Diagnosing breast diseases using ultrasound (US) images remains challenging because it is time-consuming and requires expert radiologist knowledge. As a result, the diagnostic performance is significantly biased. To assist radiologists in this process, computer-aided diagnosis (CAD) systems have been developed and used in practice. This type of system is used not only to assist radiologists in examining breast ultrasound images (BUS) but also to ensure the effectiveness of the diagnostic process. In this study, we propose a new approach for breast lesion localization and segmentation using a multi-scale pyramid of the ultrasound image of a breast organ and a convolutional semantic segmentation network. Unlike previous studies that used only a deep detection/segmentation neural network on a single breast ultrasound image, we propose to use multiple images generated from an input image at different scales for the localization and segmentation process. By combining the localization/segmentation results obtained from the input image at different scales, the system performance was enhanced compared with that of the previous studies. The experimental results with two public datasets confirmed the effectiveness of the proposed approach by producing superior localization/segmentation results compared with those obtained in previous studies.

Aerial objects are more challenging to segment than normal objects, which are usually smaller and have less textural detail. In the process of segmentation, target objects are easily omitted and misdetected, which is problematic. To alleviate these issues, we propose local aggregation feature pyramid networks (LAFPNs) and pyramid integrated context modules (PICMs) for aerial object segmentation. First, using an LAFPN, while strengthening the deep features, the extent to which low-level features interfere with high-level features is reduced, and numerous dense and small aerial targets are prevented from being mistakenly detected as a whole. Second, the PICM uses global information to guide local features, which enhances the network's comprehensive understanding of an entire image and reduces the missed detection of small aerial objects due to insufficient texture information. We evaluate our network with the MS COCO dataset using three categories: airplanes, birds, and kites. Compared with Mask R-CNN, our network achieves performance improvements of 1.7%, 4.9%, and 7.7% in terms of the AP metrics for the three categories. Without pretraining or any postprocessing, the segmentation performance of our network for aerial objects is superior to that of several recent methods based on classic algorithms.

Rating prediction is an important issue in recommender systems, and its accuracy affects the experience of the user and the revenue of the company. Traditional recommender systems use Factorization Machinesfor rating predictions and each feature is selected with the same weight. Thus, there are problems with inaccurate ratings and limited data representation. This study proposes a deep recommendation model based on self-attention Factorization (SAFMR) to solve these problems. This model uses Convolutional Neural Networks to extract features from user and item reviews. The obtained features are fed into self-attention mechanism Factorization Machines, where the self-attention network automatically learns the dependencies of the features and distinguishes the weights of the different features, thereby reducing the prediction error. The model was experimentally evaluated using six classes of dataset. We compared MSE, NDCG and time for several real datasets. The experiment demonstrated that the SAFMR model achieved excellent rating prediction results and recommendation correlations, thereby verifying the effectiveness of the model.

Text recognition in natural scene images is a challenging problem in computer vision. The accurate identification of ship number characters can effectively improve the level of ship traffic management. However, due to the blurring caused by motion and text occlusion, the accuracy of ship number recognition is difficult to meet the actual requirements. To solve these problems, this paper proposes a dual-branch network based on the CRNN identification network. The network couples image restoration and character recognition. The CycleGAN module is used for blur restoration branch, and the Pix2pix module is used for character occlusion branch. The two are coupled to reduce the impact of image blur and occlusion. Input the recovered image into the text recognition branch to improve the recognition accuracy. After a lot of experiments, the model is robust and easy to train. Experiments on CTW datasets and real ship maps illustrate that our method can get more accurate results.

Wrestling is one of the popular events for modern sports. It is difficult to quantitatively describe a wrestling game between athletes. And deep learning can help wrestling training by human recognition techniques. Based on the characteristics of latest wrestling competition rules and human recognition technologies, a set of wrestling competition video analysis and retrieval system is proposed. This system uses a combination of literature method, observation method, interview method and mathematical statistics to conduct statistics, analysis, research and discussion on the application of technology. Combined the system application in targeted movement technology. A deep learning-based facial recognition psychological feature analysis method for the training and competition of classical wrestling after the implementation of the new rules is proposed. The experimental results of this paper showed that the proportion of natural emotions of male and female wrestlers was about 50%, indicating that the wrestler's mentality was relatively stable before the intense physical confrontation, and the test of the system also proved the stability of the system.

Human decision-making is a complex behavior. A replication of human decision making offers a potential to enhance the capacity of intelligent systems by providing additional user assistance in decision making. By reducing the effort and task complexity on behalf of the user, such replication would improve the overall user experience, and affect the degree of intelligence exhibited by the system. This paper explores individuals' decision-making processes when using recommender systems, and its related outcomes. In this study, human decision-making (HDM) refers to the selection of an item from a given set of options that are shown as recommendations to a user. The goal of our study was to identify IS constructs that contribute towards such decision-making, thereby contributing towards creating a mental model of HDM. This was achieved through recording Electroencephalographic (EEG) readings of subjects while they performed a decision-making activity. Readings from 16 righthanded healthy avid readers reflect that reward, theory of mind, risk, calculation, task intention, emotion, sense of touch, ambiguity and decision making are the primary constructs that users employ while deciding from a given set of recommendations in an online bookstore. In all 10 distinct brain areas were identified. These brain areas that lead to their respective constructs were found to be cingulate gyrus, precentral gyrus, inferior parietal lobule, posterior cingulate, medial frontal gyrus, anterior cingulate, postcentral gyrus, superior frontal gyrus, inferior frontal gyrus, and middle frontal gyrus (also referred to as dorsolateral prefrontal gyrus (DLPFC)). The identified constructs would help in developing a design theory for enhancing user assistance, especially in the context of recommender systems.

The rapid development of mobile communication not only has made the industry gradually diversified, but also has enhanced the service quality requirements of users. In this regard, it is imperative to consider jointly network slicing and mobile edge computing. The former mainly ensures the requirements of varied vertical services preferably, and the latter solves the conflict between the user's own energy and harsh latency. At present, the integration of the two faces many challenges and need to carry out at different levels. The main target of the paper is to minimize the energy consumption of the system, and introduce a multi-slice joint task offloading and resource allocation scheme for massive multiple input multiple output enabled heterogeneous networks. The problem is formulated by collaborative optimizing offloading ratios, user association, transmission power and resource slicing, while being limited by the dissimilar latency and rate of multi-slice. To solve it, assign the optimal problem to two sub-problems of offloading decision and resource allocation, then solve them separately by exploiting the alternative optimization technique and Karush-Kuhn-Tucker conditions. Finally, a novel slices task offloading and resource allocation algorithm is proposed to get the offloading and resource allocation strategies. Numerous simulation results manifest that the proposed scheme has certain feasibility and effectiveness, and its performance is better than the other baseline scheme.

In a random vector functional link (RVFL) network, shortcomings such as local optimal stagnation and decreased convergence performance cause a reduction in the accuracy of illumination correction by only inputting the weights and biases of hidden neurons. In this study, we proposed an improved regularized random vector functional link (RRVFL) network algorithm with an optimized grey wolf optimizer (GWO). Herein, we first proposed the moth-flame optimization (MFO) algorithm to provide a set of excellent initial populations to improve the convergence rate of GWO. Thereafter, the MFO-GWO algorithm simultaneously optimized the input feature, input weight, hidden node and bias of RRVFL, thereby avoiding local optimal stagnation. Finally, the MFO-GWO-RRVFL algorithm was applied to ameliorate the performance of illumination correction of various test images. The experimental results revealed that the MFO-GWO-RRVFL algorithm was stable, compatible, and exhibited a fast convergence rate.

Aiming at the serious occlusion and slow tracking speed in pedestrian target tracking and recognition in complex scenes, a target tracking method based on improved YOLO v5 combined with Deep SORT is proposed. By merging the attention mechanism ECA-Net with the Neck part of the YOLO v5 network, using the CIoU loss function and the method of CIoU non-maximum value suppression, connecting the Deep SORT model using Shuffle Net V2 as the appearance feature extraction network to achieve lightweight and fast speed tracking and the purpose of improving tracking under occlusion. A large number of experiments show that the improved YOLO v5 increases the average precision by 1.3% compared with other algorithms. The improved tracking model, MOTA reaches 54.3% on the MOT17 pedestrian tracking data, and the tracking accuracy is 3.7% higher than the related algorithms and The model presented in this paper improves the FPS by nearly 5 on the fps indicator.

Semantic segmentation of road scene is the key technology of autonomous driving, and the improvement of convolutional neural network architecture promotes the improvement of model segmentation performance. The existing convolutional neural network has the simplification of learning knowledge and the complexity of the model. To address this issue, we proposed a road scene semantic segmentation algorithm based on multi-task collaborative learning. Firstly, a depthwise separable convolution atrous spatial pyramid pooling is proposed to reduce model complexity. Secondly, a collaborative learning framework is proposed involved with saliency detection, and the joint loss function is defined using homoscedastic uncertainty to meet the new learning model. Experiments are conducted on the road and nature scenes datasets. The proposed method achieves 70.94% and 64.90% mIoU on Cityscapes and PASCAL VOC 2012 datasets, respectively. Qualitatively, Compared to methods with excellent performance, the method proposed in this paper has significant advantages in the segmentation of fine targets and boundaries.

Modern image inpainting techniques based on deep learning have achieved remarkable performance, and more and more people are working on repairing more complex and larger missing areas, although this is still challenging, especially for facial image inpainting. For a face image with a huge missing area, there are very few valid pixels available; however, people have an ability to imagine the complete picture in their mind according to their subjective will. It is important to simulate this capability while maintaining the identity features of the face as much as possible. To achieve this goal, we propose a three-stage network model, which we refer to as the identity and structure feature refinement network (ISFRNet). ISFRNet is based on 1) a pre-trained pSp-styleGAN model that generates an extremely realistic face image with rich structural features; 2) a shallow structured network with a small receptive field; and 3) a modified U-net with two encoders and a decoder, which has a large receptive field. We choose structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), L1 Loss and learned perceptual image patch similarity (LPIPS) to evaluate our model. When the missing region is 20%-40%, the above four metric scores of our model are 28.12, 0.942, 0.015 and 0.090, respectively. When the lost area is between 40% and 60%, the metric scores are 23.31, 0.840, 0.053 and 0.177, respectively. Our inpainting network not only guarantees excellent face identity feature recovery but also exhibits state-of-the-art performance compared to other multi-stage refinement models.

The network function virtualization (NFV) uses virtualization technology to separate software from hardware. One of the most important challenges of NFV is the resource management of virtual network functions (VNFs). According to the dynamic nature of NFV, the resource allocation of VNFs must be changed to adapt to the variations of incoming network traffic. However, the significant delay may be happened because of the reallocation of resources. In order to balance the performance between delay and quality of service, this paper firstly made a compromise between VNF migration and energy consumption. Then, the long short-term memory (LSTM) was utilized to forecast network traffic. Also, the asymmetric loss function for LSTM (LO-LSTM) was proposed to increase the predicted value to a certain extent. Finally, an experiment was conducted to evaluate the performance of LO-LSTM. The results demonstrated that the proposed LO-LSTM can not only reduce migration times, but also make the energy consumption increment within an acceptable range.

Most of the existing Distributed Denial-of-Service mitigation schemes in Software-Defined Networking are only implemented in the network domain managed by a single controller. In fact, the zombies for attackers to launch large-scale DDoS attacks are actually not in the same network domain. Therefore, abnormal traffic of DDoS attack will affect multiple paths and network domains. A single defense method is difficult to deal with large-scale DDoS attacks. The cooperative defense of multiple domains becomes an important means to effectively solve cross-domain DDoS attacks. We propose an efficient multi-domain DDoS cooperative defense mechanism by integrating blockchain and SDN architecture. It includes attack traceability, inter-domain information sharing and attack mitigation. In order to reduce the length of the marking path and shorten the traceability time, we propose an AS-level packet traceability method called ASPM. We propose an information sharing method across multiple domains based on blockchain and smart contract. It effectively solves the impact of DDoS illegal traffic on multiple domains. According to the traceability results, we designed a DDoS attack mitigation method by replacing the ACL list with the IP address black/gray list. The experimental results show that our ASPM traceability method requires less data packets, high traceability precision and low overhead. And blockchain-based inter-domain sharing scheme has low cost, high scalability and high security. Attack mitigation measures can prevent illegal data flow in a timely and efficient manner.

The limited computing power of sensor nodes in wireless sensor networks (WSNs) and data tampering during wireless transmission are two important issues. In this paper, we propose a scheme for independent individual authentication of WSNs data based on digital watermarking technology. Digital watermarking suits well for WSNs, owing to its lower computational cost. The proposed scheme uses independent individual to generate a digital watermark and embeds the watermark in current data item. Moreover, a sink node extracts the watermark in single data and compares it with the generated watermark, thereby achieving integrity verification of data. Inherently, individual validation differs from the grouping-level validation, and avoids the lack of grouping robustness. The improved performance of individual integrity verification based on proposed scheme is validated through experimental analysis. Lastly, compared to other state-of-the-art schemes, our proposed scheme significantly reduces the false negative rate by an average of 5%, the false positive rate by an average of 80% of data verification, and increases the correct verification rate by 50% on average.

Due to laws, regulations, privacy, etc., between 70-90 percent of providers do not share medical data, forming a "data island". It is essential to collaborate across multiple institutions without sharing patient data. Most existing methods adopt distributed learning and centralized federal architecture to solve this problem, but there are problems of resource heterogeneity and data heterogeneity in the practical application process. This paper proposes a collaborative deep learning modelling method based on the blockchain network. The training process uses encryption parameters to replace the original remote source data transmission to protect privacy. Hyperledger Fabric blockchain is adopted to realize that the parties are not restricted by the third-party authoritative verification end. To a certain extent, the distrust and single point of failure caused by the centralized system are avoided. The aggregation algorithm uses the FedProx algorithm to solve the problem of device heterogeneity and data heterogeneity. The experiments show that the maximum improvement of segmentation accuracy in the collaborative training mode proposed in this paper is 11.179% compared to local training. In the sequential training mode, the average accuracy improvement is greater than 7%. In the parallel training mode, the average accuracy improvement is greater than 8%. The experimental results show that the model proposed in this paper can solve the current problem of centralized modelling of multicenter data. In particular, it provides ideas to solve privacy protection and break "data silos", and protects all data.

In Low Earth Orbit (LEO) satellite networks, satellites operate fast and the inter-satellite link change period is short. In order to sense the spectrum state in LEO satellite networks in real-time, a space-based satellite network intelligent spectrum sensing algorithm based on artificial neural network (ANN) is proposed, while Geosynchronous Earth Orbit (GEO) satellites are introduced to make fast and effective judgments on the spectrum state of LEO satellites by using their stronger arithmetic power. Firstly, the visibility constraints between LEO satellites and GEO satellites are analyzed to derive the inter-satellite link building matrix and complete the inter-satellite link situational awareness. Secondly, an ANN-based energy detection (ANN-ED) algorithm is proposed based on the traditional energy detection algorithm and artificial neural network. The ANN module is used to determine the spectrum state and optimize the traditional energy detection algorithm. GEO satellites are used to fuse the information sensed by LEO satellites and then give the spectrum decision, thereby realizing the inter-satellite spectrum state sensing. Finally, the sensing quality is evaluated by the analysis of sensing delay and sensing energy consumption. The simulation results show that our proposed algorithm has lower complexity, the sensing delay and sensing energy consumption compared with the traditional energy detection method.

Differential spatial modulation uses the antenna index to transmit information, which improves the spectral efficiency, and completely bypasses any channel side information in the recommended setting. A generalized distributed multiple turbo coded-cooperative differential spatial modulation based on distributed multiple turbo code is put forward and its performances in Rayleigh fading channels is analyzed. The generalized distributed multiple turbo coded-cooperative differential spatial modulation scheme is a coded-cooperation communication scheme, in which we proposed a new joint parallel iterative decoding method. Moreover, the code matched interleaver is considered to be the best choice for the generalized multiple turbo coded-cooperative differential spatial modulation schemes, which is the key factor of turbo code. Monte Carlo simulated results show that the proposed cooperative differential spatial modulation scheme is better than the corresponding non-cooperative scheme over Rayleigh fading channels in multiple input and output communication system under the same conditions. In addition, the simulation results show that the code matched interleaver scheme gets a better diversity gain as compared to the random interleaver.

Various aspects of artificial intelligence (AI) have become of significant interest to academia and industry in recent times. To satisfy these academic and industrial interests, it is necessary to comprehensively investigate trends in AI-related changes of diverse areas. In this study, we identified and predicted emerging convergences with the help of AI-associated research abstracts collected from the SCOPUS database. The bidirectional encoder representations obtained via the transformers-based topic discovery technique were subsequently deployed to identify emerging topics related to AI. The topics discovered concern edge computing, biomedical algorithms, predictive defect maintenance, medical applications, fake news detection with block chain, explainable AI and COVID-19 applications. Their convergences were further analyzed based on the shortest path between topics to predict emerging convergences. Our findings indicated emerging AI convergences towards healthcare, manufacturing, legal applications, and marketing. These findings are expected to have policy implications for facilitating the convergences in diverse industries. Potentially, this study could contribute to the exploitation and adoption of AI-enabled convergences from a practical perspective.

The IEEE 802.11 WLAN adopts a random backoff algorithm for its collision avoidance mechanism, and it is well known that the contention-based algorithm may suffer from performance degradation especially in congested networks. In this paper, we design an efficient backoff algorithm that utilizes a reinforcement learning method to determine optimal values of backoffs. The mobile nodes share a common contention window (CW) in our scheme, and using a Q-learning algorithm, they can avoid collisions by finding and implicitly reserving their optimal time slot(s). In addition, we introduce Frame Size Control (FSC) algorithm to minimize the possible degradation of aggregate throughput when the number of nodes exceeds the CW size. Our simulation shows that the proposed backoff algorithm with FSC method outperforms the 802.11 protocol regardless of the traffic conditions, and an analytical modeling proves that our mechanism has a unique operating point that is fair and stable.