Hui Fu’s research while affiliated with Academy of Technical Industrial Engineering and other places

... In 2022 Song [7] et al. invented a bed-mounted breast puncture system and a unique grid-like breast support device for limiting breast deformation and improving accuracy during puncture in the prone position. In 2023 Rao et al [8] designed a 5-DOFs hybrid puncture robot for MRI-guided breast puncture procedures, which was also bed-mounted and consisted of a series-parallel hybrid mechanism and a 2-DOFs needle delivery module. Zhang et al [9] at Harbin University of Science and Technology have also developed a series of breast puncture robots, such as the 2020 design of a bedmounted breast puncture robot with a novel pitching mechanism mechanism that enables dexterous operation in a limited space. ...

Reference:

Structural Design and Needle Deflection Prediction of Body-Mounted Breast Puncture Robot Modeled After a Compass

... Within the digital realm, a mechanical analysis model is crafted to enhance operational awareness and safety across the bridge network within the regional transportation framework, significantly bolstering the development of an intelligent transportation system. In the realm of innovative smart highways, ref. [88] forged a framework and operational protocol for smart freeways enabled by DTs. By amalgamating control mechanisms from both upstream urban networks and traffic management of freeway segments, the effectiveness of the proposed strategies for freeway control was confirmed, advancing the evolution of smart highway systems. ...

Reference:

Digital Twin Technology in Transportation Infrastructure: A Comprehensive Survey of Current Applications, Challenges, and Future Directions

... In the literature, various algorithms have been applied in the preliminary partitioning of road networks. [3,17,18] The random walk algorithm has been applied to various fields, including image segmentation. [19] One advantage of random walk algorithm lies in that it can maintain correlation of partition results over time, because the result will strongly depend on the initial location of random walkers. ...

Reference:

Dynamic partition of urban network considering congestion evolution based on random walk

... Zone division could be helpful in handling the heterogeneity during the analysis [6]. Furthermore, the management strategies could be specifcally designed for diferent parts in the study area with consideration of their special characteristics [7,8]. ...

Reference:

A Bus-Service-Based Zone Division Approach for the Spatial Analysis of Public Bus: A Case Study in South China

... Subsequently, Geroliminis and Daganzo (2008) confirmed the existence of a well-defined and demand-insensitive MFD through empirical studies. Currently, MFD models are extensively applied in developing network-level traffic control strategies including perimeter control (Aalipour et al., 2018;Geroliminis et al., 2012;, route guidance Fu et al., 2021;, congestion pricing (Daganzo & Lehe, 2015;Y. Li & Ramezani, 2022;Zheng et al., 2012), and parking pricing (Gu et al., 2020;W. ...

Reference:

A flexible road network partitioning framework for traffic management via graph contrastive learning and multi‐objective optimization

... This raises the pertinent question of which particular feature engineering method proves most effective in the context of clinical and multiomics datasets. A thorough analysis of feature engineering methods and their applicability with respect to clinical and multiomics datasets reveals that methods like Cox regression, CCA, AIC, and ANOVA have been quite widely utilized in studies involving only clinical data 29,67,114,118 . These methods have been applied to clinical data for multiple reasons for instance, such methods are interpretable which is important to gain meaningful insights for healthcare professionals. ...

Reference:

Survival Prediction Landscape: An In-Depth Systematic Literature Review on Activities, Methods, Tools, Diseases, and Databases

... (3) Duration of tinnitus < 3 months. All participants were required to sign an informed consent form (Mai et al. 2021). ...

Reference:

EEG signal classification of tinnitus based on SVM and sample entropy

... These events are generally characterized by their suddenness, urgency, and potential hazards. Current research on human-made disasters primarily concentrates on the characteristics of emergency evacuation behavior [14][15][16], emergency evacuation simulations [17,18], and the optimization of emergency evacuation routes [19,20]. Notably, the research on evacuation route optimization tends to focus on addressing variants of the VRP through heuristic algorithms, as well as examining the characteristics of emergency evacuations through simulation. ...

Reference:

Urban Emergency Evacuation Path Optimization Based on Uncertain Environments to Enhance Response for Symmetric and Asymmetric Evacuation Problems

... The varying natural environments and traffic conditions [11] [12] [13] leverages GPS to address multiple issues related to traffic safety and efficiency. For instance, by monitoring the movement patterns and speed variations of buses, abnormal driving behaviors can be detected, e.g., abnormal driving behaviors [14] [15], over speeding [16], the deviation from the predetermined route [17] [18] [19], and black spots identification [20]. ...

Reference:

Unsupervised Abnormal Stop Detection for Long Distance Coaches with Low-Frequency GPS

... Data fusion involves integrating multiple data sources, such as LDD (Geroliminis and Daganzo 2008;Gayah and Daganzo 2011;Geroliminis and Sun 2011;Mahmassani et al. 2013;Leclercq et al. 2014;Saberi et al. 2014;Tsubota et al. 2014;Ambühl and Menendez 2016;Du et al. 2016;Ambühl et al. 2017;Shim et al. 2019), FCD (Geroliminis and Sun 2011; Leclercq et al. 2014;Tsubota et al. 2014;Ambühl et al. 2017), and public transport data (PTD) (Geroliminis et al. 2014;Loder et al. 2017;Huang et al. 2019;Fu et al. 2020), to provide more accurate NMFD estimations by addressing the biases present in individual data sources. The challenges with LDD are the heterogeneous spatial distribution within the network, link selection, and the uneven relative positioning to the nearest intersection (Leclercq et al. 2014). ...

Reference:

Estimating Spatial Mean Speeds from Local Sensors: A Machine-Learning Approach