Previously, pseudomyogenic hemangioendothelioma (PMHE) is regarded as epithelioid sarcoma-like hemangioendothelioma due to significant histologic overlapping and diffuse cytokeratin expression since the first description in 1992. After considerable controversy and long-term debating, it is currently defined as a distinct intermediate malignant, rarely metastasizing neoplasm with vascular/endothelial differentiation in nature. PMHE is characterized by young age (typically < 40 years old) and extremity location (approximately ~80%) with t(7:19) SERPINE1-FOSB fusion as the most common molecular alteration. Here we reported a 59-year-old male presenting with multifocal lesions, including right temporalis muscle, right frontoparietal calvarium, right pterygoid muscles, and right mandibular condyle. Histologic examination of the lesion from right temporal mass revealed a multinodular biphasic lesion composed of sheets and fascicles of elongated spindle cells, and epithelioid small round to ovoid cells infiltrating into the adjacent skeletal muscle admixed with abundant neutrophilic infiltration. No rhabdomyoblast-like cells, prominent nuclear pleomorphism and mitosis were identified. IHC staining showed that the tumor cells were diffusely and strongly positive for FOSB, pan-cytokerain (AE1/AE3), CD31, ERG, and molecular testing further demonstrated a t(9:19) EGFL7::FOSB fusion mRNA. This constellation of morphological, IHC and molecular findings was consistent with the diagnosis of PMHE. This is the first reported case of multiple PMHEs with EGFL7::FOSB fusion in a patient aged more than 50 years old in the head and neck area. Since the vast majority of the differential diagnoses of PMHE are high-grade malignancies with aggressive clinical behavior and PMHE is rarely reported in the head and neck region, awareness of this tumor will avoid misdiagnosis and over-treatments of this entity.

High-power laser facilities necessitate predicting incremental damage to final optics to identify evolving damage trends. In this study, we propose a surface damage detection method utilizing image segmentation employing ResNet-18, and a damage area estimation network employing U-Net++. Paired sets of online and offline images of optics obtained from a large laser facility is used to train the network. The trends of varying damage could be identified by incorporating additional experimental parameters. A key advantage of the proposed method is that the network can be trained end-to-end on small samples, eliminating the need for manual labeling or feature extraction. The software developed based on these models can facilitate the daily inspection and maintenance of optics in large laser facilities.

A portable laser photoacoustic sensor based on a Field-Programmable Gate Array (FPGA) is reported for methane detection. A tunable DFB diode laser in the 1654 nm wavelength range is used as an excitation source. The photoacoustic signal processing was implemented by a FPGA device. A small resonant photoacoustic cell is designed. The minimum detection limit (1σ) of 10 ppm for methane (CH₄) is demonstrated.

To ensure consumers can purchase high-quality rice, accurate identification of rice varieties is particularly important. Methods: This article conducts research based on machine learning algorithms from the perspectives of image, spectrum, and spectrogram fusion. Six types of hyperspectral image data of rice were preprocessed using convolutional smoothing (SG) and multiple scatter correction (MSC). Texture information of the images was extracted using gray-level co-occurrence matrix. Spectra, texture, and spectrogram data were fused into a new matrix. Spectral, texture, and spectrogram fusion data were used as inputs for the model, and support vector machines (SVM), logistic regression (LR), and K-nearest neighbors (KNN) classification models were constructed and compared. Results: From the classification results, the spectrogram fusion classification performance was better than classification models using only spectra or texture. Conclusion: The research results showed that the accuracy of SVM and LR classification models exceeded 90%, and the LR model performed the best, effectively classifying rice varieties.

This study extends the CGAN-based MODIS cloud vertical-profile (64×64-scene, about 70km width×15km height) retrieval technique developed by Leinonen et al. (2019) [1] to construct seamless 3D cloud fields for the MODIS granules [2]. Firstly, the accuracy and spatial continuity of the Leinonen et al. [1] retrievals are statistically evaluated. Then, according to the characteristics of the retrieval error, a spatially overlapping-scene ensemble generation method and a bi-directional Ensemble Binning Probability Fusion (CGAN-BEBPF) technique are developed, which improves the CGAN retrieval accuracy and support to construct seamless 3D clouds. The CGAN-BEBPF technique involves three steps: cloud masking, intensity scaling, and optimal value selection. It ensures adequate coverage of the low reflectivity areas while preserving the high reflectivity cloud cores. The technique is applied to retrieve the 3D cloud fields of Typhoon Chaba and a multi-cell convective system. The cloud structures of the CGAN-BEBPF results are highly consistent with the ground-based radar observations. It can retrieve weak clouds at the top levels of convective storms and hurricanes that were missed by ground-based radars and fill the gaps of the ground-based radar lower-level PPI scan. Overall, CGAN-BEBPF can be automated to retrieve the rich informative 3D structures of typhoons and severe convective systems over the oceans along the MODIS swath, which certainly presents great value for improving maritime and near-shore typhoons and convection prediction and other cloud-sensitive applications.

Ambulatory heart rate (HR) monitors that acquire electrocardiogram (ECG) or/and photoplethysmographm (PPG) signals from the torso, wrists, or ears are notably less accurate in tasks associated with high levels of movement compared to clinical measurements. However, reliable estimation of HR can be obtained through data fusion from different sensors. These methods are especially suitable for multimodal hearable devices, where heart rate can be tracked from different modalities, including electrical ECG, optical PPG, and sounds (heart tones). Combined information from different modalities can compensate for single source limitations. In this paper, we evaluate the possible application of data fusion methods in hearables. We assess data fusion for heart rate estimation from simultaneous in-ear ECG and in-ear PPG, recorded on eight subjects while performing 5-minute sitting and walking tasks. Our findings show that data fusion methods provide a similar level of mean absolute error as the best single-source heart rate estimation but with much lower intra-subject variability, especially during walking activities. We conclude that data fusion methods provide more robust HR estimation than a single cardiovascular signal. These methods can enhance the performance of wearable devices, especially multimodal hearables, in heart rate tracking during physical activity.

In pattern recognition domain, deep architectures are widely used nowadays and they have achieved fine grades. However, these deep architectures need special demands, especially big datasets and GPU. Aiming to gain better grades without deep networks, we propose a simplified algorithm framework using fusion features extracted from the salient areas of faces. Furthermore, the proposed algorithm has achieved a better result than some deep architectures. For extracting more effective features, this paper firstly defines the salient areas on the faces. This paper normalizes the salient areas of the same location in the faces to the same size, therefore it can gain more similar features from different subjects. LBP and HOG features are extracted from the salient areas, fusion features’ dimensions are reduced by Principal Component Analysis( PCA) and we apply softmax to classify the six basic expressions at once. This paper proposes a salient areas definitude method which uses peak expressions frames to compare with their neutral faces. This paper also proposes and applies the idea of normalizing the salient areas to align the specific areas which express the different expressions. This makes the salient areas found from different subjects have the same size. Besides, gamma correction method is firstly applied on LBP features in our algorithm framework which improves our recognition rates significantly. By applying this algorithm framework, our research has gained state-of-the-art performances on CK+ database and JAFFE database.

This paper proposes a new approach for multi-focus images fusion based on Region Mosaicing on Contrast Pyramids (REMCP). A density-based region growing method is developed to construct a focused region mask for multi-focus images. The segmented focused region mask is decomposed into a mask pyramid, which is then used for supervised region mosaicking on a contrast pyramid. In this way, the focus measurement and the continuity of focused regions are incorporated and the pixel level pyramid fusion is improved at the region level. Objective and subjective experiments show that the proposed REMCP is more robust to noise than compared algorithms and can fully preserves the focus information of the multi-focus images meanwhile reducing distortions of the fused images.

In this paper, we proposed the fusion of two projection based face recognition algorithms: local binary Patterns in DCT domain and singular value decomposition (SVD) characterized by its simplicity and efficiently. Standard databases ORL are used to test the experimental results which prove that proposed system achieves more accurate face recognition as compared to individual method.

In order to improve contrast and restore color for underwater image captured by camera sensors without suffering from insufficient details and color cast, a fusion algorithm for image enhancement in different color spaces based on contrast limited adaptive histogram equalization (CLAHE) is proposed in this article. The original color image is first converted from RGB color space to two different special color spaces: YIQ and HSI. The color space conversion from RGB to YIQ is a linear transformation, while the RGB to HSI conversion is nonlinear. Then, the algorithm separately operates CLAHE in YIQ and HSI color spaces to obtain two different enhancement images. The luminance component (Y) in the YIQ color space and the intensity component (I) in the HSI color space are enhanced with CLAHE algorithm. The CLAHE has two key parameters: Block Size and Clip Limit, which mainly control the quality of CLAHE enhancement image. After that, the YIQ and HSI enhancement images are respectively converted backward to RGB color. When the three components of red, green, and blue are not coherent in the YIQ-RGB or HSI-RGB images, the three components will have to be harmonized with the CLAHE algorithm in RGB space. Finally, with 4 direction Sobel edge detector in the bounded general logarithm ratio operation, a self-adaptive weight selection nonlinear image enhancement is carried out to fuse YIQ-RGB and HSI-RGB images together to achieve the final fused image. The enhancement fusion algorithm has two key factors: average of Sobel edge detector and fusion coefficient, and these two factors determine the effects of enhancement fusion algorithm. A series of evaluate metrics such as mean, contrast, entropy, colorfulness metric (CM), mean square error (MSE) and peak signal to noise ratio (PSNR) are used to assess the proposed enhancement algorithm. The experiments results showed that the proposed algorithm provides more detail enhancement and higher values of colorfulness restoration as compared to other existing image enhancement algorithms. The proposed algorithm can suppress effectively noise interference, improve the image quality for underwater image availably.

The last-mile logistics in cities have become an indispensable part of the urban logistics system. This study aims to explore the effective selection of last-mile logistics nodes to enhance the efficiency of logistics distribution, strengthen the corporate distribution image, and further reduce corporate operating costs and alleviate urban traffic congestion. This paper proposes a clustering-based approach to identify urban logistics nodes from the perspective of geographic information fusion. This method comprehensively considers several key indicators, including the coverage, balance, and urban traffic conditions of logistics distribution. Additionally, we employed a greedy algorithm to identify secondary nodes around primary nodes, thus constructing an effective nodal network. To verify the practicality of this model, we conducted an empirical simulation study using the logistics demand and traffic conditions in the Xianlin District of Nanjing. This research not only identified the locations of primary and secondary logistics nodes but also provided a new perspective for constructing the urban last-mile logistics system, enriching the academic research related to logistics node construction. The results of this study are of significant theoretical and practical importance for optimizing urban logistics networks, enhancing logistics efficiency, and promoting the improvement of urban traffic conditions.

Background/Objectives:The first attempts of posterior lumbar interbody fusion can be traced back to the 1940s, where their performance was marked by animosity due to high rates of failure. Nowadays, the use of interbody fusion involves a much more complicated consideration of factors such as global alignment, disc height, fusion rates, and operative risk, all combined at once.Our study aims to examine all these effects using Flarehawk 9 as a means of interbody fusion.Materials and methods: A total of 58 patients underwent open posterior lumbar surgery using Flarehawk 9 between September 2021 and February 2023 with a mean follow up of 1 year.The mean age was 59.8 years old ( range between 33 and 79 years old), 36 of them are males while 22 of them are females. The diagnostic groups included spinal canal stenosis (n=40), failed back surgery syndrome-revision surgery (n=5),spondylolisthesis with slip percentage 25% (n=4),recurrent herniated disc (n=7) and adjacent segment disease (n=2). Results: The majority of patients demonstrated remarkable improvement based on ODI scores.The rate of union varied based on the fused levels and whether the patients had previous surgery or not.The amount of lordosis postoperatively is increased by 2±0.4 degrees.Conclusions: Even though anterior approaches become more and more popular and advanced nowadays, posterior fusion with interbody cage still remains a safe and effective method to treat various spine surgical pathologies with optimal results.

Chromium (Cr) metal has garnered significant attention in alloy systems owing to its exceptional properties, such as high melting point, low density, and superior oxidation and corrosion resistance. However, its processing capabilities are hindered by the high Ductile-Brittle Transition Temperature (DBTT). Recently, powder bed fusion-laser beam for metals (PBF-LB/M) has emerged as a promising technique, offering the fabrication of net shapes and precise control over crystallographic texture. Nevertheless, research investigating the mechanism underlying crystallographic texture development in pure Cr via PBF-LB/M still needs to be conducted. This study explores the impact of scan speed on relative density and crystallographic texture. At the optimal scan speed, an increase in grain size attributed to epitaxial growth was observed, resulting in the formation of cubic texture. Consequently, a reduction in High Angle Grain Boundaries (HAGB) was achieved, suppressing defects such as cracks and enhancing relative density up to 98.1%. Furthermore, with increasing densification, Vickers hardness also exhibited a corresponding increase. These findings underscore the efficacy of PBF-LB/M for processing metals with high DBTT properties.

Introduction: Anterior cervical discectomy and fusion (ACDF) for cervical disc herniation (CDH) is commonly performed. Specific postoperative complications include dysphagia, dysphonia, cervicalgia, adjacent segment disorder, cage subsidence, and infections. However, interscapular pain is commonly reported by these patients after surgery, although its mechanisms have been not clarified yet. Methods: This retrospective series of 31 patients undergoing ACDF for CDH at a single Academic Hospital. Baseline and postoperative clinical, radiological, and surgical data were analyzed. The linear regression analysis was conducted to identify any factor independently influencing the occurrence rate of postoperative interscapular pain. Results: The mean age was 57.6±10.8 years, and the M:F ratio was 2.1. The preoperative mean VAS-arm was 7.15±0.81 among the 20 patients reporting brachialgia, and the mean VAS-neck was 4.36±1.43 among those 9 patients reporting cervicalgia. At 1 month interscapular pain was still reported by 8 out of the 17 patients who experienced it postoperatively, and it was recovered in all patients after 2 months. The regression analysis showed how the interscapular pain was not directly associated to age(p=0,74), gender(p=0,46), smoking status(p=0,44), diabetes(0,42), preoperative brachialgia(p=0,21) or cervicalgia(p=0,48), symptoms duration(p=0,13), baseline VAS-arm(p=0,11), VAS-neck(p=0,93), or mJOA(p=0,63) scores, or disc height modification(p=0,90). However, the postoperative increase of the mean zygapophyseal joint rims distance was identified as an independent factor in determining interscapular pain (p=0,02). Conclusions: Our study revealed that the onset of interscapular pain following ACDF may be determined by over-distraction of the zygapophyseal joints rim. Then, proper sizing of prosthetic implants could reduce this painful complication.

Dissimilar welds between ferritic and austenitic steels represent a good solution for exploiting the best performance of stainless steels at high and low temperatures and in aggressive environments, while minimizing costs. Therefore, they are widely used in nuclear and petrochemical plants, however, due to the different properties of the steels involved, the welding process can be challenging. Fusion welding can be specifically addressed to connect low-carbon, or low-alloy steels, with high-alloy steels, which have similar melting point. Welding of thick plates can be performed with electric arc in multiple passes or in a single pass by means of a laser beam equipment. Since microstructure and consequently mechanical properties of the weld are closely related to composition, the choice of the filler metal and processing parameters, which in turn affects the dilution rate, plays a fundamental role. Numerous technical solutions were proposed for welding dissimilar steels and much research was developed on the weldment metallurgy; therefore, this article is aimed at a review of the most recent scientific literature on the issues relating to the fusion welding of ferritic / austenitic steels. Two specific sections are dedicated respectively to electric arc and laser beam welding; finally, metallurgical issues, related to dilution and thermal field are debated in the discussion section.

Nuclear fusion is essential for the sexual reproduction of various organisms, including plants, animals, and fungi. During the life cycle of flowering plants, nuclear fusion occurs three times: once during female gametogenesis and twice during double fertilization, when two sperm cells fertilize the egg and the central cell. Haploid nuclei migrate in an actin filament-dependent manner to become in close contact, then two nuclei fuse. The nuclear fusion process in plant reproduction is achieved by the sequential nuclear membrane fusion events. Recent molecular genetic analyses using Arabidopsis thaliana showed the conservation of nuclear membrane fusion machinery between plants and the budding yeast Saccharomyces cerevisiae. These include the heat shock protein 70 in the endoplasmic reticulum and conserved nuclear membrane proteins. Analyses of A. thaliana mutants of these components show that completion of the sperm nuclear fusion at fertilization is essential for proper embryo and endosperm development.

Sensor fusion algorithms and models have been widely used in recent times. Although research evidence has informed the use of sensor fusion models in diverse applications, there is room for improvement, especially in home-based health monitoring applications which require less supervision and technical knowledge of users. The present work compares data mining-based fusion software packages such as RapidMiner Studio, Anaconda, Weka, and Orange, and proposes a data fusion framework suitable for in-home applications. 574 privacy-friendly (binary) images and 1,722 datasets gleaned from thermal and Radar sensing solutions respectively, were fused using the software packages on instances of homogeneous and heterogeneous data aggregation. Experimental results indicated that the proposed fusion framework achieved an average Classification Accuracy of 84.7% and 95.7% on homogeneous and heterogeneous datasets respectively, with the help of data mining and machine learning models such as Naïve Bayes, Decision Tree, Neural Network, Random Forest, Stochastic Gradient Descent, Support Vector Machine, K-Nearest Neighbours and CN2 induction. Further evaluation of the sensor data fusion framework based on cross validation of features indicated average values of 94.4% for Classification Accuracy, 95.7% Precision and 96.4% for Recall.

In the context of Shared Autonomous Vehicles, the need to monitor the environment inside the car will be crucial. This article focuses on the application of deep learning algorithms to detect objects, namely lost/forgotten items to inform the passengers, and aggressive items to monitoring if violent actions may arise between passengers. For object detection algorithms was used public datasets (COCO and TAO) to train state-of-the-art algorithms, such as YOLOv5. For violent action detection was used the MoLa InCar dataset to train on state-of-the-art algorithms such as I3D, R(2+1)D, SlowFast, TSN and TSM. At the end an embedded automotive solution was used to demonstrate both methods running in real-time.

The market for autonomous vehicles (AV) is expected to experience significant growth over the coming decades and to revolutionize the future of transportation and mobility. The AV is a vehicle that is capable of perceiving its environment and perform driving tasks safely and efficiently with little or no human intervention and is anticipated to eventually replace conventional vehicles. Self-driving vehicles employ various sensors to sense and perceive their surroundings and, also rely on advances in 5G communication technology to achieve this objective. Sensors are fundamental to the perception of surroundings and the development of sensor technologies associated with AVs has advanced at a significant pace in recent years. Despite remarkable advancements, sensors can still fail to operate as required, due to for example, hardware defects, noise and environment conditions. Hence, it is not desirable to rely on a single sensor for any autonomous driving task. The practical approaches shown in recent research is to incorporate multiple, complementary sensors to overcome the shortcomings of individual sensors operating independently. This article reviews the technical performance and capabilities of sensors applicable to autonomous vehicles, mainly focusing on vision cameras, LiDAR and Radar sensors. The review also considers the compatibility of sensors with various software systems enabling the multi-sensor fusion approach for obstacle detection. This review article concludes by highlighting some of the challenges and possible future research directions.

Face verification for unrestricted faces in the wild is a challenging task. This paper proposes a method based on two deep convolutional neural networks(CNN) for face verification. In this work, we explore to use identification signal to supervise one CNN and the combination of semi-verification and identification to train the other one. In order to estimate semi-verification loss at a low computation cost, a circle, which is composed of all faces, is used for selecting face pairs from pairwise samples. In the process of face normalization, we propose to use different landmarks of faces to solve the problems caused by poses. And the final face representation is formed by the concatenating feature of each deep CNN after PCA reduction. What's more, each feature is a combination of multi-scale representations through making use of auxiliary classifiers. For the final verification, we only adopt the face representation of one region and one resolution of a face jointing Joint Bayesian classifier. Experiments show that our method can extract effective face representation with a small training dataset and our algorithm achieves 99.71% verification accuracy on LFW dataset.

In the dynamic landscape of E-commerce, the proliferation of user-generated queries regarding products highlights the critical need for advanced automatic question answering (AQA) systems. These systems are instrumental in harnessing the vast array of information available online to deliver immediate and informative responses to potential buyers. Recognizing the complexity of such queries, which often require synthesis of reviews, product specifications, and responses to similar questions, we introduce a sophisticated model, the Comprehensive E-commerce Answer Generation System (CEAGS). This model adeptly navigates the challenges posed by irrelevant data and sentiment ambiguity in user-generated content. Our approach leverages a dual-phase process of relevance determination and sentiment clarity, setting the stage for a transformative response generation mechanism. Empirical analyses reveal the superiority of CEAGS, with our relevance assessment framework outstripping existing models by a notable margin in precision metrics, and our answer generation module achieving unprecedented gains in content preservation and coherence. Notably, CEAGS marks a pioneering contribution to the E-commerce domain by integrating disparate information sources to formulate responses that are not only accurate but also contextually rich and user-centric.

Aiming at the problems that are poor generalization performance, low retrieval accuracy and large time consumption of existing content-based image retrieval system, the hierarchical image retrieval method based on multi feature fusion is proposed in this paper. The retrieval accuracy rates on Corel5K, UKbeach and Holidays are 68.23(Top 1), 3.73(N-S) and 88.20(mAp), respectively. The experimental results show that the method proposed in this paper can effectively improve the deficiency of single feature retrieval and save time significantly in the premise of a small amount of loss of accuracy.

This paper investigates the effect of Fe contamination on the microstructure and mechanical properties of Al-7Si-0.7Mg-Fe2.5 alloy processed by Laser Powder Bed Fusion (LPBF) and heat treated in two different conditions: (1) Solution Heat Treatment (SHT) at 520 °C, followed by artificial ageing at 160 °C (T6), and (2) Direct Artificial Ageing of the as-printed material at 160 °C (DAA). Microstructural characterization was carried out by Optical Microscopy (OM), X-Ray Diffraction (XRD), Scanning Electron Microscopy (SEM), and Transmission Electron Microscope (TEM). Mechanical characterization was carried out by tensile tests at room temperature. The formation of fine AlSiFe phases such as α-AlFeSi, β-AlFeSi, and π-Al8Si6Mg3Fe had no deleterious effect on the mechanical properties compared to previous studies for AlSIMg alloys without Fe. However, compared to the as-printed condition, the T6 heat treatment decreased the ultimate tensile strain significantly, while the elongation to the fracture presented a slight improvement.

Wetlands benefits can be summarized but are not limited to their ability to store floodwaters and improve water quality, providing habitats for wildlife and supporting biodiversity, as well as aesthetic values. Over the past few decades, remote sensing and geographical information technologies has proven to be a useful and frequent applications in monitoring and mapping wetlands. Combining both optical and microwave satellite data can give significant information about the biophysical characteristics of wetlands and wetlands` vegetation. Also, fusing data from different sensors, such as radar and optical remote sensing data, can increase the wetland classification accuracy. In this paper we investigate the ability of fusion two fine spatial resolution satellite data, Sentinel-2 and the Synthetic Aperture Radar Satellite, Sentinel-1, for mapping wetlands. As a study area in this paper, Balikdami wetland located in the Anatolian part of Turkey has been selected. Both Sentinel-1 and Sentinel-2 images require pre-processing before their use. After the pre-processing, several vegetation indices calculated from the Sentinel-2 bands were included in the data set. Furthermore, an object-based classification was performed. For the accuracy assessment of the obtained results, number of random points were added over the study area. In addition, the results were compared with data from Unmanned Aerial Vehicle collected on the same data of the overpass of the Sentinel-2, and three days before the overpass of Sentinel-1 satellite. The accuracy assessment showed that the results significant and satisfying in the wetland classification using both multispectral and microwave data. The statistical results of the fusion of the optical and radar data showed high wetland mapping accuracy, with an overall classification accuracy of approximately 90% in the object-based classification. Compared with the high resolution UAV data, the classification results give promising results for mapping and monitoring not just wetlands, but also the sub-classes of the study area. For future research, multi-temporal image use and terrain data collection are recommended.

Robotic odor source localization (OSL) is a technology that enables mobile robots or autonomous vehicles to find an odor source in unknown environments. An effective navigation algorithm that guides the robot to approach the odor source is the key to successfully locating the odor source. While traditional OSL approaches primarily utilize an Olfaction-only strategy, guiding robots to find the odor source by tracing emitted odor plumes, our work introduces a fusion navigation algorithm that combines both vision and olfaction-based techniques. This hybrid approach addresses challenges such as turbulent airflow, which disrupts olfaction sensing, and physical obstacles inside the search area, which may impede vision detection. In this work, we propose a hierarchical control mechanism that dynamically shifts the robot’s search behavior among four strategies: crosswind maneuver, Obstacle-avoid Navigation, Vision-based Navigation, and Olfaction-based Navigation. Our methodology includes a custom-trained deep-learning model for visual target detection and a moth-inspired algorithm for Olfaction-based navigation. To assess the effectiveness of our approach, we implemented the proposed algorithm on a mobile robot in a search environment with obstacles. Experimental results demonstrate that our Vision and Olfaction Fusion algorithm significantly outperforms Vision-only and Olfaction-only methods, reducing average search time by 54% and 30%, respectively.

Multispectral image (MSI) and hyperspectral image (HSI) fusion (MHIF) aims to address the challenge of acquiring high-resolution (HR) HSI images. This field combines a low-resolution (LR) HSI with an HR-MSI to reconstruct HR-HSI. Existing methods directly utilize transformers to perform feature extraction and fusion. Despite the demonstrated success, there exist two limitations: 1) Employing the entire transformer model for feature extraction and fusion fails to fully harness the transformer’s potential in integrating the spectral of the HSI and spatial information of the MSI. 2) HSI has a strong spectral correlation and exhibits sparsity in the spatial domain. Existing transformer-based models do not optimize this physical property, which makes their methods prone to spectral distortion. To accomplish these issues, this paper introduces a novel framework for MHIF called Sparse Mix-Attention Transformer (SAMformer). Specifically, to fully harness the advantages of the Transformer architecture, we propose a Spectral Mix Attention Block (SMAB), which concatenates the keys and values extracted from LR-HSI and HR-MSI to create a new multi-head attention module. This design facilitates the extraction of detailed long-range information across spatial and spectral dimensions. Besides, to address the spatial sparsity inherent in HSI, we incorporated a sparse mechanism within the core of SMAB called Sparse Spectral Mix Attention Block (SSMAB). In the SSMAB, we compute attention maps from queries and keys and select the K highly correlated values as the sparse attention map. This approach enables us to achieve a sparse representation of spatial information while eliminating spatially disruptive noise. Extensive experiments conducted on three benchmark datasets, namely Cave, Harvard, and Pavia Center, demonstrate the SMAformer method outperforms state-of-the-art methods.

This paper applies a new artificial intelligence architecture, the Temporal Fusion Transformer (TFT), for the joint GDP forecasting of 25 OECD countries at different time horizons. This new attention-based architecture offers significant advantages over other deep learning methods. First, results are interpretable since the impact of each explanatory variable on each forecast can be calculated. Second, it allows to visualize persistent temporal patterns and to identify significant events and different regimes. Third, it provides quantile regressions and permits to train the model on multiple time series from different distributions. Results suggest that TFTs outperform regression models, especially in periods of turbulence such as the COVID-19 shock. Interesting economic interpretations are obtained depending on whether the country is domestic demand-led or export-led growth. In essence, TFT is revealed as a new tool that artificial intelligence provides to economists and policy makers, with enormous prospects for the future.

Use of a multi-sensor approach can provide citizens a holistic insight in the air quality in their immediate surroundings and assessment of personal exposure to urban stressors. Our work, as part of the ICARUS H2020 project, which included over 600 participants from 7 European cities, discusses data fusion and harmonization on a diverse set of multi-sensor data streams to provide a comprehensive and understandable report for participants, and offers possible solutions and improvements. Harmonizing the data streams identified issues with the used devices and protocols, such as non-uniform timestamps, data gaps, difficult data retrieval from commercial devices, and coarse activity data logging. Our process of data fusion and harmonization allowed us to automate the process of generating visualizations and reports and consequently provide each participant with a detailed individualized report. Results showed that a key solution was to streamline the code and speed up the process, which necessitated certain compromises in visualizing the data. A thought-out process of data fusion and harmonization on a diverse set of multi-sensor data streams considerably improved the quality and quantity of data that a research participant receives. Though automatization accelerated the production of the reports considerably, manual structured double checks are strongly recommended.

This paper deals with the viscoelastic behavior during crystallization and melting of semicrystalline polymers with the aim of later modeling the residual stresses after processing in case where crystallization occurs in quasi static conditions (in additive manufacturing for example). Despite of an abundant literature on polymer crystallization, the current state of scientific knowledge does not yet allow ab initio modeling. Therefore, an alternative and pragmatic way has been explored to propose a first approximation of the impact of crystallization and melting on the storage and the loss moduli during crystallization-melting-crystallization cycle. An experimental approach, combining DSC, optical microscopy and oscillatory shear rheology was used to define macroscopic parameters related to the microstructure. These parameters have been integrated into a phenomenological model. Isothermal measurements were used to describe the general framework, and crystallization at a constant cooling rate was used to evaluate the feasibility of a general approach. It can be concluded that relying solely on the crystalline fraction is inadequate to model the rheology. Instead accounting for the microstructure at the spherulitic level could be more useful. Additionally, the results obtained from the experiments help to enhance our understanding of the correlations between crystallization kinetics and its mechanical effects.

UAV network operation enables gathering and fusion from disparate information sources for flight control in both manned and unmanned platforms. In this investigation, a novel procedure for detecting runways and horizons as well as enhancing surrounding terrain is introduced based on fusion of enhanced vision system (EVS) and synthetic vision system (SVS) images. EVS and SVS image fusion has yet to be implemented real-world situations due to signal misalignment. We address this through a registration step to align the EVS and SVS images. Four fusion rules combining discrete wavelet transform (DWT) sub-bands are formulated, implemented and evaluated. The resulting procedure is tested on real EVS-SVS image pairs and pairs containing simulated turbulence. Evaluations reveal that runways and horizons can be detected accurately even in poor visibility. Furthermore, it is demonstrated that different aspects of the EVS and SVS images can be emphasized by using different DWT fusion rules. The procedure is autonomous throughout landing, irrespective of weather. We believe the fusion architecture developed holds promise for incorporation into head-up displays (HUDs) and UAV remote displays to assist pilots landing aircraft in poor lighting and varying weather. The algorithm also provided a basis rule selection in other signal fusion applications.

Hyperspectral anomaly detection is to recognize anomalies from complex scene in an unsupervised way. Currently, many spectral-spatial detection methods have been proposed with a cascaded manner. However, they often neglect complementary characteristics between spectral and spatial dimensions, which easily leads to yield high false alarm rate. To alleviate this issue, a spectral-spatial information fusion (SSIF) method is designed for hyperspectral anomaly detection. First, an isolation forest is exploited to obtain spectral anomaly map, in which the object-level feature is constructed with entropy rate segmentation algorithm. Then, a local spatial saliency detection scheme is proposed to produce spatial anomaly result. Finally, the spectral and spatial anomaly scores are integrated together followed by a domain transform recursive filtering to generate the final detection result. Experiments on five hyperspectral datasets prove that the proposed SSIF produces superior detection result over other state-of-the-art detection techniques.

CD74 is a type II cell surface receptor found to be highly expressed in several hematological and solid cancers, due to its ability to activate pathways associated with tumor cell survival and proliferation. Over the past 16 years, CD74 is emerging as a commonly detected fusion partner in multiple oncogenic fusion proteins. Studies have found CD74 fusion proteins in a range of cancers including lung adenocarcinoma, inflammatory breast cancer, and pediatric acute lymphoblastic leukemia. To date, there are five known CD74 fusion proteins, CD74-ROS1, CD74-NTRK1, CD74-NRG1, CD74-NRG2a, and CD74-PDGFRB, with a total of 16 different variants, each with unique genetic signatures. Importantly, the occurrence of CD74 in the formation of fusion proteins has not been well explored despite the fact that ROS1 and NRG1 families utilize CD74 as the primary partner for the formation of oncogenic fusions. Fusion proteins known to be oncogenic drivers, including those of CD74, are typically detected, and targeted after standard chemotherapeutic plans fail and the disease relapses. The analysis reported herein provides insights into early intervention of CD74 fusions and highlight the need for improved routine assessment methods so that targeted therapies can be applied while they are most effective.

The advent of the era of big data will bring more convenience to people and greater development to society. But at the same time, it will also bring people the problem of 'information overload', i.e., when people are faced with huge information data, there are many redundant and worthless data. The redundant and worthless data information seriously interferes with the accurate selection of information data. Even though people can use Internet search engines to access information data, they cannot meet the individual needs of specific users in specific contexts. The personalized needs of a particular user in a particular context. Therefore, how to find useful and valuable information quickly has become one of the key issues in the development of big data. With the advent of the era of big data, recommendation systems, as an important technology to alleviate information overload, have been widely used in the field of e-commerce. Recommender systems suffer from a key problem: data sparsity. The sparsity of user history rating data causes insufficient training of collaborative filtering recommendation models, which leads to a significant decrease in the accuracy of recommendations. In fact, traditional recommendation systems tend to focus on scoring information and ignore the contextual context in which users interact. There are various contextual modal information in people's real life, which also plays an important role in the recommendation process. In this paper we achieve data degradation and feature extraction, solving the problem of sparse data in the recommendation process. An interaction context-aware sub-model is constructed based on a tensor decomposition model with interaction context information to model the specific influence of interaction context in the recommendation process. Then an attribute context-aware sub-model is constructed based on the matrix decomposition model and using attribute context information to model the influence of user attribute contexts and item attribute contexts on recommendations. In the process of building the model, the method not only utilizes the explicit feedback rating information of users in the original dataset, but also utilizes the interaction context and attribute context information of the implicit feedback and the unlabeled rating data. We evaluate our model by extensive experiments. The results illustrate the effectiveness of our recommender model.

Pedestrian multi-target tracking technology plays an important role in artificial intelligence, driverless, virtual reality and other fields. The pedestrian multi-target tracking algorithm DeepSORT based on detection is widely used in industry. It mainly tracks multiple pedestrian targets continuously and keeps their ID unchanged. In order to improve the applicability and tracking accuracy of DeepSORT algorithm, this paper improved the IOU distance measurement in the matching process. At the same time, ResNet50 is used as the feature extraction backbone network, and combined with FPN (Feature Pyramid Network), the appearance features of multi-layer pedestrians are fused to improve the tracking accuracy of DeepSORT algorithm. The proposed algorithm is verified on the public data set MOT-16 and it’s tracking accuracy is enhanced to 4.1%.

Deep learning has recently attracted much attention due to its excellent performance in processing audio, image, and video data. However, few studies are devoted to the field of automatic modulation classification (AMC). It is one of the most well-known research topics in communication signal recognition, which remains challenging for traditional methods due to the complex disturbance from other sources. This paper proposes a heterogeneous deep model fusion (HDMF) method to solve the problem in a unified framework. The contributions include: 1) The convolutional neural network (CNN) and long short-term memory (LSTM) are combined by two different ways without prior knowledge involved; 2) A large database, including eleven types of single-carrier modulation signals with various noises as well as a fading channel, is collected with various signal-to-noise ratios (SNRs) based on a real geographical environment; and 3) Experimental results demonstrate that HDMF is super capable of copping with the AMC problem, and achieves much better performance when compared with the independent network. The source code and the database will be publically available.

Some of the most promising small molecule toxins used to generate antibody drug conjugates (ADCs) include anti-mitotic agents (e.g auristatin and its derivatives) which are designed to attack cancerous cells at their most vulnerable state during mitosis. We were interested to identify a human cystostatic protein eventually showing comparable activities and allowing the generation of corresponding targeted fully human cytolytic fusion proteins. Recently, we identified the human microtubule associated protein tau (MAP tau) which binds specifically to tubulin and modulates the stability of microtubules thereby blocking mitosis and presumably vesicular transport. By binding and stabilizing polymerized microtubule filaments, MAP tau-based fusion proteins skew microtubule dynamics towards cell cycle arrest and apoptosis. This biological activity makes rapidly proliferating cells (e.g cancer and inflammatory cells) an excellent target for MAP tau-based targeted treatments. Their superior selectivity for proliferating cells confers additional selectivity towards upregulated tumor-associated antigens at their surface, thereby preventing off-target related toxicity against normal cells bearing tumor-associated antigens at physiologically normal to low levels. In this review, we highlight recent findings on MAP tau-based targeted cytolytic fusion proteins reported in preclinical immunotherapeutic studies.

Infrared and visible image fusion technologies are used to characterize the same scene by diverse modalities. However, most existing deep learning-based fusion methods are designed as symmetric networks, which ignore the differences between modal images and lead to the source image information loss during feature extraction. In this paper, we propose a new fusion framework for the different characteristics of infrared and visible images. Specifically, we design a dual-stream asymmetric network with two different feature extraction networks to extract infrared and visible feature maps respectively. The transformer architecture is introduced in the infrared feature extraction branch, which can force the network to focus on the local features of infrared images while still obtaining their contextual information. And the visible feature extraction branch uses residual dense blocks to fully extract the rich background and texture detail information of visible images. In this way, it can provide better infrared targets and visible details for the fused image. Experimental results on multiple datasets indicate that DSA-Net outperforms state-of-the-art methods in both qualitative and quantitative evaluations. In addition, we also apply the fusion results to the target detection task, which indirectly demonstrates the fusion performances of our method.

Abstract: (1) Background: Minimally-invasive sacroiliac joint (SIJ) fusion is the preferred surgical intervention to treat chronically severe pain associated with SIJ degeneration and dysfunction. (2) Methods: This paper details the ten-step surgical procedure associated with the postero-inferior approach using the PsiF™DNA Sacroiliac Joint Fusion System. (3) Results: The posterior surgical approach with an inferior operative trajectory (postero-inferior) utilizes easily identifiable landmarks to provide the safest, most direct access to the articular joint space for transfixing device placement. Implanting the device through the subchondral bone, provides maximum fixation and stabilization of the joint by utilizing an optimal amount of cortical bone-implant interface. Approaching the joint from the inferior trajectory also places the implant perpendicular to the S1 endplate at a “pivot point” near the sacral axis of rotation, which addresses the most significant motion of the joint. (4) Conclusions: Further observational data from real-world clinical use are encouraged to further validate this procedure as the surgical preference for minimally-invasive SIJ fusion.

Galectins are β-galactosyl-binding proteins that fulfill essential physiological functions. Recently, we introduced galectin-1 (Gal-1) and galectin-3 (Gal-3) as fusion proteins of a His6-tag, a SNAP-tag, and a fluorescent protein. We characterized their binding in ELISA-type assays and their application in cell-surface binding. In the present study, we have constructed further fusion proteins of galectins with fluorescent protein color code. The fusion proteins of Gal-1, Gal-3, and Gal-8 were purified by affinity chromatography. For this, we have prepared glycoprotein affinity resins based on asialofetuin (ASF) and fetuin and combined this in a two-step purification with Immobilized Metal Affinity chromatography (IMAC) to get pure and active galectins. Purified galectin fractions were analyzed by size-exclusion chromatography. The binding characteristics to ASF of solely His6-tagged galectins and galectin fusion proteins were compared. As an example, we demonstrate a 1.6-3-fold increase in binding efficiency for HSYGal-3 (His6-SNAP-yellow fluorescent protein-Gal-3) compared to the HGal-3 (His6-Gal-3). Our results reveal an apparent higher binding efficiency for galectin SNAP-tag fusion proteins compared to His6-tagged galectins which are independent of the purification mode. This is also demonstrated by the binding of galectin fusion proteins to extracellular glycoconjugates laminin, fibronectin, and collagen IV. Our results indicate the probable involvement of the SNAP-tag in apparently higher binding signals, which we discuss in this study.

Recent deep learning frameworks draw a strong research interest in the application of ego-motion estimation as they demonstrate a superior result compared to geometric approaches. However, due to the lack of multimodal datasets, most of these studies primarily focused on a single sensor-based estimation. To overcome this challenge, we collect a unique multimodal dataset named LboroAV2, using multiple sensors including camera, Light Detecting And Ranging (LiDAR), ultrasound, e-compass and rotary encoder. We also propose an end-to-end deep learning architecture for fusion of RGB images and LiDAR laser scan data for odometry application. The proposed method contains a convolutional encoder, a compressed representation and a recurrent neural network. Besides feature extraction and outlier rejection, the convolutional encoder produces a compressed representation which is used to visualise the network's learning process and to pass useful sequential information. The recurrent neural network uses this compressed sequential data to learn the relation between consecutive time steps. We use the LboroAV2 and KITTI VO datasets to experiment and evaluate our results. In addition to visualising the network's learning process, our approach gives superior results compared to other similar methods. The code for the proposed architecture is released in GitHub and accessible publicly.

Skin cancer is an exquisite disease globally nowadays. Because of the poor contrast and apparent resemblance between skin and lesions, automatic identification of skin cancer is complicated. The rate of human death can be massively reduced if melanoma skin cancer can be detected quickly using dermoscopy images. In this research, an anisotropic diffusion filtering method is used on dermoscopy images to remove multiplicative speckle noise and the fast-bounding box (FBB) method is applied to segment the skin cancer region. Furthermore, the paper consists of two feature extractor parts. One of the two features extractor parts is the hybrid feature extractor (HFE) part and another is the convolutional neural network VGG19 based CNN feature extractor part. The HFE portion combines three feature extraction approaches into a single fused feature vector: Histogram-Oriented Gradient (HOG), Local Binary Pattern (LBP), and Speed Up Robust Feature (SURF). The CNN method also is used to extract additional features from test and training datasets. This two-feature vector is fused to design the classification model. This classifier performs the classification of dermoscopy images whether it is melanoma or non-melanoma skin cancer. The proposed methodology is performed on two ordinary datasets and achieved the accuracy 99.85%, sensitivity 91.65%, and specificity 95.70%, which makes it more successful than previous machine learning algorithms.

We developed a novel hybrid approach for solving global optimization, computer science, bio-medical and engineering real life applications that is based on the coupling of the Whale Optimizer and Sine Cosine Algorithms via a surrogate model. We relate the whale optimizer algorithm to balance between the exploitation and the exploration process in the proposed method. There exist confirmed techniques for searching approximate best optimal solutions, but our algorithm will further guarantee that such numerical and statistical solutions satisfy physical bounds of the standard and real life functions. Our experiments with the benchmark, bio-medical, computer science and engineering real life problems have illustrated the advantages of using a newly hybrid approach based on mixing Whale Optimizer and Sine Cosine algorithms. It holds considerable potential for reducing execution time for solving standard and real life problems and at the same time improving the quality of the solution.

The study of co-fusion was one of the essential topics in the history of metallurgy in China. Simulation experiments had been an essential concept in the study of the co-fusion steelmaking process. This paper mainly studied the simulation experiments of co-fusion from two aspects: the replication of co-fusion swords by three different methods, and the micro-analysis of the co-fusion samples. The experimental results indicated that several co-fusion swords could be made by different processes, but the carbon content and surface hardness were quite different. During repeated forging welded, the microstructure of the samples transformed from laminated to homogenized, finally the steel with a uniform carbon content was obtained. It was challenging to find the characteristics of co-fusion from the homogenized samples. The results prompted people to rethink the microstructure characteristics of ancient co-fusion artifacts.

A method for infrared and cameras sensor fusion, applied to indoor positioning in intelligent spaces, is proposed in this work. The fused position is obtained with a maximum likelihood estimator from infrared and camera independent observations. Specific models are proposed for variance propagation from infrared and camera observations (phase shifts and image respectively) to their respective position estimates and to the final fused estimation. Model simulations are compared with real measurements in a setup designed to validate the system. The difference between theoretical prediction and real measurements is between 0.4 cm (fusion) and 2.5 cm (camera), within a 95% confidence margin. The positioning precision is in the cm level (sub-cm level can be achieved at most tested positions) in a 4x3 m locating cell with 5 infrared detectors on the ceiling and one single camera, at distances from target up to 5 m and 7 m respectively. Due to the low cost system design and the results observed, the system is expected to be feasible and scalable to large real spaces.

Using the senses is essential to interact with objects in real-world environments. However, not all the senses are available when interacting with virtual objects in virtual environments. This paper presents a diamond methodology to fuse two technologies to represent the senses of sight and touch when interacting with a virtual object. The sense of sight is represented through augmented reality, and the sense of touch is represented through kinesthetic haptics. The diamond methodology is centered on the user experience and comprises five general stages: Experience design, Sensory representation, Development, Display, and Fusion. The first stage comes from the expected, proposed, or needed user experience. Then, each technology takes its homologous activities from the second to the fourth stage, diverging from each other along their development. Finally, the technologies converge to the fifth and final stage for fusion in the user experience. The diamond methodology was tested by generating a user's dual sensation when interacting with the elasticity of a tension virtual spring. The user can simultaneously perceive the visual and tactile change of the virtual spring during the interaction, representing the object's deformation. The experimental results demonstrated that an interactive experience can be felt and seen in augmented reality following the diamond methodology.

With worsening environmental degradation and increasing international demand for human health, plant cell based technology will be more important. The aim of this review is to give an overview regarding key points of current progress and development trend of nature medical and edible plants from the framework of whole plant cell engineering including cell cultures, cell fusion and cell splitting derived biotechnology. Here we sum up three main application trends of medical plants cell cultures covering industrial output, technology upgrading and potential resource development. We also provide classification and typification insights to summarize the development of somatic hybridization in cereal, vegetables crops and other medicinal and edible plants as well as application of artificial polyploidy induction in major medicinal herbs. Development medicinal and edible homologous plants based on modern plant cell engineering will bring us a promising future.

Object detection is important in many applications, such as autonomous driving. While 2D images are lack of depth information and are sensitive to environmental conditions, 3D point cloud can provide accurate depth information and a more descriptive environment. However, sparsity is always a challenge in single-frame point cloud object detection. This paper introduces a two-stage proposal-based feature fusion method for object detection using multiple frames. The proposed method, called proposal features fusion (PFF), utilizes a cosine-similarity approach to associate proposals from multiple frames and employs an attention weighted fusion module to merge features from these proposals. It allows for feature fusion specific to individual objects and offers lower computational complexity while achieving higher precision. The experimental results on the nuScenes dataset demonstrate the effectiveness of our approach, achieving a mAP of 46.7%, which is 1.3% higher than the state-of-the-art 3D object detection method.

In the field of vision-based robot grasping, effectively leveraging RGB and depth information to accurately determine the position and pose of a target is a critical issue. To address this challenge, we propose a tri-stream cross-modal fusion architecture for 2-DoF visual grasp detection. This architecture facilitates the interaction of RGB and depth bilateral information and is designed to efficiently aggregate multiscale information. Our novel modal interaction module (MIM) with spatial-wise cross-attention algorithm adaptively captures cross-modal feature information. Meanwhile, the channel interaction modules (CIM) further enhance the aggregation of different modal streams. In addition, we efficiently aggregate global multiscale information through a hierarchical structure with skipping connections. To evaluate the performance of our proposed method, we conduct validation experiments on standard public datasets and real robot grasping experiments. We achieve the image-wise detection accuracy of 99.4% and 96.7% on Cornell and Jacquard datasets respectively. The object-wise detection accuracy reaches 97.8% and 94.6% on the same datasets. Furthermore, physical experiments using the 6-DoF Elite robot demonstrate a success rate of 94.5%. These experiments highlight the superior accuracy of our proposed method.

Although the fusion energy sector is at a nascent stage, the private fusion energy market has grown. There are currently 38 private fusion energy companies around the world aiming to commercialise fusion energy in early 2030s and 2040s. Given the capability of fusion energy in transforming today’s energy paradigm and the global character of the market, it is important to analyse how these companies are interacting with international human rights standards. Therefore, this work investigates the involvement of the private fusion energy sector with two voluntary international initiatives in particular: the UN Global Compact and the UN Guiding Principles on Business and Human Rights (UNGP). This study attempts to answer two research questions: (i) Are private fusion energy companies participating in the UN Global Compact? (ii) How are private fusion energy companies publicly implementing the UNGP? Content analysis of secondary data collected from the UN Global Compact, Fusion Industry Association, ITER and companies’ official website as well as published reports is adopted. In summary, this work finds that private fusion energy companies are neither participants nor signatories of the UN Global Compact. Their observance of the UNGP is also very poor. This study contributes to the field by highlighting this gap which the private fusion energy companies need to consider and take measures in order to create a salutary human rights sector.

Image fusion is a useful tool for producing a high-resolution multispectral image to be used for land use and land cover mapping. In this study, we use nine pansharpening algorithms namely Color Normalized (CN), Gram-Schmidt (GS), Hyperspherical Color Space (HCS), High Pass Filter (HPF), Nearest-Neighbor Diffusion (NND), Principal Component Analysis (PCA), Resolution Merge (RM), Stationary Wavelet Transform (SWT), and Wavelet Resolution Merge (WRM) to fusion Worldview-3 multispectral Bands and panchromatic band. In spectral and spatial fidelity, several image quality metrics are used to evaluate the performance of pansharpening algorithms. The SWT and PCA algorithms showed better results compared to other pansharpening algorithms while GS and CN algorithms showed the worst results for the original image fusion. The effect of fusion on each band was separately investigated and according to the calculations, we found that the CoastalBlue band and the Blue band showed the best result and the NIR-1 band and NIR-2 band show the worst result for the original image fusion. In the end, we conclude that the choice of fusion method depends on the requirement of remote sensing application.

Cellular substructure has been widely observed in the sample fabricated by laser powder bed fusion, while its growth direction and the crystallographic orientation have seldom been studied. This research tries to build a general model to construct the substructure from its two-dimensional morphology. All the three Bunge Euler angles to specify a unique growth direction are determined, and the crystallographic orientation corresponding to the growth direction is also obtained. Based on the crystallographic orientation, the substructure in the single track of austenitic stainless steel 316L is distinguished between the cell-like dendrite and the cell. It is found that, with the increase of scanning velocity, the substructure transits from cell-like dendrite to cell. When the power is 200 W, the critical growth rate of the transition in the single track can be around 0.31 ms^-1.

The theoretical limit of link prediction is a fundamental problem in this field. Taking the network structure as object to research this problem is the mainstream method. This paper proposes a new viewpoint that link prediction methods can be divided into single or combination methods, based on the way they derive the similarity matrix, and investigates whether there a theoretical limit exists for combination methods. We propose and prove necessary and sufficient conditions for the combination method to reach the theoretical limit. The limit theorem reveals the essence of combination method that is to estimate probability density functions of existing links and nonexistent links. Based on limit theorem, a new combination method, theoretical limit fusion (TLF) method, is proposed. Simulations and experiments on real networks demonstrated that TLF method can achieve higher prediction accuracy.

Multivariate Time Series Classification (MTSC) is one of most important tasks in time series analysis, aiding in activities such as human motion recognition and medical diagnostics. Existing methods for MTSC do not explicitly model temporal differences and generalize the idea of temporal difference into a efficient temporal module. Additionally, existing methods are not yet able to capture cross-variable relationships well during network training. As a result, they are unable to achieve convincing feature representation, leading to suboptimal classification accuracy. In this paper, we propose a novel MTSC model called Temporal Difference and Cross-variate Fusion Network (TDCFN), which integrates a two-stream differential LSTM network and a cross-variate feature extraction network to enhance feature representation. TDCFN achieves superior classification accuracy by capturing dynamic temporal evolution and inter-variable relationships. The experimental results show that TDCFN can achieve competitive performance with state-of-the-art multivariate time series classification approaches.

With the development of remote sensing satellite technology for Earth observation, remote sensing stereo images have been used for three-dimensional reconstruction in various fields, such as urban planning and construction. However, remote sensing images often include noise, occluded regions, weakly textured areas and repeated textures, which can lead to reduced accuracy in stereo matching and affect the quality of the 3D reconstruction results. To reduce the impact of complex scenes in remote sensing images on stereo matching and to ensure both speed and accuracy, we propose a new end-to-end stereo matching network based on convolutional neural networks (CNNs). The proposed stereo matching network can learn features at different scales from the original images and construct cost volumes with varying scales to obtain richer scale information. Additionally, when constructing the cost volume, we introduce negative disparity to adapt to the common occurrence of both negative and nonnegative disparities in remote sensing stereo image pairs. For cost aggregation, we employ a 3D convolution-based encoder-decoder structure that allows the network to adaptively aggregate information. Before feature aggregation, we also introduce an attention module to retain more valuable feature information, enhance feature representation, and obtain a higher-quality disparity map. By training on the publicly available US3D dataset, we obtain the accuracy that 1.115 pixel in end-point error (EPE) and 5.32% in the error pixel ratio (D1) on the test dataset, and the inference speed is 92 ms. Comparing our model with existing state-of-the-art models, we achieve higher accuracy, and the network is beneficial for the three-dimensional reconstruction of remote sensing images.

The prediction of system degradation is very important as it serves as an important basis for the formulation of condition-based maintenance strategies. An effective health indicator (HI) plays a key role in the prediction of system degradation as it enables vital information for critical tasks ranging from fault diagnosis to remaining useful life prediction. To address this issue, a method for monitoring data fusion and health indicator construction based on autoencoder (AE) and long short-term memory (LSTM) network is proposed to improve the predictability and effectiveness of health indicator in this study. Firstly, an unsupervised method and overall framework for HI construction is built based on deep autoencoder and LSTM neural network. The neural network is trained fully based on the normal operating monitoring data and then the construction error of the AE model is adopted as the health indicator of the system. Secondly, we propose related machine learning techniques for monitoring data processing to overcome the issue of data fusion, like mutual information for sensor selection and t-distributed stochastic neighbor embedding (T-SNE) for operating condition identification, etc. Thirdly, in order to verify the performance of the proposed method, experiments are conducted based on CMAPSS dataset and results are compared with algorithms of principal component analysis (PCA) and vanilla autoencoder model. Result shows that LSTM-AE model outperforms the PCA and Vanilla-AE model in metrics of monotonicity, trendability, prognosability and fitness. Fourthly, in order to analyze the impact of the time step of the LSMT-AE model on HI construction, we construct and analyze the system HI curve under different time steps of 5, 10, 15, 20, and 25 cycles. Finally, the results demonstrate that the proposed method for HI construction can effectively characterize the health state of system, which is helpful for further failure prognostics and converting the scheduled maintenance into condition-based maintenance.

Convolutional neural networks (CNN) have attracted much attention as a commonly used method for hyperspectral image (HSI) classification in recent years, however, CNNs can only be applied to Euclidean data and have limitations in dealing with relationships due to the limitations of local feature extraction. However, each pixel of a hyperspectral image contains a set of spectral bands that are correlated and interact with each other, and the methods used to process Euclidean data cannot effectively obtain these correlations. In contrast, the graph convolutional network (GCN) can be used in non-Euclidean data, but usually leads to oversmoothing and ignoring local detail features due to the need for superpixel segmentation processing to reduce computational effort. To overcome the above problems, we constructed a network a fusion network based on GCN and CNN, which contains two branches: a graph convolutional network based on superpixel segmentation and a convolutional network with added attention mechanism. The graph convolu-tional branch can extract the structural features and capture the relationships between the nodes, and the convolutional branch can extract the detailed features in the local fine region. Owing to the fact that the features extracted from the two branches are different, the classification performance can be improved by fusing the complementary features extracted from the two branches. To vali-date the proposed algorithm, experiments were conducted on three widely used datasets, namely Indian Pines, Pavia University, and Salinas, and the overall accuracy of 98.78% was obtained in the Indian Pines dataset, and the overall accuracy of 98.99% and 98.69% was obtained in the other two datasets. The results showed that the proposed fusion network can obtain richer features and achieve high classification accuracy.

Powder bed fusion (PBF) process is a metal additive manufacturing process which can build parts with any complexity from a wide range of metallic materials. PBF process research has predominantly focused on the impact of only a few parameters on product properties due to the lack of a systematic approach for optimizing a large set of process parameters simultaneously. The pivotal challenges regarding this process require a quantitative approach for mapping the material properties and process parameters onto the ultimate quality; this will then enable the optimization of those parameters. In this study, we propose a two-phase framework for optimizing the process parameters and developing a predictive model for 316L stainless steel material. We also discuss the correlation between process parameters -- i.e., laser specifications -- and mechanical properties and how to achieve parts with high density (> 98%) as well as better ultimate mechanical properties. In this paper, we introduce and test an innovative approach for developing AM predictive models, with a relatively low error percentage of 10.236% that are used to optimize process parameters in accordance with user or manufacturer requirements. These models use support vector regression, random forest regression, and neural network techniques. It is shown that the intelligent selection of process parameters using these models can achieve an optimized density of up to 99.31% with uniform microstructure, which improves hardness, impact strength, and other mechanical properties.

Metal powder bed fusion (PBF) additive manufacturing (AM) builds metal parts layer by layer upon a substrate material. The strength of this interface between substrate and printed material is important to characterize, especially in applications where the substrate is retained and included in the finished part. This paper studied the tensile and torsional strengths of wrought and additively manufactured (through PBF) SS316L and compared them to specimens composed of half wrought material and half PBF material. The PBF specimens consistently exhibited higher strength and lower ductility than the wrought specimens. The hybrid PBF/wrought specimens performed similarly to the wrought material. In no specimens did any failure appear to occur at or near the interface between wrought substrate and PBF material. In addition, most of the deformation in the PBF/wrought specimens appeared to be limited to the wrought portion of the specimens. These results are consistent with microscopy showing smaller grain size in the PBF material, which often leads to increased strength in SS316L due to the Hall-Petch relationship.

Αbstract: To date, countless satellite image fusions have been made, mainly with panchromatic spatial resolution to a multispectral image ratio of 1/4, fewer fusions with lower ratios, and relatively recently fusions with much higher spatial resolution ratios have been published. Apart from this, there is a small number of publications studying the fusion of aerial photographs with satellite images, with the year of image acquisition varying and the dates of acquisition not mentioned. In addition, in these publications, either no quantitative controls are performed on the composite images produced, or the aerial photographs are recent and colorful and only the RGB bands of the satellite images are used for data fusion purposes. The objective of this paper is the study of the addition of multispectral information from satellite images to black and white aerial photographs of the 80s decade (1980–1990) with small difference (just a few days) in their image acquisition date, the same year and season. Quantitative tests are performed in two case studies and the results are encouraging, as the accuracy of the classification of the features and objects of the Earth’s surface is improved and the automatic digital extraction of their form and shape from the archived aerial photographs is now allowed. This opens up a new field of use for the black and white aerial photographs and archived multispectral satellite images of the same period in a variety of applications, such as the temporal changes of cities, forests and archaeological sites.

One of the challenges in Content-Based Image Retrieval (CBIR) is to reduce the semantic gaps between low-level features and high-level semantic concepts. In CBIR, the images are represented in the feature space and the performance of CBIR depends on the type of selected feature representation. Late fusion also known as visual words integration is applied to enhance the performance of image retrieval. The recent advances in image retrieval diverted the focus of research towards the use of binary descriptors as they are reported computationally efficient. In this paper, we aim to investigate the late fusion of Fast Retina Keypoint (FREAK) and Scale Invariant Feature Transform (SIFT). The late fusion of binary and local descriptor is selected because among binary descriptors, FREAK has shown good results in classification-based problems while SIFT is robust to translation, scaling, rotation and small distortions. The late fusion of FREAK and SIFT integrates the performance of both feature descriptors for an effective image retrieval. Experimental results and comparisons show that the proposed late fusion enhances the performances of image retrieval.

Background and Objectives: Although adult spinal deformity (ASD) surgery brought about the improvement of quality of life in patients, it accompanied with a high invasiveness of surgery and several complications. Specifically, mechanical complications of rod fracture, instrumentation failures, and pseudarthrosis are still unsolved issues. To better improve these problems, the oblique lateral interbody fusion at L5/S1 (OLIF51) was introduced since 2015 in my institution. The objective of this study was to compare the clinical and radiographic outcomes of anterior-posterior combined surgery for ASD between the use of OLIF51 versus transforaminal interbody fusion (TLIF) at L5/S1. Materials and Methods :A total of 117 ASD patients received anterior-posterior correction surgeries either use of OLIF51 (35 patients) or L5/S1 TLIF (82 patients). In both groups, L1-5 OLIF and minimally invasive posterior procedures of hybrid or circumferential MIS were employed. The sagittal and coronal spinal alignment and spino-pelvic parameters are recorded preoperatively and at follow-up. The quality of life parameters and visual analogue scale were evaluated as well as surgical complications at follow-up. Results: The average follow-up period was thirty months (13-84). The average fused segments were eight (4-12). The operation time and estimated blood loss were significantly smaller in OLIF51 that those in TLIF. The PI-LL mismatch, LLL, L5/S1 segmental lordosis, and L5 coronal tilt were significantly better in OLIF51 than TLIF. The complication rate was statistically equivalent between two groups. Conclusion: The introduction of OLIF51 for adult spine deformity surgery led to the decrease of operation time and estimated blood loss as well as the improvement of sagittal and coronal correction when compared to TLIF.

Gyroscopes are fascinating instruments with a history of about 200 years. When J.G.F. Bohnenberger presented his machine to his students in 1810 at the University of Tuebingen, Germany, nobody could have foreseen that this fascinating development would be used for complex orientation and positioning. At the University of Stuttgart, Germany, a collection of 160 exhibits is available and in transition for a sustainable future. Here, the systems are digitized in 2D, 2.5D and 3D and are made available for a world-wide community using OpenAccess platforms. The technologies being used are Computed Tomography, Computer Vision, Endoscopy and Photogrammetry. The workflows for combining voxel representations and colored point clouds are described, to create Digital Twins of the tangible assets. Advantages and disadvantages are discussed und work for near future is outlined in this new and challenging field of Tech Heritage digitization.

The unexploited unification of general relativity and quantum physics is a painstaking issue that prevents physicists to properly understanding the whole of Nature. Here we propose a pure mathematical approach that introduces the problem in terms of group theory. Indeed, we build a cyclic groupoid (a nonempty set with a binary operation defined on it) that encompasses both the theories as subsets, making it possible to join together two of their most dissimilar experimental results, i.e., the commutativity detectable in our macroscopic relativistic world and the noncommutativity detectable in the quantum, microscopic world. This approach, combined with the Connes fusion operator, leads to a mathematical framework useful in the investigation of relativity/quantum mechanics relationships.

In the autonomous navigation of mobile robots, precise positioning is crucial. In forest environments with weak satellite signals or in sites disturbed by complex environments, satellite positioning accuracy has difficulty in meeting the requirements of autonomous navigation positioning accuracy for robots. This article proposes a binocular vision SLAM/UWB tightly coupled localization method. The core of this algorithm is based on an Extended Kalman Filter (EKF), which utilizes the displacement increment output by binocular vision ORB-SLAM and the positioning coordinates calculated via UWB positioning as measurement information to achieve data fusion. The research utilized the constructed experimental platform to collect images and UWB ranging data in outdoor environments and experimentally validated the combined positioning method. The experimental results show that this algorithm outperforms the use of the individual UWB or visual SLAM localization methods in terms of positioning accuracy. Compared with traditional single positioning algorithms, this algorithm exhibits better practicality and stability, and can effectively suppress the impact of UWB non line of sight errors. The average error under normal line of sight conditions is 0.058 m, the root mean square error (RMSE) is 0.080, and the average error under non-line-of-sight conditions is 0.081 m, with an RMSE of 0.084. There is no significant jump or drift. Through the tightly coupled processing of binocular vision SLAM and UWB positioning, more reliable and accurate mobile robot positioning can be achieved, providing a useful reference for the autonomous navigation of mobile robots in complex environments.

Recently, deep learning models have been widely applied to modulation recognition, which have become a hot topic due to their excellent end-to-end learning capabilities. However, current methods are mostly based on uni-modal inputs, which suffer from incomplete information and local optimization. To complement the advantages of different modalities, we focus on the multi-modal fusion method. Therefore, we introduce an iterative dual-scale attentional fusion (iDAF) method to integrate multimodal data. Firstly, two feature maps with different receptive field sizes are constructed using local and global embedding layers. Secondly, the feature inputs are iterated into the Iterative Dual Scale Attention Module (iDCAM), where the two branches capture the details of high-level features and the global weights of each modal channel, respectively. The iDAF not only extracts the recognition characteristics of each specific domains, but also complements the strengths of different modalities to obtain a fruitful view. Our iDAF achieves a recognition accuracy of 93.5\% at 10dB and 0.6232 at full SNR. The comparative experiments and ablation studies effectively demonstrate the effectiveness and superiority of the iDAF.

A distinctive feature of the SARS-CoV-2 spike protein is its ability to efficiently fuse cells, thus producing syncytia found in COVID-19 patients. This commentary proposes how this ability enables spike to cause COVID-19 complications as well as side effects of COVID-19 vaccines, and suggests how these effects can be prevented..

Rapid and accurate prediction of residual stress in metal additive manufacturing processes is of great importance to guarantee the quality of the fabricated part to be used in a mission-critical application in the aerospace and automotive industries. Experimentation and numerical modeling are valuable tools for measuring and predicting the residual stress; however, to-date conducting experimentation and numerical modeling is expensive and time-consuming. Thus, herein, a physics-based thermomechanical analytical model is proposed to predict the residual stress of the additively manufactured part rapidly and accurately. A moving point heat source approach is used to predict the temperature field by considering the effects of scan strategies, heat loss, and energy needed for solid-state phase transformation. Due to the high temperature gradient in this process, part experiences a high amount of thermal stress following solidification which may exceed the yield strength of the material. The thermal stress is obtained using Green’s function of stresses due to the point body load. The Johnson-Cook flow stress model is used to predict the yield surface of the part under repeated heating and cooling. As a result of the cyclic heating and cooling and the fact that the material is yielded, the residual stress build-up is predicted based on incremental plasticity and kinematic hardening behavior of the metal according to the property of volume invariance in plastic deformation in coupling with the equilibrium and compatibility conditions. The computational methodology is realized with the laser powder fusion of maraging steel 350 as a material of example. The validation of the predictive models has been presented in terms of the comparison of predicted and measured scan-direction and build-direction residual stress distributions along depth of build under various process parameter combinations. Moreover, for the first time, the Jonson-Cook parameters of maraging steel 350 are predicted using analytical modeling of machining forces and non-linear optimization techniques.

Sensor fusion technology is one of extensive used methods in the field of robot, aerospace and target tracking control. In this paper, the generalized sensor fusion framework, named the closed-loop fusion (CLF) is analyzed and the optimal design principle of filter is proposed in detail. Fusion error optimization problem, which is the core issue of fusion design, is also solved better through the feedback compensation law of CLF framework. Differently from conventional methods, the fusion filter of CLF can be optimally designed and the determination of superposition of fusion information is avoided. To show the validity, simulation and experimental results are to be submitted.

Traditional path planning algorithms have drawbacks in unmanned vehicle path planning, such as low efficiency, unsuitability for dynamic environments, and high computational complexity. To address these issues, this paper proposes a dynamic path planning method for unmanned vehicles that combines the A* algorithm with an improved Dynamic Window Approach (DWA). Firstly, a collision risk function is incorporated into the DWA algorithm to evaluate scores based on the braking distance corresponding to the current vehicle speed and the distance to obstacles, determining whether timely braking or obstacle avoidance is feasible. The earlier the braking or obstacle avoidance, the higher the score, thereby enhancing the evaluation algorithm of the DWA. Secondly, the key points extracted by the A* algorithm are used as temporary target points for the DWA algorithm, reducing the eight search directions to five. Finally, the key points of the A* algorithm’s path are set as the temporary end points for the DWA algorithm, integrating the two algorithms to plan a smoother curved path that can avoid unknown and dynamic obstacles. Simulation data demonstrates that compared to traditional artificial potential field methods, RRT, and Dijkstra’s algorithm, the new fusion algorithm reduces time by 11.71 seconds, a decrease of 6.9%, and shortens path length by 3.093 meters, a reduction of 4.16%, while increasing average linear velocity by 2.9%. The proposed algorithm ensures smoother paths while also making paths more rational and efficient

This paper presents a method of fusion of identification (attribute) information provided by two types of sensors: combined primary and secondary (IFF) surveillance radars and ESM (Electronic Support Measures). In the first section, the basic taxonomy of attribute identification is adopted in accordance with the standards of STANAG 1241 ed. 5 and STANAG 1241 ed. 6 (draft). These standards provide the following basic values of the attribute identifications: FRIEND, HOSTILE, NEUTRAL, UNKNOWN and additional values: ASSUMED FRIEND and SUSPECT. The basis of theoretical considerations is Dezert-Smarandache theory (DSmT) of inference. The paper presents and practically uses for combining identification information from different ESM sensors and radars six information fusion rules proposed by DSmT - the Proportional Conflict Redistribution rules (PCR1, PCR2, PCR3, PCR4, PCR5 and PCR6). In the paper, rules of determining attribute information by ESM sensor equipped with the data base of radar emitters are presented. It was proposed that each signal vector sent by the ESM sensor contained an extension specifying a randomized identification declaration (hypothesis) - basic belief assignment (BBA). The paper also presents a model for determining the basic belief assignment for a combined primary and secondary radar. Results of the PCR rules of sensor information combining for different scenarios of radio-electronic situation (deterministic and Monte Carlo) are presented in the final part of the paper. They confirm the legitimacy of the use of Dezert-Smarandache theory into information fusion for primary radars, secondary radars and ESM sensors.

Oncogenic fusion proteins, arising from chromosomal rearrangements, have emerged as prominent drivers of tumorigenesis and crucial therapeutic targets in cancer research. In recent years, the potential of small molecular inhibitors in selectively targeting fusion proteins has exhibited significant prospects, offering a novel approach to combat malignancies harboring these aberrant molecular entities. This review provides a comprehensive overview of the current state of small molecular inhibitors as therapeutic agents for oncogenic fusion proteins. We discuss the rationale for targeting fusion proteins, elucidate the mechanism of action of inhibitors, assess the challenges associated with their utilization, and provide a summary of the clinical progress achieved thus far. The objective is to provide the medicinal community with current and pertinent information and to expedite the drug discovery programs in this area.

Most machine learning and deep learning algorithms can only use low-dimensional data as input, but the data that must be processed in practical applications is diverse and irregular. There are two main problems with big dynamic data. (1) The size of the embedding table grows linearly with the vocabulary size, resulting in massive memory consumption. (2) For different newly added vocabularies. To solve these two problems, this paper proposes a novel embedding algorithm that can learn attribute associations with entities based on deep and hash algorithms. Taking movie data as an example, the encoding method and the specific flow of the algorithm are presented in detail, and the effect of dynamic reuse of data models is realized. Compared with the four existing embedding algorithms which can fuse entity attribute information, the deep hash embedding algorithm proposed in this paper has obvious optimization of time and space complexity.

The advancement of precision medicine critically depends on the robustness and specificity of the carriers used for the targeted delivery of effector molecules in the human body. Numerous nanocarriers have been explored in vivo, to ensure the precise delivery of molecular cargos via tissue-specific targeting, including the endocrine part of the pancreas, thyroid, and adrenal glands. However, even after reaching the target organ, the cargo-carrying vehicle needs to enter the cell and then escape from lysosomal destruction. Most of artificial nanocarriers suffer from intrinsic limitations that either prevent them from completing the specific delivery of the cargo. In this respect, extracellular vesicles (EVs) seem to be the natural tool for payload delivery due to their versatility and low toxicity. However, EV-mediated delivery is not selective and usually short-ranged. By inserting the viral membrane fusion proteins into exosomes, it is possible to increase the efficiency of membrane recognition and also ease the process of membrane fusion. This review describes the molecular details of the viral-assisted interaction between the target cell and extracellular vesicles. We also discuss the question of the usability of viral fusion proteins in developing extracellular vesicle-based nanocarriers with higher efficacy of payload delivery. Finally, this review specifically highlights the role of Gag and RNA binding proteins in RNA sorting into extracellular vesicles.

This paper aims at tackling with the task of fusion feature from images and its corresponding point clouds for 3D object detection in autonomous driving scenarios basing on AVOD, an Aggregate View Object Detection network. The proposed fusion algorithms fuse features targeted from Bird’s Eye View (BEV) LIDAR point clouds and its corresponding RGB images. Differs in existing fusion methods, which are simply the adoptions of concatenation module, element-wise sum module or element-wise mean module, our proposed fusion algorithms enhance the interaction between BEV feature maps and its corresponding images feature maps by designing a novel structure, where single level feature maps and another utilizes multilevel feature maps. Experiments show that our proposed fusion algorithm produces better results on 3D mAP and AHS with less speed loss comparing to existing fusion method used on the KITTI 3D object detection benchmark.

Virtual Histology- Intravascular Ultrasound (VH-IVUS) image is an available method for visualizing plaque component to detect thin cap fibroatheroma. Nevertheless, this imaging modality has considerable limitations to extract the plaque component features and identifying the TCFA plaque. The aim of this paper is to improve the identification of TCFA using fusion of IVUS and VH-IVUS images. In order to generate the automatic technique for reducing the human interaction, a new method namely Active Contour based Plaque Border Detection (ACPB) is proposed. In order to perform the pixel wise classification, hybrid of K-means algorithm with Particle Swarm Optimization and Plaque based Minimum Euclidean Distance (KMPSO-PMED) method is presented to classify the plaque region as well. Moreover, to obtain more significant information of imaging modalities, fusion of two different images consisting of VH-IVUS and IVUS is performed. Therefore, geometric features are extracted from the plaque region and combine with IVUS features. Furthermore, different group of plaque features are divided by means of the histopathological studies. SVM classifiers is applied to detect the TCFA and non-TCFA plaques. The proposed method is applied on 566 in-vivo IVUS and their matching VH-IVUS images obtained from 9 patients. The best result of SVM illustrates the accuracy rates of 99.41% for classification of TCFA plaque. The results prove that the highest accuracy is achieved by integrated features of IVUS and VH-IVUS images.

Hyphal and germling fusion is a common phenomenon in ascomycetous fungi. Due to the formed hyphal network, this process enables coordinated development, interaction with plant hosts and efficient nutrient distribution. Recently, our lab showed a positive correlation of germling fusion with the formation of penetrating hyphopodia on maize leaves outgoing from Colletotrichum graminicola oval conidia. To investigate the probable interconnectivity of these processes, we have generated a deletion mutant in Cgso, which homologs are essential for cellular fusion in other fungal species. Indeed, plant infection studies combined with microscopy revealed a significant decrease in symptom development of the ∆Cgso mutant on maize leaves. However, hyphopodia development was not affected, indicating that both processes are not directly connected. Instead, we were able to link the decreased symptom development to a reduced formation of acervuli, asexual fruiting bodies of C. graminicola, which give rise to falcate conidia. Monitoring of a fluorescent labelled autophagy marker eGFP-CgAtg8 revealed a high autophagy activity in hyphae surrounding acervuli. Since the ∆Cgso mutant shows no hyphal fusions at these sites, we conclude that efficient nutrient transport of degraded cellular material by hyphal fusions enables proper acervuli maturation and symptom development on leaves.

Saliency detection in synthetic aperture radar (SAR) image is a difficult problem. This paper proposed a multitask saliency detection (MSD) model for the saliency detection task of SAR image. Firstly, we extract four features of SAR image as the input of the MSD model, which include the intensity, orientation, uniqueness and global contrast. Then, the saliency map is generated by the multitask sparsity pursuit (MTSP) which integrates the multiple features collaboratively. Subjective and objective evaluation of the MSD model verifies its effectiveness. Based on the saliency maps of the source images, an image fusion method is proposed for the SAR and color optical image fusion. The experimental results of real data show the proposed image fusion method is superior to the presenting methods in terms of several universal quality evaluation indexes, as well as in the visual quality. The salient areas in the SAR image can be highlighted and the spatial and spectral details of color optical image can also be preserved in the fusion result.

Plant cells are omnipotent and breeding of new varieties can be achieved by protoplast fusion. Such fusions can be achieved by treatment with poly(ethylene glycol) or by applying an electric field. Microfluidic devices allow for controlled conditions and targeted manipulation of small batches of cells down to single cell analysis. To provide controlled conditions for protoplast fusions and achieve high reproducibility, we developed and characterized a microfluidic device to reliably trap few of Arabidopsis thaliana protoplasts and induced a cell fusion by controlled addition of poly(ethylene glycol) (PEG, with a molecular weight of 6000). Experiments were conducted to determine the survival rate of isolated protoplasts in our microfluidic system. Afterwards, PEG induced fusion was studied. Our results indicate that the following fusion parameters had significant impact on the fusion efficiency and duration: PEG concentration, osmolarity of solution, and flow velocity. PEG concentration below 10% led to only partial fusion. Osmolarity of the PEG fusion solution was found to strongly impact the fusion process; complete fusion of two source cells sufficiently took part in slightly hyper osmotic solutions, whereas iso-osmotic solutions led to only partial fusion at 20% PEG concentration. We observed accelerated fusion for higher fluid velocities. Up to this study, it was common sense that fusion is one directional, i.e. once two cells were fused into one cell they stay fused. Here, we present for the first time reversible fusion of protoplasts. Our microfluidic device paves the way to a deeper understanding on the kinetics and processes of cell fusion.

Epilepsy is a prevalent neurological disorder with considerable risks, including physical impairment and irreversible brain damage from seizures. Given these challenges, the urgency for prompt and accurate seizure detection cannot be overstated. Traditionally, experts have relied on manual EEG signal analyses for seizure detection, which is labor-intensive and prone to hu-man error. Recognizing this limitation, the rise of deep learning methods has been heralded as a promising avenue, offering more refined diagnostic precision. On the other hand, the prevailing challenge in many models is their constrained emphasis on specific domains, potentially diminishing their robustness and precision in complex real-world environments. This paper presents a novel model that seamlessly integrates the salient features from the time-frequency domain alongside pivotal statistical attributes derived from EEG signals. This fusion process involves the integration of essential statistics, including the mean, median, and variance, combined with the rich data from compressed time-frequency (CWT) images processed using auto-encoders. This multidimensional feature set provides a robust foundation for subsequent analytic steps. A long short-term memory (LSTM) network, meticulously optimized for the renowned Bonn Epilepsy dataset, was used to enhance the capability of the proposed model. Preliminary evaluations underscore the prowess of the proposed model: remarkable 100% accuracy in most of the binary classifications, impressive performance exceeding 95% for three-class and four-class challenges, and a commendable rate exceeding 93.5% for the five-class classification.

The robust fusion estimation problem of a multi-sensor system with communication constraints, random packet drops, d-step state delays, and deterministic control inputs is investigated. The state augmentation method is used to transform the time delay system into a non-time delay system, and then a robust fusion estimation algorithm based on sensitivity penalty is proposed and the pseudo-cross-covariance matrix is updated. An event-triggered robust fusion estimator with state delay and deterministic control inputs is considered to make the model closer to reality while effectively reducing network congestion and lowering communication costs. Conditions are given to ensure that the estimation errors of the robust fusion estimator are uniform boundedness. Two sets of numerical simulations are provided to illustrate the effectiveness of the derived fusion estimator.

This study presents a modest attempt to interpret, formulate, and manipulate emotion of robots within the precepts of quantum mechanics. Our proposed framework encodes the emotion information as a superposition state whilst unitary operators are used to manipulate the transition of the emotion states which are recovered via appropriate quantum measurement operations. The framework described provides essential steps towards exploiting the potency of quantum mechanics in a quantum affective computing paradigm. Further, the emotions of multi-robots in a specified communication scenario are fused using quantum entanglement thereby reducing the number of qubits required to capture the emotion states of all the robots in the environment, and fewer quantum gates are needed to transform the emotion of all or part of the robots from one state to another. In addition to the mathematical rigours expected of the proposed framework, we present a few simulation-based demonstrations to illustrate its feasibility and effectiveness. This exposition is an important step in the transition of formulations of emotional intelligence to the quantum era.

The COVID-19 pandemic has disrupted the supply chain for personal protective equipment (PPE) for medical professionals, including N95-type respiratory protective masks. To address this shortage, many have looked to the agility and accessibility of additive manufacturing (AM) systems to provide a democratized, decentralized solution to producing respirators with equivalent protection for last-resort measures. However, there are concerns about the viability and safety in deploying this localized download, print, and wear strategy. Several polymer-based AM processes produce porous parts, and inherent process variation between printers and materials also threaten the integrity of tolerances and seals within the printed respirator assembly. The goal of this paper is to quantitatively measure particle transmission through printed respirators of different designs, materials, and AM processes, and assess the viability of printed respirators as N95 equivalents. Results from this study show that respirators printed using desktop/industrial-scale fused filament fabrication processes and industrial-scale powder bed fusion processes have insufficient filtration efficiency at the size of the SARS-CoV-2 virus, even while assuming a perfect seal between the respirator and the user’s face. Almost all printed respirators provided <60% filtration efficiency at the 100-300 nm particle range. Only one respirator, printed on an industrial-scale fused filament fabrication system provided >90% efficiency as-printed. Post-processing procedures including cleaning, sealing surfaces, and reinforcing the filter cap seal generally improved performance, but no respirator sustained the filtration efficiency of an N95 respirator, which filters 95% of SARS-CoV-2 virus particles. Instead, the printed respirators showed similar performance to various cloth masks. While continued optimization of printing process parameters and design tolerances could be implemented to directly print respirators that provide the requisite 95% filtration efficiency, AM processes are not sufficiently reliable for widespread distribution and local production of N95-type respiratory protection without commensurate quality assurance processes in place. Certain design/printer/material combinations may provide sufficient protection for specific users, but the respirators should not be trusted without quantitative filtration efficiency testing. It is currently not advised to expect printed respirators originating from distributed designs to replicate performance across different printers and materials.

It's challenging to achieve robust lane detection depending on single frame when considering complicated scenarios. In order to detect more credible lane markings by using sequential frames, a novel approach to fusing vision and Inertial Measurement Unit (IMU) is proposed in this paper. The hough space is employed as the space where lane markings are stored and it's calculated by three steps. Firstly, a basic hough space is extracted by Hough Transform and primary line segments are extracted from it. In order to measure the possibility about line segments belong to lane markings, a CNNs based classifier is introduced to transform the basic hough space into a probabilistic space by using the networks outputs. However, this probabilistic hough space based on single frame is easily disturbed. In the third step, a filtering process is employed to smooth the probabilistic hough space by using sequential information. Pose information provided by IMU is applied to align hough spaces extracted at different times to each other. The final hough space is used to eliminate line segments with low possibility and output those with high confidence as the result. Experiments demonstrate that the proposed approach has achieved a good performance.

This paper presents a methodology to design sensor fusion parameters using real performance indicators of navigation in UAVs based on PixHawk flight controller and peripherals. This methodology and the selected performance indicators allows to find the best parameters for the fusion system of a determined configuration of sensors and a predefined real mission. The selected real platform is described with stress on available sensors and data processing software, and the experimental methodology is proposed to characterize sensor data fusion output and determine the best choice of parameters using quality measurements of tracking output with performance metrics not requiring ground truth.

Laser powder bed fusion can fabricate porous structure through lattices, but it remains a challenge to prepare micropores (

Language bias stands as a noteworthy concern in Visual Question Answering (VQA), wherein models tend to rely on spurious correlations between questions and answers for prediction. This prevents the models from effectively generalizing, leading to a decrease in performance. To address this bias, we propose a novel modality fusion collaborative de-biasing algorithm (CoD). In our approach, bias is considered as the model’s neglect of information from a particular modality during prediction. We employ a collaborative training approach to facilitate mutual modeling between different modalities, achieving efficient feature fusion and enabling the model to fully leverage multi-modal knowledge for prediction. Our experiments on various datasets, including VQA-CP v2, VQA v2, and VQA-VS, using different validation strategies, demonstrate the effectiveness of our approach. Notably, employing a basic baseline model resulted in an accuracy of 60.14% on VQA-CP v2.

This paper proposes a multimodal fusion 3D target detection algorithm based on the attention mechanism to improve the performance of 3D target detection. The algorithm utilizes point cloud data and information from camera. For image feature extraction, the ResNet50+FPN architecture extracts features at four levels. Point cloud feature extraction employs the voxel method and FCN to extract point and voxel features. The fusion of image and point cloud features is achieved through regional point fusion and regional voxel fusion methods. After information fusion, the Coordinate attention mechanism and SimAM attention mechanism extract fusion features at a deep level. The algorithm's performance is evaluated using the DAIR-V2X dataset. The results show that compared to the Part-A2 algorithm, the proposed algorithm improves the mAP value by 7.9% in BEV view and 7.8% in 3D view at IOU=0.5 (cars) and IOU=0.25 (pedestrians and cyclist). At IOU=0.7 (cars) and IOU=0.5 (pedestrians and cyclist), the mAP value of the SECOND algorithm is improved by 5.4% in the BEV view and 4.3% in the 3D view, compared to other comparison algorithms.

This research uses ARM-based FPGA to implement the computation of a virtual-real fusion hardware system. It also evaluates the acceleration effect of virtual-real fusion execution speed after connecting related hardware acceleration and provides a reference for real-time information fusion system design. The hardware uses Xilinx Zynq UltraScale+ MPSoC ZCU102 Evaluation Kit. It also obtains color and depth images with Intel® RealsenseTM D435i depth cameras. This system receives image data through the Linux system built on the ARM and fed to the FPGA for object detection using CNN models. In addition, it develops a module for rapidly performing registration between the color images and the depth images. It can calculate the size and position of the display information on the transparent display according to the pixel coordinates and depth values of the human eye and the object. The fusion took about 47ms on a personal computer with a GPU RTX2060 and 25ms on the ZCU102. The acceleration is nearly 168%. Finally, the results were successfully transplanted into the retail display system for demonstration.

With the rise of piano teaching in recent years, many people have joined the team of piano learners. However, the expensive cost of manual instruction and the unique one-on-one teaching model have made piano learning an extravagant event. Most existing approaches based on the audio modality aim to evaluate piano players' skills. Unfortunately, these methods ignored the information contained in the video, which led to a one-sided and simplistic evaluation of the piano player's skills. More recently, multimodal-based methods are proposed to assess the skill level of piano players using both video and audio information. However, existing multimodal approaches use shallow networks to extract video and audio features, which are deficient in extracting complex spatio-temporal and time-frequency features from piano performance. Furthermore, the fingering and the pitch-rhythm information of the piano performance is contained in the spatio-temporal and time-frequency features, respectively. In the paper, we propose a ResNet-based audio-visual fusion model that combines video and audio features to assess the skill level of piano players. Firstly, ResNet18-3D is used as the backbone network for our visual branches, which can extract feature information from the video data. Then, we consider ResNet18-2D as the backbone network of the aural branch and extract the feature information from the audio data. The extracted video features are fused with the audio features to generate multimodal features for the final piano skill evaluation. The experimental results on the PISA dataset show that our proposed audio-visual fusion model, with a validation accuracy of 70.80%, outperforms the state-of-the-art methods in both performance and efficiency. Then, we also explore the impact of different layers of ResNet on model performance, and the experimental results show that the audio-visual fusion model dealing with the piano skill assessment problem can make full use of both feature information when the number of video features is close to the number of audio features.

Abstract: Image aesthetic assessment (IAA) with neural attention has made significant progress due to its effectiveness in object recognition. Current studies have shown that the features learned by convolutional neural networks (CNN) at different learning stages indicate meaningful information. The shallow feature contains the low-level information of images and the deep feature perceives the image semantics and themes. Inspired by this, we propose a visual enhancement network with feature fusion (FF-VEN). It consists of two sub-modules, the visual enhancement module (VE module) and the shallow and deep feature fusion module (SDFF module). The former uses an adaptive filter in the spatial domain to simulate human eyes according to the region of interest (ROI) extracted by neural feedback. The latter not only takes out the shallow feature and the deep feature by transverse connection, but also uses a feature fusion unit (FFU) to fuse the pooled features together with the aim of information contribution maximization. Experiments on standard AVA dataset and Photo.net dataset show the effectiveness of FF-VEN.

The importance of both recycling and additive manufacturing (AM) is increasing, however there has been a limited focus on development of AM alloys that are recyclably compatible with the larger scrap loops of wrought 5xxx, 6xxx and cast 3xx aluminium alloys. In this work the powder bed fusion (PBF) printability of AlMgSi alloys in the interval of 0-30wt%Mg and 0-4wt%Si is screened experimentally with a high throughput method. This method produces PBF mimicked material by PVD co-sputtering followed by laser remelting. Strong evidence was found for AlMgSi alloys being printable in two different composition ranges; Si+Mg<0.7wt% or for Si+2/3Mg>4wt% when Mg < 3wt% and Si > 3wt%. Increasing the amount of Mg and Si influence the grain structure by introducing fine columnar grains at the melt pool boundary, although the melt pool interior was unaffected. Hardness in as-built state increased with both Mg and Si, alt-hough Si had neglectable effect at low levels of Mg. Both evaporative loss of Mg and the amount of Mg in solid solution increased linearly with the amount of Mg.

Precision Agriculture is the ability to handle variations in productivity within a field and maximize financial return, optimize resource utilization and minimize impact of the environment. It is also the process of automated data collection, cloud storage and utilization to build robust decision support system. In case of Ethiopia, due to poor communication infrastructure coverage and absence of the state-of-the-art technology in the agriculture sector, implementing precision farming system is a challenging tasks in the domain area. In this work, we proposed a fusion of multiple sensors using IOT and IIOT infrastructure to collect critical data from farming fields to develop precision farming facility for decision makers. The main purpose was to monitor weather variability, automate irrigation process, extract critical soil properties. In addition, we have used time series data collected from sensor devices to build forecasting model. Fusion of multiple IoT device provide a mechanism in the agriculture area to deal with real-time monitoring of crops. It is cost-effective technology and required low-energy with edge computing sensor device. We employed the Message Queuing Telemetry Transport (MQTT) protocol to connect the Industrial/Internet of Things (I/IoT) to the cloud server. The communication between system user and sensor device has been done via cloud using Node-RED platform, web android APIs. The cloud-based Eco-system allows us to aggregate, visualize, and analyze live streams output from each sensor in real-time manner. Finally, we have built time series forecasting model using records collected by each sensor device. Using the multi-variate time series data-set, we have obtained about 99 forecasting accuracy on some important variables. Finally, we have developed mobile and web-based application for the end-user to monitor the proposed system remotely.

Many engineered approaches have been proposed over the years for solving the hard problem of performing indoor localisation using smartphone sensors. However, specialising these solutions for difficult edge cases remains challenging. Here we propose an end-to-end hybrid multimodal deep neural network localisation system, MM-Loc, relying on zero hand-engineered features, learning them automatically from data instead. This is achieved by using modality-specific neural networks to extract preliminary features from each sensing modality, which are then combined by cross-modality neural structures. We show that our choice of modality-specific neural architectures is capable of estimating the location with good accuracy independently. But for better accuracy, a multimodal neural network fusing the features of early modality-specific representations is a better proposition. Our proposed MM-Loc solution is tested on cross-modality samples characterised by different sampling rates and data representation (inertial sensors, magnetic and WiFi signals), outperforming traditional approaches for location estimation. MM-Loc elegantly trains directly from data unlike conventional indoor positioning systems, which rely on human intuition.

This paper describes a proposed fractional filter-based multi-scale underwater and hazy image enhancement algorithm. The proposed system combines a modified global contrast operator with fractional order-based multi-scale filters used to generate several images, which are fused based on entropy and standard deviation. The multi-scale-global enhancement technique enables fully adaptive and controlled colour correction and contrast enhancement without over exposure of highlights when processing hazy and underwater images. This in addition to illumination/reflectance estimation coupled with global and local contrast enhancement. The proposed algorithm is also compared with the most recent available state-of-the-art multi-scale fusion de-hazing algorithm. Experimental comparisons indicate that the proposed approach yields better edge and contrast enhancement results without halo effect, colour degradation and is faster and more adaptive than all other algorithms from the literature.

Sensitivity to weather conditions, and specially to clouds, is a severe limiting factor to the use of optical remote sensing for Earth monitoring applications. A possible alternative, is to resort to weather-insensitive synthetic aperture radar (SAR) images. However, in many real-world applications, critical decisions are made based on some informative spectral features, such as water, vegetation or soil indices, which cannot be extracted from SAR images. In the absence of optical sources, these data must be estimated. The current practice is to perform linear interpolation between data available at temporally close time instants. In this work, we propose to estimate missing spectral features through data fusion and deep-learning. Several sources of information are taken into account - optical sequences, SAR sequences, DEM - so as to exploit both temporal and cross-sensor dependencies. Based on these data, and a tiny cloud-free fraction of the target image, a compact convolutional neural network (CNN) is trained to perform the desired estimation. To validate the proposed approach, we focus on the estimation of the normalized difference vegetation index (NDVI), using coupled Sentinel-1 and Sentinel-2 time-series acquired over an agricultural region of Burkina Faso from May to November 2016. Several fusion schemes are considered, causal and non-causal, single-sensor or joint-sensor, corresponding to different operating conditions. Experimental results are very promising, showing a significant gain over baselines methods according to all performance indicators.

This study explores novel techniques to improve the detection accuracy of skarn iron deposits using advanced image processing methodologies. Leveraging the capabilities of Aster image, Band Ratio (BR) images, and Principal Component Analysis (PCA), alongside the power of 3D Convolutional Neural Networks (3D-CNN), the research aims to enhance the precision and efficiency of ore detection in complex geological environments. The proposed method employs a specific 3D-CNN architecture, accepting input as a 7×7×C image patch, where C represents the combined number of selected Aster image bands, Principal Component (PC) bands, and computed BR images. To evaluate the accuracy of the proposed method, five distinct image bands combinations, including the proposed bands combination, were tested and evaluated based on the overall accuracy (OA), average accuracy (AA), and kappa coefficient. The results demonstrated that while the incorporation of BR images alongside Aster bands initially seemed promising, it introduced significant confusion in certain classifications, leading to unexpected mis-classification rates. Surprisingly, utilizing solely Aster bands as input parameters yielded higher accuracy rates (OA= 93.13%, AA = 91.96%, Kappa = 90.91%) compared to scenarios involving the integration with band ratios (OA = 87.02%, AA = 79.15, and Kappa = 82.60%) or the integration of BR images to PC bands (OA= 87.78%, AA = 82.39%, Kappa = 83.81%). However, the amalgamation of Aster bands with selected PC bands showed slight improvements in accuracy (OA= 94.65%, AA = 92.93%, Kappa = 93.45%), although challenges in accurately classifying certain features persisted. Ultimately, the proposed combination of Aster bands, PC bands, and BR images (proposed bands combination) presented the most visually appealing and statistically accurate results (OA = 96.95%, AA= 94.87%, and Kappa = 95.93%), effectively addressing misclassifications observed in the other combinations. These findings underscore the synergistic contributions of each of the Aster bands, PC bands, and BR images, with Aster bands proving pivotal for optimal skarn classification, PC bands enhancing intrusions classification accuracy, and BR images strengthening wall rock classification accuracy. In conclusion, the proposed combination of input image bands emerges as a robust and comprehensive methodology, demonstrating unparalleled accuracy in the remote sensing detection of skarn iron minerals.

In this work, we propose an approach for the autonomous navigation of mobile robots using fusion of sensor data by a Double Deep Q-Network with collision avoidance by detecting moving people via computer vision techniques. We evaluate two data fusion methods for the proposed autonomous navigation approach: Interactive and Late fusion strategy. Both are used to integrate mobile robot sensors through the following sensors: GPS, IMU and, an RGB-D camera. The proposed collision avoidance module is implemented along with the sensor fusion architecture in order to prevent the autonomous mobile robot from colliding with moving people. The simulation results indicate a significant impact on the success of completing the proposed mission by the mobile robot with the fusion of sensors, indicating a performance increase (success rate) of 27% in relation to navigation without sensor fusion. With the addition of moving people in the environment, deploying the people detection and collision avoidance security module has improved about 14% the success rate when compared to that of the autonomous navigation approach without the security module. Video was developed with robot navigation using the DDQN-Late Fusion https://www.loom.com/share/684afa6a5b0148afadc9a200ab9f3483.

Polymeric composites such as Poly-ether-ether-ketone (PEEK)/carbon fiber (CF) have been widely utilized due to outstanding performances such as high specific strength and specific modulus. The PEEK/CF components via powder-bed fusion additive manufacturing usually show brittle fracture behaviors induced by their poor interfacial affinity and inner voids. These defects are strongly associated with powder packing quality upon deposition. The particle dynamic model has been widely employed to study the interactions of particle motions. Powder property, bulk material property, and interfacial features of composite powders are key factors in the particle dynamic model. In this work, an efficient and systematic material evaluation is developed for composite powders to investigate their deposition mechanism. The discrete element method is utilized to simulate the dynamic behaviors of PEEK/CF composite powders. The powder properties, bulk material properties, and interfacial features of powders are calibrated and justified by experimental measurement, numerical simulation, and design of experiments. The particle dynamic model can well explain the powder flow behaviors and interactions. It reveals that the addition of short CF particles can assist the flow of PEEK powders and improve the packing quality of the composite powders.

Drone and aerial remote sensing images are widely used, but their imaging environment is complex and prone to image blurring. Existing CNN deblurring algorithms usually use multi-scale fusion to extract features in order to make full use of aerial remote sensing blurred image information, but images with different degrees of blurring use the same weights, leading to increasing errors in the feature fusion process layer by layer. Based on the physical properties of image blurring, this paper proposes an adaptive multi-scale fusion blind deblurred generative adversarial network (AMD-GAN), which innovatively applies the degree of image blurring to guide the adjustment of the weights of multi-scale fusion, effectively suppressing the errors in the multi-scale fusion process and enhancing the interpretability of the feature layer. The research work in this paper reveals the necessity and effectiveness of a priori information on image blurring levels in image deblurring tasks. By studying and exploring the image blurring levels, the network model focuses more on the basic physical features of image blurring. Meanwhile, this paper proposes an image blurring degree description model, which can effectively represent the blurring degree of aerial remote sensing images. The comparison experiments show that the algorithm in this paper can effectively recover images with different degrees of blur, obtain high-quality images with clear texture details, outperform the comparison algorithm in both qualitative and quantitative evaluation, and can effectively improve the object detection performance of aerial remote sensing blurred images. Moreover, the average PSNR of this paper's algorithm tested on the publicly available dataset RealBlur-R reached 41.02dB, surpassing the latest SOTA algorithm.

The multi-modal data fusion method based on IA-net and CHMM technical proposed is designed to solve the problem that the incompleteness of target behavior information in complex family environment leads to the low accuracy of human behavior recognition.The two improved neural networks(STA-ResNet50、STA-GoogleNet)are combined with LSTM to form two IA-Nets respectively to extract RGB and skeleton modal behavior features in video. The two modal feature sequences are input CHMM to construct the probability fusion model of multi-modal behavior recognition.The experimental results show that the human behavior recognition model proposed in this paper has higher accuracy than the previous fusion methods on HMDB51 and UCF101 datasets. New contributions: attention mechanism is introduced to improve the efficiency of video target feature extraction and utilization. A skeleton based feature extraction framework is proposed, which can be used for human behavior recognition in complex environment. In the field of human behavior recognition, probability theory and neural network are cleverly combined and applied, which provides a new method for multi-modal information fusion.