The rapid development of deep learning models that can produce and synthesize hyper-realistic videos are known as DeepFakes. Moreover, the growth of forgery data has prompted concerns about malevolent intent usage. Detecting forgery videos are a crucial subject in the field of digital media. Nowadays, most models are based on deep learning neural networks and vision transformer, SOTA model with EfficientNetB7 backbone. However, due to the usage of excessively large backbones, these models have the intrinsic drawback of being too heavy. In our research, a high performance DeepFake detection model for manipulated video is proposed, ensuring accuracy of the model while keeping an appropriate weight. We inherited content from previous research projects related to distillation methodology but our proposal approached in a different way with manual distillation extraction, target-specific regions extraction, data augmentation, frame and multi-region ensemble, along with suggesting a CNN-based model as well as flexible classification with a dynamic threshold. Our proposal can reduce the overfitting problem, a common and particularly important problem affecting the quality of many models. So as to analyze the quality of our model, we performed tests on two datasets. DeepFake Detection Dataset (DFDC) with our model obtains 0.958 of AUC and 0.9243 of F1-score, compared with the SOTA model which obtains 0.972 of AUC and 0.906 of F1-score, and the smaller dataset Celeb-DF v2 with 0.978 of AUC and 0.9628 of F1-score.

Vietnam is one of the developing countries and people’s lives depend on agricultural production for 80% of the economy. Global climate change has been seriously affecting agricultural production in Vietnam and agricultural countries around the world. Farmers work agriculture manually and lack a scientific basis, so irrigation and fertilization often waste resources, increasing unnecessary costs. Meanwhile, water resources are increasingly depleted and degraded due to climate change, and the quality of agricultural production is affected. Therefore, agricultural production needs to be improved, the authors research and combine technologies in agricultural production such as IoT, smart sensors, MQTT, intelligent pumping systems, using edge computing to design automatic or semi-automatic irrigation systems to support farmers in crop care, saving costs and increasing labor productivity. In this article, we experimented with the system on cantaloupe, with a timer program for drip irrigation and fertilizer application for plants through formula settings. Mobile, desktop, and nutrient control charting software were designed for easy monitoring, manipulation, control, and administration functions are integrated into the system. We designed the Anomaly detector model with Google Firebase cloud messaging technology to detect environmental anomalies such as PH, EC, and sprinkler pressure to automatically send alerts and reports to smart devices.

Purpose: Drawing from a resource-based perspective in the work–family interface literature, the current study examines how emotional exhaustion, as a resource depletion mechanism, mediates the relationship between family–work conflict and job satisfaction. The authors also considered the content and nature of coworker support to investigate whether there were differential moderating effects of the two distinct types of coworker support: emotional and instrumental support.Design/methodology/approach: The authors surveyed 321 kindergarten employees across multiple sites located in South Korea. Using this sample, the authors performed random coefficient modeling to test the proposed research model.Findings: The results showed a significant negative indirect relationship between family–work conflict and job satisfaction through emotional exhaustion. Furthermore, the findings suggested differential effects of the two coworker support types, such that the positive relationship between family–work conflict and emotional exhaustion was stronger when coworker emotional support was low than when it was high; the positive relationship was stronger when coworker instrumental support was high than when it was low. Moderated mediation analyses revealed that the two types of coworker support moderated the indirect relationship.Originality/value: These results highlight the mixed blessing of distinct types of coworker support for researchers and practitioners. A lack of emotional support and greater instrumental support from coworkers each, respectively, exacerbate the negative impact of family–work conflict on employees' well-being and, subsequently, job satisfaction.

Although point cloud segmentation has a principal role in 3D understanding, annotating fully large-scale scenes for this task can be costly and time-consuming. To resolve this issue, we propose Point Central Transformer (PointCT), a novel end-to-end trainable transformer network for weakly-supervised point cloud semantic segmentation. Divergent from prior approaches, our method addresses limited point annotation challenges exclusively based on 3D points through central-based attention. By employing two embedding processes, our attention mechanism integrates global features across neighborhoods, thereby effectively enhancing unlabeled point representations. Simultaneously, the interconnections between central points and their distinct neighborhoods are bidirectional cohered. Position encoding is further applied to enforce geometric features and improve overall performance. Notably, PointCT achieves outstanding performance under various labeled point settings without additional supervision. Extensive experiments on public datasets S3DIS, ScanNet-V2, and STPLS3D demonstrate the superiority of our proposed approach over other state-of-the-art methods.

Purpose: This study aims to use the voice of the customer (VoC) strategy to collect user-generated content (UGC) compare customer expectations with reality, make the necessary improvements for the business and create personalized strategies for each customer to maximize revenue, focus on hospitality industry in Vietnam market.Design/methodology/approach: This study proposes a synthesis of techniques for a deep understanding of the VoC based on online reviews in the hospitality industry. First, 409,054 comments were collected from websites in the hospitality sector. Second, the data will be organized, stored, cleaned, analyzed and evaluated. Next, research using business intelligence (BI) solutions integrating three models, including net promoter score (NPS), graph model and latent Dirichlet allocation (LDA), based on natural language processing (NLP) technique, experiment on Vietnamese and English data to explore the multidimensional voice of customer’s row. Finally, a dashboard system will be implemented to visualize analysis results and recommendations on marketing strategies to improve product and service quality.Findings: Experimental results allow analysts and managers to “listen to the customer’s voice” accurately and effectively, identify relationships between entities, topics of discussion in favor of positive and negative trends.Originality/value: The novelty in this study is the integration of three models, including NPS, graph model and LDA. These models are combined based on the BI solution and NLP technique. The study also conducted experiments on both Vietnamese and English languages, which ensures more effective practical application.