Search

Hashtag is an important advertising tool and a musthave feature for social media nowadays. In the past, many hashtag recommendation methods have been proposed from different perspectives of images, texts, and users. However, most previous works consider neither the mutual influence between multi-modalities, nor the visual similarity between images. In this paper, we devise a novel model, named Triplet-Attention Graph Network (TAGNet). The rationale behind our method is that visually similar images share some common hashtags. Therefore, we build an image graph, and apply a new Aggregated Graph Convolution (AGC) module to propagate information in a collective way. Furthermore, it is noted that text and user also have rich content information within posts, and we hence propose a Triplet Attention (TA) module to incorporate multi-modalities into node features. Experiments on the large-scale dataset collected from Instagram show that TAGNet achieved significant improvement in recall rate over the best state-of-the-art method.

PurposeTelecommunication (telecom) fraud is one of the most common crimes and causes the greatest financial losses. To effectively eradicate fraud groups, the key fraudsters must be identified and captured. One strategy is to analyze the fraud interaction network using social network analysis. However, the underlying structures of fraud networks are different from those of common social networks, which makes traditional indicators such as centrality not directly applicable. Recently, a new line of research called deep random walk has emerged. These methods utilize random walks to explore local information and then apply deep learning algorithms to learn the representative feature vectors. Although effective for many types of networks, random walk is used for discovering local structural equivalence and does not consider the global properties of nodes.Design/methodology/approachThe authors proposed a new method to combine the merits of deep random walk and social network analysis, which is called centrality-guided deep random walk. By using the centrality of nodes as edge weights, the authors’ biased random walks implicitly consider the global importance of nodes and can thus find key fraudster roles more accurately. To evaluate the authors’ algorithm, a real telecom fraud data set with around 562 fraudsters was built, which is the largest telecom fraud network to date.FindingsThe authors’ proposed method achieved better results than traditional centrality indices and various deep random walk algorithms and successfully identified key roles in a fraud network.Research limitations/implicationsThe study used co-offending and flight record to construct a criminal network, more interpersonal relationships of fraudsters, such as friendships and relatives, can be included in the future.Originality/valueThis paper proposed a novel algorithm, centrality-guided deep random walk, and applied it to a new telecom fraud data set. Experimental results show that the authors’ method can successfully identify the key roles in a fraud group and outperform other baseline methods. To the best of the authors’ knowledge, it is the largest analysis of telecom fraud network to date.

This paper introduces a radio sensing device that is easy to manufacture and maintain, easy to install and relocate, can store solar energy, resistant to typhoon and heavy rains, and has low power consumption. With the radio sensing devices constantly collecting information on environmental changes and sending data back to the backend system designated by the customer, our system can assist the farmers predicting the production period of crops in the area, which allow farmers to plan the different field operations. In this paper, we propose an unified sensor framework and compare our design with various hardware, software and mechanism of sensing devices in the literature. The height of our device is 275mm, the bottom circle radius is 63.3mm, the weight is less than 2kg, the minimum power consumption during radio transmission is only 0.58W, and the end point transmission distance can reach 16 kilometers. Our devices are highly integrated and low power, and have been commercialized and sold worldwide.

Over the years, Machine Learning models have been successfully employed on neuroimaging data for accurately predicting brain age. Deviations from the healthy brain aging pattern are associated to the accelerated brain aging and brain abnormalities. Hence, efficient and accurate diagnosis techniques are required for eliciting accurate brain age estimations. Several contributions have been reported in the past for this purpose, resorting to different data-driven modeling methods. Recently, deep neural networks (also referred to as deep learning) have become prevalent in manifold neuroimaging studies, including brain age estimation. In this review, we offer a comprehensive analysis of the literature related to the adoption of deep learning for brain age estimation with neuroimaging data. We detail and analyze different deep learning architectures used for this application, pausing at research works published to date quantitatively exploring their application. We also examine different brain age estimation frameworks, comparatively exposing their advantages and weaknesses. Finally, the review concludes with an outlook towards future directions that should be followed by prospective studies. The ultimate goal of this paper is to establish a common and informed reference for newcomers and experienced researchers willing to approach brain age estimation by using deep learning models

Even in the era of the Internet of Things (IoT), existing smart cameras still cannot efficiently run complex neural networks of image segmentation due to restricted storage and computing capacities. To address this issue, we proposed a high-efficient semantic segmentation for IoT-enabled smart cameras. The experiment results show that the accuracy of the proposed semantic segmentation model can improve the classwise accuracy by 4%, given that the model is reduced by 12.5% and even runs faster than prior studies.

Herein, the electrodeposited-film electrode CFeCoNiP was fabricated to serve as a bifunctional electrocatalyst for the hydrogen evolution reaction (HER) and oxygen evolution reaction (OER). Kinetic Tafel slope analysis suggests that the HER follows the Volmer–Tafel mechanism (29 mV dec−1), indicating that the recombination of the two adsorbed hydrogen atoms is the rate-determining step. The FeCoNi-based thick film (thickness: 168.3 μm) shows a metallic state favorable for electron transfer; on the other hand, in the case of the FeCoNi-based thin film (thickness: 389.2 nm), the in operando XAS investigation reveals that Fe3+-assisted water dissociation promotes the formation of Co2+–μ-H–Ni3+ (catalyst-Had) species, which subsequently undergoes reductive elimination to furnish H2 gas via the HER process. During the OER, the CoNi–oxide matrix acts as a chemical and electroconductive host to build/stabilize the key intermediate [Fe4+O/Fe3+–O˙] motifs; this subsequently triggers the catalytic O–O bond formation (30 mV dec−1) through the radical–radical coupling of the adjacent [Fe4+O/Fe3+–O˙] motifs or/and OH− attack on the Fe4+-induced electrophilic oxygen center, leading to the release of O2. The mechanistic experiments provide advanced insights into the catalytic kinetics/intermediates and demonstrate that the electronically cooperative interplay among Fe/Co/Ni leads to enhanced alkaline water electrolysis. The CFeCoNiP catalyst exhibits an excellent HER activity (specific activity js = 0.227 mA cm−2) with a low charge transfer resistance (3.9 Ω) and an overpotential of 37 mV, achieving the current density of 10 mA cm2; moreover, it shows good OER activity (js = 1.798 mA cm−2) with low charge transfer resistance (2.1 Ω) and an overpotential of 250 mV, approaching a current density of 10 mA cm−2 in a 1 M NaOH aqueous solution. The CFeCoNiP/NF (electrodeposited on Ni foam) electrode-pair device achieved the current densities of 100 and 500 mA cm−2 at the voltages of 1.65 and 1.86 V, respectively, under alkaline conditions.

Mobile phones have become a necessity of modern life and are used for various tasks, including audio calls, text messaging, Web surfing, video streaming, gaming, and payments. Most of these tasks consume significant battery power, which makes public charging services increasingly important. Therefore, there are many public places and private stores have started to provide free charging services. However, there are several issues that restrict the popularity of public charging service. First, people cannot easily find charging spots. Second, there is no effective way to monitor charging status and manage the chargers. Third, a free charging service increases business expenses. To address these issues, we developed a Internet of Things (IoT)-based wireless charging service system, which is called AnyCharge. There are five major components of AnyCharge: 1) a Wi-Fi enabled wireless charger; 2) an IoT gateway; 3) a cloud-based management platform; 4) a secure Wi-Fi auto-connection algorithm; and 5) a mobile app. The charger is connected to an IoT gateway through Wi-Fi using our secure auto-connection algorithm, and the gateways are linked to the cloud server using message queue telemetry transport. The administrators can monitor and control chargers using the management platform. In addition, Android and iOS apps have been created to allow users to locate free chargers and find the shortest route to the nearest charging spot. We initiated a large-scale experimental deployment in Taiwan, Thailand, Singapore, and Japan. More than 200 chargers have been installed in different places, including restaurants, hospitals, telecom stores, and hotels. Statistics shows that there is a strong demand for public charging services.

In this paper, an efficient instance segmentation scheme based on deep convolutional neural networks is proposed to deal with unconstrained psoriasis images for computer-aided diagnosis. To achieve instance segmentation, the You Only Look At CoefficienTs (YOLACT) network composed of backbone, feature pyramid network (FPN), Protonet, and prediction head is used to deal with psoriasis images. The backbone network is used to extract feature maps from an image, and FPN is designed to generate multiscale feature maps for effectively classifying and localizing objects with multiple sizes. The prediction head is used to predict the classification information, bounding box information, and mask coefficients of objects. Some prototypes generated by Protonet are combined with mask coefficients to estimate the pixel-level shapes for objects. To achieve instance segmentation for unconstrained psoriasis images, YOLACT++ with a pretrained model is retrained via transfer learning. To evaluate the performance of the proposed scheme, unconstrained psoriasis images with different severity levels are collected for testing. As for subjective testing, the psoriasis regions and normal skin areas can be located and classified well. The four performance indices of the proposed scheme were higher than 93% after cross validation. About object localization, the Mean Average Precision (mAP) rates of the proposed scheme were at least 85.9% after cross validation. As for efficiency, the frames per second (FPS) rate of the proposed scheme reached up to 15. In addition, the F1_score and the execution speed of the proposed scheme were higher than those of the Mask Region-Based Convolutional Neural Networks (R-CNN)-based method. These results show that the proposed scheme based on YOLACT++ can not only detect psoriasis regions but also distinguish psoriasis pixels from background and normal skin pixels well. Furthermore, the proposed instance segmentation scheme outperforms the Mask R-CNN-based method for unconstrained psoriasis images.

Pothole detection is an important function in autonomous vehicles, which can help vehicles to avoid dangerous traps on roads, or change suspension to make passengers more comfortable. However, it is challenging to train a high quality pothole detector, mainly due to the difficulty of collecting training data. Sending automobiles with cameras to record videos of potholes is time consuming, expensive, and may lead to unexpected accidents. To address this issue, we leverage the recent emerging virtualto-real learning and use latest virtual reality technology to train a pothole detector. We develop a pothole generation system that can generate holes with various shapes, sizes, and depths. The virtual pothole images are added to the training dataset, and the detector performance is evaluated on real data. Experiment results show that virtual pothole images can successfully increase the overall detection accuracy and enable users to train detectors with less real data.

The sintered aluminum nitride granules were prepared in a continuous process through a two-step heat treatment at 1600 °C for 5 h and 1850 °C for 5 h using the spherical γ-alumina/phenol-resin precursor obtained by spray granulation as the starting material. In the first step of heat treatment, the alumina powders were nitrided to form porous aluminum nitride granules via a carbothermal reduction reaction and then were continuously heated in the second step of heat treatment to produce dense spherical aluminum nitride granules without using sintering aids. The obtained porous and sintered aluminum nitride granules were characterized by XRD, SEM and BET measurements and exhibited an average grain size of about 1 and 3 µm, respectively. Furthermore, the specific surface area of the obtained porous and sintered aluminum nitride granules dramatically decreased from 2.49 to 0.16 m2/g showing that the low-porosity, dense, polycrystalline aluminum nitride granules were successfully prepared.

A primary goal for human-autonomy integration (HAI) is to balance the strengths of human and autonomy in order to achieve performance objectives more efficiently and robustly than either the human ...