Mixed Information Flow for Cross-Domain Sequential Recommendations

Cross-domain sequential recommendation is the task of predict the next item that the user is most likely to interact with based on past sequential behavior from multiple domains. One of the key challenges in cross-domain sequential recommendation is to grasp and transfer the flow of information from multiple domains so as to promote recommendations in all domains. Previous studies have investigated the flow of behavioral information by exploring the connection between items from different domains. The flow of knowledge (i.e., the connection between knowledge from different domains) has so far been neglected. In this article, we propose a mixed information flow network for cross-domain sequential recommendation to consider both the flow of behavioral information and the flow of knowledge by incorporating a behavior transfer unit and a knowledge transfer unit . The proposed mixed information flow network is able to decide when cross-domain information should be used and, if so, which cross-domain information should be used to enrich the sequence representation according to users’ current preferences. Extensive experiments conducted on four e-commerce datasets demonstrate that the proposed mixed information flow network is able to improve recommendation performance in different domains by modeling mixed information flow. In this article, we focus on the application of mixed information flow network s to a scenario with two domains, but the method can easily be extended to multiple domains.

Research on Global Security Sharing of Power Grid Information Based on Differential Privacy Model

With the advancement of science and technology, intelligent power transmission technology is also constantly developing. Among them, the information security of the transmission grid in the power system is an important content that cannot be ignored. This article first analyzes the current status of power information security issues, including research on the current status of foreign power information security. Secondly, it studies the differential privacy model, finally it studies the power grid security domain information sharing technology.

Islamic Leadership School Curriculum Development in Taruna Panatagama Putri Yogyakarta

This research focuses on the process of curriculum development at Islamic Leadership School (ILS) in Taruna Panatagama Yogyakarta. This study aims to determine the concept and implementation of ILS curriculum development and its implications for learning outcomes. The method used in this research is descriptive qualitative method. The subjects were the founder, the Principal, the Caregiver, the teachers, the students and the alumni of the ILS Taruna Panatagama School. The data were obtained through interviews, observation, and documentation. The data were analyzed by using Spradley model, namely data analysis and data collection processes carried out simultaneously, consisting of analysis of conceptual domain information, taxonomic analysis (exploring important domains and subdomains by referring to library materials to obtain in-depth understanding), componential analysis (contrasting elements in the domains obtained and the subsequent relevant categorization), and theme analysis. The results of the study indicate that the curriculum with a homeschooling model has been built based on the potential development of each student. The basic concepts and ideas are applied based on Islamic teachings with a focus on leadership competencies by building awareness of Islamic personality and developing leadership. The implications for student learning outcomes are the changes in attitudes and behavior of students and achievements.

Research on Key Security Detection Method of Cross Domain Information Sharing Based on PKG Trust Gateway

Aiming at the problems of low precision, long detection time and poor detection effect in current cross domain information sharing key security detection methods, a cross domain information sharing key security detection method based on PKG trust gateway is proposed. By analyzing bilinear pairing based on elliptic curve and identity based encryption scheme, according to the independent system parameters of PKG management platform, cross domain authentication access mechanism is proposed. PKG of different trust domains is used as the trust gateway for cross domain authentication. The key escrow problem of PKG of different trust domains is solved through key sharing, and the communication key agreement mechanism is established to mutually authenticate the user nodes in the trust domains with different system parameters. The formal description of the rule detection of cryptographic functions, parameters and other information, supported by the dynamic binary analysis platform pin, dynamically records the encryption and decryption process information during the operation of the program, and realizes cross domain information sharing key security detection through the design of correlation vulnerability detection algorithm. The experimental results show that the cross-domain information shared key security detection effect of the proposed method is better, which can effectively improve the detection accuracy and shorten the detection time.

Cooccurrence of N501Y, P681R and other key mutations in SARS-CoV-2 Spike

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has produced five variants of concern (VOC) to date. The important Spike mutation N501Y is common to Alpha, Beta, Gamma and Omicron VOC, while the P681R is key to the spread of Delta. We have analysed circa 4.2 million SARS-CoV-2 genome sequences from the largest repository Global Initiative on Sharing All Influenza Data (GISAID) and demonstrated that these two mutations have cooccurred on the Spike D614G mutation background at least 3,678 times from 17 October 2020 to 1 November 2021. In contrast, the Y501-H681 combination, which is common to Alpha and Omicron VOC, is present in circa 1.1 million entries. Two-thirds of the 3,678 cooccurrences were in France, Turkey or US (East Coast), and the rest across 57 other countries. 55.5% and 4.6% of the cooccurrences were Alpha Q.4 and Gamma P.1.8 sub-lineages acquiring the P681R; 10.7% and 3.8% were Delta B.1.617.2 lineage and AY.33 sub-lineage acquiring the N501Y; the remaining 10.2% were in other variants. Despite the selective advantages individually conferred by N501Y and P681R, the Y501-R681 combination counterintuitively did not outcompete other variants in every instance we have examined. While this is a relief to worldwide public health efforts, in vitro and in vivo studies are urgently required in the absence of a strong in silico explanation for this phenomenon. This study demonstrates a pipeline to analyse combinations of key mutations from public domain information in a systematic manner and provide early warnings of spread.

Intelligent fault diagnosis using image representation of multi-domain features

Deep learning (DL) algorithms, especially the convolutional neural network (CNN), have been proven as a newly developed tool in machinery intelligent diagnosis. However, the current CNN-based fault diagnosis studies usually consider features or images extracted from a single domain as model input. This single domain information may not reflect fault patterns comprehensively, leading to low modeling accuracy and inaccurate diagnostic results. To overcome this limitation, this paper proposes a new CNN-based fault diagnosis approach using image representation considering multi-domain features of vibration signals. First, multi-domain features of vibration signals are extracted. These extracted features are then used to construct a n × n matrix, and subsequently to form images by RGB color transformations. This image transformation technique allows for capturing complementary and rich diagnostic information from multiple domains. At last, these images associated with different mechanical defects are fed into a CNN model that is improved based on the classic LeNet-5 CNN architecture for fault diagnosis and identification. Comparative experiments with the traditional feature extraction methods as well as state-of-the-art CNN-based methods are also investigated. Experimental studies on rolling bearings validate the effectiveness and superiorities of the proposed approach.

Leveraging Multimodal Out-of-Domain Information to Improve Low-Resource Speech Translation

Speech translation (ST) is a bimodal conversion task from source speech to the target text. Generally, deep learning-based ST systems require sufficient training data to obtain a competitive result, even with a state-of-the-art model. However, the training data is usually unable to meet the completeness condition due to the small sample problems. Most low-resource ST tasks improve data integrity with a single model, but this optimization has a single dimension and limited effectiveness. In contrast, multimodality is introduced to leverage different dimensions of data features for multiperspective modeling. This approach mutually addresses the gaps in the different modalities to enhance the representation of the data and improve the utilization of the training samples. Therefore, it is a new challenge to leverage the enormous multimodal out-of-domain information to improve the low-resource tasks. This paper describes how to use multimodal out-of-domain information to improve low-resource models. First, we propose a low-resource ST framework to reconstruct large-scale label-free audio by combining self-supervised learning. At the same time, we introduce a machine translation (MT) pretraining model to complement text embedding and fine-tune decoding. In addition, we analyze the similarity at the decoder side. We reduce multimodal invalid pseudolabels by performing random depth pruning in the similarity layer to minimize error propagation and use additional CTC loss in the nonsimilarity layer to optimize the ensemble loss. Finally, we study the weighting ratio of the fusion technique in the multimodal decoder. Our experiment results show that the proposed method is promising for low-resource ST, with improvements of up to +3.6 BLEU points compared to baseline low-resource ST models.

Combining data augmentation and domain information with TENER model for Clinical Event Detection

Background In recent years, with the development of artificial intelligence, the use of deep learning technology for clinical information extraction has become a new trend. Clinical Event Detection (CED) as its subtask has attracted the attention from academia and industry. However, directly applying the advancements in deep learning to CED task often yields unsatisfactory results. The main reasons are due to the following two points: (1) A great number of obscure professional terms in the electronic medical record leads to poor recognition performance of model. (2) The scarcity of datasets required for the task leads to poor model robustness. Therefore, it is urgent to solve these two problems to improve model performance. Methods This paper proposes a combining data augmentation and domain information with TENER Model for Clinical Event Detection. Results We use two evaluation metrics to compare the overall performance of the proposed model with the existing model on the 2012 i2b2 challenge dataset. Experimental results demonstrate that our proposed model achieves the best F1-score of 80.26%, type accuracy of 93% and Span F1-score of 90.33%, and outperforms the state-of-the-art approaches. Conclusions This paper proposes a multi-granularity information fusion encoder-decoder framework, which applies the TENER model to the CED task for the first time. It uses the pre-trained language model (BioBERT) to generate word-level features, solving the problem of a great number of obscure professional terms in the electronic medical record lead to poor recognition performance of model. In addition, this paper proposes a new data augmentation method for sequence labeling tasks, solving the problem of the scarcity of datasets required for the task leads to poor model robustness.