With the proliferating of video surveillance system deployment and related applications, real-time video analysis is very critical to achieve intelligent monitoring, autonomous driving, etc. It is non-trivial to achieve high accuracy and low latency video stream analysis through the traditional cloud computing. In this paper, we propose a non-orthogonal multiple access (NOMA) based edge real-time video analysis framework with one edge server (ES) and multiple user equipments (UEs). A cost minimization problem composed of delay, energy and accuracy is formulated to improve the QoE of UEs. In order to efficiently solve this problem, we propose the joint video frame resolution scaling, task offloading, and resource allocation algorithm based on the Deep Q-Learning Network (JVFRS-TO-RA-DQN), which effectively overcomes the sparsity of the single-layer reward function and accelerates the training convergence speed. JVFRS-TO-RA-DQN consists of two DQN networks to reduce the curse of dimension, which respectively select the offloading and resource allocation action, the resolution scaling action. Experimental results show that JVFRS-TO-RA-DQN can effectively reduce the cost of transmission and computation, and have better performance in convergence compared to other baseline.

In recent decades, with the ever-growing scale of video data, near-duplicate videos continue to emerge. Data quality issue caused by near-duplicate videos is becoming more and more prominent, which has affected the application of normal videos. Although current studies on near-duplicate video detection can be helpful to uncover data quality issues for videos, they still lack a process of automatic merging for the video data represented by high-dimensional features, which are difficult to automatically clean the near-duplicate videos to improve data quality for video datasets. At present, there are few studies on near-duplicate video data cleaning. The existing studies have the sensitive problems of video data orderliness and clustering initial center under a condition that prior distribution is unknown, which seriously affect the accuracy of near-duplicate video data cleaning. To address the above issues, an automatic near-duplicate video data cleaning method based on a consistent feature hash ring is proposed in this paper. First, a residual network with convolutional block attention modules, a long short-term memory deep network, and an attention model are integrated to construct an RCLA deep network with the multi-headed attention mechanism to extract spatiotemporal features of video data. Then, a consistent feature hash ring is constructed, which can effectively alleviate the sensitivity of video data orderliness while providing a condition of near-duplicate video merging. To reduce the sensitivity of the initial cluster centers to results of near-duplicate video cleansing, an optimized feature distance-means clustering algorithm is constructed by utilizing a mountain peak function on a consistent feature hash ring, which can implement automatic cleaning of near-duplicate video data. Finally, experiments are conducted based on a commonly used dataset named CC_WEB_VIDEO and a coal mining video dataset. Compared with some existing works, simulation results demonstrate that the performance of the proposed method.

Single-phase-to-ground fault in non-effectively grounded systems poses serious public safety concern. Along with increasing deployment of low-voltage (LV) sensors, new opportunities and ways are created for solving this traditional problem in distribution systems. A new approach, identifying primary single-phase-to-ground line fault and locating it through measurement data from smart sensors deployed in the secondary side of distribution transformers, is proposed in this paper. When a fault occurs in primary distribution feeder, the transient aerial mode voltage (AMV) of each LV smart sensor is calculated. The fault line can be identified by an abrupt change value of AMV at LV side. Next, by finding the position of the maximum value of this AMV from LV sensors on the fault line, the fault location can be pinpointed to two neighboring distribution transformers. The proposed method has been proven to be efficient and reliable by simulation studies.

Field of ResearchThis research study investigates the role of distributed leadership and culture within small enterprises in Malta, an area in which there has been very limited research. It focuses on the interaction between these two elements and their impact on organizational behaviour and effectiveness. Several studies (Jardon et al 2019; Cope et al., 2011; de Oliveira et al., 2015; Mohanty et al., 2012;) suggest that effective leadership and culture are vital elements in the successful endeavours of small organizations. Schein (2006) further asserts that they are two different faces on the same coin and the dyadic interaction characterizes “how leaders create culture and how culture defines and creates leaders”. Distributed Leadership is a systematic practice of interactions and synergies between leaders, followers, and the situation (Spillane 2013). It is different from traditional leadership, which involves top-down management because it tends to be more democratic and participatory, whereby influence and decision-making are shared among multiple individuals rather than being controlled by a single leader. (Xhemajli et al. 2022) MethodologyAdopting a naturalistic approach and guided by an interpretivist, constructivist epistemological stance, this research delves into the intricate interplay between leadership and culture within small businesses. The chosen research methodology employs Grounded Theory, recognized for its robust and systematic process facilitating the observation of patterns through intensive iterative and highly analytical procedures (Charmaz, 2015).In the initial stages of field research, characterized by 'responsive interviewing' (Rubin and Rubin, 2012), data sampling commenced with convenience sampling. This initial phase gradually evolved into a refined strategy incorporating selective sampling and theoretical sampling (Corbin and Strauss, 2015). The shift in sampling approaches reflects a deliberate focus on collecting data based on its specific contribution to the development and comprehension of the dimensions, properties, and characteristics of key concepts.The induction of theory is a product of successive comparative analyses, involving the systematic comparison of data points to identify both similarities and variations. Abductive reasoning is integral throughout the analytical process, with particular emphasis during constant comparative analysis of categories, leading to theoretical integration (Charmaz, 2006). This meticulous approach aligns with the assertion of Strauss and Corbin (2015) that grounding theory in data enhances the likelihood of deriving theories that authentically reflect reality.The key advantage of using this approach is that the analysis carried out goes beyond deep exploration and rich description and actually develops a framework that explains the phenomena observed (Parker and Roffey, 1997, p.218). This is very important if the findings are to contribute to the knowledge enhancement of any field of practiceThe culmination of this research effort is the presentation of a set of interconnected concepts, intricately woven together into an emergent parsimonious model (Corbin and Strauss, 2015). This model serves to explain the dynamic interplay between leadership and culture, elucidating its tangible impact on the effectiveness of small enterprises. Research Contribution:Implications for PracticeThis research contributes to the literature on leadership and organizational culture in small enterprises, particularly in the context of Malta where such studies are scarce. By providing an initial exploration of these phenomena and their impact on organizational behavior, this paper lays the groundwork for further inquiry into this important area. Furthermore, the study offers practical insights for leaders of small enterprises by elucidating leadership behaviors observed in established organizations. Through applied cases, it demonstrates how the abstract concept of culture can be translated into a practical instrument that supports leadership and organizational development. This not only enriches the understanding of leadership dynamics but also provides tangible strategies for implementation. Moreover, the research contributes empirical evidence on the development of leadership functions within small enterprises, emphasizing the potential of shared and distributed leadership models. By grounding its findings in data, the study equips leaders with a deeper understanding of how these leadership approaches can shape organizational development, fostering more effective management practices in small businesses. Methodologically, the adoption of Grounded Theory methodology showcases its efficacy in exploring complex management phenomena. By employing this approach, the researchers were able to gather rich descriptions and develop an explanatory framework, highlighting its applicability in studying nuanced organizational dynamics. Implications for Policy and TheoryThis research also holds significant implications for policymakers, academic researchers and institutions involved in supporting small businesses. By providing insights into distributed leadership and cultural influences on organizational effectiveness, it offers a basis for informed policy formulation and support mechanisms. The conceptual model emerging from this study serves as a foundation for designing more targeted policies that cater to the unique needs of small enterprises. By understanding the intricacies of leadership dynamics and cultural contexts, policymakers can develop interventions that foster a conducive environment for small business growth and sustainability. Additionally, academic researchers can use these findings to further refine theoretical frameworks and empirical studies in the field, contributing to ongoing scholarly dialogue and knowledge advancement.

In recent years, the scientific and technological developments led to an explosion of available videos on the web, increasing the necessity of fast and effective video analysis and summarization. Video summarization methods aim to generate a synopsis by selecting the most informative parts of the video content. The user’s personal preferences, often involved in the expected results, should be taken into account in the video summaries. In this paper, we provide the first comprehensive survey on personalized video summarization relevant to the techniques and datasets used. In this context, we classify and review personalized video summary techniques based on the type of personalized summary, on criteria, on the video domain, on the source of information, on the time of summarization, and on the machine learning technique. Depending on the type of methodology used by the personalized video summarization techniques for the summary production process, we classify the techniques into five major categories, which are feature-based video summarization, key frame selection, shot selection-based approach, video summarization using trajectory analysis, and personalized video summarization using clustering. We also compare personalized video summarization methods and present 37 datasets used to evaluate personalized video summarization methods. Finally, we analyze opportunities and challenges in the field and suggest innovative research lines.

Short video addiction refers to a psychological dependency on short video applications, characterized by an intense attachment and an inability to control usage, leading to typical addiction symptoms. While its definition bears similarities to substance addiction, significant differences also exist. According to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5), published in 2013, short video addiction has not yet been officially classified as an addiction disorder. To facilitate more in-depth and standardized research on short video addiction, it is essential to synthesize and organize existing studies on its theoretical foundations and mechanisms.

To assess the usefulness of an attachable video laryngoscope (AVL) by attaching a camera and monitor to a conventional Macintosh laryngoscope (CML). Normal and tongue edema airway scenarios were simulated using a manikin. Twenty physicians performed tracheal intubations using CML, AVL, Pentax AWS® (AWS), and McGrath MAC® (MAC) in each scenario. Ten physicians with more than 10 cases of clinical experience with tracheal intubation using CML were included in the skilled group. Ten physicians with less than 10 cases of clinical experience with tracheal intubation using CML were included in the unskilled groups. The time required to intubate and the success rate were recorded. The degree of difficulty of use and glottic view assessment scored by participants. All 20 participants successfully completed the study. There was no difference in the success rate and time required for tracheal intubation in the normal airway scenarios. For the skilled group, in the tongue edema airway scenario, the AWS had the highest success rate (100%) followed by AVL (60%), MAC (60%), and CML (20%) (p = 0.001). The time required to intubate with the AWS was significantly shorter than with AVL (10.2 vs 22.3 s; p=0.002) or MAC (10.2 vs 23.7 s; p=0.001). There was no significant (p > 0.05) difference between AVL and MAC. The degree of Difficulty of Use for AVL was significantly lower than that for CML (7.8 vs 2.8; p < 0.001). There was no significant (p > 0.05) difference between AVL and other video laryngoscopes. AVL had a higher rate of successful tracheal intubation than CML in the tongue edema scenario. AVL showed a similar success rate and time of tracheal intubation to the MAC. Therefore, AVL may be a possible alternative video laryngoscope device.

Accurate traffic simulation models play a crucial role in developing intelligent transport systems that offer timely traffic information to users and efficient traffic management. However, calibrating these models to represent real-world traffic conditions accurately poses a significant challenge due to the dynamic nature of traffic flow and the limitations of traditional calibration methods. This article introduces a machine learning-based approach to calibrate macroscopic traffic simulation models using real-time traffic video stream data. By leveraging computer vision technologies to extract key traffic parameters from video streams, the approach demonstrated a notable improvement in aligning the generated data from the calibrated simulation model with car sensor data, achieving an average improvement of over 50% compared to the uncalibrated macroscopic model. Moreover, there was a substantial reduction in data drift for the machine learning model integrated into the virtual transport space using vehicle-to-everything technology, resulting in a more than fourfold decrease in the average absolute error of the model.