Task In Applications Research Articles

An Ensemble Approach using Self-attention based MobileNetV2 for SAR classification

The Synthetic Aperture Radar (SAR) image classification has become an essential task in numerous applications. Despite its significance, SAR image classification remains challenging due to the inherent complexity and speckle noise characteristics of SAR data. To address this, an innovative approach is proposed in this study, combining the power of ensemble learning and the efficiency of MobileNetV2 architecture to achieve robust and accurate SAR image classification. The proposed deep learning model consists of two main components: an ensemble learning approach that combines multiple binary classifiers, and the employment of MobilenetV2 architecture with self-attention mechanism as a binary classifier. The ensemble approach uses a max-value selector for predicting final class from the individual classifier output. The MobileNetV2 architecture is finetuned by freezing weights and removing the last four layers. The inclusion of the attention layer within the architecture aids in refining the learning process by focusing on crucial features while disregarding irrelevant background elements in the images.. The effectiveness of the model is evaluated using Moving and Stationary Target Acquisition and Recognition (MSTAR) benchmark dataset with accuracy of classification as performance metric.The model is trained and tested with images captured at various aspect angles. This approach enhances the robustness of the results, making them more applicable to real-world scenarios when compared to prior methods. This study also compares the performance of the ensemble method using MobileNetV2 with state-of-art individual classifiers and different CNN architectures. The proposed ensemble method OVA-MbNN achieves an impressive classification accuracy of 76.63%, surpassing the performance of state-of-the-art classifiers while maintaining robustness.

Collaborative human-centered design of manufacturing tasks: a multi-user immersive VR experience

Work-related musculoskeletal disorders are among the top factors impacting the individual’s performance and the overall company’s productivity. Virtual Reality (VR) has enabled proactive consideration of human factors. However, there are still barriers impeding the broader adoption of human-in-the-loop approaches, including the number and roles of people involved in simulation stages and the complexity of modelling lengthy task sequences. This paper presents a multi-user immersive VR simulation framework for collaborative human-centered task evaluation involving engineers and operators. The software architecture enabling multi-user VR sessions is discussed, together with a hierarchical approach for modelling complex manufacturing tasks in VR applications and collecting structured data from the simulations. Metrics such as heatmap and Rapid Upper Limb Assessment are integrated for informed decision-making about task redesign. The proposed approach was tested in a case study inspired by large parts manufacturing, where operators need to work in teams. The server-client network enabled the engineer to comprehensively assess the design of the task having two operators executing virtual actions in parallel as they would in the actual workstation. The collection of data from the team of operators and their intuitive visualization enhanced the effectiveness in identifying aspects introducing discomfort and assessing the overall suitability of the design for human operators.

DisenSemi: Semi-Supervised Graph Classification via Disentangled Representation Learning.

Graph classification is a critical task in numerous multimedia applications, where graphs are employed to represent diverse types of multimedia data, including images, videos, and social networks. Nevertheless, in the real world, labeled graph data are always limited or scarce. To address this issue, we focus on the semi-supervised graph classification task, which involves both supervised and unsupervised models learning from labeled and unlabeled data. In contrast to recent approaches that transfer the entire knowledge from the unsupervised model to the supervised one, we argue that an effective transfer should only retain the relevant semantics that align well with the supervised task. We introduce a novel framework termed in this article, which learns disentangled representation for semi-supervised graph classification. Specifically, a disentangled graph encoder is proposed to generate factorwise graph representations for both supervised and unsupervised models. Then, we train two models via supervised objective and mutual information (MI)-based constraints, respectively. To ensure the meaningful transfer of knowledge from the unsupervised encoder to the supervised one, we further define an MI-based disentangled consistency regularization between two models and identify the corresponding rationale that aligns well with the current graph classification task. Experiments conducted on various publicly available datasets demonstrate the effectiveness of our .

Adaptive Approximation Tracking Control of a Continuum Robot With Uncertainty Disturbances.

Continuum robot has certain compliance and intrinsic safety, which makes it an excellent substitute for the traditional rigid robot in the various tasks, such as human-robot interaction or medical surgery. However, due to the complex nonlinearities which are induced by the compliance, parameter uncertainties, and unknown disturbances, good performance control scheme for the continuum robot is always a challenging task for the practical applications. Thus, to overcome this challenge of the uncertain dynamics and unknown external disturbances, this article develops a novel adaptive control scheme for a continuum robot using the function approximation technique (FAT). Specifically, for the proposed continuum robot, an adaptive FAT control (AFATC) strategy with no update laws is proposed to handle the uncertain parameters of the robot dynamics and external disturbances. The control law is expressed as a finite linear combination of the orthogonal basis functions by the FAT. The proposed AFATC scheme uses a fixed control structure, and the weight matrices are not updated in time. Then, the stability of the proposed controller is proved based on the Lyapunov function. Afterwards, the simulation results indicate the proposed AFATC scheme has good control performance compared with the regressor-free adaptive control (RFAC) method. Finally, the effectiveness of the proposed AFATC scheme is demonstrated in a group of real-time experiments.

EviPrompt: A Training-Free Evidential Prompt Generation Method for Adapting Segment Anything Model in Medical Images.

Medical image segmentation is a critical task in clinical applications. Recently, the Segment Anything Model (SAM) has demonstrated potential for natural image segmentation. However, the requirement for expert labour to provide prompts, and the domain gap between natural and medical images pose significant obstacles in adapting SAM to medical images. To overcome these challenges, this paper introduces a novel prompt generation method named EviPrompt. The proposed method requires only a single reference image-annotation pair, making it a training-free solution that significantly reduces the need for extensive labelling and computational resources. First, prompts are automatically generated based on the similarity between features of the reference and target images, and evidential learning is introduced to improve reliability. Then, to mitigate the impact of the domain gap, committee voting and inference-guided in-context learning are employed, generating prompts primarily based on human prior knowledge and reducing reliance on extracted semantic information. EviPrompt represents an efficient and robust approach to medical image segmentation. We evaluate it across a broad range of tasks and modalities, confirming its efficacy. The source code is available at https://github.com/SPIresearch/EviPrompt.

TRI-POSE-Net: Adaptive 3D human pose estimation through selective kernel networks and self-supervision with trifocal tensors.

Accurate and flexible 3D pose estimation for virtual entities is a strenuous task in computer vision applications. Conventional methods struggle to capture realistic movements; thus, creative solutions that can handle the complexities of genuine avatar interactions in dynamic virtual environments are imperative. In order to tackle the problem of precise 3D pose estimation, this work introduces TRI-POSE-Net, a model intended for scenarios with limited supervision. The proposed technique, which is based on ResNet-50 and includes integrated Selective Kernel Network (SKNet) blocks, has proven to be efficient for feature extraction customised specifically to pose estimation scenarios. Furthermore, trifocal tensors and their trio-view geometry allow us to generate 3D ground truth poses from 2D poses, resulting in more refined triangulations. Through the proposed approach, the 3D poses can be estimated from a single 2D RGB image. Moreover, the proposed approach was evaluated on the HumanEva-I dataset yielding a Mean-Per-Joint-Position-Error (MPJPE) of 47.6 under self-supervision and an MPJPE of 29.9 under full supervision. In comparison with the other works, the proposed work has performed well in the self-supervision paradigm.

Rich Action-semantic Consistent Knowledge for Early Action Prediction.

Early action prediction (EAP) aims to recognize human actions from a part of action execution in ongoing videos, which is an important task for many practical applications. Most prior works treat partial or full videos as a whole, ignoring rich action knowledge hidden in videos, i.e., semantic consistencies among different partial videos. In contrast, we partition original partial or full videos to form a new series of partial videos and mine the Action-Semantic Consistent Knowledge (ASCK) among these new partial videos evolving in arbitrary progress levels. Moreover, a novel Rich Action-semantic Consistent Knowledge network (RACK) under the teacher-student framework is proposed for EAP. Firstly, we use a two-stream pre-trained model to extract features of videos. Secondly, we treat the RGB or flow features of the partial videos as nodes and their action semantic consistencies as edges. Next, we build a bi-directional semantic graph for the teacher network and a single-directional semantic graph for the student network to model rich ASCK among partial videos. The MSE and MMD losses are incorporated as our distillation loss to enrich the ASCK of partial videos from the teacher to the student network. Finally, we obtain the final prediction by summering the logits of different subnetworks and applying a softmax layer. Extensive experiments and ablative studies have been conducted, demonstrating the effectiveness of modeling rich ASCK for EAP. With the proposed RACK, we have achieved state-of-the-art performance on three benchmarks. The code is available at https://github.com/lily2lab/RACK.git.

Digital Twinning Stacks, a modular communication system approach for IOT implementation in Unity3D

Manufacturing scenarios have become more data-intense and displaying the vast amount of data for human oversight has become a major task in various applications. The growing need for real-time data visualization in industrial applications has led to the development of numerous communication frameworks, each often designed for specific methods and purposes. This specialization requires developers to master multiple frameworks and integrate them into cohesive applications, a process that can be both complex and time-consuming. Human oversight interface for users in manufacturing can be categorized into displaying the (aggregated) past, current or future state of robots or different manufacturing equipment. This publication look into realizing these industrial XR applications with Unity3D and introduces a modular, open-source framework designed to streamline the integration of real-time data communication pipelines. This framework supports inputs from a diverse range of sources, offering a unified solution that simplifies the development process for applications requiring real-time data integration and is available as an open-source solution for researchers and practitioners.

The structure of the polymodel complex for modeling the operation of the lubrication system of an internal combustion engineThe paper presents the structure of the polymodel complex for modeling the operation of the lubrication system of an internal combu

The paper presents the structure of the polymodel complex for modeling the operation of the lubrication system of an internal combustion engine with a pneumohydroaccumulator, outlines the general requirements for the composition of this model complex. The ways of solution for realization of component models and tasks of application of the given polymodel complex at estimation of efficiency of lubrication systems of internal combustion engines with pneumohydroaccumulator, for application at realization of urban passenger transportation are defined. Keywords internal combustion engine, pneumohydroaccumulator, lubrication system, polymodel complex, modeling

Enhancing QoS for IoT Devices through Heuristics-based Computation Offloading in Multi-access Edge Computing

Multi-access Edge Computing (MEC) networks, particularly with the advent of 5G, aim to reduce latency and increase speed to meet the demands of resource-intensive applications in the Internet of Things (IoT), such as private wireless networks, online gaming, industry, and remote healthcare. These applications require guaranteed performance. However, while Quality of Service (QoS) management is well established in the Cloud, improving it remains a challenge in MEC environments. This study addresses this challenge by proposing heuristic computation offloading algorithms for IoT-intensive devices in MEC networks. These algorithms aim to minimize service time while maximizing the QoS, taking into account tasks and resource characteristics to determine the optimal execution location for IoT device applications. We evaluated our approach using the EdgeCloudSim simulator, and the results demonstrate its superiority over existing solutions. Our approach significantly improves QoS by reducing the service time of IoT application tasks. This research fills a gap in efficient QoS improvement and contributes to advances in computation offloading strategies in MEC environments. It paves the way for enhanced performance of IoT applications in these networks.

A Cascaded Multimodule Image Enhancement Framework for Underwater Visual Perception.

Underwater images usually exhibit severe color cast, hazy appearance, and/or dark regions because of the complex lighting absorption and scattering in water. How to increase the quality of these degraded underwater images has emerged as a key issue for various underwater application tasks. Recent efforts have been made to deal with single type degradation, however, it is still challenging to deal with multiple degradations that usually coexist in an underwater image with a general network. The degradations in underwater images can be divided into medium-agnostic (hazy or low-light which also encountered in in-air images) and medium-specific (color distortion caused by the specific light attenuation property in water) ones. According to this observation, this article proposes a cascaded multimodule underwater image enhancement (UIE) framework to address the coexisted multiple degradations. In the proposed framework, an in-air image enhancement module and a novel proposed adaptive color channel compensation network (AC 3 Net) are cascaded, in which the former focuses primarily on solving medium-agnostic degradations and the latter is for handling the medium-specific degradation. This framework has good flexibility by cascading different types of in-air image enhancement networks with AC 3 Net to achieve various UIE. The effectiveness of the proposed framework has been extensively validated on various degraded underwater images as well as different underwater visual perception tasks.

Recovering sign bits of DCT coefficients in digital images as an optimization problem

Recovering unknown, missing, damaged, distorted, or lost information in DCT coefficients is a common task in multiple applications of digital image processing, including image compression, selective image encryption, and image communication. This paper investigates the recovery of sign bits in DCT coefficients of digital images, by proposing two different approximation methods to solve a mixed integer linear programming (MILP) problem, which is NP-hard in general. One method is a relaxation of the MILP problem to a linear programming (LP) problem, and the other splits the original MILP problem into some smaller MILP problems and an LP problem. We considered how the proposed methods can be applied to JPEG-encoded images and conducted extensive experiments to validate their performances. The experimental results showed that the proposed methods outperformed other existing methods by a substantial margin, both according to objective quality metrics and our subjective evaluation.

Green synthesis of reduced graphene oxide (rGO) and its applications in non-enzymatic electrochemical glucose sensors

The synthesis of reduced graphene oxide (rGO) is a challenging task for industrial applications due to the absence of a simple and cost-effective synthesis method. This study proposes an environmentally friendly approach to synthesizing rGO using cow urine as a reducing agent, which eliminates the use of hazardous chemicals. The efficacy of this method was confirmed through various analyses, including UV Vis, Fourier transform infrared, and X-ray diffraction, which demonstrated the successful removal of oxygen-containing functions in GO via reduction with cow urine. The synthesized rGO-10 was utilized to fabricate electrochemical nonenzymatic glucose sensors, which exhibited a rapid response time and excellent amperometry response. The sensors used in this study demonstrated a sensitivity of 19.17 μAcm−2mM−1 when optimized for a glucose concentration of 2 mM in human serum. The sensors demonstrated a wide response range, covering a range of 0.2 to 10 mM, and a low detection limit of 1.9019 µM. Additionally, the sensors displayed desirable attributes about repeatability, reproducibility, and stability.

TransformerG2G: Adaptive time-stepping for learning temporal graph embeddings using transformers

Dynamic graph embedding has emerged as a very effective technique for addressing diverse temporal graph analytic tasks (i.e., link prediction, node classification, recommender systems, anomaly detection, and graph generation) in various applications. Such temporal graphs exhibit heterogeneous transient dynamics, varying time intervals, and highly evolving node features throughout their evolution. Hence, incorporating long-range dependencies from the historical graph context plays a crucial role in accurately learning their temporal dynamics. In this paper, we develop a graph embedding model with uncertainty quantification, TransformerG2G, by exploiting the advanced transformer encoder to first learn intermediate node representations from its current state (t) and previous context (over timestamps [t−1,t−l], l is the length of context). Moreover, we employ two projection layers to generate lower-dimensional multivariate Gaussian distributions as each node’s latent embedding at timestamp t. We consider diverse benchmarks with varying levels of “novelty” as measured by the TEA (Temporal Edge Appearance) plots. Our experiments demonstrate that the proposed TransformerG2G model outperforms conventional multi-step methods and our prior work (DynG2G) in terms of both link prediction accuracy and computational efficiency, especially for high degree of novelty. Furthermore, the learned time-dependent attention weights across multiple graph snapshots reveal the development of an automatic adaptive time stepping enabled by the transformer. Importantly, by examining the attention weights, we can uncover temporal dependencies, identify influential elements, and gain insights into the complex interactions within the graph structure. For example, we identified a strong correlation between attention weights and node degree at the various stages of the graph topology evolution.

Harnessing Causal Structure Alignment for Enhanced Cross-Domain Named Entity Recognition

Cross-domain named entity recognition (NER) is a crucial task in various practical applications, particularly when faced with the challenge of limited data availability in target domains. Existing methodologies primarily depend on feature representation or model parameter sharing mechanisms to enable the transfer of entity recognition capabilities across domains. However, these approaches often ignore the latent causal relationships inherent in invariant features. To address this limitation, we propose a novel framework, the Causal Structure Alignment-based Cross-Domain Named Entity Recognition (CSA-NER) framework, designed to harness the causally invariant features within causal structures to enhance the cross-domain transfer of entity recognition competence. Initially, CSA-NER constructs a causal feature graph utilizing causal discovery to ascertain causal relationships between entities and contextual features across source and target domains. Subsequently, it performs graph structure alignment to extract causal invariant knowledge across domains via the graph optimal transport (GOT) method. Finally, the acquired causal invariant knowledge is refined and utilized through the integration of Gated Attention Units (GAUs). Comprehensive experiments conducted on five English datasets and a specific CD-NER dataset exhibit a notable improvement in the average performance of the CSA-NER model in comparison to existing cross-domain methods. These findings underscore the significance of unearthing and employing latent causal invariant knowledge to effectively augment the entity recognition capabilities in target domains, thereby contributing a robust methodology to the broader realm of cross-domain natural language processing.

Second-order Confidence Network for Early Classification of Time Series

Time series data are ubiquitous in a variety of disciplines. Early classification of time series, which aims to predict the class label of a time series as early and accurately as possible, is a significant but challenging task in many time-sensitive applications. Existing approaches mainly utilize heuristic stopping rules to capture stopping signals from the prediction results of time series classifiers. However, heuristic stopping rules can only capture obvious stopping signals, which makes these approaches give either correct but late predictions or early but incorrect predictions. To tackle the problem, we propose a novel second-order confidence network for early classification of time series, which can automatically learn to capture implicit stopping signals in early time series in a unified framework. The proposed model leverages deep neural models to capture temporal patterns and outputs second-order confidence to reflect the implicit stopping signals. Specifically, our model exploits the data not only from a time step but also from the probability sequence to capture stopping signals. By combining stopping signals from the classifier output and the second-order confidence, we design a more robust trigger to decide whether or not to request more observations from future time steps. Experimental results show that our approach can achieve superior results in early classification compared to state-of-the-art approaches.

Flexible Offloading and Task Scheduling for IoT Applications in Dynamic Multi-Access Edge Computing Environments

Nowadays, multi-access edge computing (MEC) has been widely recognized as a promising technology that can support a wide range of new applications for the Internet of Things (IoT). In dynamic MEC networks, the heterogeneous computation capacities of the edge servers and the diversified requirements of the IoT applications are both asymmetric, where and when to offload and schedule the time-dependent tasks of IoT applications remains a challenge. In this paper, we propose a flexible offloading and task scheduling scheme (FLOATS) to adaptively optimize the computation of offloading decisions and scheduling priority sequences for time-dependent tasks in dynamic networks. We model the dynamic optimization problem as a multi-objective combinatorial optimization problem in an infinite time horizon, which is intractable to solve. To address this, a rolling-horizon-based optimization mechanism is designed to decompose the dynamic optimization problem into a series of static sub-problems. A genetic algorithm (GA)-based computation offloading and task scheduling algorithm is proposed for each static sub-problem. This algorithm encodes feasible solutions into two-layer chromosomes, and the optimal solution can be obtained through chromosome selection, crossover and mutation operations. The simulation results demonstrate that the proposed scheme can effectively reduce network costs in comparison to other reference schemes.

MAPPING LOCAL CLIMATE ZONES WITH MULTIPLE GEODATA AND THE OPEN DATA CUBE: INSIGHTS OF DOMAIN USER REQUIREMENTS AND OUTLOOKS OF THE LCZ-ODC PROJECT

Abstract. Rapid urbanization and climate change are intensifying the urban heat island (UHI) phenomenon across cities worldwide. There is a pressing need to implement evidence-based mitigation and adaptation strategies as well as to develop tools for effectively measuring the impact of such actions on UHI patterns. In this context, the Local Climate Zone (LCZ) concept is a well-established classification system commonly used for the assessment of UHI. With this in mind, we present here the LCZ-ODC project aiming to develop a methodology for LCZ mapping in the Metropolitan City of Milan (northern Italy) by leveraging multiple geospatial data and cutting-edge software tools, including the Open Data Cube (ODC). A key aim of the project is to develop user-oriented solutions facilitating the exploitation of the generated LCZ maps for different application tasks. In this paper, we first present a brief overview of the methodologies and data sources used in the literature for LCZ mapping. Then, we introduce the LCZ-ODC project, with a focus on the end-user requirements which were gathered through a questionnaire distributed to a sample of potential stakeholders. The primary objective of the survey was to collect insights and consolidate requirements related to the key features of LCZ maps that will be produced within the project. The outcomes of the survey play a pivotal role in guiding the project’s development phase, ensuring that the project outputs will effectively address the identified end-user needs.

RECOGNITION OF OBJECT PROPERTIES BASED ON PASSIVE TRIANGULATION AND 2D CAMERA SYSTEM

Every advanced knowledge about the process, object, or workplace is fundamental. It concerns current trends (digitalization, automation, intelligent industry) and the need to fill the missing technological gaps. Their goal is to increase quality and competitiveness. Therefore, this article aims to present a framework of the systematic approach as an affordable way to obtain relevant information about the object in the field of view of the captured scene. In addition, by using known triangulation methods, the article wants to build a relevant knowledge base that can be used as a suitable basis for solving similarly focused application tasks. Regardless, concerning the sensitive integration of image recognition and a methodological point of view, the article wants to summarize and verify the knowledge of epipolar geometry on a practical example of a selected object.

Mathematical Camera Array Optimization for Face 3D Modeling Application.

Camera network design is a challenging task for many applications in photogrammetry, biomedical engineering, robotics, and industrial metrology, among other fields. Many driving factors are found in the camera network design including the camera specifications, object of interest, and type of application. One of the interesting applications is 3D face modeling and recognition which involves recognizing an individual based on facial attributes derived from the constructed 3D model. Developers and researchers still face difficulty in reaching the required high level of accuracy and reliability needed for image-based 3D face models. This is caused among many factors by the hardware limitations and imperfection of the cameras and the lack of proficiency in designing the ideal camera-system configuration. Accordingly, for precise measurements, we still need engineering-based techniques to ascertain the specific level of deliverables quality. In this paper, an optimal geometric design methodology of the camera network is presented by investigating different multi-camera system configurations composed of four up to eight cameras. A mathematical nonlinear constrained optimization technique is applied to solve the problem and each camera system configuration is tested for a facial 3D model where a quality assessment is applied to conclude the best configuration. The optimal configuration is found to be a 7-camera array, comprising a pentagon shape enclosing two additional cameras, offering high accuracy. For those who prioritize point density, a 9-camera array with a pentagon and quadrilateral arrangement in the X-Z plane is a viable choice. However, a 5-camera array offers a balance between accuracy and the number of cameras.