Multidomain Object Detection Framework Using Feature Domain Knowledge Distillation.

Object detection techniques have been widely studied, utilized in various works, and have exhibited robust performance on images with sufficient luminance. However, these approaches typically struggle to extract valuable features from low-luminance images, which often exhibit blurriness and dim appearence, leading to detection failures. To overcome this issue, we introduce an innovative unsupervised feature domain knowledge distillation (KD) framework. The proposed framework enhances the generalization capability of neural networks across both low-and high-luminance domains without incurring additional computational costs during testing. This improvement is made possible through the integration of generative adversarial networks and our proposed unsupervised KD process. Furthermore, we introduce a region-based multiscale discriminator designed to discern feature domain discrepancies at the object level rather than from the global context. This bolsters the joint learning process of object detection and feature domain distillation tasks. Both qualitative and quantitative assessments shown that the proposed method, empowered by the region-based multiscale discriminator and the unsupervised feature domain distillation process, can effectively extract beneficial features from low-luminance images, outperforming other state-of-the-art approaches in both low-and sufficient-luminance domains.

SFA-Net: A Selective Features Absorption Network for Object Detection in Rainy Weather Conditions.

In recent years, object detection approaches using deep convolutional neural networks (CNNs) have derived major advances in normal images. However, such success is hardly achieved with rainy images due to lack of visibility. Aiming to bridge this gap, in this article, we present a novel selective features absorption network (SFA-Net) to improve the performance of object detection not only in rainy weather conditions but also in favorable weather conditions. SFA-Net accomplishes this objective by utilizing three subnetworks, where the feature selection subnetwork is concatenated with the object detection subnetwork through the feature absorption subnetwork to form a unified model. To promote further advancement in object detection impaired by rain, we propose a large-scale rainy image dataset, named srRain, which contains both synthetic rainy images and real-world rainy images for training and testing purposes. srRain is comprised of 25 900 rainy images depicting diverse driving scenarios in the presence of rain with a total of 181 164 instances interpreting five common object categories. Experimental results display that our SFA-Net reaches the highest mean average precision (mAP) of 77.53% on a normal image set, 62.52% on a synthetic rainy image set, 37.34% on a collected natural rainy image set, and 32.86% on a published real rainy image set, surpassing current state-of-the-art object detectors and the combination of image deraining and object detection models while retaining a high speed.

Underwater Image Enhancement Based on Histogram-Equalization Approximation Using Physics-Based Dichromatic Modeling.

This work proposes to develop an underwater image enhancement method based on histogram-equalization (HE) approximation using physics-based dichromatic modeling (PDM). Images captured underwater usually suffer from low contrast and color distortions due to light scattering and attenuation. The PDM describes the image formation process, which can be used to restore nature-degraded images, such as underwater images. However, it does not assure that the restored images have good contrast. Thus, we propose approximating the conventional HE based on the PDM to recover the color distortions of underwater images and enhance their contrast through convex optimization. Experimental results demonstrate the proposed method performs favorably against state-of-the-art underwater image restoration approaches.

An Advanced Noise Reduction and Edge Enhancement Algorithm.

Complementary metal-oxide-semiconductor (CMOS) image sensors can cause noise in images collected or transmitted in unfavorable environments, especially low-illumination scenarios. Numerous approaches have been developed to solve the problem of image noise removal. However, producing natural and high-quality denoised images remains a crucial challenge. To meet this challenge, we introduce a novel approach for image denoising with the following three main contributions. First, we devise a deep image prior-based module that can produce a noise-reduced image as well as a contrast-enhanced denoised one from a noisy input image. Second, the produced images are passed through a proposed image fusion (IF) module based on Laplacian pyramid decomposition to combine them and prevent noise amplification and color shift. Finally, we introduce a progressive refinement (PR) module, which adopts the summed-area tables to take advantage of spatially correlated information for edge and image quality enhancement. Qualitative and quantitative evaluations demonstrate the efficiency, superiority, and robustness of our proposed method.

Redox sensor NPGPx restrains ZAP70 activity and modulates T cell homeostasis.

Emerging evidences implicate the contribution of ROS to T cell activation and signaling. The tyrosine kinase, ζ-chain-associated protein of 70 kDa (ZAP70), is essential for T cell development and activation. However, it remains elusive whether a direct redox regulation affects ZAP70 activity upon TCR stimulation. Here, we show that deficiency of non-selenocysteine containing phospholipid hydroperoxide glutathione peroxidase (NPGPx), a redox sensor, results in T cell hyperproliferation and elevated cytokine productions. T cell-specific NPGPx-knockout mice reveal enhanced T-dependent humoral responses and are susceptible to experimental autoimmune encephalomyelitis (EAE). Through proteomic approaches, ZAP70 is identified as the key interacting protein of NPGPx through disulfide bonding. NPGPx is activated by ROS generated from TCR stimulation, and modulates ZAP70 activity through redox switching to reduce ZAP70 recruitment to TCR/CD3 complex in membrane lipid raft, therefore subduing TCR responses. These results reveal a delicate redox mechanism that NPGPx serves as a modulator to curb ZAP70 functions in maintaining T cell homeostasis.

DSNet: Joint Semantic Learning for Object Detection in Inclement Weather Conditions.

In the past half of the decade, object detection approaches based on the convolutional neural network have been widely studied and successfully applied in many computer vision applications. However, detecting objects in inclement weather conditions remains a major challenge because of poor visibility. In this article, we address the object detection problem in the presence of fog by introducing a novel dual-subnet network (DSNet) that can be trained end-to-end and jointly learn three tasks: visibility enhancement, object classification, and object localization. DSNet attains complete performance improvement by including two subnetworks: detection subnet and restoration subnet. We employ RetinaNet as a backbone network (also called detection subnet), which is responsible for learning to classify and locate objects. The restoration subnet is designed by sharing feature extraction layers with the detection subnet and adopting a feature recovery (FR) module for visibility enhancement. Experimental results show that our DSNet achieved 50.84 percent mean average precision (mAP) on a synthetic foggy dataset that we composed and 41.91 percent mAP on a public natural foggy dataset (Foggy Driving dataset), outperforming many state-of-the-art object detectors and combination models between dehazing and detection methods while maintaining a high speed.

Pancreatic cancer-derived small extracellular vesical Ezrin regulates macrophage polarization and promotes metastasis.

Small extracellular vesicles (sEVs) mediate the interaction between tumor and tumor-associated macrophages (TAMs). This study aims to demonstrate that the pancreatic ductal adenocarcinoma (PDAC)-derived sEV Ezrin (sEV-EZR) could modulate macrophage polarization and promote PDAC metastasis. We isolated PDAC-derived sEVs and plasma sEVs from PDAC patients. Human blood mononuclear cell (PBMC)-derived macrophages were treated with PDAC-derived sEVs or the counterpart depleted Ezrin (EZR) with shRNA-mediated knockdown. We used enzyme-linked immunosorbent assays and flow cytometry to monitor macrophages polarization. NOD/SCID/IL2Rγnull mice were treated with sEVs to study PDAC liver metastasis. The plasma sEV-EZR levels of 165 PDAC patients and 151 high-risk controls were analyzed. The EZR levels are higher in sEVs derived from PDAC cells and PDAC-patient plasma than that of the normal controls. PDAC-derived sEVs modulate the polarization of macrophages to M2 phenotype, while PDAC-shEZR-derived sEVs polarize macrophages into M1 phenotype. We found an increase in M1 TAMs and a decrease in M2 TAMs in orthotropic tumors treated with PDAC-shEZR-derived sEVs. The amount of liver metastasis in PDAC-shEZR-derived sEVs-treated mice was observed to be smaller than that of controls. The mean plasma sEV-EZR levels from PDAC patients were significantly higher than those from the controls (32.43±20.78 vs. 21.88±11.43 pg/ml; P<0.0001). The overall survival in the high-plasma sEV-EZR patients was significantly shorter than that in the low-EZR group (6.94±15.25 vs. 9.63±15.11 months; P=0.0418). sEV-EZR could modulate macrophage polarization and promote metastasis in PDAC. Targeting sEV-EZR can be considered a promising therapeutic strategy to inhibit PDAC metastasis.

An Evolutionary Multiobjective Carpool Algorithm Using Set-Based Operator Based on Simulated Binary Crossover.

Sharing vehicle journeys with other passengers can provide many benefits, such as reducing traffic congestion and making urban transportation more environmentally friendly. For the procedure of sharing empty seats, we need to consider increased ridership and driving distances incurred by carpool detours resulting from matching passengers to drivers, as well as maximizing the number of simultaneous matches. In accordance with these goals, this paper proposes and defines the multiobjective optimization carpool service problem (MOCSP). Previous studies have used evolutionary algorithms by combining multiple objectives into a single objective through a weighted linear or/and nonlinear combination of different objectives, thus turning to a single-objective optimization problem. These single-objective problems are optimized, but there is no guarantee of the performance of the respective objectives. By improving the individual representation and genetic operation, we developed a set-based simulated binary and multiobjective carpool matching algorithm that can more effectively solve MOCSP. Furthermore, the proposed algorithm can provide better driver-passenger matching results than can the binary-coded and set-based nondominated sorting genetic algorithms.

Unobtrusive Activity Recognition of Elderly People Living Alone Using Anonymous Binary Sensors and DCNN.

Elderly population (over the age of 60) is predicted to be 1.2 billion by 2025. Most of the elderly people would like to stay alone in their own house due to the high eldercare cost and privacy invasion. Unobtrusive activity recognition is the most preferred solution for monitoring daily activities of the elderly people living alone rather than the camera and wearable devices based systems. Thus, we propose an unobtrusive activity recognition classifier using deep convolutional neural network (DCNN) and anonymous binary sensors that are passive infrared motion sensors and door sensors. We employed Aruba annotated open data set that was acquired from a smart home where a voluntary single elderly woman was living inside for eight months. First, ten basic daily activities, namely, Eating, Bed_to_Toilet, Relax, Meal_Preparation, Sleeping, Work, Housekeeping, Wash_Dishes, Enter_Home, and Leave_Home are segmented with different sliding window sizes, and then converted into binary activity images. Next, the activity images are employed as the ground truth for the proposed DCNN model. The 10-fold cross-validation evaluation results indicated that our proposed DCNN model outperforms the existing models with F1-score of 0.79 and 0.951 for all ten activities and eight activities (excluding Leave_Home and Wash_Dishes), respectively.

Self-Organizing Neuroevolution for Solving Carpool Service Problem With Dynamic Capacity to Alternate Matches.

Traffic congestion often incurs environmental problems. One of the most effective ways to mitigate this is carpooling transportation, which substantially reduces automobile demands. Due to the popularization of smartphones and mobile applications, a carpool service can be conveniently accessed via the intelligent carpool system. In this system, the service optimization required to intelligently and adaptively distribute the carpool participant resources is called the carpool service problem (CSP). Several previous studies have examined viable and preliminary solutions to the CSP by using exact and metaheuristic optimization approaches. For CSP-solving, evolutionary computation (e.g., metaheuristics) is a more promising option in comparison to exact-type approaches. However, all the previous state-of-the-art approaches use pure optimization to solve the CSP. In this paper, we employ the framework of neuroevolution to propose the self-organizing map-based neuroevolution (SOMNE) solver by which the SOM-like network represents the abstract CSP solution and is well-trained by using neural learning and evolutionary mechanism. The experimental section of this paper investigates the comparisons and analyses of two objective functions of the CSP and demonstrates that the proposed SOMNE solver achieves superior results when compared against those the other approaches produce, especially in regard to the optimization of the primary objective functions of the CSP. Finally, the visual results of the SOM are illustrated to show the effectiveness and efficiency of the evolutionary neural learning process.

Histidine-Dependent Protein Methylation Is Required for Compartmentalization of CTP Synthase.

CTP synthase (CTPS) forms compartmentalized filaments in response to substrate availability and environmental nutrient status. However, the physiological role of filaments and mechanisms for filament assembly are not well understood. Here, we provide evidence that CTPS forms filaments in response to histidine influx during glutamine starvation. Tetramer conformation-based filament formation restricts CTPS enzymatic activity during nutrient deprivation. CTPS protein levels remain stable in the presence of histidine during nutrient deprivation, followed by rapid cell growth after stress relief. We demonstrate that filament formation is controlled by methylation and that histidine promotes re-methylation of homocysteine by donating one-carbon intermediates to the cytosolic folate cycle. Furthermore, we find that starvation stress and glutamine deficiency activate the GCN2/ATF4/MTHFD2 axis, which coordinates CTPS filament formation. CTPS filament formation induced by histidine-mediated methylation may be a strategy used by cancer cells to maintain homeostasis and ensure a growth advantage in adverse environments.

DesnowNet: Context-Aware Deep Network for Snow Removal.

Existing learning-based atmospheric particle-removal approaches such as those used for rainy and hazy images are designed with strong assumptions regarding spatial frequency, trajectory, and translucency. However, the removal of snow particles is more complicated because they possess additional attributes of particle size and shape, and these attributes may vary within a single image. Currently, hand-crafted features are still the mainstream for snow removal, making significant generalization difficult to achieve. In response, we have designed a multistage network named DesnowNet to in turn deal with the removal of translucent and opaque snow particles. We also differentiate snow attributes of translucency and chromatic aberration for accurate estimation. Moreover, our approach individually estimates residual complements of the snow-free images to recover details obscured by opaque snow. Additionally, a multi-scale design is utilized throughout the entire network to model the diversity of snow. As demonstrated in the qualitative and quantitative experiments, our approach outperforms state-of-the-art learning-based atmospheric phenomena removal methods and one semantic segmentation baseline on the proposed Snow100K dataset. The results indicate our network would benefit applications involving computer vision and graphics.

Haze Removal Using Radial Basis Function Networks for Visibility Restoration Applications.

Restoration of visibility in hazy images is the first relevant step of information analysis in many outdoor computer vision applications. To this aim, the restored image must feature clear visibility with sufficient brightness and visible edges, while avoiding the production of noticeable artifacts. In this paper, we propose a haze removal approach based on the radial basis function (RBF) through artificial neural networks dedicated to effectively removing haze formation while retaining not only the visible edges but also the brightness of restored images. Unlike traditional haze-removal methods that consist of single atmospheric veils, the multiatmospheric veil is generated and then dynamically learned by the neurons of the proposed RBF networks according to the scene complexity. Through this process, more visible edges are retained in the restored images. Subsequently, the activation function during the testing process is employed to represent the brightness of the restored image. We compare the proposed method with the other state-of-the-art haze-removal methods and report experimental results in terms of qualitative and quantitative evaluations for benchmark color images captured in typical hazy weather conditions. The experimental results demonstrate that the proposed method is able to produce brighter and more vivid haze-free images with more visible edges than can the other state-of-the-art methods.

TGF-ß1 secreted by Tregs in lymph nodes promotes breast cancer malignancy via up-regulation of IL-17RB.

Lymph node (LN) metastasis is commonly associated with systemic distant organ metastasis in human breast cancer and is an important prognostic predictor for survival of breast cancer patients. However, whether tumor-draining LNs (TDLNs) play a significant role in modulating the malignancy of cancer cells for distant metastasis remains controversial. Using a syngeneic mouse mammary tumor model, we found that breast tumor cells derived from TDLN have higher malignancy and removal of TDLNs significantly reduced distant metastasis. Up-regulation of oncogenic Il-17rb in cancer cells derived from TDLNs contributes to their malignancy. TGF-ß1 secreted from regulatory T cells (Tregs) in the TDLNs mediated the up-regulation of Il-17rb through downstream Smad2/3/4 signaling. These phenotypes can be abolished by TGF-ß1 neutralization or depletion of Tregs. Consistently, clinical data showed that the up-regulation of IL-17RB in cancer cells from LN metastases correlated with the increased prevalence of Tregs as well as the aggressive growth of tumors in mouse xenograft assay. Together, these results indicate that Tregs in TDLNs play an important role in modulating the malignancy of breast cancer cells for distant metastasis. Blocking IL-17RB expression could therefore be a potential approach to curb the process.

Stochastic Set-Based Particle Swarm Optimization Based on Local Exploration for Solving the Carpool Service Problem.

The growing ubiquity of vehicles has led to increased concerns about environmental issues. These concerns can be mitigated by implementing an effective carpool service. In an intelligent carpool system, an automated service process assists carpool participants in determining routes and matches. It is a discrete optimization problem that involves a system-wide condition as well as participants' expectations. In this paper, we solve the carpool service problem (CSP) to provide satisfactory ride matches. To this end, we developed a particle swarm carpool algorithm based on stochastic set-based particle swarm optimization (PSO). Our method introduces stochastic coding to augment traditional particles, and uses three terminologies to represent a particle: 1) particle position; 2) particle view; and 3) particle velocity. In this way, the set-based PSO (S-PSO) can be realized by local exploration. In the simulation and experiments, two kind of discrete PSOs-S-PSO and binary PSO (BPSO)-and a genetic algorithm (GA) are compared and examined using tested benchmarks that simulate a real-world metropolis. We observed that the S-PSO outperformed the BPSO and the GA thoroughly. Moreover, our method yielded the best result in a statistical test and successfully obtained numerical results for meeting the optimization objectives of the CSP.

A new hardware-efficient algorithm and reconfigurable architecture for image contrast enhancement.

Contrast enhancement is crucial when generating high quality images for image processing applications, such as digital image or video photography, liquid crystal display processing, and medical image analysis. In order to achieve real-time performance for high-definition video applications, it is necessary to design efficient contrast enhancement hardware architecture to meet the needs of real-time processing. In this paper, we propose a novel hardware-oriented contrast enhancement algorithm which can be implemented effectively for hardware design. In order to be considered for hardware implementation, approximation techniques are proposed to reduce these complex computations during performance of the contrast enhancement algorithm. The proposed hardware-oriented contrast enhancement algorithm achieves good image quality by measuring the results of qualitative and quantitative analyzes. To decrease hardware cost and improve hardware utilization for real-time performance, a reduction in circuit area is proposed through use of parameter-controlled reconfigurable architecture. The experiment results show that the proposed hardware-oriented contrast enhancement algorithm can provide an average frame rate of 48.23 frames/s at high definition resolution 1920 × 1080.

Radial Basis Function Based Neural Network for Motion Detection in Dynamic Scenes.

Motion detection, the process which segments moving objects in video streams, is the first critical process and plays an important role in video surveillance systems. Dynamic scenes are commonly encountered in both indoor and outdoor situations and contain objects such as swaying trees, spouting fountains, rippling water, moving curtains, and so on. However, complete and accurate motion detection in dynamic scenes is often a challenging task. This paper presents a novel motion detection approach based on radial basis function artificial neural networks to accurately detect moving objects not only in dynamic scenes but also in static scenes. The proposed method involves two important modules: a multibackground generation module and a moving object detection module. The multibackground generation module effectively generates a flexible probabilistic model through an unsupervised learning process to fulfill the property of either dynamic background or static background. Next, the moving object detection module achieves complete and accurate detection of moving objects by only processing blocks that are highly likely to contain moving objects. This is accomplished by two procedures: the block alarm procedure and the object extraction procedure. The detection results of our method were evaluated by qualitative and quantitative comparisons with other state-of-the-art methods based on a wide range of natural video sequences. The overall results show that the proposed method substantially outperforms existing methods with Similarity and F1 accuracy rates of 69.37% and 65.50%, respectively.

Efficient contrast enhancement using adaptive gamma correction with weighting distribution.

This paper proposes an efficient method to modify histograms and enhance contrast in digital images. Enhancement plays a significant role in digital image processing, computer vision, and pattern recognition. We present an automatic transformation technique that improves the brightness of dimmed images via the gamma correction and probability distribution of luminance pixels. To enhance video, the proposed image-enhancement method uses temporal information regarding the differences between each frame to reduce computational complexity. Experimental results demonstrate that the proposed method produces enhanced images of comparable or higher quality than those produced using previous state-of-the-art methods.

Highly accurate moving object detection in variable bit rate video-based traffic monitoring systems.

Automated motion detection, which segments moving objects from video streams, is the key technology of intelligent transportation systems for traffic management. Traffic surveillance systems use video communication over real-world networks with limited bandwidth, which frequently suffers because of either network congestion or unstable bandwidth. Evidence supporting these problems abounds in publications about wireless video communication. Thus, to effectively perform the arduous task of motion detection over a network with unstable bandwidth, a process by which bit-rate is allocated to match the available network bandwidth is necessitated. This process is accomplished by the rate control scheme. This paper presents a new motion detection approach that is based on the cerebellar-model-articulation-controller (CMAC) through artificial neural networks to completely and accurately detect moving objects in both high and low bit-rate video streams. The proposed approach is consisted of a probabilistic background generation (PBG) module and a moving object detection (MOD) module. To ensure that the properties of variable bit-rate video streams are accommodated, the proposed PBG module effectively produces a probabilistic background model through an unsupervised learning process over variable bit-rate video streams. Next, the MOD module, which is based on the CMAC network, completely and accurately detects moving objects in both low and high bit-rate video streams by implementing two procedures: 1) a block selection procedure and 2) an object detection procedure. The detection results show that our proposed approach is capable of performing with higher efficacy when compared with the results produced by other state-of-the-art approaches in variable bit-rate video streams over real-world limited bandwidth networks. Both qualitative and quantitative evaluations support this claim; for instance, the proposed approach achieves Similarity and F1 accuracy rates that are 76.40% and 84.37% higher than those of existing approaches, respectively.

Lipid raft assembly and Lck recruitment in TRAIL costimulation mediates NF-κB activation and T cell proliferation.

The TNF-related apoptosis-inducing ligand was shown to provide a costimulatory signal that cooperates with the TCR/CD3 complex to induce T cell proliferation and cytokine production. Although a number of signaling pathways were linked to the TCR/CD3 complex, it is not known how these two receptors cooperate to induce T cell activation. In this study, we show that TRAIL-induced costimulation of T cells depends on activation of the NF-κB pathway. TRAIL induced the NF-κB pathway by phosphorylation of inhibitor of κB factor kinase and protein kinase C in conjunction with anti-CD3. Furthermore, we demonstrated that TRAIL costimulation induced phosphorylation of the upstream TCR-proximal tyrosine kinases, Lck and ZAP70. Ligation of the TRAIL by its soluble receptor, DR4-Fc, alone was able to induce the phosphorylation of Lck and ZAP70 and to activate the NF-κB pathway; however, it was insufficient to fully activate T cells to support T cell proliferation. In contrast, TRAIL engagement in conjunction with anti-CD3, but not TRAIL ligation alone, induced lipid raft assembly and recruitment of Lck and PKC. These results demonstrate that TRAIL costimulation mediates NF-κB activation and T cell proliferation by lipid raft assembly and recruitment of Lck. Our results suggest that in TRAIL costimulation, lipid raft recruitment of Lck integrates mitogenic NF-κB-dependent signals from the TCR and TRAIL in T lymphocytes.