Prior Knowledge Research Articles

GMOPNet: A GAN-MLP two-stage network for optical properties measurement of kiwifruit and peaches with spatial frequency domain imaging

Spatial frequency domain imaging (SFDI) is an imaging technique using spatially modulated illumination for measurement of optical properties. Conventional SFDI methods require capturing at least six images, making it time-consuming. This study presents a Generative Adversarial Network-Multi-Layer Perceptron (GAN-MLP) two-stage network (GMOPNet) for extracting high-precision optical properties of kiwifruit and peaches from a single SFDI image, enabling real-time continuous wide-band SFDI. The GMOPNet we proposed leverages the GAN to predict diffuse reflectance, followed by the MLP with Monte Carlo prior knowledge to predict optical properties. Our method achieves mean absolute percentage errors (MAPE) of 5.91 % for the absorption coefficient (μa) and 5.23 % for the reduced scattering coefficient (μs′), reducing acquisition and processing time significantly, with single inference taking 31.13 ms. The MAPE of the μa and the μs′ were 6.73 % and 6.34 % for kiwifruit and 5.80 % and 6.65 % for peaches, respectively.

Fixed-time adaptive sliding mode-based trajectory tracking control for Wheeled Mobile Robot: Theoretical development and real-time implementation

Wheeled mobile robots (WMR) are common autonomous systems requiring efficient control methods. This work investigates fixed-time adaptive sliding mode control (FxT-ASMC) for the trajectory tracking task of a WMR subject to disturbances/uncertainties. The developed control strategy seeks to avoid the chattering problem, cope with disturbances when the upper limit is undefined, and enhance the convergence of the system states. Indeed, a new adaptive technique has been developed to effectively handle disturbances, even in the absence of prior knowledge regarding their upper bound. This technique consists in estimating the switching gain for each channel separately. On the other hand, an appropriate design of the reaching law ensures the fixed-time convergence of the sliding variables to zero. Additionally, sliding variables are designed in a way that guarantees the tracking errors will stabilize within a set amount of time. This kind of convergence was demonstrated using Lypunov stability theory. In order to realize the trajectory tracking control structure, the FxT-ASMC system is incorporated with a classical kinematic controller. The efficiency of the suggested control methodology is proven via simulations and practical implementation.

General-Kindred physics-informed neural network to the solutions of singularly perturbed differential equations

Physics-informed neural networks (PINNs) have become a promising research direction in the field of solving partial differential equations (PDEs). Dealing with singular perturbation problems continues to be a difficult challenge in the field of PINN. The solution of singular perturbation problems often exhibits sharp boundary layers and steep gradients, and traditional PINN cannot achieve approximation of boundary layers. In this manuscript, we propose the General-Kindred physics-informed neural network (GKPINN) for solving singular perturbation differential equations (SPDEs). This approach utilizes asymptotic analysis to acquire prior knowledge of the boundary layer from the equation and establishes a novel network to assist PINN in approximating the boundary layer. It is compared with traditional PINN by solving examples of one-dimensional, two-dimensional, and time-varying SPDE equations. The research findings underscore the exceptional performance of our novel approach, GKPINN, which delivers a remarkable enhancement in reducing the L2 error by two to four orders of magnitude compared to the established PINN methodology. This significant improvement is accompanied by a substantial acceleration in convergence rates, without compromising the high precision that is critical for our applications. Furthermore, GKPINN still performs well in extreme cases with perturbation parameters of 1×10−38, demonstrating its excellent generalization ability.

Improving non-uniform gravelly sand using microbially induced carbonate precipitation: An outdoor cubic-meter scale trial by engineering contractors

Soil improvement using microbially induced carbonate precipitation (MICP) remains largely confined to the laboratory, with only a very small number of large-scale experiments having been completed under field conditions and none by engineering contractors. This study presents a cubic-meter scale improvement of heterogeneous natural sand collected from a local quarry, with a wide variation in grain size, via MICP. The MICP trial was conducted by engineering contractors in a cubic test cell under variable temperatures ranging from 5 °C to 19 °C. The upscaling of cultivation of Sporosarcina pasteurii (600 L for each treatment cycle) under non-sterile conditions, as performed by engineering contractors, achieved an optical density (OD600) of 0.89 and a specific urease activity of 2.5 mM urea/min/OD600. Post-MICP-treated sands were subjected to a series of coring, block sampling and laboratory tests. The block sampling process indicated that the majority of sand was effectively cemented, with a small region near a side wall forming a less well-cemented zone, likely induced by less effective fluid delivery in this region. The unconfined compressive strengths of three cores (diameter: 10 cm, length: 22 cm) were 3.6, 4.4, and 7.6 MPa. Consolidated-drained triaxial tests on sub-sampled cores also demonstrated rock-like material behaviour, with a peak friction angle of 43.6° and peak cohesion of 0.64 MPa, and ultimate state frictional angles of 42.0° and ultimate cohesion of 0.12 MPa. The increased shear parameters of the bio-cemented samples (relative to the untreated samples) have many implications for mitigation of geotechnical hazards such as soil liquefaction. The study marks a step forward industrial implementation of MICP for soil improvement by engineering contractors without prior knowledge of MICP.

Point cloud segmentation neural network with same-type point cloud assistance

This paper proposes neural network architectures for point cloud segmentation, which leverage prior knowledge derived from same-type point clouds. The approach involves concurrent processing of two point clouds: a target point cloud necessitating segmentation and a labeled same-type point cloud. The labeled point cloud provides preliminary labeling information, assisting in segmenting the target point cloud. A feature combination module is proposed to identify and combine corresponding features across the point clouds. The module augments the feature representation of the target cloud and improves its capacity for object discrimination. Experiments on the ShapeNetPart and S3DIS datasets demonstrate that when integrated into classical network architectures, the proposed approach can achieve improved segmentation performance over the corresponding networks, significantly in some of them.

A Two-Stage Online Inertia Estimation: Identification of Primary Frequency Control Parameters and Regression-Based Inertia Tracking

In recent years, power system inertia has significantly decreased and has become more variable due to the massive integration of converter-interfaced renewable energy sources. Real-time awareness of the inertia present in the system is essential for operators to take preventive actions and mitigate potential instability risks. Online inertia tracking methods based on field data have been used to accomplish this task. However, most existing methods are disturbance-based and few have proven effective under normal operating conditions. In addition, some methods require prior knowledge of the primary frequency control dynamics, which are usually unknown, especially in presence of power converters. To overcome these limitations, this paper proposes a two-stage online inertia estimation method. The first stage estimates the primary frequency control parameters. The second stage uses a regression-based approach to track the inertia in real time. A sensitivity analysis of the parameters of the regression model is used to determine the conditions under which the primary frequency control parameters must be updated. The performance of the method is validated using the IEEE 39-bus benchmark network under normal operating conditions and under the occurrence of large disturbances. The algorithm is also tested in the presence of converter-interfaced sources controlled in both grid-following and grid-forming modes. Real-time tests validate the applicability of the method.

Robust visual question answering via polarity enhancement and contrast

The Visual Question Answering (VQA) task is an important research direction in the field of artificial intelligence, which requires a model that can simultaneously understand visual images and natural language questions, and answer questions related to images. Recent studies have shown that many Visual Question Answering models rely on statistically regular correlations between questions and answers, which in turn weakens the correlation between visual content and textual information. In this work, we propose an unbiased Visual Question Answering method to solve language priors from the perspective of strengthening the contrast between the correct answer and the positive and negative predictions. We design a new model consisting of two modules with different roles. We input the image and the question corresponding to it into the Answer Visual Attention Modules to generate positive prediction output, and then use a Dual Channels Joint Module to generate negative prediction output with great linguistic prior knowledge. Finally, we input the positive and negative predictions together with the correct answer to our newly designed loss function for training. Our method achieves high performance (61.24%) on the VQA-CP v2 dataset. In addition, most existing debiasing methods improve performance on VQA-CP v2 dataset at the cost of reducing performance on VQA v2 dataset, while our method not only does not reduce the accuracy on VQA v2 dataset. Instead, it improves performance on both datasets mentioned above.

An effective multi-scale interactive fusion network with hybrid Transformer and CNN for smoke image segmentation

Smoke has visually elusive appearances, especially in low-light conditions, so it is quite difficult to quickly and accurately detect smoke from images. To address these challenges, we design a dual-encoder structure of Transformer and Convolutional Neural Network (CNN) to propose an effective Multi-scale Interactive Fusion Network (MIFNet) for smoke image segmentation. To enhance the presentation of features, we propose a Local Feature Enhancement Propagation (LFEP) module to enhance spatial details. To optimize global and local features for efficient fusion, we integrate LFEP into the original Transformer to replace the traditional multi-head self-attention mechanism. Then, we propose a Multi-level Attention Coupled Module (MACM) to fuse Transformer and CNN features of the dual-encoder. MACM can flexibly focus on information interaction between different levels of two encoding paths. Finally, we design a Prior-guided Multi-scale Fusion Decoder (PMFD), which combines prior knowledge with a multi-scale feature fusion strategy to improve the performance of segmentation. Experimental results demonstrate that MIFNet substantially outperforms the state-of-the-art methods. MIFNet achieves a mean Intersection over Union (mIoU) of 81.6% on the synthetic smoke (SYN70K) dataset, and a remarkable accuracy of 98.3% on the forest smoke dataset.

Detecting damage in composites using volume decomposition analysis of tomographic data

Detection of damage in a single tow ceramic matrix composite specimen has been achieved using orthogonal decomposition of volumetric tomographic datasets collected at four tensile loads. This decomposition approach has been applied at two different length scales: (i) individual fibres and (ii) bulk volumes containing fibres and matrix material. Volumes were first decomposed to feature vectors, orders of magnitude smaller than the original volume they describe, and then comparisons between datasets at different load levels were made in feature vector space. The results show quantitative measurements of damage location, damage morphology and the relative growth of this damage with increased load when compared with a dataset with less or no damage. No prior knowledge of the dataset or training of algorithms is required for damage to be detected, it is only necessary that at least two datasets are available for comparison, e.g. from in situ or repeated scanning measurements. Results are generated on significantly shorter timescales when compared with previous automated approaches to tomography data processing. This approach has the potential to be applied to damage detection in a range of materials through comparisons of volumetric datasets from a range of measurement or computational techniques.

Physical, Chemical And Bacteriological Indicators Of Well Water Around A Necropolis Located In The Urban Area Of The Municipality Of Paraíso Do Tocantins

During the months of September 2023 to July 2024, groundwater samples were collected at 10 sampling sites, distributed in the Sector Oeste neighborhood, in the city of Paraíso do Tocantins, state of Tocantins, with the aim of assessing the quality of groundwater captured in tube wells potentially used for human consumption. For all the groundwater samples, the physicochemical parameters ammonia, chloride, apparent color, hardness, nitrate, nitrite, pH, turbidity and microbiological total and thermotolerant coliforms were analyzed. Based on these results and in order to better understand the physicochemical behavior of these waters, principal component analysis (PCA) was used to carry out a more complete evaluation of the original data. The physicochemical and microbiological parameters assessed in the groundwater collected showed that 90% of the wells had pH values below those recommended in Ordinance GM/MS No. 888/2021 and the presence of total and thermotolerant coliforms in all the water samples from the wells analyzed, which is in disagreement with the legislation. In addition, the PCA explained 49.84% of the total variance of the data, making it possible to assess the degree of similarity between the samples. It is important to have more reliable monitoring and assessment of groundwater in cemetery areas and prior knowledge of the chemical composition of this water, as this is the only way to assess whether any parameter is altered, even if its concentration is equal to or lower than that considered naturally occurring by current legislation.

Combinatorial transition testing in dynamically adaptive systems: Implementation and test oracle

Due to the large number of possible interactions and transitions among features in dynamically adaptive systems, testing such systems poses significant challenges. To verify that such systems behave correctly, combinatorial interaction testing (CIT) can create concise test suites covering all valid pairs of features of such systems. While CIT claims to find all errors caused by two features, it does not cover certain errors occurring only for specific transitions between features. To address this issue we study the technique of Combinatorial Transition Testing (CTT), which includes both generation and detection of what we call behavioural transition errors. From an initial generation algorithm that combines both interaction and transition coverage but lacks scalability, we propose an optimised version that enables CTT even for hundreds of features. From a valid test suite covering all transitions, we complete our testing approach with a test oracle that detects all behavioural transition errors without any prior knowledge of the system’s behaviour. After a comprehensive analysis over a large number of feature models, we conclude that size of CTT-generated test suites and test effort needed to use our test oracle are linearly correlated to CIT-generated ones and that CTT grows logarithmically in the number of features.

Attribute enhanced random walk for community detection in attributed networks

Traditional community detection methods often rely solely on network topology, potentially overlooking the influence of attributes. However, community detection in attributed networks presents a unique challenge due to the complex interplay between network topology and node attributes. In this paper, we present AERW, a novel approach that integrates both network topology and node attributes for effective community detection. AERW leverages the principle of homophily by aggregating neighbor attributes within triangles to capture higher-order structural information. Then constructing a bipartite graph to effectively integrate topological and attribute information, ensuring that both aspects are equally represented in the community detection process. Next AERW utilizes hierarchical clustering applied to the probability transition matrix derived from the random walk, enabling the identification of community structures without needing prior knowledge of the number of communities. Extensive experimentation across synthetic and real-world networks underscores AERW’s efficacy, establishing it as a superior approach in community detection within attributed networks.

ST-SHAP: A hierarchical and explainable attention network for emotional EEG representation learning and decoding

Background:Emotion recognition using electroencephalogram (EEG) has become a research hotspot in the field of human–computer interaction, how to sufficiently learn complex spatial–temporal representations of emotional EEG data and obtain explainable model prediction results are still great challenges. New methodIn this study, a novel hierarchical and explainable attention network ST-SHAP which combines the Swin Transformer (ST) and SHapley Additive exPlanations (SHAP) technique is proposed for automatic emotional EEG classification. Firstly, a 3D spatial–temporal feature of emotional EEG data is generated via frequency band filtering, temporal segmentation, spatial mapping, and interpolation to fully preserve important spatial–temporal-frequency characteristics. Secondly, a hierarchical attention network is devised to sufficiently learn an abstract spatial–temporal representation of emotional EEG and perform classification. Concretely, in this decoding model, the W-MSA module is used for modeling correlations within local windows, the SW-MSA module allows for information interactions between different local windows, and the patch merging module further facilitates local-to-global multiscale modeling. Finally, the SHAP method is utilized to discover important brain regions for emotion processing and improve the explainability of the Swin Transformer model. Results:Two benchmark datasets, namely SEED and DREAMER, are used for classification performance evaluation. In the subject-dependent experiments, for SEED dataset, ST-SHAP achieves an average accuracy of 97.18%, while for DREAMER dataset, the average accuracy is 96.06% and 95.98% on arousal and valance dimension respectively. In addition, import brain regions that conform to prior knowledge of neurophysiology are discovered via a data-driven approach for both datasets. Comparison with existing methods:In terms of subject-dependent and subject-independent emotional EEG decoding accuracies, our method outperforms several closely related existing methods. Conclusion:These experimental results fully prove the effectiveness and superiority of our proposed algorithm.

Deficit to development: rethinking centralised workshops

Centralised academic skills provision has been criticised for being ‘generic’, ‘remedial’, or ‘bolt on’ (Wingate, 2006). Critics argue it takes a deficit approach towards student learning, simplifying academic processes and failing to meet students’ discipline-specific needs. Embedded provision is often seen as the solution. However, embedded does not necessarily mean non-deficit. Indeed, Schneider (2023) highlights that academic tutors can perceive students in relation to skills they are lacking. Subsequently, Learning Developers can be brought in to ‘fix’ students, and as such, embedded sessions may still be disconnected from the curriculum and designed to offer pre-prescribed solutions, reflecting deficit approaches. As Webster (2023) asserts, the Learning Developer’s role is not ‘to give students academic skills’ but rather to help them make sense of the skills and literacies that are hidden in the curriculum. In this workshop, we discussed how we redesigned our entire skills programme using a non-deficit pedagogic approach that aims to help students ‘uncover their curriculum’. Inspired by the University of Manchester’s constructive and collective approach (Blake and Illingworth, 2015), we see our co-curricular offer as providing a unique opportunity to create empowering and developmental learning spaces which sit alongside embedded provision. To meet these aims, our redesign was informed by four principles: Reflection: centring students’ prior knowledge and experience. Collaboration: harnessing knowledge from a community of learners, rather than a ‘sage on the stage’. Choice: students customise their own learning experience, tailoring sessions to meet their own needs. Application: students relate session content to their own discipline and apply learning to their own work. Workshop participants considered debates around deficit thinking in relation to centralised training, working together to redesign learning activities and reflect on the opportunities and challenges of such an approach.

LF-SynthSeg: Label-Free Brain Tissue-Assisted Tumor Synthesis and Segmentation.

Unsupervised brain tumor segmentation is pivotal in realms of disease diagnosis, surgical planning, and treatment response monitoring, with the distinct advantage of obviating the need for labeled data. Traditional methodologies in this domain, however, often fall short in fully capitalizing on the extensive prior knowledge of brain tissue, typically approaching the task merely as an anomaly detection challenge. In our research, we present an innovative strategy that effectively integrates brain tissues' prior knowledge into both the synthesis and segmentation of brain tumor from T2-weighted Magnetic Resonance Imaging scans. Central to our method is the tumor synthesis mechanism, employing randomly generated ellipsoids in conjunction with the intensity profiles of brain tissues. This methodology not only fosters a significant degree of variation in the tumor presentations within the synthesized images but also facilitates the creation of an essentially unlimited pool of abnormal T2-weighted images. These synthetic images closely replicate the characteristics of real tumor-bearing scans. Our training protocol extends beyond mere tumor segmentation; it also encompasses the segmentation of brain tissues, thereby directing the networkâs attention to the boundary relationship between brain tumor and brain tissue, thus improving the robustness of our method. We evaluate our approach across five widely recognized public datasets (BRATS 2019, BRATS 2020, BRATS 2021, PED and SSA), and the results show that our method outperforms state-of-the-art unsupervised tumor segmentation methods by large margins. Moreover, the proposed method achieves more than 92 % of the fully supervised performance on the same testing datasets.

Design and Optimization of an Origami Gripper for Versatile Grasping and Manipulation

Robotic grasping and manipulation demand the ability to handle a multitude of objects with different shapes, sizes, quantities, surface smoothness, vulnerability, and stiffness, which is challenging without prior knowledge about object properties. Herein, a novel origami‐inspired gripper for universal grasping is presented. The innovative structure seamlessly transforms a simple uniaxial pulling motion into a flexible and robust envelope or pinch grasp, enabling it to tackle various scenarios. The origami gripper offers distinctive advantages, including scalable and optimizable design, grasping compliance and robustness, providing material flexibility, and providing solutions to challenging manipulation tasks. The working principles of the origami gripper are characterized and analyzed. An optimization‐based inverse design method is presented to adjust gripper properties for various scenarios. Through comprehensive experimentation and evaluation, the gripper's capabilities to grasp various objects with a wide range of distinctive properties, including ultrasoft, slippery, granular, and multiple objects, which is a challenge for the existing robotic grippers, are demonstrated. The research holds promise for transformative applications in areas such as the food industry, waste handling, fine and fragile objects grasping, and environmental sampling.

The API Model of Strategic and Tactical Marketing Thinking for Management Education

This paper addresses the need to improve marketing education for managers, particularly those from non-economic fields. Research indicates that effectively transferring marketing knowledge involves translating theory into practice, connecting with research, addressing diverse participant needs - relevance, and employing innovative working methods. The study was conducted on a sample of 142 MBA program participants from various non-economic backgrounds, who were presented with and explained the API (analysis, planning, implementation) model of strategic marketing thinking and tactical actions. The results show that visual presentation is a good method for displaying the connections in the model and can even change the perception of marketing. It is important to consider the participants’ prior knowledge of marketing since they show differences in the perceived clarity and usefulness of the model. After being introduced to the model, there are statistically significant differences in the changed perception of its clarity and usefulness among different groups based on their level of prior marketing knowledge. The findings suggest that the API model aids in comprehending environmental complexities and developing effective strategies and tactics, benefiting participants, employers, educators, and society overall.

Erratum to: Quantum search with prior knowledge

Erratum to: Quantum search with prior knowledge

A Study on the Influencing Factors of Problem Foot Care Consumers’ Intention to Visit Nail Shop: Focusing on Extended Planned Behavior Theory

This study studied the intention of consumers to visit a nail shop incorporating the expanded theory of planned behavior to suggest suggestions related to the qualitative growth and marketing strategy of foot health care services. To this end, a measurement tool was prepared through a review of each previous study, and a research analysis was conducted with a total of 300 adult male and female responses through the method of the questionnaire. The main research results of this study according to the above research objectives and methods are summarized as follows. First, as a result of analyzing the effect of the planned behavior theory variable on the intention to visit the nail shop, both attitude and norm and perceived behavioral control had a significant positive effect on the intention to visit the nail shop, and among them, it was analyzed that the positive influence of attitude and norm was stronger. Second, as a result of analyzing the moderating effect of consumer experience characteristics consisting of prior experience and prior knowledge in the influence of the variable of the planning behavior theory on the problem development management of the study subjects on the intention to visit nail shops, both prior experience and knowledge showed no moderating effect. Based on these facts, the conclusions of this study are largely summarized in two ways. First, in order to increase the demand for nail shops that provide problematic foot care services, it is necessary to prepare a management strategy to increase the attitude and norms of problematic foot care service through visits to nail shops. Second, it is necessary to prepare a strategy to positively promote the problematic foot care service in nail shops regardless of new and existing customers.

Acceleration in multilingual children: the case of French

ABSTRACT The acquisition of the null-subject property has received much attention. Languages differ as to whether they allow (pronominal) subjects to be unexpressed. French is generally assumed to be a language not allowing null-subjects, while languages like Italian and European Portuguese are treated as null-subject languages. The present study locates these language types within the null-argument hierarchy. This hierarchy “emerges” through the interaction of (non-language specific) cognitive strategies and linguistic features. In such a hierarchy, Italian and European Portuguese are less marked than French. The study of the longitudinal data of three Italian/Portuguese-French bilingual children between the age of 1;0 to 5;0 shows that bilingual children can reach the French target grammar more quickly than monolingual French-speaking children, even if they have a “weak” language. The children are accelerated with respect to (pronominal) subject realizations and target-like inflection of finite verbs. The findings indicate that bilingual children are not statistical learners, but they can rely on prior knowledge attained in their respective other, radically different, and less marked language. Consequently, educational programs with a focus on multilingualism (like pedagogical translanguaging) which aim to activate prior linguistic knowledge can be effective to compensate for disadvantages related to critical periods.