Fusion Parameters Research Articles

Multi-joint Cooperative Control of Athletes under High Intensity Training

The control structure and performance of high intensity sports training on the trunk joint of athletes is analyzed to improve the quality of sports training, a multi-joint cooperative control model for athletes under high intensity sports training is proposed based on attitude sensor fusion tracking compensation. The multi-joint kinematics model of the athletes’ torso under high intensity sports training is constructed, and the constraint parameters of the multi-joint linkage and cooperative control of the athletes are analyzed combined with the identification method of the parameters of the state space model. The mechanical control model of the action of high intensity sports training on athletes’ torso is established by using the coupling method of driving branch chain inertia, and the characteristics of multi-joint linkage coupling of athletes are analyzed. The collaborative filtering Kalman fusion method is used to realize the parameter fusion and adaptive parameter identification of athletes’ multi-joint linkage. According to the results of parameter recognition, athletes’ multi-joint linkage collaborative control is realized. The simulation results show that the high intensity sports training method has good stability and low error of attitude parameter adjustment for athletes’ multi-joint linkage and coordination control, which improves the effect of sports training.

Multimodal Gait Recognition With Inertial Sensor Data and Video Using Evolutionary Algorithm

Evolutionary decision fusion has applications in biometric authentication and verification. Gray wolf optimizer (GWO) is one such evolutionary decision fusion approach that can be used to tune the fusion parameters in a multimodal data acquisition system. Human gait is a proven biometric trait with applications in security and authentication. However, acquiring human-gait data can be erroneous due to various factors and multimodal fusion of such erroneous gait data can be challenging. In this paper, we propose a new decision fusion-based approach to solve the above problem. Gait data is recorded simultaneously using motion sensors and visible-light camera. The signals of the motion sensors are modeled using a long short-term memory neural network and corresponding video recordings are processed using a three-dimensional convolutional neural network. GWO has been used to optimize the parameters during fusion. It has been chosen based on the underlying hunting strategy that leads to better approximation of the solution. Interestingly, in our case it converges quicker than other optimization techniques such as genetic algorithm or particle swarm optimization. To test the model, a dataset involving 23 males and females has been recorded while they perform four different types of walks, including, normal walk, fast walk, walking while listening to music , and walking while watching multimedia content on a mobile . An overall accuracy of 91.3% has been recorded across all test scenarios. Results reveal that the proposed study can further be explored to design robust gait biometric systems.

Infrared intensity and polarization image mimicry fusion based on the combination of variable elements and matrix theory

The current dual-mode infrared image lacks the selection and combination basis of each element when constructing the fusion method, and the fusion model cannot dynamically adjust for the image difference feature, resulting in poor fusion effect. Aiming at the above problems, referring to the multi-parameters of biological characters, this paper proposes infrared intensity and polarization image mimicry fusion based on the combination of variable elements and matrix theory. Firstly, the fusion model was divided into four parts: fusion algorithm, fusion rule, fusion parameter and fusion structure. The single mapping relationship between different parts and the difference of image feature fusion is established. Secondly, using the imaginary transformation idea, the imaginary transformation fusion method was established, and the necessary four parts of the fusion process are combined to derive a new fusion algorithm. Finally, it used the different source images with different features to verify the proposed mimetic fusion algorithm. Experimental results show that when the image difference features are different, the fusion method was more suitable for deriving image features, so as to achieve active selection and adjustment of the fusion algorithm. The different features in the fusion image can be effectively combined, and the visual effect of the original image is significantly improved.

Convex clustering for binary data

We present a new clustering algorithm for multivariate binary data. The new algorithm is based on the convex relaxation of hierarchical clustering, which is achieved by considering the binomial likelihood as a natural distribution for binary data and by formulating convex clustering using a pairwise penalty on prototypes of clusters. Under convex clustering, we show that the typical $$\ell _1$$ pairwise fused penalty results in ineffective cluster formation. In an attempt to promote the clustering performance and select the relevant clustering variables, we propose the penalized maximum likelihood estimation with an $$\ell _2$$ fused penalty on the fusion parameters and an $$\ell _1$$ penalty on the loading matrix. We provide an efficient algorithm to solve the optimization by using majorization-minimization algorithm and alternative direction method of multipliers. Numerical studies confirmed its good performance and real data analysis demonstrates the practical usefulness of the proposed method.

Consistent and reproducible cultures of large-scale 3D mammary epithelial structures using an accessible bioprinting platform

BackgroundStandard three-dimensional (3D) in vitro culture techniques, such as those used for mammary epithelial cells, rely on random distribution of cells within hydrogels. Although these systems offer advantages over traditional 2D models, limitations persist owing to the lack of control over cellular placement within the hydrogel. This results in experimental inconsistencies and random organoid morphology. Robust, high-throughput experimentation requires greater standardization of 3D epithelial culture techniques.MethodsHere, we detail the use of a 3D bioprinting platform as an investigative tool to control the 3D formation of organoids through the “self-assembly” of human mammary epithelial cells. Experimental bioprinting procedures were optimized to enable the formation of controlled arrays of individual mammary organoids. We define the distance and cell number parameters necessary to print individual organoids that do not interact between print locations as well as those required to generate large contiguous organoids connected through multiple print locations.ResultsWe demonstrate that as few as 10 cells can be used to form 3D mammary structures in a single print and that prints up to 500 μm apart can fuse to form single large structures. Using these fusion parameters, we demonstrate that both linear and non-linear (contiguous circles) can be generated with sizes of 3 mm in length/diameter. We confirm that cells from individual prints interact to form structures with a contiguous lumen. Finally, we demonstrate that organoids can be printed into human collagen hydrogels, allowing for all-human 3D culture systems.ConclusionsOur platform is adaptable to different culturing protocols and is superior to traditional random 3D culture techniques in efficiency, reproducibility, and scalability. Importantly, owing to the low-cost accessibility and computer numerical control–driven platform of our 3D bioprinter, we have the ability to disseminate our experiments with absolute precision to interested laboratories.

A Hand-Based Biometric Verification System Using Ant Colony Optimization

This paper presents a novel personal authentication system using hand-based biometrics, which utilizes internal (beneath the skin) structure of veins on the dorsal part of the hand and the outer shape of the hand. The hand-vein and the hand-shape images can be simultaneously acquired by using infrared thermal and digital camera respectively. A claimed identity is authenticated by integrating these two traits based on the score-level fusion in which four fusion rules are used for the integration. Before their fusion, each modality is evaluated individually in terms of error rates and weights are assigned according to their performance. In order to achieve an adaptive security in the proposed bimodal system, an optimal selection of fusion parameters is required. Hence, Ant Colony Optimization (ACO) is employed in the bimodal system to select the weights and also one out of the four fusion rules optimally for the adaptive fusion of the two modalities to meet the user defined security levels. The databases of hand-veins and the hand-shapes consisting of 150 users are acquired using the peg-free imaging setup. The experimental results show genuine acceptance rate (GAR) of 98% at false acceptance rate (FAR) of 0.001% and the system has the potential for any online personal authentication based application.

Multi-PSF fusion in image restoration of range-gated systems

For the task of image restoration, an accurate estimation of degrading PSF/kernel is the premise of recovering a visually superior image. The imaging process of range-gated imaging system in atmosphere associates with lots of factors, such as back scattering, background radiation, diffraction limit and the vibration of the platform. On one hand, due to the difficulty of constructing models for all factors, the kernels from physical-model based methods are not strictly accurate and practical. On the other hand, there are few strong edges in images, which brings significant errors to most of image-feature-based methods. Since different methods focus on different formation factors of the kernel, their results often complement each other. Therefore, we propose an approach which combines physical model with image features. With an fusion strategy using GCRF (Gaussian Conditional Random Fields) framework, we get a final kernel which is closer to the actual one. Aiming at the problem that ground-truth image is difficult to obtain, we then propose a semi data-driven fusion method in which different data sets are used to train fusion parameters. Finally, a semi blind restoration strategy based on EM (Expectation Maximization) and RL (Richardson-Lucy) algorithm is proposed. Our methods not only models how the lasers transfer in the atmosphere and imaging in the ICCD (Intensified CCD) plane, but also quantifies other unknown degraded factors using image-based methods, revealing how multiple kernel elements interact with each other. The experimental results demonstrate that our method achieves better performance than state-of-the-art restoration approaches.

Iterative-based visualization-oriented fusion scheme for hyperspectral images

This article investigates a novel visualization-based fusion of hyperspectral image bands using an iterative approach. Given a multi-objective function and the pixel-based hyperspectral image fusion method, the optimization process is described as finding the optimal fusion parameters to improve the fusion performance. Accordingly, an iterative-based approach is adopted. In the first step, the fusion process is developed using the pixel-based fusion technique. In the second step, the fused image is produced, and the fusion quality is assessed for multi-objective function construction. For multi-objective formulation, we focus three desired properties of the fused image such as entropy, variance, and smoothness. In the last step, fusion parameters are updated iteratively by examining the objective function. Here, the self-adaptive learning particle swarm optimizer is used to refine the fusion parameters iteratively. Different hyperspectral images, such as Cuprite mining, AVIRIS Indian pines scene, are employed in the evaluation. Quantitative analysis of fused images is carried out through some efficient fusion metrics such as correlation coefficient, entropy, Q-average, ERGAS, SAM, and SID. Experimental results show that the proposed approach outperforms existing methods in terms of both objective function criteria and visual effect.

New biocompatible near-beta Ti-Zr-Nb alloy processed by laser powder bed fusion: Process optimization

The laser powder bed fusion parameters were determined for a novel biomedical Ti-18Zr-14Nb (at%) alloy using both analytical and experimental approaches. An analytical model was used to calculate the laser powder bed fusion parameters such as laser power, scanning speed and hatching space providing the energy density on the powder bed surface ranging from 9 to 85J/mm3, and the build rate – from 12 to 52cm3/h. A technological processing window corresponding to a 25–45J/mm3 energy density range and a 10–25cm3/h build rate range is recommended for the fabrication of the fully dense Ti-18Zr-14Nb alloy with improved surface roughness.

Effect of Laser Powder Bed Fusion Parameters on the Microstructure and Texture Development in Superelastic Ti–18Zr–14Nb Alloy

The effect of different laser powder bed fusion (L-PBF) parameters on the phase composition, microstructure, and crystallographic texture of Ti–18Zr–14Nb alloy was studied. Two levels of laser power, scanning speed, and hatching space were used, while the layer thickness was kept constant. The resulting volume energy density was ranged from 20 to 60 J/mm3, and the build rate, from 12 to 36 cm3/h. The manufactured coupons were analyzed by X-ray diffractometry, transmission, and scanning electron microscopy. It was found that the greater influence observed on the microstructure and texture development was caused by the value of laser power, while the lowest, by that of hatching space. Based on the results obtained, the processing optimization strategy aimed at improving the density, superelastic, and fatigue properties of the L-PBF manufactured Ti–18Zr–14Nb alloy was proposed.

IoT-Based Sensor Data Fusion for Occupancy Sensing Using Dempster–Shafer Evidence Theory for Smart Buildings

With the advent of Internet of Things technologies and smart buildings, the need for building automation systems that automatically performs computations without the intervention of humans have also increased. This paper deals with detection of occupancy in a room from various ambient sources like temperature, humidity, light, and CO2. With the help of this system, remote monitoring of the building as well as leveraging control on the indoor parameters through HVAC control systems is possible at real-time. This paper adopts Dempster–Shafer evidence theory for fusing sensory information collected from heterogeneous sensors, assigns probability mass assignments (PMAs) to the raw sensor readings, and finally performs mass combination to derive a conclusion about the occupancy status in a room. A PMA function has been proposed for this purpose. The results reveal a substantially high percentage of accuracy (up to 99.09%) which was observed to increase with the increase in number of fusion parameters.

Distributed quantized multi-modal H∞ fusion filtering for two-time-scale systems

In this paper, we deal with the distributed H∞ fusion filtering problem for a class of discrete-time system with significant modal difference in the time-scale. The nonstandard singularly perturbed model (SPM) is employed to describe the addressed two-time-scale system, where the small perturbation parameter ε reflects the discrepancies in the time-scale. Some sufficient conditions are provided to guarantee the existence of the parameters of the local filters for the SPM, where O(ε2) (the second-order correction terms in ε) is eliminated and an upper bound of ε is calculated. To enhance the filtering accuracy and scalability, the estimates provided by the local filter are transmitted to the fusion centre via the communication network. In the presence of the bandwidth constraint, a quantized fusion scheme is developed and the design of the fusion parameters is cast into a convex optimization problem. Finally, an example on the F-8 airplane is provided to verify the validity and applicability of the proposed methodology.

Storage Life Prediction of Space Relay Based on Elman Neural Network

When the linear equation is used to fit the life data for predicting the storage life at room temperature, there is a large error. From this point of view, the parameter degradation is considered and the contact pressure drop parameter is fused according to the comprehensive correlation degree at 60°C, 73°C, 92°C and 125°C. The accelerating factors of four temperature gradients are obtained by using the Arrhenius equation. The parameters and storage life in high temperature state are equivalent to normal temperature. The Elman neural network is used to study and train the fusion parameters, then the storage life of the relay at room temperature is predicted. The prediction error of this method is 2.44%, which is smaller than expected.

Nonsubsampled rotated complex wavelet transform (NSRCxWT) for medical image fusion related to clinical aspects in neurocysticercosis

Neurocysticercosis (NCC) is a parasite infection caused by the tapeworm Taenia solium in its larvae stage which affects the central nervous system of the human body (a definite host). It results in the formation of multiple lesions in the brain at different locations during its various stages. During diagnosis of such symptomatic patients, these lesions can be better visualized using a feature based fusion of Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). This paper presents a novel approach to Multimodality Medical Image Fusion (MMIF) used for the analysis of the lesions for the diagnostic purpose and post treatment review of NCC. The MMIF presented here is a technique of combining CT and MRI data of the same patient into a new slice using a Nonsubsampled Rotated Complex Wavelet Transform (NSRCxWT). The forward NSRCxWT is applied on both the source modalities separately to extract the complementary and the edge related features. These features are then combined to form a composite spectral plane using average and maximum value selection fusion rules. The inverse transformation on this composite plane results into a new, visually better, and enriched fused image. The proposed technique is tested on the pilot study data sets of patients infected with NCC. The quality of these fused images is measured using objective and subjective evaluation metrics. Objective evaluation is performed by estimating the fusion parameters like entropy, fusion factor, image quality index, edge quality measure, mean structural similarity index measure, etc. The fused images are also evaluated for their visual quality using subjective analysis with the help of three expert radiologists. The experimental results on 43 image data sets of 17 patients are promising and superior when compared with the state of the art wavelet based fusion algorithms. The proposed algorithm can be a part of computer-aided detection and diagnosis (CADD) system which assists the radiologists in clinical practices.

Application of cement on strategic vertebrae in the treatment of the osteoporotic spine

Background ContextThe application of pedicle screws with cement to strengthen the fixation of the osteoporotic spine has increasingly gained popularity. However, the technique has also led to an increase in cement-related complications. PurposeThe aim of the present study was to compare the clinical and radiological results of the patients with degenerative spinal pathologies who were treated with pedicle screws and cement injections on all segments versus those who were treated with cement injections only on the strategic vertebrae selected. Study DesignA retrospective clinical study. Patient SampleThe sample consists of 31 patients who underwent spinal surgery due to degenerative spinal pathologies. Outcome MeasuresPatients were assessed for the adequate spinal fusion and cement-related complication parameters. MethodsThirty-one patients with a minimum follow-up period of 2 years were divided into two groups and evaluated. Group A consisted of 17 patients (14 females, 3 males; mean age: 68.1 years) with cemented pedicle screws and Group B consisted of 14 patients (12 females, 2 males; mean age: 67.2 years) with cemented screws on selected vertebrae alone. Selection of the strategic vertebrae was made by taking the most stressed regions in the fusion site into account. Prophylactic vertebroplasty was performed in all patients in Group A and on strategic segments in Group B to avoid an adjacent segment fracture. Early- and late-term complications during the follow-up period were recorded. ResultsMean follow-up period was 51.8 (range: 31 to 80) months in Group A and 41.2 (range: 26 to 61) months in Group B. Cemented pedicle screws were bilaterally placed on 94 vertebrae in Group A. In Group B, cement was applied on 28 of 80 vertebrae. Including the prophylactic vertebroplasties, a total of 111 cement applications were performed in Group A and 38 in Group B. Cement embolism, symptomatic chest discomfort, and duration of surgery were significantly higher in Group A (p<.05). No adjacent segment fracture in the proximal or distal vertebra, implant failure, or loss of correction was seen throughout the follow-up period. ConclusionsThe application of cemented pedicle screws on all segments of the osteoporotic spine increases the cement volume and rate of cement-related complications. Cementing the strategic vertebrae alone will enhance the fixation strength and endurance and decrease the complications caused by cement application.

Monocular visual odometry: A cross-spectral image fusion based approach

This manuscript evaluates the usage of fused cross-spectral images in a monocular visual odometry approach. Fused images are obtained through a Discrete Wavelet Transform (DWT) scheme, where the best setup is empirically obtained by means of a mutual information based evaluation metric. The objective is to have a flexible scheme where fusion parameters are adapted according to the characteristics of the given images. Visual odometry is computed from the fused monocular images using an off the shelf approach. Experimental results using data sets obtained with two different platforms are presented. Additionally, comparison with a previous approach as well as with monocular-visible/infrared spectra are also provided showing the advantages of the proposed scheme.

Gnotobiotic Miniature Pig Interbreed Somatic Cell Nuclear Transfer for Xenotransplantation.

Transgenic animal producing technology has improved consistently over the last couple of decades. Among the available methods, somatic cell nuclear transfer (SCNT) technology was officially the most popular. However, SCNT has low efficiency and requires a highly skilled individual. Additionally, the allo-SCNT nuclear reprogramming mechanism is poorly understood in the gnotobiotic miniature pig, which is a candidate for xenotransplantation, making sampling in oocytes very difficult compared to commercial hybrid pigs. Therefore, interbreed SCNT (ibSCNT), which is a combination of miniature pig and commercial pig (Landrace based), was analyzed and was found to be similar to SCNT in terms of the rate of blastocyst formation (12.6% ± 2.9% vs. 15.5% ± 2.2%; p > 0.05). However, a significantly lower fusion rate was observed in the ibSCNT compared to normal SCNT with Landrace pig somatic cells (29.6% ± 0.8% vs. 65.0% ± 4.9%). Thus, the optimization of fusion parameters was necessary for efficient SCNT. Our results further revealed that ibSCNT by the whole-cell intracytoplasmic injection (WCICI) method had a significantly higher blastocyst forming efficiency than the electrofusion method (31.1 ± 8.5 vs. 15.5% ± 2.2%). The nuclear remodeling and the pattern of changes in acetylation at H3K9 residue were similar in both SCNT and ibSCNT embryos.

Target Tracking Based on Biological-Like Vision Identity via Improved Sparse Representation and Particle Filtering

To effectively track targets under partial occlusion and illumination variation, an improved target tracking method based on combination of sparse representation and particle filtering is proposed in this paper. We regard the candidate target particle set as redundant dictionary and the target template as observation signal to reduce the computational complexity and enhance the real-time performance of target tracking. Besides, to enhance tracking robustness for better adaption to illumination and occlusion, the density histogram, local binary pattern feature fusion, trivial templates and energy control parameters are also utilized in this study. Finally, extensive simulation experiments under different circumstances show that the proposed method performs better compared with other methods, and the average computation time decreases greatly.

Characteristics of Fusion-Welded Joints Made Using Martensitic Steel after 100,000 Hours in Service

The paper presents the results of tests of mixed fusion-welded joints consisting of superheater pipes of grades T91 and HCM12A(T122) after 100,000 hours in service in a BB-1150 boiler welded to new pipes (in “as-delivered” condition) of grades T91 and VM12-SHC. The state of the microstructure and properties of the used tube material after long term service are characterized. The paper describes fusion welding conditions and parameters, and evaluates the quality of the created butt joints. The results of tests of the macro-and microstructure of the joints and their mechanical properties are presented. It was determined that the welding process intensifies further degradation of the tested materials to a small extent only. This work was performed under the Strategic Research Project No SP/E/1/67484/10 supported by the National Centre for Research and Development.

Screening of biotechnical parameters for production of bovine inter-subspecies embryonic chimeras by the aggregation of tetraploid Bos indicus and diploid crossbred Bos taurus embryos

The aggregation of a tetraploid zebu embryo (Bos indicus, a thermotolerant breed) with a diploid taurine embryo (Bos taurus, a thermosensitive breed) should create a complete taurine fetus, whose extra-embryonic components, e.g., the chorion, is derived mainly from the zebu embryo. These zebu-derived extra-embryonic components may interact positively with the taurine embryo/fetus during pregnancy in a tropical environment. We tested different parameters for the production of tetraploid Nelore (Bos indicus) embryos to be combined via aggregation with crossbred Bos taurus (diploid) embryos in order to produce viable chimeric blastocysts. Bovine (Bos indicus or crossbred Bos taurus) embryos were produced in vitro according to standard procedures. Two-cell Bos indicus embryos were submitted to electrofusion with varying numbers of pulses (1 or 2), voltages (0.4, 0.5, 0.75, 1.0, 1.4 and 5.0kV/cm) and time (20, 25, 50 and 60μs) to produce tetraploid embryos. Electrofused embryos were cultured with crossbred non-fused embryos to form chimeras that developed until the blastocyst stage. The best fusion parameter was 0.75kV/cm for 60μs. Four chimeric blastocysts (tetraploid Nelore with diploid crossbred Holstein) were formed after 31 attempts in 4 replicates (13%). We established an optimal procedure for the production of tetraploid Bos indicus (4n) embryos and embryonic chimeras by aggregation of crossbred Bos taurus (2n) with Bos indicus (4n) embryos. This technique would be valid in applied research, by producing exclusively taurine calves, but with placental elements from the Bos indicus breed, following transfer of these chimeras into recipient cows.