Competitive Performance Research Articles

Enhancing Integrated Sensing and Communication (ISAC) Performance for a Searching–Deciding Alternation Radar-Comm System with Multi-Dimension Point Cloud Data

In developing modern intelligent transportation systems, integrated sensing and communication (ISAC) technology has become an efficient and promising method for vehicle road services. To enhance traffic safety and efficiency through real-time interaction between vehicles and roads, this paper proposes a searching–deciding scheme for an alternation radar-communication (radar-comm) system. Firstly, its communication performance is derived for a given detection probability. Then, we process the echo data from real-world millimeter-wave (mmWave) radar into four-dimensional (4D) point cloud datasets and thus separate different hybrid modes of single-vehicle and vehicle fleets into three types of scenes. Based on these datasets, an efficient labeling method is proposed to assist accurate vehicle target detection. Finally, a novel vehicle detection scheme is proposed to classify various scenes and accurately detect vehicle targets based on deep learning methods. Extensive experiments on collected real-world datasets demonstrate that compared to benchmarks, the proposed scheme obtains substantial radar performance and achieves competitive communication performance.

Deep Learning-Based Liver Vessel Segmentation

Abstract Liver vessel segmentation in computed tomography represents a highly challenging task due to the imbalanced distribution within the liver parenchyma, the small and branched vessels with decreased image contrast to surrounding tissue and in general, due to the scarcity of highresolution and -contrast images, which hampers the efficient training of deep learning-based approaches. This study applies two state-of-the-art networks, the fully convolutional nnUnet and the transformer-based VT-Unet to three publicly available datasets, 3DIRCADb, one task of the Medical Segmentation Decathlon (MSD) and the more recent LiVS dataset. The nnUnet achieved Dice scores of 0.761, 0.714, and 0.696 on the 3DIRCADb, LiVS, and MSD datasets, respectively. In contrast, the experiments with the VT-UNet resulted in Dice scores of 0.795, 0.713, and 0.610. These findings indicates good accordance of the performance of the nnUnet and the transformer-based VT-Unet, with differences regarding individual datasets. Both network variants show competitive performances regarding the current state-of-the-art, yet the need for large-scale and high-quality datasets becomes evident to further enhance the accuracy of liver vessel segmentation.

Frequency domain task-adaptive network for restoring images with combined degradations

Image restoration seeks to obtain a high-quality image by eliminating degradations. While existing methods have shown remarkable performance in image restoration, the majority are designed for single degradation. However, in the real world, environmental factors are complex and variable, leading to images with combined degradation factors—like the simultaneous presence of rain, noise, and haze in a single image. This complexity poses a challenge for existing methods to be effectively applied in real-world scenes. In this paper, we propose a frequency domain-based network for adaptively restoring images with various combinations of degradation factors. Specifically, we design a frequency domain-based gate block (FDGB) to selectively determine which low and high-frequency information should be preserved, choosing the most informative components for recovery. Additionally, we develop a task adaptive block (TAB) composed of FDGBs and frequency domain-based re-weight blocks (FDRBs) to adaptively restore various combined degraded images. FDRB ensures that the TAB can explore various combinations of FDGBs by utilizing a gating mechanism to re-weight the output features of FDGB based on the input signals. Finally, we introduce a Fast Fourier Block (FFB) to enrich the feature set and provide collaborative refinement for the FDGB. To facilitate the training of our proposed method, we create a dataset with various combinations of degradation factors. The resulting tightly interlinked architecture, named as FDTANet, extensive experiments demonstrate that our approach excels not only in restoring images afflicted with combined degradations but also demonstrates competitive performance when compared to state-of-the-art models for single-degradation restoration. The code and the pre-trained models are released at https://github.com/Tombs98/FDTANet/.

An Efficient Robotic Pushing and Grasping Method in Cluttered Scene.

Pushing and grasping (PG) are crucial skills for intelligent robots. These skills enable robots to perform complex grasping tasks in various scenarios. These PG methods can be categorized into single-stage and multistage approaches. Single-stage methods are faster but less accurate, while multistage methods offer high accuracy at the expense of time efficiency. To address this issue, a novel end-to-end PG method called efficient PG network (EPGNet) is proposed in this article. EPGNet achieves both high accuracy and efficiency simultaneously. To optimize performance with fewer parameters, EfficientNet-B0 is used as the backbone of EPGNet. Additionally, a novel cross-fusion module is introduced to enhance network performance in robotic PG tasks. This module fuses and utilizes local and global features, aiding the network in handling objects of varying sizes in different scenes. EPGNet consists of two branches dedicated to predicting PG actions, respectively. Both branches are trained simultaneously within a Q-learning framework. Training data is collected through trial and error, involving the robot performing PG actions. To bridge the gap between simulation and reality, a unique PG dataset is proposed. Additionally, a YOLACT network is trained on the PG dataset to facilitate object detection and segmentation. A comprehensive set of experiments is conducted in simulated environments and real-world scenarios. The results demonstrate that EPGNet outperforms single-stage methods and offers competitive performance compared to multistage methods, all while utilizing fewer parameters. A video is available at https://youtu.be/HNKJjQH0MPc.

Geometry-Augmented Molecular Representation Learning for Property Prediction.

Accurate molecular representation plays a crucial role in expediting the process of drug discovery. Graph neural networks (GNNs) have demonstrated robust capabilities in molecular representation learning, adept at capturing structural and spatial information in molecular graphs. For molecular representation learning, most previous GNN methods are specialized in dealing with 2D or 3D molecular data formats. By further fusing the geometric attributes and structural features of molecules, we can elevate the performance of molecular representation. To realize this, we present a novel geometry-augmented molecular representation learning model, designed to effectively encode both the 2D structural and 3D spatial information inherent in molecular graphs. By incorporating structural and spatial information as attention biases in the graph Transformer framework, our model offers a comprehensive architecture that introduces molecular structural details at both atom and bond levels. We further propose a geometry information fusion module to encode the geometry information within 3D molecular graphs. The experimental results show the efficacy of our model, demonstrating its ability to achieve competitive performance when compared to state-of-the-art (SOTA) models in various property prediction tasks.

ResGAT: Residual Graph Attention Networks for molecular property prediction

Molecular property prediction is an important step in the drug discovery pipeline. Numerous computational methods have been developed to predict a wide range of molecular properties. While recent approaches have shown promising results, no single architecture can comprehensively address all tasks, making this area persistently challenging and requiring substantial time and effort. Beyond traditional machine learning and deep learning architectures for regular data, several deep learning architectures have been designed for graph-structured data to overcome the limitations of conventional methods. Utilizing graph-structured data in quantitative structure–activity relationship (QSAR) modeling allows models to effectively extract unique features, especially where connectivity information is crucial. In our study, we developed residual graph attention networks (ResGAT), a deep learning architecture for molecular graph-structured data. This architecture is a combination of graph attention networks and shortcut connections to address both regression and classification problems. It is also customizable to adapt to various dataset sizes, enhancing the learning process based on molecular patterns. When tested multiple times with both random and scaffold sampling strategies on nine benchmark molecular datasets, QSAR models developed using ResGAT demonstrated stability and competitive performance compared to state-of-the-art methods.

Deep active learning with high structural discriminability for molecular mutagenicity prediction

The assessment of mutagenicity is essential in drug discovery, as it may lead to cancer and germ cells damage. Although in silico methods have been proposed for mutagenicity prediction, their performance is hindered by the scarcity of labeled molecules. However, experimental mutagenicity testing can be time-consuming and costly. One solution to reduce the annotation cost is active learning, where the algorithm actively selects the most valuable molecules from a vast chemical space and presents them to the oracle (e.g., a human expert) for annotation, thereby rapidly improving the model’s predictive performance with a smaller annotation cost. In this paper, we propose muTOX-AL, a deep active learning framework, which can actively explore the chemical space and identify the most valuable molecules, resulting in competitive performance with a small number of labeled samples. The experimental results show that, compared to the random sampling strategy, muTOX-AL can reduce the number of training molecules by about 57%. Additionally, muTOX-AL exhibits outstanding molecular structural discriminability, allowing it to pick molecules with high structural similarity but opposite properties.

A dual-region speech enhancement method based on voiceprint segmentation

Single-channel speech enhancement primarily relies on deep learning models to recover clean speech signals from noise-contaminated speech. These models establish a mapping relationship between noisy and clean speech. However, considering the sparse distribution characteristics of speech energy across the entire time–frequency spectrogram, constructing the mapping relationship from noisy to clean speech exhibits significant differences in regions where speech energy is concentrated and non-concentrated. Utilizing one deep model to simultaneously address these two distinct regression tasks increases the complexity of the mapping relationships, consequently restricting the model’s performance. To validate our hypothesis, we propose a dual-region speech enhancement model based on voiceprint region segmentation. Specifically, we first train a voiceprint segmentation model to classify noisy speech into two regions. Subsequently, we establish dedicated speech enhancement models for each region, with the dual-region models concurrently constructing mapping relationships for noise-corrupted speech to clean speech in distinct regions. Finally, by merging the results, the complete restored speech can be obtained. Experimental results on public datasets demonstrate that our method achieves competitive speech enhancement performance, outperforming the state-of-the-art. Ablation study results confirm the effectiveness of the proposed approach in enhancing model performance.

GlobalSR: Global context network for single image super-resolution via deformable convolution attention and fast Fourier convolution

Vision Transformer have achieved impressive performance in image super-resolution. However, they suffer from low inference speed mainly because of the quadratic complexity of multi-head self-attention (MHSA), which is the key to learning long-range dependencies. On the contrary, most CNN-based methods neglect the important effect of global contextual information, resulting in inaccurate and blurring details. If one can make the best of both Transformers and CNNs, it will achieve a better trade-off between image quality and inference speed. Based on this observation, firstly assume that the main factor affecting the performance in the Transformer-based SR models is the general architecture design, not the specific MHSA component. To verify this, some ablation studies are made by replacing MHSA with large kernel convolutions, alongside other essential module replacements. Surprisingly, the derived models achieve competitive performance. Therefore, a general architecture design GlobalSR is extracted by not specifying the core modules including blocks and domain embeddings of Transformer-based SR models. It also contains three practical guidelines for designing a lightweight SR network utilizing image-level global contextual information to reconstruct SR images. Following the guidelines, the blocks and domain embeddings of GlobalSR are instantiated via Deformable Convolution Attention Block (DCAB) and Fast Fourier Convolution Domain Embedding (FCDE), respectively. The instantiation of general architecture, termed GlobalSR-DF, proposes a DCA to extract the global contextual feature by utilizing Deformable Convolution and a Hadamard product as the attention map at the block level. Meanwhile, the FCDE utilizes the Fast Fourier to transform the input spatial feature into frequency space and then extract image-level global information from it by convolutions. Extensive experiments demonstrate that GlobalSR is the key part in achieving a superior trade-off between SR quality and efficiency. Specifically, our proposed GlobalSR-DF outperforms state-of-the-art CNN-based and ViT-based SISR models regarding accuracy-speed trade-offs with sharp and natural details.

Reshaping of Global Shipping Dynamics: Implications for Strategic Resilience Capabilities, Marketing Capabilities, Supply Chain Orientation Capabilities and Port Competitiveness in Indonesia

The phenomenon of dynamic maritime environment have affected port business and it is substantially changing the business environment in which large-scale container trade growth is being facilitated. In this paper will illustrate the dynamic features of port users, discuss the port competition strategy and analyse the marketing strategic for port business under transformation phases. Using qualitative methods using case studies through a literature review and empirical evidence to prove, deepen and expand the results of the study. In this article, we develop and examine the implication such marketing capabilities approach to the effectiveness of the marketing strategies and strategic resilience capabilities to determine sustainable competitive performance. Based on a discussion among with its managements, this paper could prove a conceptual framework in which strategic resilience capabilities and supply chain orientation capabilities have a profound impact on the company’s sustainable competitive performance.

CosineTR: A dual-branch transformer-based network for semantic line detection

Semantic line is a straight line based representation designed to well capture the spatial layout or structural shape of the scene in an image that is valuable as a high-level visual property. In this paper, we propose an efficient end-to-end trainable semantic line detection model named Complementary semantic line TRansformer (CosineTR), which is designed according to an old proverb “two heads are better than one”. CosineTR adopts a dual-branch framework to detect semantic lines with a coarse to fine strategy. These two branches are built based on well-designed attention modules to capture multi-scale line semantic features locally and globally, and are equipped with heatmap prediction head and parameter regression head respectively to perform semantic line detection from two different perspectives. In addition, we introduce bilateral region attention and Gaussian prior cross-attention modules to reinforce semantic contexts extracted by the two branches, and couple them to form complementary feature representations by leveraging a feature interaction method. Extensive experiments demonstrate that our approach is effective and achieves competitive semantic line detection performance on multiple datasets.

Lean Management and Firms Competitive Advantage

This study focused on lean management and firms' competitive advantage in Akwa Ibom State. Two hypotheses and two research questions were developed for the study, using a survey methodology. The population consisted of 59 employees in top management, middle management, and lower management positions at particular manufacturing companies in the state of Akwa Ibom. Utilizing census techniques, data on the total population was gathered. The two hypotheses were tested at the 0.05 level of significance using the Ordinal Regression Tool Analysis. The findings indicated that the Lean Management dimension (employee involvement: 8.298, PV = 0.003; Just-in-Time: 7.246, PV = 0.002) and firms' competitive advantage in Akwa Ibom State were significantly correlated. Just-in-time and employee involvement are relational characteristics that might improve enterprises' competitive advantage and organizational performance in Akwa Ibom State. The study’s management was advised to improve their policies to support manufacturing and operations by figuring out what the customer values, mapping out the value stream the complete sequence of steps necessary to deliver a good or service—and analyzing the value stream to find and get rid of wasteful practices like overproduction, waiting times, needless motion, defects, and excess inventory. To boost overall cost efficiency, it was also advised that manufacturing companies integrate waste elimination into their operational processes.

Impact of sustainable supply chain management practices on competitive advantage and organizational performance in the manufacturing sector

Impact of sustainable supply chain management practices on competitive advantage and organizational performance in the manufacturing sector

Dynamic and static mutual fitting for action recognition

Action recognition is intended to classify a video into a certain category by aggregating and summarizing its temporal and spatial information. Existing methods have achieved remarkable performance on the standard datasets. However, how to accurately recognize the action under occluded scenarios remains the major challenge in practical applications and is barely explored. Although previous augmentation methods have made some efforts by introducing additional modalities to deal with occlusion cases, the continuous occlusion related to temporal in the video is rarely focused. To tackle this issue, this paper takes the sample augmentation and feature representation into consideration. Specifically, we design a Dynamic Temporal-aware Erasing (DTE) augmentation strategy to enrich the occlusion samples. The proposed DTE builds upon an explicit analysis conditioned with temporal dimension along with the actors’ trajectories, which ensures the capability of carrying the temporal relation to an arbitrary spatial augmentation setting. Specifically, DTE makes the added augmentation samples more temporally consistent with obtaining the motion trajectories of the actors, enhancing the robustness against occlusions. Besides, we revisit the necessity of diverse backgrounds and propose Dynamic and Static Mutual Fitting (DSMF) to optimize the action recognition model. DSMF incorporates background auxiliary mutual fitting actors to distinguish features, which learns a smooth representation with the global temporal consistency. Extensive experiments conducted on standard benchmarks have proved that the proposed DSMF achieves competitive performance over powerful competitors.

Enhancing source code classification effectiveness via prompt learning incorporating knowledge features

Researchers have investigated the potential of leveraging pre-trained language models, such as CodeBERT, to enhance source code-related tasks. Previous methodologies have relied on CodeBERT’s ‘[CLS]’ token as the embedding representation of input sequences for task performance, necessitating additional neural network layers to enhance feature representation, which in turn increases computational expenses. These approaches have also failed to fully leverage the comprehensive knowledge inherent within the source code and its associated text, potentially limiting classification efficacy. We propose CodeClassPrompt, a text classification technique that harnesses prompt learning to extract rich knowledge associated with input sequences from pre-trained models, thereby eliminating the need for additional layers and lowering computational costs. By applying an attention mechanism, we synthesize multi-layered knowledge into task-specific features, enhancing classification accuracy. Our comprehensive experimentation across four distinct source code-related tasks reveals that CodeClassPrompt achieves competitive performance while significantly reducing computational overhead.

Hybrid raven roosting intelligence framework for enhancing efficiency in data clustering

The field of data exploration relies heavily on clustering techniques to organize vast datasets into meaningful subgroups, offering valuable insights across various domains. Traditional clustering algorithms face limitations in terms of performance, often getting stuck in local minima and struggling with complex datasets of varying shapes and densities. They also require prior knowledge of the number of clusters, which can be a drawback in real-world scenarios. In response to these challenges, we propose the "hybrid raven roosting intelligence framework" (HRIF) algorithm. HRIF draws inspiration from the dynamic behaviors of roosting ravens and computational intelligence. What distinguishes HRIF is its effective capacity to adeptly navigate the clustering landscape, evading local optima and converging toward optimal solutions. An essential enhancement in HRIF is the incorporation of the Gaussian mutation operator, which adds stochasticity to improve exploration and mitigate the risk of local minima. This research presents the development and evaluation of HRIF, showcasing its unique fusion of nature-inspired optimization techniques and computational intelligence. Extensive experiments with diverse benchmark datasets demonstrate HRIF's competitive performance, particularly its capability to handle complex data and avoid local minima, resulting in accurate clustering outcomes. HRIF's adaptability to challenging datasets and its potential to enhance clustering efficiency and solution quality position it as a promising solution in the world of data exploration.

Athlete Insights on Climate Change and Winter Sport: Impacts, Thresholds, Adaptations, and Implications for the Future

Relying directly on snow, ice, and cold temperatures, outdoor winter sports are already experiencing and responding to climate change. Through an online survey of elite-level athletes and coaches (n = 390), and semi-structured key stakeholder interviews (n = 8), this research investigates the climate thresholds and adaptations that enable world-class performance in safe and fair competitions. Ideal competition conditions include temperatures within −1 to −10 °C, on consistent snow surfaces. Over 95% of respondents stated climate change is or will negatively impact their sport, with current adaptations ranging from good (snowmaking) to poor (canceled training runs). Beyond competitions, athletes and coaches are concerned climate change will reduce training opportunities, negatively impacting next-generation athlete development and winter sport culture. The results yield important insight into athlete and coach perspectives on climate change impacts, thresholds, and adaptations that can inform future policy, planning, and management for winter sport organizations at all levels.

Industrialization Dynamics in Organization of Islamic Cooperation (OIC) Countries: Evidence from the Club Convergence Approach

The primary objective of this study is to scrutinize the industrialization patterns across 36 member states of the Organization of Islamic Cooperation (OIC) spanning from 1990 to 2021, adopting a club convergence approach. This study employed the Competitive Industrial Performance (CIP) index developed by the United Nations Industrial Development Organization. The CIP index serves as a yardstick for assessing countries’ effectiveness in manufacturing and exporting industrial goods, facilitating comparisons of industrial competitiveness across nations. The empirical findings derived from the convergence methodology established by Phillips & Sul (2007, 2009) unveiled the absence of convergence in CIP among OIC countries yet delineate the existence of four distinct convergence clusters. Notably, the CIP scores of countries exerted a significant influence on the formation of these clusters, with member states within the same cluster exhibiting comparable CIP performances. This outcome underscored the persistent dual structure characterizing the OIC panel, wherein nations with lower CIP standings failed to converge toward those with higher performance levels.

Effects of Psychological Training on Competitive Fencing Outcomes

This study assesses how psychological training affects Fencing competition results, with a particular emphasis on improving cognitive skills and overall performance. Psychological techniques like stress reduction, mindfulness, and visualization have been shown to help with decision-making, focus, and emotional regulation in a variety of sports, including Fencing. Twenty fencers, ages 17 to 20, participated in the study and completed a six-month psychological training course. The findings show that psychological training greatly improves competitive performance as measured by improved response times, win/loss ratios, and psychological evaluations. These results support earlier studies and imply that regular athletic preparation can greatly benefit from the inclusion of psychological training. The brief training period and small sample size are limitations that call for additional research on long-term effects and a variety of participant groups.

Outlier detection using local density and global structure

Outlier detection, a critical process for enhancing data quality, has been applied to a broad spectrum of real-world applications. This study introduces a novel and effective outlier detection method that incorporates both local density and global structural information. Specifically, we employ the concept of potential energy, a well-established principle in physics, to represent local densities or neighbor distributions of data. Additionally, we also exploit the notion of hubness, a measure explored in network science, to further capture global structural information of data. To facilitate this, we construct a strongly connected digraph by introducing a virtual node along with an associated set of virtual edges. This digraph underpins a tailored Markov random walk process that is used to estimate the hubness scores of data objects. Subsequently, the importance degrees of data objects are estimated according to their potential energies and hubness scores. The data objects with lower importance degrees are deemed to be outliers. Extensive experiments conducted on thirteen publicly accessible real-world datasets against nine popular outlier detection algorithms show that the proposed method achieved encouraging and competitive performance in comparing the state-of-the-art outlier detection algorithms.