizing the LSTM guidance process to tune SNN parameters on a long timescale. Experimental results demonstrate that the collaborative optimization of multi-timescale neural dynamics can make SNNs achieve promising performance for the few-shot learning tasks.

Rapid Cortical Adaptation and the Role of Thalamic Synchrony during Wakefulness.

Rapid sensory adaptation is observed across all sensory systems, and strongly shapes sensory percepts in complex sensory environments. Yet despite its ubiquity and likely necessity for survival, the mechanistic basis is poorly understood. A wide range of primarily in vitro and anesthetized studies have demonstrated the emergence of adaptation at the level of primary sensory cortex, with only modest signatures in earlier stages of processing. The nature of rapid adaptation and how it shapes sensory representations during wakefulness, and thus the potential role in perceptual adaptation, is underexplored, as are the mechanisms that underlie this phenomenon. To address these knowledge gaps, we recorded spiking activity in primary somatosensory cortex (S1) and the upstream ventral posteromedial (VPm) thalamic nucleus in the vibrissa pathway of awake male and female mice, and quantified responses to whisker stimuli delivered in isolation and embedded in an adapting sensory background. We found that cortical sensory responses were indeed adapted by persistent sensory stimulation; putative excitatory neurons were profoundly adapted, and inhibitory neurons only modestly so. Further optogenetic manipulation experiments and network modeling suggest this largely reflects adaptive changes in synchronous thalamic firing combined with robust engagement of feedforward inhibition, with little contribution from synaptic depression. Taken together, these results suggest that cortical adaptation in the regime explored here results from changes in the timing of thalamic input, and the way in which this differentially impacts cortical excitation and feedforward inhibition, pointing to a prominent role of thalamic gating in rapid adaptation of primary sensory cortex.SIGNIFICANCE STATEMENT Rapid adaptation of sensory activity strongly shapes representations of sensory inputs across all sensory pathways over the timescale of seconds, and has profound effects on sensory perception. Despite its ubiquity and theoretical role in the efficient encoding of complex sensory environments, the mechanistic basis is poorly understood, particularly during wakefulness. In this study in the vibrissa pathway of awake mice, we show that cortical representations of sensory inputs are strongly shaped by rapid adaptation, and that this is mediated primarily by adaptive gating of the thalamic inputs to primary sensory cortex and the differential way in which these inputs engage cortical subpopulations of neurons.

An Adaptive Synchronous Rectifier Control Scheme for High Power Density High Efficiency Interleaved Boost Converter With Passive Soft-Switching Cell

This study proposes an adaptive synchronous rectifier (SR) control scheme for high power density and high-efficiency interleaved boost converter (IBC) with passive soft-switching cell (PSC) (IBC-PSC). The PSC designed for the IBCs is one of the good solutions to minimize switching losses. However, the PSC needs a large boost inductance; otherwise, the conduction loss dramatically increases as the load decrease due to large circulating currents. Finally, there is a tradeoff between power density and efficiency. The proposed control scheme provides adaptive gating signals for the SR switches. It deactivates the SR switches at zero SR current and makes the main switches turn on with zero-voltage-switching (ZVS) regardless of the input voltage and load conditions, which results in reducing the conduction and switching losses despite significantly smaller boost inductance compared to the traditional IBC-PSCs. As a result, IBC-PSC with high power density and high efficiency can be realized. Theoretical analysis, implementation, and design considerations for the proposed control scheme were discussed and verified experimentally.

PMAN: Progressive Multi-Attention Network for Human Pose Transfer

This paper presents a novel approach for human pose transfer, progressive multi-attention network (PMAN), which generates a new human image by transferring the pose of a given person to a target pose. The network gradually updates the pose feature and the image feature through a series of multi-attention transfer blocks (MATBs). Each MATB consists of two attention mechanisms: pose-conditioned batch normalization (PCBN) and cooperative attention mechanism (CAM). Specifically, in low-level feature space, the PCBN layer with pose information is used to replace the BN layer of the image channel to realize the preliminary guidance of pose to image. The CAM is implemented as two gated mechanisms in high-level feature space, which reveals the essence of human pose transfer, that is, mutual guidance and dynamic control between pose and image. Gated memory writing is used to calculate the pixel-wise weight of the pose by using global image information to guide the update of the pose. Gated response utilizes an adaptive gating mechanism to dynamically control the pose information flow so as to update the image. A large number of subjective and objective experiments on DeepFashion and Market-1501 demonstrate the superiority of our method. The proposed multi-attention mechanism is well adapted to the human pose transfer task and provides a possible new idea for other cross-domain generation tasks.

Adaptive Context-Aware Multi-Modal Network for Depth Completion

Depth completion aims to recover a dense depth map from the sparse depth data and the corresponding single RGB image. The observed pixels provide the significant guidance for the recovery of the unobserved pixels' depth. However, due to the sparsity of the depth data, the standard convolution operation, exploited by most of existing methods, is not effective to model the observed contexts with depth values. To address this issue, we propose to adopt the graph propagation to capture the observed spatial contexts. Specifically, we first construct multiple graphs at different scales from observed pixels. Since the graph structure varies from sample to sample, we then apply the attention mechanism on the propagation, which encourages the network to model the contextual information adaptively. Furthermore, considering the mutli-modality of input data, we exploit the graph propagation on the two modalities respectively to extract multi-modal representations. Finally, we introduce the symmetric gated fusion strategy to exploit the extracted multi-modal features effectively. The proposed strategy preserves the original information for one modality and also absorbs complementary information from the other through learning the adaptive gating weights. Our model, named Adaptive Context-Aware Multi-Modal Network (ACMNet), achieves the state-of-the-art performance on two benchmarks, i.e., KITTI and NYU-v2, and at the same time has fewer parameters than latest models. Our code is available at: https://github.com/sshan-zhao/ACMNet.

Dosimetric and geometric end-to-end accuracy of a magnetic resonance guided linear accelerator.

The introduction of real-time imaging by magnetic resonance guided linear accelerators (MR-Linacs) enabled adaptive treatments and gating on the tumor position. Different end-to-end tests monitored the accuracy of our MR-Linac during the first year of clinical operation. We report on the stability of these tests covering a static, adaptive and gating workflow. Film measurements showed gamma passing rates of 96.4% ± 3.4% for the static tests (five measurements) and for the two adaptive tests 98.9% and 99.99%, respectively (criterion 2%/2mm). The gated point dose measurements in the breathing phantom were 2.7% lower than in the static phantom.

A motion prediction confidence estimation framework for prediction-based radiotherapy gating.

Motion prediction can compensate for latency in image-guided radiotherapy and has been an active area of research. However, motion predictions are subject to error and variations. We have developed and evaluated a novel motion prediction confidence estimation framework to improve the efficacy and robustness of prediction-based radiotherapy gating decision-making. The specific scenario of adaptive gating in magnetic resonance imaging (MRI)-guided radiotherapy is studied as an example, but the method generalizes to other modalities and motion management setups. The proposed prediction confidence estimator is based on a generic training/testing paradigm and consists of a weighted combination of three components: the prediction model's goodness of fit, variation in the prediction using a leave-one-out process and the velocity of the tracked target. Roughly, these terms quantify respectively the consistency between prediction and the training data, the robustness of model inference, and the stability due to target speed. The weight parameters and the action level in triggering beam-off decision are optimized. The method is assessed and validated in 8 healthy volunteer and 13 patient studies using a 0.35T MRI-guided radiotherapy system predicting 0.25-0.33s ahead. The effect of the action level on the predicted gating decision accuracy, beam-on positive predictive value (PPV) and median distance between the predicted and ground-truth target centroids were evaluated. Statistical significance was evaluated using a paired t-test. The tradeoff between these performance metrics and gating duty cycle was assessed. Use of the confidence estimator threshold increased gating accuracy by up to 2.42%, increased PPV by up to 3.00%, and reduced the median centroid distance up to 0.28mm. The confidence estimator threshold on average increased gating accuracy to 96.5% (P=2.08×10-4 ), increased PPV to 96.7% (P=1.46×10-5 ), reduced the median centroid distance to 0.54mm (P=1.71×10-5 ) at the cost of reducing the gating duty cycle by 14.3% to 48.5%. Hyperparameter tuning revealed that contrary to intuition, the velocity term offered only minimal performance improvement in some cases but also introduced potential stability issues. The combination of goodness of fit and leave-one-out prediction variation provided the most effective confidence estimator, yielding universally better performance in gating decisions. Confidence estimation utilizing prediction model fitness criterion and validation principles can complement prediction methods to guide MRI-guided radiotherapy gating. Results from both volunteer and patient studies showed improved gating quality.

Improving antenna gain estimations in non-ideal test sites with auto-tunable filters

• Antenna calibration in non-ideal OATS is investigated. • Time gating can fail in low SNR conditions and other correction techniques can require many test runs. • We propose an auto-tunable signal processing structure based on adaptive filtering and time gating. • We propose a new fitness function for the PSO-based tuning mechanism. • Results show a reduction of the test duration and good performances in low SNR environments. Estimating the gain of an antenna prototype is an important step during both design and validation phases. Nevertheless, many small technology companies and universities are not provided with adequate infrastructure to run this type of test. In this paper, we propose a computational tool to deal with undesirable contributions coming from non-ideal test conditions over electromagnetic measurements. It is based on auto-tunable filters and therefore it allows a lab technician to run the test without a major knowledge on signal processing. After a series of evaluations based on lab measurements, the proposed tool gives results as good as those provided by two other approaches but with a reduction of the total number of experimental runs. Furthermore, it is more efficient than the traditional time gating approach for low signal-to-noise ratio environments. Finally, a validation with different antennas and test sites confirmes its robustness.

Remote Sensing Imagery Super Resolution Based on Adaptive Multi-Scale Feature Fusion Network.

Due to increasingly complex factors of image degradation, inferring high-frequency details of remote sensing imagery is more difficult compared to ordinary digital photos. This paper proposes an adaptive multi-scale feature fusion network (AMFFN) for remote sensing image super-resolution. Firstly, the features are extracted from the original low-resolution image. Then several adaptive multi-scale feature extraction (AMFE) modules, the squeeze-and-excited and adaptive gating mechanisms are adopted for feature extraction and fusion. Finally, the sub-pixel convolution method is used to reconstruct the high-resolution image. Experiments are performed on three datasets, the key characteristics, such as the number of AMFEs and the gating connection way are studied, and super-resolution of remote sensing imagery of different scale factors are qualitatively and quantitatively analyzed. The results show that our method outperforms the classic methods, such as Super-Resolution Convolutional Neural Network(SRCNN), Efficient Sub-Pixel Convolutional Network (ESPCN), and multi-scale residual CNN(MSRN).