Search

CTR prediction has been widely used in the real world. Many methods model feature interaction to improve their performance. However, most methods only learn a fixed representation for each feature without considering the varying importance of each feature under different contexts, resulting in inferior performance. Recently, several methods tried to learn vector-level weights for feature representations to address the fixed representation issue. However, they only produce linear transformations to refine the fixed feature representations, which are still not flexible enough to capture the varying importance of each feature under different contexts. In this paper, we propose a novel module named Feature Refinement Network (FRNet), which learns context-aware feature representations at bit-level for each feature in different contexts. FRNet consists of two key components: 1) Information Extraction Unit (IEU), which captures contextual information and cross-feature relationships to guide context-aware feature refinement; and 2) Complementary Selection Gate (CSGate), which adaptively integrates the original and complementary feature representations learned in IEU with bit-level weights. Notably, FRNet is orthogonal to existing CTR methods and thus can be applied in many existing methods to boost their performance. Comprehensive experiments are conducted to verify the effectiveness, efficiency, and compatibility of FRNet., Comment: SIGIR 2022

One of the major obstacles in using deep belief network (DBN) is the structure design. Numerous studies, both empirically and theoretically, show that choosing suitable structure can improve the performance of DBN. In this paper, a self-organizing DBN (S-DBN), based on the information relevance strategy (IRS), was proposed to design the structure of DBN. For this IRS, the maximal information coefficient was designed to measure the input and output information relevance of hidden neurons. Meanwhile, the mutual information was introduced to measure the information relevance among the hidden layers. Then, a novel self-organizing strategy was developed to grow and prune both the hidden neurons and layers during the training process. Moreover, a contrastive divergence algorithm was used to adjust the parameters of S-DBN. Finally, several benchmark problems were used to illustrate the effectiveness of S-DBN. The experimental results demonstrate that the proposed S-DBN owns better performance for classification problems and modeling nonlinear systems than some existing methods.

Recently, as a consequence of the COVID-19 pandemic, dependence on Contact Tracing (CT) models has significantly increased to prevent spread of this highly contagious virus and be prepared for the potential future ones. Since the spreading probability of the novel coronavirus in indoor environments is much higher than that of the outdoors, there is an urgent and unmet quest to develop/design efficient, autonomous, trustworthy, and secure indoor CT solutions. Despite such an urgency, this field is still in its infancy. The paper addresses this gap and proposes the Trustworthy Blockchain-enabled system for Indoor Contact Tracing (TB-ICT) framework. The TB-ICT framework is proposed to protect privacy and integrity of the underlying CT data from unauthorized access. More specifically, it is a fully distributed and innovative blockchain platform exploiting the proposed dynamic Proof of Work (dPoW) credit-based consensus algorithm coupled with Randomized Hash Window (W-Hash) and dynamic Proof of Credit (dPoC) mechanisms to differentiate between honest and dishonest nodes. The TB-ICT not only provides a decentralization in data replication but also quantifies the node's behavior based on its underlying credit-based mechanism. For achieving high localization performance, we capitalize on availability of Internet of Things (IoT) indoor localization infrastructures, and develop a data driven localization model based on Bluetooth Low Energy (BLE) sensor measurements. The simulation results show that the proposed TB-ICT prevents the COVID-19 from spreading by implementation of a highly accurate contact tracing model while improving the users' privacy and security.

The novel Coronavirus disease, COVID-19, has rapidly and abruptly changed the world as we knew in 2020. It becomes the most unprecedent challenge to analytic epidemiology in general and signal processing theories in specific. Given its high contingency nature and adverse effects across the world, it is important to develop efficient processing/learning models to overcome this pandemic and be prepared for potential future ones. In this regard, medical imaging plays an important role for the management of COVID-19. Human-centered interpretation of medical images is, however, tedious and can be subjective. This has resulted in a surge of interest to develop Radiomics models for analysis and interpretation of medical images. Signal Processing (SP) and Deep Learning (DL) models can assist in development of robust Radiomics solutions for diagnosis/prognosis, severity assessment, treatment response, and monitoring of COVID-19 patients. In this article, we aim to present an overview of the current state, challenges, and opportunities of developing SP/DL-empowered models for diagnosis (screening/monitoring) and prognosis (outcome prediction and severity assessment) of COVID-19 infection. More specifically, the article starts by elaborating the latest development on the theoretical framework of analytic epidemiology and hypersignal processing for COVID-19. Afterwards, imaging modalities and Radiological characteristics of COVID-19 are discussed. SL/DL-based Radiomic models specific to the analysis of COVID-19 infection are then described covering the following four domains: Segmentation of COVID-19 lesions; Predictive models for outcome prediction; Severity assessment, and; Diagnosis/classification models. Finally, open problems and opportunities are presented in detail.

Aiming at the existing problems of high-voltage transmission line inspection robot, such as large size, low obstacle crossing efficiency, and inability to cross over obstacles such as diversion lines and insulators, this paper presents a two-arm swinging inspection robot based on primates by observing the movement characteristics of gibbons and combining with the principle of bionics. The robot can swing cantilever on the high-voltage line to achieve obstacle crossing. After kinematics analysis of the bionic model of the inspection robot, the 3d model of the robot is established in SolidWorks. Simulation analysis of the robot is carried out through the built-in motion plug-in to ensure that the robot can achieve the desired motion effect, which verifies the stability and rationality of the mechanism design.

In view of the difficulties in modeling, large external interference, weak adaptability and other problems in the control strategy adopted by the lower limb exoskeleton robot for medical rehabilitation at the present stage. This paper applies the bionic control method based on CPG to the exoskeleton control of lower limb rehabilitation. By adopting Dynamic Hebbian learning algorithm to improve the Hopf oscillator. And build a CPG oscillator network, realize the gait signal study, and eventually to improve lower limb exoskeleton robot movement performance and enhance its adaptability. Through the patient's wear-wearing test. It is proved that CPG bionic control exoskeleton can be matched with the control signal of the limb produced by the human body in the case of the human body motion cycle, and it can effectively control the exoskeleton of the lower extremity and to perform rehabilitation exercises.

Although deeper and larger neural networks have achieved better performance, the complex network structure and increasing computational cost cannot meet the demands of many resource-constrained applications. Existing methods usually choose to execute or skip an entire specific layer, which can only alter the depth of the network. In this paper, we propose a novel method called Dynamic Multi-path Neural Network (DMNN), which provides more path selection choices in terms of network width and depth during inference. The inference path of the network is determined by a controller, which takes into account both previous state and object category information. The proposed method can be easily incorporated into most modern network architectures. Experimental results on ImageNet and CIFAR-100 demonstrate the superiority of our method on both efficiency and overall classification accuracy. To be specific, DMNN-101 significantly outperforms ResNet-101 with an encouraging 45.1% FLOPs reduction, and DMNN-50 performs comparably to ResNet-101 while saving 42.1% parameters.

A methane steam reforming catalyst was selected by the comparison of its catalytic properties and resistance to carbon deposition. The performance of a molten carbon fuel cell (MCFC) using this catalyst was studied. The effect of discharge magnitude, gas pressure, and steam-carbon ratio (S/C) on the catalyst was also investigated. The results indicated that the catalyst could make the cell perform well, and the increment of the current affected the content of H(2) in the cell, but it had minor effect on the content of CH(4). In addition, the reforming reaction depended on the gas pressure. There was a maximal content of H(2) in the cell at 0.36 MPa. With the decrease of S/C, the performance of MCFC was improved.

The original and postnatal scale patterns of guard hairs were compared. The comparisons illustrate that acquired morphological changes take place in the scales on the coarse section of guard hairs. Scales on this part changes from regular smooth to irregular wave. The primary reason would be friction. Scales on the lower part of guard hairs are thick and strong to bear friction. Additionally, they are berried in the bottom layer of pelage where friction is avoided. Scales on the coarse section are thin, broad, dense and overlap, and exposed in the environment as a cover of pelage. So friction always happen on them. Factors which enhance coefficient of friction and weaken keratin bonds are combined to damage hair scales. The results suggest that regular smooth and irregular wave are actually the same type exhibiting the same origin morphological characters, so they should be counted together in the species identification.