Social recommendation algorithm can alleviate data sparsity and cold start problems in recommendation system by integrated social information. Among them, matrix-based decomposition algorithms are the most widely used and studied. Such algorithms use dot product operations to calculate the similarity between users and items, which ignores user's potential preferences, reduces algorithms' recommendation accuracy. This deficiency can be avoided by a metric learning-based social recommendation algorithm, which learns the distance between user embedding vectors and item embedding vectors instead of vector dot-product operations. However, previous works provide no theoretical explanation for its plausibility. Moreover, most works focus on the indirect impact of social friends on user's preferences, ignoring the direct impact on user's rating preferences, which is the influence of user rating preferences. To solve these problems, this study proposes a user bias drift social recommendation algorithm based on metric learning (BDML). The main work of this paper is as follows: (1) the process of introducing metric learning in the social recommendation scenario is introduced in the form of equations, and explained the reason why metric learning can replace the click operation; (2) a new user bias is constructed to simultaneously model the impact of social relationships on user's ratings preferences and user's preferences; Experimental results on two datasets show that the BDML algorithm proposed in this study has better recommendation accuracy compared with other comparison algorithms, and will be able to guarantee the recommendation effect in a more sparse dataset.

Density-based outlier detection is one of the hot issues in data mining. A point is determined as outlier on basis of the density of points near them. The existing density-based detection algorithms have high time complexity, in order to reduce the time complexity, a new outlier detection algorithm DODMD (Density-based Outlier Detection in Multidimensional Datasets) is proposed. Firstly, on the basis of ZH-tree, the concept of micro-cluster is introduced. Each leaf node is regarded as a micro-cluster, and the micro-cluster is calculated to achieve the purpose of batch filtering. In order to obtain n sets of approximate outliers quickly, a greedy method is used to calculate the boundary of LOF and mark the minimum value as LOF_min. Secondly, the outliers can filtered out by LOF_min, the real outliers are calculated, and then the result set is updated to make the boundary closer. Finally, the accuracy and efficiency of DODMD algorithm are verified on real dataset and synthetic dataset respectively.

The student group division is benefit for universities to do the student management based on the group profile. With the widespread use of student smart cards on campus, especially where students living in campus residence halls, students' daily activities on campus are recorded with information such as smart card swiping time and location. Therefore, it is feasible to depict the students with the daily activity data and accordingly group students based on objective measuring from their campus behavior with some regular student attributions collected in the management system. However, it is challenge in feature representation due to diverse forms of the student data. To effectively and comprehensively represent students' behaviors for further student group division, we proposed to adopt activity data from student smart cards and student attributes as input data with taking account of activity and attribution relationship types from different perspective. Specially, we propose a novel student group division method based on a multi-view student attribute heterogeneous information network (MSA-HIN). The network nodes in our proposed MSA-HIN represent students with their multi-dimensional attribute information. Meanwhile, the edges are constructed to characterize student different relationships, such as co-major, co-occurrence, and co-borrowing books. Based on the MSA-HIN, embedded representations of students are learned and a deep graph cluster algorithm is applied to divide students into groups. Comparative experiments have been done on a real-life campus dataset collected from a university. The experimental results demonstrate that our method can effectively reveal the variability of student attributes and relationships and accordingly achieves the best clustering results for group division.

Name separation (splitting full names into surnames and given names) is not a tedious task in a multiethnic country because the procedure for splitting surnames and given names is ethnicity-specific. Malaysia has multiple main ethnic groups; therefore, separating Malaysian full names into surnames and given names proves a challenge. In this study, we develop a two-phase framework for Malaysian name separation using deep learning. In the initial phase, we predict the ethnicity of full names. We propose a recurrent neural network with long short-term memory network-based model with character embeddings for prediction. Based on the predicted ethnicity, we use a rule-based algorithm for splitting full names into surnames and given names in the second phase. We evaluate the performance of the proposed model against various machine learning models and demonstrate that it outperforms them by an average of 9%. Moreover, transfer learning and fine-tuning of the proposed model with an additional dataset results in an improvement of up to 7% on average.

A widely used social networking service like Twitter has the ability to disseminate information to large groups of people even during a pandemic. At the same time, it is a convenient medium to share irrelevant and unverified information online and poses a potential threat to society. In this research, conventional machine learning algorithms are analyzed to classify the data as either non-rumor data or rumor data. Machine learning techniques have limited tuning capability and make decisions based on their learning. To tackle this problem the authors propose a deep learning-based Rumor Detection Neural Network model to predict the rumor tweet in real-world events. This model comprises three layers, AttCNN layer is used to extract local and position invariant features from the data, AttBi-LSTM layer to extract important semantic or contextual information and HPOOL to combine the down sampling patches of the input feature maps from the average and maximum pooling layers. A dataset from Kaggle and ground dataset #gaja are used to train the proposed Rumor Detection Neural Network to determine the veracity of the rumor. The experimental results of the RDNN Classifier demonstrate an accuracy of 93.24% and 95.41% in identifying rumor tweets in real-time events.

To address the problem of low detection accuracy due to training noise caused by mislabeling when Tri-training for network intrusion detection (NID), we propose a Tri-training algorithm based on cross entropy and K-nearest neighbors (TCK) for network intrusion detection. The proposed algorithm uses cross-entropy to replace the classification error rate to better identify the difference between the practical and predicted distributions of the model and reduce the prediction bias of mislabeled data to unlabeled data; K-nearest neighbors are used to remove the mislabeled data and reduce the number of mislabeled data. In order to verify the effectiveness of the algorithm proposed in this paper, experiments were conducted on 12 UCI datasets and NSL-KDD network intrusion datasets, and four indexes including accuracy, recall, F-measure and precision were used for comparison. The experimental results revealed that the TCK has superior performance than the conventional Tri-training algorithms and the Tri-training algorithms using only cross-entropy or K-nearest neighbor strategy.

As a research hotspot, pedestrian detection has a wide range of applications in the field of computer vision in recent years. However, current pedestrian detection methods have problems such as insufficient detection accuracy and large models that are not suitable for large-scale deployment. In view of these problems mentioned above, a lightweight pedestrian detection and early warning method using a new model called you only look once (Yolov5) is proposed in this paper, which utilizing advantages of Yolov5s model to achieve accurate and fast pedestrian recognition. In addition, this paper also optimizes the loss function of the batch normalization (BN) layer. After sparsification, pruning and fine-tuning, got a lot of optimization, the size of the model on the edge of the computing power is lower equipment can be deployed. Finally, from the experimental data presented in this paper, under the training of the road pedestrian dataset that we collected and processed independently, the Yolov5s model has certain advantages in terms of precision and other indicators compared with traditional single shot multiBox detector (SSD) model and fast region-convolutional neural network (Fast R-CNN) model. After pruning and lightweight, the size of training model is greatly reduced without a significant reduction in accuracy, and the final precision reaches 87%, while the model size is reduced to 7,723 KB.

Environment, price, regulation, and other factors influence the price of agricultural products, which is a social signal of product supply and demand. The price of many agricultural products fluctuates greatly due to the asymmetry between production and marketing details. Horticultural goods are particularly price sensitive because they cannot be stored for long periods of time. It is very important and helpful to forecast the price of horticultural products which is crucial in designing a cropping plan. The proposed method guides the farmers in agricultural product production and harvesting plans. Farmers can benefit from long-term forecasting since it helps them plan their planting and harvesting schedules. Customers can also profit from daily average price estimates for the short term. This paper study the time series models such as ARIMA, SARIMA, and neural network models such as BPN, LSTM and are used for wheat cost prediction in India. A large scale available data set is collected and tested. The results shows that since ARIMA and SARIMA models are well suited for small-scale, continuous, and periodic data, the BPN and LSTM provide more accurate and faster results for predicting well weekly and monthly trends of price fluctuation.

People are constantly exposed to stress and anxiety environment, which could contribute to a variety of psychological and physical health problems. Therefore, it is particularly important to identify psychological stress in time and to find a feasible and universal method of stress reduction. This research investigated the influence of different music, such as relaxation music and natural rhythm music, on stress relief based on Electroencephalogram signals. Mental arithmetic test was implemented to create a stressful environment. 23 participants performed the mental arithmetic test with and without music respectively, while their Electroencephalogram signal was recorded. The effect of music on stress relief was verified through stress test questionnaires, including Trait Anxiety Inventory (STAI-6) and Self-Stress Assessment. There was a significant change in the stress test questionnaire values with and without music according to paired t-test (p<0.01). Furthermore, a model based on Transformer for stress level classification from Electroencephalogram signal was proposed. Experimental results showed that the method of listening to relaxation music and natural rhythm music achieved the effect of reducing psychological stress and the proposed model yielded a promising accuracy in classifying the Electroencephalogram signal of mental stress.

To analyze and compare the most influencing factors on cloud computing adoption (CCA) in the healthcare organization, a systematic review and meta-analyses of studies was performed using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) and Cochrane collaboration recommendations. A search of PubMed, ScienceDirect, Springer, Wiley Online, and Taylor & Francis Online digital libraries (From inception to January 19, 2022) was performed. A total of 17 studies met the defined studies' inclusion and exclusion criteria. Statistical significance difference favoring most influencing factors on CCA were (MD 0.76, 95% CI -1.48 - 3.01, p <0.00001, I² = 90%), (MD 1.40, 95% CI -4.76 - 7.55, p < 0.00007, I² = 97%) (MD 0.17, 95% CI -2.69 - 3.03, p<0.00001, I² = 96%) for technology vs. organizational, technology vs. environmental and business vs. human factors, respectively. Organizational and environmental factors had greater impacts on CCA compared with technological factors. Moreover, business factors were more influential than the human factors.

Currently, cross-attention is widely used in Siamese trackers to replace traditional correlation operations for feature fusion between template and search region. The former can establish a similar relationship between the target and the search region better than the latter for robust visual object tracking. But existing trackers using cross-attention only focus on rich semantic information of high-level features, while ignoring the appearance information contained in low-level features, which makes trackers vulnerable to interference from similar objects. In this paper, we propose a Multi-level Cross-attention Siamese network(MCSiam) to aggregate the semantic information and appearance information at the same time. Specifically, a multi-level cross-attention module is designed to fuse the multi-layer features extracted from the backbone, which integrate different levels of the template and search region features, so that the rich appearance information and semantic information can be used to carry out the tracking task simultaneously. In addition, before cross-attention, a target-aware module is introduced to enhance the target feature and alleviate interference, which makes the multi-level cross-attention module more efficient to fuse the information of the target and the search region. We test the MCSiam on four tracking benchmarks and the result show that the proposed tracker achieves comparable performance to the state-of-the-art trackers.

In the public healthcare, a computational system that can automatically and efficiently detect and classify falls from a video sequence has significant potential. With the advancement of deep learning, which can extract temporal and spatial information, has become more widespread. However, traditional 3D CNNs that usually adopt shallow networks cannot obtain higher recognition accuracy than deeper networks. Additionally, some experiences of neural network show that the problem of gradient explosions occurs with increasing the network layers. As a result, an enhanced three-dimensional ResNet-based method for fall detection (3D-ERes-FD) is proposed to directly extract spatio-temporal features to address these issues. In our method, a 50-layer 3D residual network is used to deepen the network for improving fall recognition accuracy. Furthermore, enhanced residual units with four convolutional layers are developed to efficiently reduce the number of parameters and increase the depth of the network. According to the experimental results, the proposed method outperformed several state-of-the-art methods.

Since machine learning was introduced into cross-site scripting (XSS) attack detection, many researchers have conducted related studies and achieved significant results, such as saving time and labor costs by not maintaining a rule database, which is required by traditional XSS attack detection methods. However, this topic came across some problems, such as poor generalization ability, significant false negative rate (FNR) and false positive rate (FPR). Moreover, the automatic clustering property of graph convolutional networks (GCN) has attracted the attention of researchers. In the field of natural language process (NLP), the results of graph embedding based on GCN are automatically clustered in space without any training, which means that text data can be classified just by the embedding process based on GCN. Previously, other methods required training with the help of labeled data after embedding to complete data classification. With the help of the GCN auto-clustering feature and labeled data, this research proposes an approach to detect XSS attacks (called GCNXSS) to mine the dependencies between the units that constitute an XSS payload. First, GCNXSS transforms a URL into a word homogeneous graph based on word co-occurrence relationships. Then, GCNXSS inputs the graph into the GCN model for graph embedding and gets the classification results. Experimental results show that GCNXSS achieved successful results with accuracy, precision, recall, F1-score, FNR, FPR, and predicted time scores of 99.97%, 99.75%, 99.97%, 99.86%, 0.03%, 0.03%, and 0.0461ms. Compared with existing methods, GCNXSS has a lower FNR and FPR with stronger generalization ability.

Robust reversible watermarking has attracted widespread attention in the field of information hiding in recent years. It should not only have robustness against attacks in transmission but also meet the reversibility of distortion-free transmission. According to our best knowledge, the most recent robust reversible watermarking methods adopt a single image as the carrier, which might lead to low efficiency in terms of carrier utilization. To address the issue, a novel dual-image robust reversible watermarking framework is proposed in this paper to effectively utilize the correlation between both carriers (namely dual images) and thus improve the efficiency of carrier utilization. In the dual-image robust reversible watermarking framework, a two-layer robust watermarking mechanism is designed to further improve the algorithm performances, i.e., embedding capacity and robustness. In addition, an optimization model is built to determine the parameters. Finally, the proposed framework is applied in different domains (namely domain-independent), i.e., Slantlet Transform and Singular Value Decomposition domain, and Zernike moments, respectively to demonstrate its effectiveness and generality. Experimental results demonstrate the superiority of the proposed dual-image robust reversible watermarking framework.

Recently, various security threats such as data leakage and data forgery have been possible in the communication and storage of data shared in the cloud environment. This paper conducted a study on the CP-ABSC scheme to solve these security threats. In the existing CP-ABSC scheme, if the data is obtained by the unsigncryption of the data user incorrectly, the identity of the data owner who uploaded the ciphertext cannot be known. Also, when verifying the leaked secret key, the identity information of the data user who leaked the secret key cannot be known. In terms of efficiency, the number of attributes can affect the ciphertext. In addition, a large amount of computation is required for the user to unsigncrypt the ciphertext. In this paper, we propose ECP-ABSC that provides data user traceability, and use it in a cloud environment to provide an efficient and secure data sharing scheme. The proposed ECP-ABSC scheme can trace and verify the identity of the data owner who uploaded the ciphertext incorrectly and the data user who leaked the secret key for the first time. In addition, the ciphertext of a constant size is output and the efficiency of the user's unsigncryption computation were improved.

COVID-19, a highly infectious disease, has affected the globe tremendously since its outbreak during late 2019 in Wuhan, China. In order to respond to the pandemic, governments around the world introduced a variety of public health measures including contact-tracing, a method to identify individuals who may have come into contact with a confirmed COVID-19 patient, which usually leads to quarantine of certain individuals. Like many other governments, the South Korean health authorities adopted public health measures using latest data technologies. Key data technology-based quarantine measures include:(1) Electronic Entry Log; (2) Self-check App; and (3) COVID-19 Wristband, and heavily relied on individual's personal information for contact-tracing and self-isolation. In fact, during the early stages of the pandemic, South Korea's strategy proved to be highly effective in containing the spread of coronavirus while other countries suffered significantly from the surge of COVID-19 patients. However, while the South Korean COVID-19 policy was hailed as a success, it must be noted that the government achieved this by collecting and processing a wide range of personal information. In collecting and processing personal information, the data minimum principle - one of the widely recognized common data principles between different data protection laws - should be applied. Public health measures have no exceptions, and it is even more crucial when government activities are involved. In this study, we provide an analysis of how the governments around the world reacted to the COVID-19 pandemic and evaluate whether the South Korean government's digital quarantine measures ensured the protection of its citizen's right to privacy.

With the aim of tackling the contradiction between computation intensive industrial applications and resource-weak Edge Devices (EDs) in Industrial Internet of Things (IIoT), a novel computation task offloading scheme in SDIN-enabled MEC based IIoT is proposed in this paper. With the aim of reducing the task accomplished latency and energy consumption of EDs, a joint optimization method is proposed for optimizing the local CPU-cycle frequency, offloading decision, and wireless and computation resources allocation jointly. Based on the optimization, the task offloading problem is formulated into a Mixed Integer Nonlinear Programming (MINLP) problem which is a large-scale NP-hard problem. In order to solve this problem in an accessible time complexity, a sub-optimal algorithm GPCOA, which is based on hybrid evolutionary computation, is proposed. Outcomes of emulation revel that the proposed method outperforms other baseline methods, and the optimization result shows that the latency-related weight is efficient for reducing the task execution delay and improving the energy efficiency.

In this paper, we propose improved maximum access delay time, noise variance, and power delay profile (PDP) estimation schemes for orthogonal frequency division multiplexing (OFDM) system in multipath fading channels. To this end, we adopt the approximate maximum likelihood (ML) estimation strategy. For the first step, the log-likelihood function (LLF) of the received OFDM symbols is derived by utilizing only the cyclic redundancy induced by cyclic prefix (CP) without additional information. Then, the set of the initial path powers is sub-optimally obtained to maximize the derived LLF. In the second step, we can select a subset of the initial path power set, i.e. the maximum access delay time, so as to maximize the modified LLF. Through numerical simulations, the benefit of the proposed method is verified by comparison with the existing methods in terms of normalized mean square error, erroneous detection, and good detection probabilities.