Venus Medtech (China)

The gradient coils of MRI equipment can induce vibrations in implantable medical devices, causing periodic vibrations of implantable medical devices with respect to the surrounding tissue. This not only results in instrument failure but also causes discomfort to the patient. Therefore, studying the vibration characteristics of implantable devices under different scanning sequences and the orientation of the device relative to the magnetic field is crucial for comprehending vibration performance. This study observed the vibration spectra of a full cranial bone-implanted neurostimulator by using laser vibrometry under typical rapid imaging sequences and explored the impact of different magnetic field orientations on vibration. The results demonstrated that the rapid echo sequences induced diverse and rich vibration components, whereas the planar echo sequences caused relatively simple vibrations. Additionally, the strongest vibrations normally occurred in the maximum conductive surface parallel to the phase-coded direction. It revealed the factors influencing the vibrations of skull fixation active implantable devices and provided guidance for enhancing device safety and protecting patient well-being during MR examinations.

Job recommendation aims to provide potential talents with suitable job descriptions (JDs) consistent with their career trajectory, which plays an essential role in proactive talent recruitment. In real-world management scenarios, the available JD-user records always consist of JDs, user profiles, and click data, in which the user profiles are typically summarized as the user's skill distribution for privacy reasons. Although existing sophisticated recommendation methods can be directly employed, effective recommendation still has challenges considering the information deficit of JD itself and the natural heterogeneous gap between JD and user profile. To address these challenges, we proposed a novel skill-aware recommendation model based on the designed semantic-enhanced Transformer to parse JDs and complete personalized job recommendation. Specifically, we first model the relative items of each JD and then adopt an encoder with the local-global attention mechanism to better mine the intra-job and inter-job dependencies from JD tuples. Moreover, we adopt a two-stage learning strategy for skill-aware recommendation, in which we utilize the skill distribution to guide JD representation learning in the recall stage and then combine the user profiles for final prediction in the ranking stage. Consequently, we can embed rich contextual semantic representations for learning JDs, while skill-aware recommendation provides effective JD-user joint representation for click-through rate (CTR) prediction. To validate the superior performance of our method for job recommendation, we present a thorough empirical analysis of large-scale real-world and public datasets to demonstrate its effectiveness and interpretability.

Reciprocal Recommender Systems (RRSs) which aim to satisfy the preferences of both service providers and seekers simultaneously has attracted significant research interest in recent years. Existing studies on RRSs mainly focus on modeling the bilateral interactions between the users on both sides to capture the user preferences. However, due to the presence of exposure bias, modeling user preferences solely based on bilateral interactions often lacks precision. Additionally, in RRSs, users may exhibit varying preferences when acting in different roles, and how to effectively model users from multiple perspectives remains a substantial problem. To solve the above challenges, in this paper, we propose a novel MultI-view Reciprocal Recommender system for Online Recruitment (MIRROR). Specifically, we first propose to model the users from three different views, respectively search, active, and passive views, and we further design several Transformer-based sequential models to capture the user representation corresponding to each view. Then, we propose to divide the bilateral matching process into three stages, respectively apply, reply, and match, and a multi-stage output layer is designed based on the above multi-view modeling results. To train our MIRROR model, we first design a multi-task learning loss based on the multi-stage output results. Moreover, to bridge the semantic gap between search queries and user behaviors, we additionally design a supplementary task for next-query prediction. Finally, we conduct both offline experiments on five real-world datasets and online A/B tests, and the experiment results clearly validate the effectiveness of our MIRROR model compared with several state-of-the-art baseline methods.

Recent advances in Large Language Models (LLMs) have been changing the paradigm of Recommender Systems (RS). However, when items in the recommendation scenarios contain rich textual information, such as product descriptions in online shopping or news headlines on social media, LLMs require longer texts to comprehensively depict the historical user behavior sequence. This poses significant challenges to LLM-based recommenders, such as over-length limitations, extensive time and space overheads, and suboptimal model performance. To this end, in this paper, we design a novel framework for harnessing Large Language Models for Text-Rich Sequential Recommendation (LLM-TRSR). Specifically, we first propose to segment the user historical behaviors and subsequently employ an LLM-based summarizer for summarizing these user behavior blocks. Particularly, drawing inspiration from the successful application of Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) models in user modeling, we introduce two unique summarization techniques in this paper, respectively hierarchical summarization and recurrent summarization. Then, we construct a prompt text encompassing the user preference summary, recent user interactions, and candidate item information into an LLM-based recommender, which is subsequently fine-tuned using Supervised Fine-Tuning (SFT) techniques to yield our final recommendation model. We also use Low-Rank Adaptation (LoRA) for Parameter-Efficient Fine-Tuning (PEFT). We conduct experiments on two public datasets, and the results clearly demonstrate the effectiveness of our approach.

In recent years, the rise of online Knowledge Management Systems (KMSs) has significantly improved work efficiency in enterprises. Knowledge development prediction, as a critical application within these online platforms, enables organizations to proactively address knowledge gaps and align their learning initiatives with evolving job requirements. However, it still confronts challenges in exploring the influence of collaborative networks on knowledge development and adapting to ecological situations in working environment. To this end, in this paper, we propose a Collaboration-Aware Hybrid Learning approach (CAHL) for predicting the future knowledge acquisition of employees and quantifying the impact of various knowledge learning patterns. Specifically, to fully harness the inherent rules of knowledge development, we first learn the knowledge co-occurrence and prerequisite relationships with an association prompt attention mechanism to generate effective knowledge representations through a specially-designed Job Knowledge Embedding module. Then, we aggregate the features of mastering knowledge and work collaborators for employee representations in another Employee Embedding module. Moreover, we propose to model the process of employee knowledge development via a Hybrid Learning Simulation module that integrates both collaborative learning and self learning to predict future-acquired job knowledge of employees. Finally, extensive experiments conducted on a real-world dataset clearly validate the effectiveness of CAHL.

Personality has been considered as a driving factor for work engagement, which significantly affects people’s role performance at work. Although existing research has provided some intuitive understanding of the connection between personality traits and employees’ work behaviors, it still lacks effective quantitative tools for modeling personality traits, job position characteristics, and employee work behaviors simultaneously. To this end, in this article, we introduce a data-driven joint Bayesian learning approach, Joint-PJB, to discover explainable joint patterns from massive personality and job-position-related behavioral data. Specifically, Joint-PJB is designed with the knowledgeable guidance of the four-quadrant behavioral model, namely, DISC (Dominance, Influence, Steadiness, Conscientiousness). Based on the real-world data collected from a high-tech company, Joint-PJB aims to highlight personality-job-behavior joint patterns from personality traits, job responsibilities, and work behaviors. The model can measure the matching degree between employees and their work behaviors given their personality and job position characteristics. We find a significant negative correlation between this matching degree and employee turnover intention. Moreover, we also showcase how the identified patterns can be utilized to support real-world talent management decisions. Both case studies and quantitative experiments verify the effectiveness of Joint-PJB for understanding people’s personality traits in different job contexts and their impact on work behaviors.

Text similarity is an important taskin natural language processing. The pre-training BERT model which is get from through large-scale corpus traininghas achieved good results in various natural language processing tasks. However, domain knowledge is not introduced to the model. After the post-training through domain data, the bias of the model for the domain knowledge will be reduced, which improves performance in reading comprehension and emotional aspect extraction. In this paper, the domain knowledge is introduced through the post-training andthen text similarity is discussed.

With the rapid development of social network analysis (SNA for short), people increasingly pay attention to segment micro-blog users in the SNAs. It's a new trend on classic marketing technique segmentation. In the case of micro-blog, it's useful to get a group of users with a common set of characters and learn what's on their mind. As is usually the case, the standard for measuring the category of the micro-blog users is multi-objective, i.e., the data is high dimensional. If you have a personal micro-blog account, it's easy enough to create the lists that might be most meaningful to you by using generic clustering algorithms. And if your business has Tens of millions of users, the near real-time requirement and the lack of efficient clustering algorithms to identify and distinguish them limits the power and scalability of this approach. To overcome these limitations, in this paper we introduce a novel distributed high dimensional data clustering algorithm based on Map-Reduce framework to distinguish the different communities from the entire social network, called CDGM-Clu. Extensive experiments on real and synthetic datasets show that the CDGM-Clu algorithm is significantly efficient and scalable, and useful for analyzing a large social network data.

Some applications of the technology of mobile agent (MA) in intrusion detection system (IDS) have been developed. MA technology can bring IDS flexibility and enhanced distributed detection ability. However, the security of mobile agents and methods of collaboration among mobile agents are important problems cared by many researchers. For that, we designed a security mobile agent system for distributed intrusion detection and implemented a prototype. In this paper, we firstly analyze the shortcomings of current IDSs and discuss the state of the art for applying MA technology in IDS. Then we present our MA-IDS architecture and detail methods of local intrusion detection and distributed intrusion detection. The structure and security architecture of MAs are expatriated emphatically in Section 3. Finally we demonstrate the advantages of our MA-IDS architecture and our future research contents.