Mapping Module Research Articles

Photovoltaic power forecasting: A dual-attention gated recurrent unit framework incorporating weather clustering and transfer learning strategy

Accurate forecasting of photovoltaic power is essential in the integration, operation, and scheduling of hybrid energy systems. However, modeling for newly built photovoltaic sites is restricted by insufficient training data and computational burden. In this study, a weather clustering-based photovoltaic power forecasting framework incorporating attention mechanism and transfer learning strategy is proposed. By clustering historical days into multiple weather types, the gated recurrent unit-based encoder-decoders with dual-attention mechanism are designed to predict the photovoltaic power generations. The input attention and temporal attention mechanism are responsible for rebuilding input variables and context vectors of the encoder-decoder structure, respectively. Furthermore, a knowledge-transferring strategy, which focuses on establishing an alignment mapping module between the pre-trained structure and the target domain data, is designed for overcoming insufficient data of newly built sites. The data from the actual photovoltaic system are acquired to validate the proposed framework. The proposed forecasting model presents superior performance than other benchmark models, and the knowledge-transferring strategy not only addresses data shortage but also significantly accelerates the training process. With the introduction of knowledge-transferring, the maximum improvement in forecasting accuracy and training efficiency reaches 67.40% and 59.10%.

Pengembangan Modul Pembelajaran Biologi Berbasis Inkuiri Terbimbing dan Peta Konsep

The learning of biology encompasses two main dimensions, namely products and processes, which ideally should not be separated. However, in practice, dominant biology learning still focuses primarily on the product dimension. One solution to address this issue is to develop guided inquiry-based biology learning modules and concept maps. This developmental research aims to produce biology learning modules that meet valid criteria. The development model used refers to the Plomp model. The instruments used include questionnaires and validation sheets. The validation results by the learning design validator were 95.67 (valid), the biology learning material validator was 91.72 (valid), and the biology subject teacher validator was 94.32 (valid). Thus, the developed guided inquiry-based biology learning module and concept map meet the valid criteria

MATCHING FILTER-BASED VSLAM OPTIMIZATION IN INDOOR ENVIRONMENTS

Abstract. An important factor that reduced the accuracy of motion trajectories in existing VSLAM (Visual Simultaneous Localization and Mapping) systems is the poor estimation of the position pose of the vision odometer. The existing methods generate many incorrect matches during the feature matching process, resulting in low computational accuracy of rotations and translations between cameras, which further leads to a reduction in the robustness of the overall system. In addition, the sparse feature point maps do not provide a detailed description of the surrounding environment, which makes it difficult for the devices equipped with VSLAM systems to perform advanced tasks such as navigation, path planning and human-computer interaction. To address the accuracy problem, we select the set of matches from existing feature matching algorithms based on the motion consistency constraint and use a random sampling consistency algorithm to obtain the best quality matches from the selected samples for computing the geometric transformation model and estimating the current pose. To address the problem of sparse map points, we use the depth information from the RGB-D or Stereo camera to build a dense map module to ensure that information about the surrounding environment is recorded as a point cloud, which provides data support for the implementation of advanced tasks of the device.

Robust multifunctional watermarking system based zero-watermarking and polar harmonic Fourier moments

The pseudo-randomness exhibited by chaotic systems has proven valuable not only in plaintext information encryption of images with varying dimensions but also as a key signal for protecting image copyright information. Image copyright protection is a crucial part of image information protection. Currently, digital watermarking technology is predominantly employed for copyright protection of digital images. However, most of the existing watermarking technologies primarily focus on the improvement of watermarking performance, neglecting the security of the watermarking system itself. Drawing inspiration from the Latin square rule, this paper proposes a novel hyperchaotic mapping modulation framework, which is employed to construct a new 3D hyperchaotic mapping and enhance the security of the fragile watermark and the zero-watermark generation process. Additionally, it is integrated into the classical image encryption framework of scrambling-diffusion to safeguard meaningful copyright information. Moreover, a functional watermarking system is designed based on the RSA asymmetric encryption algorithm, least significant bit (LSB), and polar harmonic Fourier moments (PHFMs). The proposed system enables identity verification, tampering location, and copyright authentication simultaneously. During the generation of zero watermarks, the binarization threshold of the PHFMs information matrix is determined by the method of maximum variance. The experimental results demonstrate that this scheme achieves a high level of security, better robustness to both conventional and geometric attacks, and precise localization for different types of tampering attacks.

SPEED:Semantic Prior and Extremely Efficient Dilated Convolution Network for Real-Time Metal Surface Defects Detection

Automatic defect detection on the metal surface is a vital task for product inspection in industrial assembly lines or production processes. Owing to miscellaneous patterns of defects, inter-class similarity, intra-class difference, and fewer defect samples, achieving accurate and automatic detection remains a big challenge. What's more, since the rising demand for production efficiency, real-time detection is increasingly desirable. This article proposes a semantic prior and extremely efficient dilated convolution network, named SPEED, for pixel-wise detection on the metal surface, which aims to address the aforementioned issues. The architecture of SPEED involves the following: (i) a semantic prior (SP) branch, with shallow layer and prior mapping module to capture low-level details; and (ii) an extremely efficient dilation (EED) branch, with lightweight bottleneck to obtain high-level context. Furthermore, an aggregation module is designed to fuse both types of feature representation. Additionally, different level features of bottleneck are fused to improve the segmentation performance. Experimental results on three metal surface defect datasets indicate that the proposed method outperforms the state-of-the-art approaches in terms of the mean intersection of union, model parameters, FLOPs, and FPS. More specifically, SPEED achieves 92.34% mIoU on NEU-Seg, 88.65% mIoU on Severstal Strip Steel, and 63.91% mIoU on MT Defect.

Multi-Channel Representation Learning Enhanced Unfolding Multi-Scale Compressed Sensing Network for High Quality Image Reconstruction.

Deep Unfolding Networks (DUNs) serve as a predominant approach for Compressed Sensing (CS) reconstruction algorithms by harnessing optimization. However, a notable constraint within the DUN framework is the restriction to single-channel inputs and outputs at each stage during gradient descent computations. This constraint compels the feature maps of the proximal mapping module to undergo multi-channel to single-channel dimensionality reduction, resulting in limited feature characterization capabilities. Furthermore, most prevalent reconstruction networks rely on single-scale structures, neglecting the extraction of features from different scales, thereby impeding the overall reconstruction network's performance. To address these limitations, this paper introduces a novel CS reconstruction network termed the Multi-channel and Multi-scale Unfolding Network (MMU-Net). MMU-Net embraces a multi-channel approach, featuring the incorporation of Adap-SKConv with an attention mechanism to facilitate the exchange of information between gradient terms and enhance the feature map's characterization capacity. Moreover, a Multi-scale Block is introduced to extract multi-scale features, bolstering the network's ability to characterize and reconstruct the images. Our study extensively evaluates MMU-Net's performance across multiple benchmark datasets, including Urban100, Set11, BSD68, and the UC Merced Land Use Dataset, encompassing both natural and remote sensing images. The results of our study underscore the superior performance of MMU-Net in comparison to existing state-of-the-art CS methods.

Robotic tomographic ultrasound and artificial intelligence for management of haemodialysis arteriovenous fistulae.

Arteriovenous fistulae (AVF) and Arteriovenous Grafts (AVG) may present a problematic vascular access for renal replacement therapy (RRT), reliant on recurrent specialist nurse and medical evaluation. Dysfunctional accesses are frequently referred 'out of the dialysis clinic' for specialist sonographic examination, with associated delays potentiating loss of vascular access viability and/or need for emergency intervention. Definitive anatomical and functional diagnostics based in the dialysis unit may help to solve these delays and associated complications. This publication reports a novel vascular access monitoring concept, Robotic Tomographic Ultrasound (RTU). Robotic Tomographic Ultrasound incorporates a semi-autonomous, robotic vascular ultrasound system and purpose designed analysis software that can be deployed at the point of care. Three-dimensional scan data, as well as conventional B-Mode and Doppler data are obtained by the system and transferred to a cloud based reporting and analysis software. Scans are remotely annotated and interpreted by a sonographer, with diagnostic data presented securely to clinicians on their preferred web based application/web connected device. Software developed specifically for pre AVF mapping, maturation and monitoring protocols, analyse the data and then present interpreted results to all caring clinicians to assist with decision making. Vascular access planning can be determined with high confidence with data from the Map module. Maturation data can be presented in line with institutional requirements to the dialysis nurse, facilitating precocious needle access. Robotic Tomographic Ultrasound is a novel approach to vascular access management that may reduce the risk of loss of functional access by regular monitoring with the system; automated alerts guiding clinicians to the need for pre-emptive intervention, and the potential to increase longevity of the vascular access.

Diffusion tensor imaging identifies atrial regional changes associated with atrial fibrillation remodelling

Abstract Background Structural remodeling in the context of persistent atrial fibrillation (PAF) has been mainly characterized by imaging techniques focused on fibrosis detection. Diffusion tensor imaging (DTI) has demonstrated its direct relationship with histological properties and myocyte organization, which may provide a more complete structural information. However, the potential of DTI in the characterization of the AF-related structural substrate remains unknown. Purposes To evaluate the performance of DTI-derived parameters to characterise the structural remodelling derived from persistent AF and its relationship with specific atrial regions associated with AF maintenance (i.e., driver regions). Methods Two experimental groups of pigs were studied: control (n=7) and PAF (n=10). The PAF swine model was developed using rapid atrial pacing until the animals reached a stage of self-sustained PAF. The AV node was ablated to prevent heart failure due to fast ventricular activation rates. A second lead in the right ventricular was used for ventricular pacing at 60-110 bpm. Animals with PAF were studied after ≥ 6 months in self-sustained persistent AF. AF animals underwent invasive electroanatomical to identify driver regions based on instantaneous frequency modulation maps. After euthanasia, explanted hearts from AF animals and controls underwent DTI including 15 diffusion weighted images with a b-value of 600 s/mm² plus a non-DWI volume (isotropic resolution, 0.6 mm³). DTI images were segmented and divided into 13 atrial anatomical regions. Driver regions in AF animals were also segmented and classified as functional regions of interest (ROIs) (Figure 2B). Afterwards, diffusion tensors were estimated and scalar features were analyzed (Figures 1A and 2A) according to both anatomical and functional ROIs. Results DTI analysis in AF animals revealed region-specific structural remodelling (Figure 1B). Compared to controls, PAF animals showed an increased fractional anisotropy (FA) in both right and left atrial free walls (Figure 1C). Other anatomical regions, such as the superior vena cava (SVC), the coronary sinus (CS) or the left atrium roof developed higher axial diffusivities in AF compared to controls (Figure 1D), without significant alterations in FA (Figure 1C). AF driver regions were frequently located in the CS, the SVC and the LAA (Figure 2C). AF driver ROIs into the CS and the SVC showed intracase increased diffusivities and decreased linear indexes compared to non-driver regions. However, AF driver ROIs in the LAA showed increased intervoxel main eigenvector dispersion in contrast to non-driver ROIs (Figure 2C). Conclusion DTI sequences provide atrial structural information associated with functional tissue properties relevant for AF maintenance.

Multi-windowing Technique for 5G and Beyond

Recently, the development of mobile technology has reached a point that requires a high data rate with high waveform aspects. So, traditional ways are no further tolerable. With the dawn of the fifth generation (5G), researchers have been investigating its waveforms and experimenting the methods to improve it. This research examines universal filter multi-carrier (UFMC) for a novel strategy by employing multi-windowing UFMC-based (MW-UFMC) to boost the power spectral density (PSD). This was accomplished by lowering out-of-band emission (OOBE), bit error rate (BER), and adjacent channel leakage ratio (ACLR). The 256quadrature amplitude modulation (256QAM) mapping modulation method was employed in this work. 256QAM is the maximum modulation level that is standard for the third-generation partnership project (3GPP). The proposed MW-UFMC is compared with the conventional UFMC and cyclic prefix orthogonal frequency division multiplexing (CP-OFDM). The proposed multi-windowing technique presents a multistage service that offer a diversity of options to the network operator, which exhibits several advantages over existing methods. These include a lower BER, improved PSD, enhanced spectral efficiency (SE), reduced OOBE that increases capacity for accommodating more bits, decreased ACLR, and lower latency.

Branch-cut phase unwrapping method based on deep learning

ObjectiveAs a typical representative of the phase unwrapping algorithm, the branch-cut method has good anti-noise performance in the phase unwrapping process. However, the branch-cut generated by the traditional branch-cut method cannot accurately block error propagation. MethodThis study proposes a branch-cut phase unwrapping method based on deep learning, which transforms the traditional problem of connecting residual points into a semantic segmentation learning problem, to improve the blocking effect of the branch-cut to the error. The article analyzes the performance of modulation and residue maps in representing phase errors and finds that residue maps have a poor perception of error information in shadow areas in the wrapped phase map. Therefore, a new branch-cut connection criterion is proposed that combines modulation maps and sets the bound of shadow and non-shadow areas as part of branch-cut. Positive and negative residual points are connected by curves along the path of poor modulation, and their polarities are accumulated to maintain branch-cut balance. By using the new branch-cut connection criterion to provide learning samples and using the U-Net++ network structure as the deployment network of branch-cut, the network generates a branch-cut for phase unwrapping, which phase unwrapping path bypasses the branch-cut. ResultsThe experimental results show that the deployment of branch-cut using the U-Net++ network structure can achieve the expected training effect, and the branch-cut generated based on the new connection principle can more effectively block the propagation of errors during phase unwrapping.

Towards reliable and explainable AI model for pulmonary nodule diagnosis

Background and ObjectiveLung cancer has the highest mortality rate of all deadly cancers in the world. Early detection is essential to the treatment of lung cancer. However, detection and accurate diagnosis of pulmonary nodules depend heavily on the experience of radiologists and can be a heavy workload for them. Computer-aided diagnosis (CAD) systems have been developed to assist radiologists in nodule detection and diagnosis, greatly easing the workload while increasing diagnosis accuracy. Recent developments in deep learning have greatly improved the performance of CAD systems. However, the lack of model reliability and interpretability remains a major obstacle for its large-scale clinical application. MethodsWe proposed a multi-task explainable deep-learning model for pulmonary nodule diagnosis, named “ExPN-Net”. The proposed ExPN-Net can not only predict lesion malignancy but also identify nodule characteristics. Further, the location of each characteristic can also be visualized for visual interpretability. We first used 3D nnU-Net to obtain the probability maps of lung nodules, which were used as attention for the following classification task. Then, we used an anatomical attention gate (AAG) mechanism to introduce the spatial attention information into the classification network. Finally, the soft activation map (SAM) module is used to generate fine-grained activation maps to indicate the nodule characteristics. To evaluate the performance, we validated ExPN-Net on both public and in-house datasets. 624 and 807 participants were enrolled from the public LIDC and our-inhouse datasets, respectively. The roles of different modules in ExPN-Net are analyzed by ablation experiments. ResultsExPN-Net achieved a test AUC of 0.992 and 0.923 on the LIDC public and in-house datasets, respectively. Moreover, experimental results proved that by incorporating characteristic identification tasks into the multi-task model, the accuracy of the malignancy classification can also be improved. ConclusionsThis work successfully updates the state-of-the-art diagnosis accuracy of pulmonary nodules by incorporating characteristics and anatomical attention mechanism. Furthermore, our multi-task explainable model provides a solution for AI models to better interact with radiologists in a clinical environment. Source code is available at: https://github.com/KumoLiu/explainablePN.

The New Four-Dimensional Fractional Chaotic Map with Constant and Variable-Order: Chaos, Control and Synchronization

Using fractional difference equations to describe fractional and variable-order maps, this manuscript discusses the dynamics of the discrete 4D sinusoidal feedback sine iterative chaotic map with infinite collapse (ICMIC) modulation map (SF-SIMM) with fractional-order. Also, it presents a novel variable-order version of SF-SIMM and discusses their chaotic dynamic behavior by employing a distinct function for the variable fractional-order. To establish the existence of chaos in the suggested discrete SF-SIMM, some numerical methods such as phase plots, bifurcation and largest Lyapunov exponent diagrams, C0 complexity and 0–1 test are utilized. After that, two different control schemes are used for the conceived discrete system. The states are stabilized and asymptotically forced towards zero by the first controller. The second controller is used to synchronize a pair of maps with non–identical parameters. Finally, MATLAB simulations will be executed to confirm the results provided.

Heritage applications of landscape design in environmental art based on image style migration

To create environmental art on the basis of preserving environmental and ecological resources, landscape design considers the peaceful coexistence of art and ecology. In picture generation and rendering for landscape design, image style migration techniques are frequently employed, however their quality is still lacking at this point. In order to enhance the migration effect, the study builds an image style migration model for landscape design, tries to employ a multi-scale discriminator, and introduces a content feature mapping module and a migration learning approach. According to the test results, adding the content feature mapping module enhanced the feature mapping effect of the photographs. The revised model's peak signal-to-noise ratio and similarity assessment indexes were 17.42 and 0.91, respectively, and the model's generated images were less distorted. While the Frey interval distance was only 16.32 and the generated images were strongly correlated, the model had good generalisation. The addition of migration learning somewhat improves all of the measures. In conclusion, the research findings are beneficial for the expression of environmental art in landscape design, and the model's picture creation assessment index and stability are both good.

BF3D: Bi-directional fusion 3D detector with semantic sampling and geometric mapping

3D object detection is a key task in environmental awareness, which plays a vital role in autonomous driving safety. Lidars and cameras are widely used sensors that provide complementary information for accurate 3D detection. However, due to the domain difference between the two modalities, it is challenging to leverage their respective strengths and fuse them perfectly. In this paper, an end-to-end detector termed BF3D is proposed, which integrates with the semantic sampling module, geometric point-image mapping module, and bi-directional attention fusion module. Specifically, the semantic sampling module incorporates a novel downsampling strategy to preserve more foreground points and pixels. Additionally, the geometric point-image mapping module is developed to find geometric correlation pixels of the point and take advantage of the high density of image features. We also introduce a bi-directional attention fusion module to combine useful information from the two modalities by attention mechanism. Extensive experiments demonstrate that BF3D outperforms both single- and multi-modal 3D detectors. Codes are available at: https://github.com/hustzyj/BF3D.

Small Object Navigation with Context Information

We introduce a novel framework designed to effectively address the object goal navigation task, specifically focusing on smaller daily household objects such as bowls or mugs. These diminutive objects present challenges to existing SLAM-based semantic mapping methods, as the object detection module employed in the mapping pipeline struggles to accurately detect them. To address this limitation, we propose to use a probabilistic semantic map. It is updated by a trained mapping module that incorporates contextual information to estimate the likelihood of object presence within the agent's current field of view. Subsequently, this probabilistic map guides the agent towards more promising areas for object search. Our experimental results demonstrate that the proposed method surpasses the SOTA approach by 26% in Small Object Navigation tasks.

A Graph-Based Hybrid Reconfiguration Deformation Planning for Modular Robots.

The self-reconfigurable modular robotic system is a class of robots that can alter its configuration by rearranging the connectivity of their component modular units. The reconfiguration deformation planning problem is to find a sequence of reconfiguration actions to transform one reconfiguration into another. In this paper, a hybrid reconfiguration deformation planning algorithm for modular robots is presented to enable reconfiguration between initial and goal configurations. A hybrid algorithm is developed to decompose the configuration into subconfigurations with maximum commonality and implement distributed dynamic mapping of free vertices. The module mapping relationship between the initial and target configurations is then utilized to generate reconfiguration actions. Simulation and experiment results verify the effectiveness of the proposed algorithm.

Tightly coupled laser-inertial pose estimation and map building based on B-spline curves

Simultaneous localization and mapping (SLAM) plays a key role in 3D environment modeling and mobile robot environment perception. However, the traditional discrete-time Laser-inertial SLAM methods are not robust due to the imbalanced registration steps between a single LiDAR frame and the global map. This paper proposes a tightly coupled laser-inertial pose estimation and map building method that uses B-spline curves to represent continuous-time trajectory and achieve high robustness of the registration steps. To ensure efficiency, the proposed method separates the SLAM task into an odometer module and a mapping module. The odometer module performs a coarse pose estimation, while the mapping module performs a fine one and builds a global map with 3D LiDAR points. B-spline curves are utilized to integrate both IMU measurement constraints and LiDAR point constraints in the proposed mapping module, which can enhance the association of consecutive LiDAR frames in the optimization step. Besides, the explicit expression of the Jacobi matrix derivation for B-spline-based laser residuals is also introduced to furtherly improve the computation efficiency. Both indoor and outdoor experiments are conducted on a self-collected dataset and a public dataset. Experimental results show that the proposed method can achieve superior performance than the baseline method LIO-mapping.

KisanQRS: A deep learning-based automated query-response system for agricultural decision-making

Delivering prompt information and guidance to farmers is critical in agricultural decision-making. Farmers’ helpline centres are heavily reliant on the expertise and availability of call centre agents, leading to inconsistent quality and delayed responses. To this end, this article presents Kisan Query Response System (KisanQRS), a Deep Learning-based robust query-response framework for the agriculture sector. KisanQRS integrates semantic and lexical similarities of farmers’ queries and employs a rapid threshold-based clustering method. Before clustering, KisanQRS employs data cleaning by performing steps such as the removal of special characters and extra white spaces. It also removes crop names from the queries, which helps in putting similar queries to the same clusters irrespective of the crop. Subsequently, semantic and lexical similarities of queries are computed, and a final similarity matrix is generated based on the weighted sum of these two similarities. Next, a clustering algorithm is applied to organize the queries into clusters according to their similarity. A query mapping module is trained on these cluster labels as the target. For this query mapping module, LSTM is found to be the optimal method. Next, the answer retrieval method clusters candidate answers for a crop, ranks these answer clusters based on the number of answers in a cluster, and selects the leader of each cluster, finally providing the top-K answers. The dataset used in our analysis consists of a subset of 34 million call logs from the Kisan Call Centre (KCC), operated under the Government of India. We evaluated the performance of the query mapping module on the data of five major states of India with 3,00,000 samples and the quantifiable outcomes demonstrate that KisanQRS significantly outperforms traditional techniques by achieving 96.58% top F1-score for a state. The answer retrieval module is evaluated on 10,000 samples and achieves a competitive NDCG score of 96.20%. KisanQRS could be useful in enabling farmers to make informed decisions about their farming practices by providing quick and pertinent responses to their queries.

Visual perception-oriented quality assessment for high dynamic range stereoscopic omnidirectional video system

High dynamic range stereoscopic omnidirectional video (HSOV) system provides users with an immersive visual experience, but the distortions generated in the process of visual content generation, coding, and visualization also brings challenges to visual quality assessment. This paper proposes a visual perception-oriented quality metric for HSOV system. Considering the computational efficiency, for frames within each second, several key frames are selected so that features reflecting distortions can be extracted from the viewports and equi-angular cubemap (EAC) projection surfaces of these frames. In viewport feature extraction module, the sum and difference maps of the left and right views of the key frames are used to simulate the binocular perception. Considering that distortions will affect the structure, color and statistical properties of the image, the gradient, local binary pattern and statistical features are extracted, respectively. To reduce projection distortion, EAC projection is used to instead of other projections normally used in quality assessment, and the Sigma domain feature extraction and color feature extraction are performed on EAC projection map. In temporal feature extraction module, wavelet decomposition is used to perform temporal domain bandpass filtering on partial continuous frames to calculate the naturalness features. Finally, the above features of the frames at different scales are pooled through random forest model to predicate the quality score of HSOV. Experimental results on the NBU-HSOVD dataset show that the proposed metric is superior to some blind image/video quality assessment metrics and has higher consistency with the human visual perception.

Improving semantic segmentation with knowledge reasoning network

Most methods cannot segment the semantic regions accurately due to the lack of global-level supervision or guidance of external knowledge. To overcome this limitation, we propose a Knowledge Reasoning Network (KRNet) that consists of two crucial modules: (1) a prior knowledge mapping module that incorporates external knowledge by graph convolutional network to guide learning semantic representations and (2) a knowledge reasoning module that correlates these representations with a graph built on the external knowledge and explores their interactions via the knowledge reasoning. In the prior knowledge mapping module, we adopt an algorithm to mine knowledge from an external large-scale relational modeling dataset. In the knowledge reasoning module, we adopt an iterative mechanism to perform knowledge reasoning and explore the interaction between features. Reasoning makes the spatial distribution of categories more significant. We establish state-of-the-art results on Cityscapes and ADE20K datasets, which demonstrates the effectiveness of our methods on semantic segmentation.