Post-processing Stage Research Articles

A Unified Virtual Model for Real-Time Visualization and Diagnosis in Architectural Heritage Conservation

The aim of this paper is to propose a workflow for the real-time visualization of virtual environments that supports diagnostic tasks in heritage buildings. The approach integrates data from terrestrial laser scanning (3D point clouds and meshes), along with panoramic and thermal images, into a unified virtual model. Additionally, the methodology incorporates several post-processing stages designed to enhance the user experience in visualizing both the building and its associated damage. The methodology was tested on the Medieval Templar Church of Vera Cruz in Segovia, utilizing a combination of visible and infrared data, along with manually prepared damage maps. The project results demonstrate that the use of a hybrid digital model—combining 3D point clouds, polygonal meshes, and panoramic images—is highly effective for real-time rendering, providing detailed visualization while maintaining adaptability for mobile devices with limited computational power.

A double-layered fully automated insomnia identification model employing synthetic data generation using MCSA and CTGAN with single-channel EEG signals.

Insomnia was diagnosed by analyzing sleep stages obtained during polysomnography (PSG) recording. The state-of-the-art insomnia detection models that used physiological signals in PSG were successful in classification. However, the sleep stages of unbalanced data in small-time intervals were fed for classification in previous studies. This can be avoided by analyzing the insomnia detection structure in different frequency bands with artificially generated data from the existing one at the preprocessing and post-processing stages. Hence, the paper proposes a double-layered augmentation model using Modified Conventional Signal Augmentation (MCSA) and a Conditional Tabular Generative Adversarial Network (CTGAN) to generate synthetic signals from raw EEG and synthetic data from extracted features, respectively, in creating training data. The presented work is independent of sleep stage scoring and provides double-layered data protection with the utility of augmentation methods. It is ideally suited for real-time detection using a single-channel EEG provides better mobility and comfort while recording. The work analyzes each augmentation layer's performance individually, and better accuracy was observed when merging both. It also evaluates the augmentation performance in various frequency bands, which are decomposed using discrete wavelet transform, and observed that the alpha band contributes more to detection. The classification is performed using Decision Tree (DT), Ensembled Bagged Decision Tree (EBDT), Gradient Boosting (GB), Random Forest (RF), and Stacking classifier (SC), attaining the highest classification accuracy of 94% using RF with a greater Area Under Curve (AUC) value of 0.97 compared to the existing works and is best suited for small datasets.

Multi-head Network based Students Behaviour Prediction with Feedback Generation for Enhancing Classroom Engagement and Teaching Effectiveness

Emotions are pivotal in the learning process, highlighting the importance of identifying students' emotional states within educational settings. While neural network models, particularly those rooted in deep learning, have demonstrated remarkable accuracy in detecting primary emotions like happiness, sadness, fear, disgust, and anger from facial expressions in videos, these emotions occur infrequently in learning environments. Conversely, cognitive emotions such as engagement, confusion, frustration, and boredom are significantly more prevalent, transpiring five times more frequently than basic emotions. However, unlike basic emotions which are relatively distinct, cognitive emotions present a subtler distinction, necessitating the utilization of more sophisticated models for accurate recognition. The proposed work presents an efficient Facial Expression Recognition (FER) model for monitoring the student engagement in a learning environment by considering their facial expressions like boredom, frustration, confusion and engagement. The proposed methodology includes certain pre-processing steps followed by facial expression recognition founded on Efficient-Net B3 CNN in which the learning parameters are optimized using Circle-Inspired Optimization Algorithm (CIOA). Finally, the post processing stage estimates the frame-wise group engagement level (GEL) of students based on certain expression labels. Based on the acquired results, it is noted that the suggested Efficient-Net B3 CNN-CIOA based FER model provides promising results in terms of accuracy by 99.5%, precision by 99.2%, recall by 99.5% and f1-score by 99.6%, when compared with some state-of-art facial expression recognition approaches. Also, the suggested approach computational complexity is very much less than the compared existing approaches.

Identification of the tyre dynamic response from cleat test measurements

The tyre dynamics strongly affects structure-borne noise and vibrations inside the vehicle compartment. Its contribution is predominant to the overall noise levels perceived by the passengers in the 0-400 Hz frequency range. In this paper, an experimental setup specifically designed to measure the tyre radial vibrations during a cleat test is presented. To acquire the data, a laser sensor is installed on a supporting structure that moves around the tyre circumference. At the post-processing stage, attention is first paid to the extraction of the tyre free response from the measurements. The tyre radial vibration has been visualized considering all measurement positions at different time instants. Then, an algorithm for the identification of the travelling waves constituting the signals has been developed. The results of the identification are discussed, through a comparison with the measured signals.

Accelerating QKD post-processing by secure offloading of information reconciliation

While quantum key distribution (QKD) offers unparalleled security in communication, its real-world application is hindered by inherent physical constraints. The challenge lies predominantly in the cumbersome, energy-intensive nature of current QKD systems, which stems largely from the time-intensive post-processing stage. This paper investigates the feasibility of offloading the computationally intensive post-processing tasks, specifically focusing on information reconciliation (IR), to potentially untrusted servers.We present a novel scheme that leverages syndrome decoding techniques to efficiently transfer the IR step of QKD protocols to a single external server. Notably, this offloading is accomplished while maintaining the highest level of security, known as unconditional security. The proposed technique is bolstered by a comprehensive theoretical analysis and validated through experimental trials. These findings demonstrate the effectiveness of our approach in bridging the gap between the theoretical promise of QKD and its real-world deployment.

Rapid investment casting: a techno-economic analysis for evaluating VAT photopolymerisation processes

Adopting additive manufacturing in investment casting, known as rapid investment casting, can significantly reduce lead time and cost. Despite many publications on these technologies, no quantitative techno-economic analyses refer to rapid investment casting. The paper provides helpful insights and a decision-making approach for replacing conventional production technologies (i.e. wax injection) with additive manufacturing technologies. The study is based on a techno-economic analysis framework. It allows assessing key performance indicators (e.g. crossover points and payback periods) for stakeholders to decide the suitable VAT photopolymerisation processes (i.e. stereolithography, digital light processing, and material jetting) according to specific production scenarios (i.e. load factors). Analytical cost models were developed in the frame of this work to assess the time and cost of the overall manufacturing process of the resin model for investment casting, considering the post-processing stages for each of the technologies investigated. The cost models were used to assess the benefits introduced by additive manufacturing in rapid investment casting. A sensitivity analysis evaluated the impact of energy, material, and labour costs for both key performance indicators (crossover points and payback periods). The techno-economic analysis yielded the following results: (i) crossover points in terms of production costs vary, ranging from thousands of units for small components in the jewellery or fashion industries to a few dozen units for larger parts in the mechanical industry, and (ii) crossover points in terms of time are lower than those related to cost. Additionally, digital light processing is regarded as the most promising technology, offering the best crossover points and payback periods across various scenarios, mainly when 3D printers are used at a low utilisation rate.

A Framework for Measuring Tree Rings Based on Panchromatic Images and Deep Learning.

Tree-ring data are pivotal for decoding the age and growth patterns of trees, reflecting the impact of environmental factors over time. Addressing the significant shortcomings of traditional, labour-intensive and resource-demanding methods, we propose an innovative automated technique that utilizes panchromatic images and deep learning for measuring tree rings. The method utilizes convolutional neural networks to enhance image quality, precisely delineate tree rings through segmentation and perform ring counting and width calculation in the post-processing stage. We compiled an extensive data set from diverse sources, including Beijing Forestry University and the Summer Palace, to train our algorithm. The performance of our method was validated empirically, demonstrating its potential to transform tree-ring analysis and provide deeper insights into ecological and climatological research.

HSP-YOLOv8: UAV Aerial Photography Small Target Detection Algorithm

To address the larger numbers of small objects and the issues of occlusion and clustering in UAV aerial photography, which can lead to false positives and missed detections, we propose an improved small object detection algorithm for UAV aerial scenarios called YOLOv8 with tiny prediction head and Space-to-Depth Convolution (HSP-YOLOv8). Firstly, a tiny prediction head specifically for small targets is added to provide higher-resolution feature mapping, enabling better predictions. Secondly, we designed the Space-to-Depth Convolution (SPD-Conv) module to mitigate the loss of small target feature information and enhance the robustness of feature information. Lastly, soft non-maximum suppression (Soft-NMS) is used in the post-processing stage to improve accuracy by significantly reducing false positives in the detection results. In experiments on the Visdrone2019 dataset, the improved algorithm increased the detection precision mAP0.5 and mAP0.5:0.95 values by 11% and 9.8%, respectively, compared to the baseline model YOLOv8s.

An improved immersed boundary method for turbulent flow simulations on Cartesian grids: extension of a global geometric approach for thin boundary layers and strong flow incidence

This paper presents further improvements to the immersed boundary method introduced in [1]. The proposed developments take place during the pre- and post-processing stages of the simulation workflow and aim to further increase the accuracy of the approach for steady-state simulations of high Reynolds number turbulent flows around aerodynamic geometries facing strong incidence. To this end, the location of the forcing points is further optimized prior to simulation, with an adaptive and local modeling height that accounts for the evolution of the turbulent boundary layer thickness, especially at the leading edge. In addition, the direct extrapolation of the pressure solution at the wall is replaced by first- and second-order reconstructions using the normal pressure gradients interpolated at a new set of image points. This second approach is used only in post-processing, after the simulation, and prevents the degradation of the wall pressure in the presence of strong curvatures or thin boundary layers. These developments have been validated by simulating subsonic turbulent flows around the NACA0012 profile, 2D multi-element airfoil (2DMEA), and HL-CRM half-plane at significant angles of attack. Smooth and accurate skin pressure and friction coefficients are observed, in excellent agreement with body fitted wall-resolved solutions, even for coarser Cartesian meshes. Better drag and lift coefficients calculated by direct near-field integrations are obtained, along with accurate predictions of the near-wall flow physics throughout the turbulent boundary layer.

Preparation of Aprepitant nanoparticles using subcritical water anti-solvent technology

The low oral bioavailability of active pharmaceutical ingredients in aqueous media causes to partial absorption through the gastrointestinal tract. Increasing surface area by particle size reduction has been accomplished to overcome these challenges. In this study, Aprepitant (APT) nanoparticles were prepared using a green solvent anti-solvent precipitation method based on subcritical water (SW) technology. Effects of three different parameters such as SW temperature (368.15–388.15 K), anti-solvent temperature (273.15–293.15 K), and polyethylene glycol concentration (0.02–0.04 wt%) were studied on the size and morphology of the produced nanoparticles. As the next step, optimization of the process was performed using the response surface Box-Behnken design (BBD), and optimum operational conditions were obtained as follows: SW temperature (388.15 K), anti-solvent temperature (283.15 K), and polyethylene glycol concentration (0.04 wt%). The results revealed a significant decline in the size of the precipitated particle by subcritical water-based technologies (5.0 nm, on average), as compared to the unprocessed drug particles (30 μm, on average). Green SW-based technologies are proposed for the preparation of APT nanoparticles with no requirement for organic solvents and post-processing purification stages.

Dentists who can auscultate: Microphone-based toothbrushing quality monitoring system for electronic toothbrush

Tooth brushing is a widely recognized and effective method for daily oral care. However, the lack of real-time feedback for monitoring the brushing process can hinder individuals in maintaining their oral hygiene. Currently, only high-end electric toothbrushes offer evaluation functions based on built-in sensors, making them unaffordable for the majority of people. In this paper, we propose a novel and cost-effective wearable acoustic-based system (both hardware and software) for monitoring the quality of daily tooth brushing. Our system combines a throat-microphone and a Bluetooth earphone to capture brushing noises, which are unique acoustical signals generated from the air and the human body during tooth brushing, respectively. By leveraging the distinctive characteristics of brushing sounds in these two different conductive media, we introduce an intelligent detection algorithm based on Single-Input Multiple-Output (SIMO) modeling and frequency response functions (FRFs) to detect the corresponding brushing area. Through experimentation, we have found that the divergence of FRFs provides more stable features compared to general statistical features used in previous studies. After comparing various machine learning algorithms, we have selected XGBoost as the final detection model. Additionally, we utilize the Symmetric Nearest Neighbor (SNN) filter in the post-processing stage to further reduce the jitter noise in continuous detection. The final system achieves an average precision of 98.46% when tested on tooth brushing data collected from different volunteers. To enhance user experience, we have developed an Android App with a user-friendly interface that incorporates the detection system. With a total wearable hardware cost of less than 10 dollars, our system shows great potential for integration into future smart wearable devices.

Possibilities of Automating the Additive Manufacturing Process of Material Extrusion – MEX

The article presents the possibilities of automating production pre-processing and post-processing operations for the Material Extrusion - MEX process based on Fused Filament Fabrication technology. Automation is based on hardware and software solutions. For this purpose, a special research station was developed, equipped with a warehouse of working platforms, a 3D printer and a collaborative robot that integrates individual elements of the manufacturing process. The developed solution allows for increasing the efficiency of the manufacturing cell and reducing the operator's involvement in manual operations at the pre-processing and post-processing stages.

Monocular Absolute Depth Estimation from Motion for Small Unmanned Aerial Vehicles by Geometry-Based Scale Recovery.

In recent years, there has been extensive research and application of unsupervised monocular depth estimation methods for intelligent vehicles. However, a major limitation of most existing approaches is their inability to predict absolute depth values in physical units, as they generally suffer from the scale problem. Furthermore, most research efforts have focused on ground vehicles, neglecting the potential application of these methods to unmanned aerial vehicles (UAVs). To address these gaps, this paper proposes a novel absolute depth estimation method specifically designed for flight scenes using a monocular vision sensor, in which a geometry-based scale recovery algorithm serves as a post-processing stage of relative depth estimation results with scale consistency. By exploiting the feature correspondence between successive images and using the pose data provided by equipped navigation sensors, the scale factor between relative and absolute scales is calculated according to a multi-view geometry model, and then absolute depth maps are generated by pixel-wise multiplication of relative depth maps with the scale factor. As a result, the unsupervised monocular depth estimation technology is extended from relative depth estimation in semi-structured scenes to absolute depth estimation in unstructured scenes. Experiments on the publicly available Mid-Air dataset and customized data demonstrate the effectiveness of our method in different cases and settings, as well as its robustness to navigation sensor noise. The proposed method only requires UAVs to be equipped with monocular camera and common navigation sensors, and the obtained absolute depth information can be directly used for downstream tasks, which is significant for this kind of vehicle that has rarely been explored in previous depth estimation studies.

Tomato leaf disease detection and management using VARMAx-CNN-GAN integration

In contemporary agriculture, farmers confront substantial challenges in maintaining crop yields and mitigating agricultural losses attributable to diseases. The existing methods for diagnosing and managing tomato leaf diseases often exhibit deficiencies in terms of accuracy, robustness, and interpretability. Typically, these methods are reactive, addressing symptoms after the disease has already impacted the plants, resulting in delayed and often ineffective interventions. The precision of disease localization and severity estimation plays a crucial role in efficient disease treatment; regrettably, existing post-processing techniques frequently fall short in this regard. While these methods have their flaws, our proposed method uses the best parts of deep learning and vector autoregressive moving average processes with eXogenous regressors (VARMAx processes) to quickly and accurately find tomato leaf diseases. Our approach represents an innovative solution to the challenges currently confronting the agriculture sector, thanks to its proactive attributes, improved categorization capabilities, and advanced post-processing stages. Convolutional neural networks (CNNs) and generative adversarial networks (GANs), built upon the “VARMAx-CNN-GAN Integration” framework, form the core of our method. In this integrated model, convolutional neural networks serve the purpose of extracting features and performing early disease classification, whereas generative adversarial networks come into play for generating synthetic images, expanding the dataset, and enhancing the model’s ability to generalize. The “VARMAx-CNN-GAN Integration” model improves disease classification and decision-making for farmers and agronomists by providing insights into critical leaf images. Compared to traditional methods, it improves precision, accuracy, recall, AUC, and delay in identifying tomato diseases. The approach also shows potential for disease prevention, revolutionizing tomato leaf disease identification and management.

A Novel Single-Sample Retinal Vessel Segmentation Method Based on Grey Relational Analysis.

Accurate segmentation of retinal vessels is of great significance for computer-aided diagnosis and treatment of many diseases. Due to the limited number of retinal vessel samples and the scarcity of labeled samples, and since grey theory excels in handling problems of "few data, poor information", this paper proposes a novel grey relational-based method for retinal vessel segmentation. Firstly, a noise-adaptive discrimination filtering algorithm based on grey relational analysis (NADF-GRA) is designed to enhance the image. Secondly, a threshold segmentation model based on grey relational analysis (TS-GRA) is designed to segment the enhanced vessel image. Finally, a post-processing stage involving hole filling and removal of isolated pixels is applied to obtain the final segmentation output. The performance of the proposed method is evaluated using multiple different measurement metrics on publicly available digital retinal DRIVE, STARE and HRF datasets. Experimental analysis showed that the average accuracy and specificity on the DRIVE dataset were 96.03% and 98.51%. The mean accuracy and specificity on the STARE dataset were 95.46% and 97.85%. Precision, F1-score, and Jaccard index on the HRF dataset all demonstrated high-performance levels. The method proposed in this paper is superior to the current mainstream methods.

Probability map-based grape detection and counting

Grape-cluster detection, grape-berry counting, and berry-per-grape-cluster counting are the three major tasks in digital viticulture. Although the detection of clusters and berries was treated as separate tasks in previous studies, due to the clustered nature of the grape phenotype and the close hierarchical spatial distribution relationship between grape clusters and berries, those three tasks should be considered at the same time in our view; further, we define these tasks as subtasks of the grape detection and counting task. The major challenge of combining the three subtasks of grape detection and counting together is how to obtain the detection results of those subtasks from the output of a single neural network. To address this issue, we propose a Probability Map-based Grape Detection and Counting framework that first detects two intermediate probability maps through a neural network and utilizes three postprocessing stages to finish the three grape detection and counting subtasks sequentially. After being trained and validated on the trainval set of WGISD, combining 100 extra images collected in Chengdu by our team, the proposed framework is tested on the test set of WGISD to verify its performance. The proposed framework achieves a localization performance of average precision (AP)(iou0.5) 0.851 and a counting performance of MAE 1.845, RMSE 2.142 for grape clusters, a counting performance of MAE 23.414, RMSE 31.391 for grape berries, and a counting performance of MRD 0.142, 1-FVU 0.865 for berries per grape cluster on the test set of WGISD. Our source code will be publicly available athttps://github.com/volcanoYcc/Probability-Map-based-Grape-Detection-and-Counting.

A [formula omitted] continuous multi-patch framework for adaptive isogeometric topology optimization of plate structures

This study proposes a novel computationally efficient methodology to perform topology optimization (TO) of fourth-order plate structures within the framework of multi-patch isogeometric analysis. This is realized by taking the multifold benefits of isogeometric PHT-Splines to (1) discretize the C1 continuous weak form of plate structures, (2) develop a C0 continuous density field for the material distribution in TO and inherently remove the need for filters, and (3) provide a hierarchical tree structure for the structural mesh to effortlessly implement an adaptive mesh refinement (AMR) strategy. Moreover, to ensure continuity between isogeometric patches, we adopt a strong C1 coupling between the boundaries. This is established by constructing new basis functions, defined as a linear combination of existing C0 functions at the patch interfaces. The density field in TO is further enhanced with a first-neighbourhood smoothening algorithm based on the Shepard function to generate printable topologies and alleviate the post-processing stages after optimization. An element-centre density, based on the control point densities of the isogeometric mesh, is used as the marking scheme for the AMR to determine the subdomains to be refined. Utilizing the Geometry Independent Field approximaTion, the design and adaptive analysis-optimization stages were independently discretized respectively through NURBS and PHT-Splines, allowing easy transfer of multi-patch geometries from industry-standard packages. Multiple numerical examples illustrate the stability of the multi-patch algorithm in optimizing the geometries effectively. The results also show considerable advantages in terms of solution accuracy such as precise field, smooth topology and computational efficiency.

Dual-frame optimization for informationally complete quantum measurements

Randomized measurement protocols such as classical shadows represent powerful resources for quantum technologies, with applications ranging from quantum state characterization and process tomography to machine learning and error mitigation. Recently, the notion of measurement dual frames, in which classical shadows are generalized to dual operators of positive operator-valued measure (POVM) effects, resurfaced in the literature. This brought attention to additional degrees of freedom in the postprocessing stage of randomized measurements that are often neglected by established techniques. In this work, we leverage dual frames to construct improved observable estimators from informationally complete measurement samples. We introduce novel classes of parametrized frame superoperators and optimization-free dual frames based on empirical frequencies, which offer advantages over their canonical counterparts while retaining computational efficiency. Remarkably, this comes at almost no quantum or classical cost, thus rendering dual frame optimization a valuable addition to the randomized measurement toolbox. Published by the American Physical Society 2024

Universal Software Only Radar with All Waveforms Simultaneously on a Single Platform

Abstract: While software-defined radars can switch their transmitted waveform on the go, they cannot transmit all waveforms at the same time, meaning they must balance the advantages and drawbacks of each configuration. Here, we propose theoretically and demonstrate experimentally the universal radar, which can apply the desired waveform in the post-processing stage after the physical measurement has been performed. This method also allows using a single measurement of a scene to design and test any other radar in complex scenarios without having to take it to the field. The method is based on post-processing the frequency response measured by a synthetically broadband stepped-frequency continuous wave radar, such as a vector network analyzer. An algorithm for overcoming distortions due to moving targets is derived as well. This approach not only provides an ultra-wideband software-only defined radar, but it also enables the acquired data from any measured site to be used for the design and analysis of almost any other future radar system, significantly cutting the time and cost of new developments. The method suggests the creation of radar raw data repositories that can be shared across diversely different radar platforms.

FocusDet: an efficient object detector for small object

The object scale of a small object scene changes greatly, and the object is easily disturbed by a complex background. Generic object detectors do not perform well on small object detection tasks. In this paper, we focus on small object detection based on FocusDet. FocusDet refers to the small object detector proposed in this paper. It consists of three parts: backbone, feature fusion structure, and detection head. STCF-EANet was used as the backbone for feature extraction, the Bottom Focus-PAN for feature fusion, and the detection head for object localization and recognition.To maintain sufficient global context information and extract multi-scale features, the STCF-EANet network backbone is used as the feature extraction network.PAN is a feature fusion module used in general object detectors. It is used to perform feature fusion on the extracted feature maps to supplement feature information.In the feature fusion network, FocusDet uses Bottom Focus-PAN to capture a wider range of locations and lower-level feature information of small objects.SIOU-SoftNMS is the proposed algorithm for removing redundant prediction boxes in the post-processing stage. SIOU multi-dimension accurately locates the prediction box, and SoftNMS uses the Gaussian algorithm to remove redundant prediction boxes. FocusDet uses SIOU-SoftNMS to address the missed detection problem common in dense tiny objects.The VisDrone2021-DET and CCTSDB2021 object detection datasets are used as benchmarks, and tests are carried out on VisDrone2021-det-test-dev and CCTSDB-val datasets. Experimental results show that FocusDet improves mAP@.5% from 33.6% to 46.7% on the VisDrone dataset. mAP@.5% on the CCTSDB2021 dataset is improved from 81.6% to 87.8%. It is shown that the model has good performance for small object detection, and the research is innovative.