Human-Robot Interaction Using Learning from Demonstrations and a Wearable Glove with Multiple Sensors.

Human-robot interaction is of the utmost importance as it enables seamless collaboration and communication between humans and robots, leading to enhanced productivity and efficiency. It involves gathering data from humans, transmitting the data to a robot for execution, and providing feedback to the human. To perform complex tasks, such as robotic grasping and manipulation, which require both human intelligence and robotic capabilities, effective interaction modes are required. To address this issue, we use a wearable glove to collect relevant data from a human demonstrator for improved human-robot interaction. Accelerometer, pressure, and flexi sensors were embedded in the wearable glove to measure motion and force information for handling objects of different sizes, materials, and conditions. A machine learning algorithm is proposed to recognize grasp orientation and position, based on the multi-sensor fusion method.

Feature-Based Occupancy Map-Merging for Collaborative SLAM.

One of the most frequently used approaches to represent collaborative mapping are probabilistic occupancy grid maps. These maps can be exchanged and integrated among robots to reduce the overall exploration time, which is the main advantage of the collaborative systems. Such map fusion requires solving the unknown initial correspondence problem. This article presents an effective feature-based map fusion approach that includes processing the spatial occupancy probabilities and detecting features based on locally adaptive nonlinear diffusion filtering. We also present a procedure to verify and accept the correct transformation to avoid ambiguous map merging. Further, a global grid fusion strategy based on the Bayesian inference, which is independent of the order of merging, is also provided. It is shown that the presented method is suitable for identifying geometrically consistent features across various mapping conditions, such as low overlapping and different grid resolutions. We also present the results based on hierarchical map fusion to merge six individual maps at once in order to constrict a consistent global map for SLAM.

A level set method based on domain transformation and bias correction for MRI brain tumor segmentation.

BACKGROUND: Intensity inhomogeneity is one of the common artifacts in image processing. This artifact makes image segmentation more challenging and adversely affects the performance of intensity-based image processing algorithms. NEW METHOD: In this paper, a novel region-based level set method is proposed for segmenting the images with intensity inhomogeneity with applications to brain tumor segmentation in magnetic resonance imaging (MRI) scans. For this purpose, the inhomogeneous regions are first modeled as Gaussian distributions with different means and variances, and then transferred into a new domain, where preserves the Gaussian intensity distribution of each region but with better separation. Moreover, our method can perform bias field correction. To this end, the bias field is represented by a linear combination of smooth base functions that enables better intensity inhomogeneity modeling. Therefore, level set fundamental formulation and bias field are modified in the proposed approach. RESULTS: To assess the performance of the proposed method, different inhomogeneous images, including synthetic images as well as real brain magnetic resonance images from BraTS 2017 dataset are segmented. Being evaluated by Dice, Jaccard, Sensitivity, and Specificity metrics, the results show that the proposed method suppresses the side effect of the over-smoothing object boundary and it has good accuracy in the segmentation of images with extreme intensity non-uniformity. The mean values of these metrics in brain tumor segmentation are 0.86 ± 0.03, 0.77 ± 0.05, 0.94 ± 0.04, 0.99 ± 0.003, respectively. COMPARISON WITH EXISTING METHOD(S): Our method were compared with six state-of-the-art image segmentation methods: Chan-Vese (CV), Local Intensity Clustering (LIC), Local iNtensity Clustering (LINC), Global inhomogeneous intensity clustering (GINC), Multiplicative Intrinsic Component Optimization (MICO), and Local Statistical Active Contour Model (LSACM) models. We used qualitative and quantitative comparison methods for segmenting synthetic and real images. Experiments indicate that our proposed method is robust to noise and intensity non-uniformity and outperforms other state-of-the-art segmentation methods in terms of bias field correction, noise resistance, and segmentation accuracy. CONCLUSIONS: Experimental results show that the proposed model is capable of accurate segmentation and bias field estimation simultaneously. The proposed model suppresses the side effect of the over-smoothing object boundary. Moreover, our model has good accuracy in the segmentation of images with extreme intensity non-uniformity.

Solvent manipulation of the pre-reduction metal-ligand complex and particle-ligand binding for controlled synthesis of Pd nanoparticles.

Understanding how to control the nucleation and growth rates is crucial for designing nanoparticles with specific sizes and shapes. In this study, we show that the nucleation and growth rates are correlated with the thermodynamics of metal-ligand/solvent binding for the pre-reduction complex and the surface of the nanoparticle, respectively. To obtain these correlations, we measured the nucleation and growth rates by in situ small angle X-ray scattering during the synthesis of colloidal Pd nanoparticles in the presence of trioctylphosphine in solvents of varying coordinating ability. The results show that the nucleation rate decreased, while the growth rate increased in the following order, toluene, piperidine, 3,4-lutidine and pyridine, leading to a large increase in the final nanoparticle size (from 1.4 nm in toluene to 5.0 nm in pyridine). Using density functional theory (DFT), complemented by 31P nuclear magnetic resonance and X-ray absorption spectroscopy, we calculated the reduction Gibbs free energies of the solvent-dependent dominant pre-reduction complex and the solvent-nanoparticle binding energy. The results indicate that lower nucleation rates originate from solvent coordination which stabilizes the pre-reduction complex and increases its reduction free energy. At the same time, DFT calculations suggest that the solvent coordination affects the effective capping of the surface where stronger binding solvents slow the nanoparticle growth by lowering the number of active sites (not already bound by trioctylphosphine). The findings represent a promising advancement towards understanding the microscopic connection between the metal-ligand thermodynamic interactions and the kinetics of nucleation and growth to control the size of colloidal metal nanoparticles.

Fast level set method for glioma brain tumor segmentation based on Superpixel fuzzy clustering and lattice Boltzmann method.

BACKGROUND AND OBJECTIVE: Brain tumor segmentation is a challenging issue due to noise, artifact, and intensity non-uniformity in magnetic resonance images (MRI). Manual MRI segmentation is a very tedious, time-consuming, and user-dependent task. This paper aims to presents a novel level set method to address aforementioned challenges for reliable and automatic brain tumor segmentation. METHODS: In the proposed method, a new functional, based on level set method, is presented for medical image segmentation. Firstly, we define a superpixel fuzzy clustering objective function. To create superpixel regions, multiscale morphological gradient reconstruction (MMGR) operation is used. Secondly, a novel fuzzy energy functional is defined based on superpixel segmentation and histogram computation. Then, level set equations are obtained by using gradient descent method. Finally, we solve the level set equations by using lattice Boltzmann method (LBM). To evaluate the performance of the proposed method, both synthetic image dataset and real Glioma brain tumor images from BraTS 2017 dataset are used. RESULTS: Experiments indicate that our proposed method is robust to noise, initialization, and intensity non-uniformity. Moreover, it is faster and more accurate than other state-of-the-art segmentation methods with the averages of running time is 3.25 seconds, Dice and Jaccard coefficients for automatic tumor segmentation against ground truth are 0.93 and 0.87, respectively. The mean value of Hausdorff distance, Mean absolute Distance (MAD), accuracy, sensitivity, and specificity are 2.70, 0.005, 0.9940, 0.9183, and 0.9972, respectively. CONCLUSIONS: Our proposed method shows satisfactory results for Glioma brain tumor segmentation due to superpixel fuzzy clustering accurate segmentation results. Moreover, our method is fast and robust to noise, initialization, and intensity non-uniformity. Since most of the medical images suffer from these problems, the proposed method can more effective for complicated medical image segmentation.

The role of nanoparticle size and ligand coverage in size focusing of colloidal metal nanoparticles.

Controlling the size distribution of nanoparticles is important for many applications and typically involves the use of ligands during synthesis. In this study, we show that the mechanism of size focusing involves a dependence of the growth rate on the size of the nanoparticles and the ligand coverage on the surface of the nanoparticles. To demonstrate these effects, we used in situ small angle X-ray scattering (SAXS) and population balance kinetic modeling (PBM) to investigate the evolution of size distribution during the synthesis of colloidal Pd metal nanoparticles. Despite temporal overlap of nucleation and growth, our in situ SAXS show size focusing of the distribution under different synthetic conditions (different concentrations of metal and ligand as well as solvent type). To understand the mechanism of size focusing using PBM, we systematically studied how the evolution of the nanoparticle size distribution is affected by nucleation rate, and dependence of the growth rate constant on ligand surface coverage, and size of the nanoparticles. We show that continuous nucleation contributes to size defocusing. However, continuous nucleation results in different reaction times for the nanoparticle population leading to time and size-dependent ligand surface coverage. Using density functional theory (DFT) calculations and Brønsted-Evans-Polanyi relations, we show that as the population grows, larger nanoparticles grow more slowly than smaller ones due to lower intrinsic activity and higher ligand coverage on the surface. Therefore, despite continuous nucleation, the faster growth of smaller nanoparticles in the population leads to size focusing. The size focusing behaviour (due to faster growth of smaller nanoparticles) was found to be model independent and similar results were demonstrated under different nucleation and growth pathways (e.g. growth via ion reduction on the surface and/or monomer addition). Our results provide a microscopic connection between kinetics and thermodynamics of nanoparticle growth and metal-ligand binding, and their effect on the size distribution of colloidal nanoparticles.

Ligand-Mediated Nucleation and Growth of Palladium Metal Nanoparticles.

The size, size distribution and stability of colloidal nanoparticles are greatly affected by the presence of capping ligands. Despite the key contribution of capping ligands during the synthesis reaction, their role in regulating the nucleation and growth rates of colloidal nanoparticles is not well understood. In this work, we demonstrate a mechanistic investigation of the role of trioctylphosphine (TOP) in Pd nanoparticles in different solvents (toluene and pyridine) using in situ SAXS and ligand-based kinetic modeling. Our results under different synthetic conditions reveal the overlap of nucleation and growth of Pd nanoparticles during the reaction, which contradicts the LaMer-type nucleation and growth model. The model accounts for the kinetics of Pd-TOP binding for both, the precursor and the particle surface, which is essential to capture the size evolution as well as the concentration of particles in situ. In addition, we illustrate the predictive power of our ligand-based model through designing the synthetic conditions to obtain nanoparticles with desired sizes. The proposed methodology can be applied to other synthesis systems and therefore serves as an effective strategy for predictive synthesis of colloidal nanoparticles.

Colloidal nanoparticle size control: experimental and kinetic modeling investigation of the ligand-metal binding role in controlling the nucleation and growth kinetics.

Despite the major advancements in colloidal metal nanoparticles synthesis, a quantitative mechanistic treatment of the ligand's role in controlling their size remains elusive. We report a methodology that combines in situ small angle X-ray scattering (SAXS) and kinetic modeling to quantitatively capture the role of ligand-metal binding (with the metal precursor and the nanoparticle surface) in controlling the synthesis kinetics. We demonstrate that accurate extraction of the kinetic rate constants requires using both, the size and number of particles obtained from in situ SAXS to decouple the contributions of particle nucleation and growth to the total metal reduction. Using Pd acetate and trioctylphosphine in different solvents, our results reveal that the binding of ligands with both the metal precursor and nanoparticle surface play a key role in controlling the rates of nucleation and growth and consequently the final size. We show that the solvent can affect the metal-ligand binding and consequently ligand coverage on the nanoparticles surface which has a strong effect on the growth rate and final size (1.4 nm in toluene and 4.3 nm in pyridine). The proposed kinetic model quantitatively predicts the effects of varying the metal concentration and ligand/metal ratio on nanoparticle size for our work and literature reports. More importantly, we demonstrate that the final size is exclusively determined by the nucleation and growth kinetics at early times and not how they change with time. Specifically, the nanoparticle size in this work and many literature reports can be predicted using a single, model independent kinetic descriptor, (growth-to-nucleation rate ratio)1/3, despite the different metals and synthetic conditions. The proposed model and kinetic descriptor could serve as powerful tools for the design of colloidal nanoparticles with specific sizes.

Cancelable face verification using optical encryption and authentication.

In a cancelable biometric system, each instance of enrollment is distorted by a transform function, and the output should not be retransformed to the original data. This paper presents a new cancelable face verification system in the encrypted domain. Encrypted facial images are generated by a double random phase encoding (DRPE) algorithm using two keys (RPM1 and RPM2). To make the system noninvertible, a photon counting (PC) method is utilized, which requires a photon distribution mask for information reduction. Verification of sparse images that are not recognizable by direct visual inspection is performed by unconstrained minimum average correlation energy filter. In the proposed method, encryption keys (RPM1, RPM2, and PDM) are used in the sender side, and the receiver needs only encrypted images and correlation filters. In this manner, the system preserves privacy if correlation filters are obtained by an adversary. Performance of PC-DRPE verification system is evaluated under illumination variation, pose changes, and facial expression. Experimental results show that utilizing encrypted images not only increases security concerns but also enhances verification performance. This improvement can be attributed to the fact that, in the proposed system, the face verification problem is converted to key verification tasks.

Synthesis and preliminary evaluation of a new (99m)tc labeled substance p analogue as a potential tumor imaging agent.

Neurokinin 1 receptors (NK1R) are overexpressed on several types of important human cancer cells. Substance P (SP) is the most specific endogenous ligand known for NK1Rs. Accordingly,a new SP analogue was synthesized and evaluated for detection of NK1R positive tumors.[6-hydrazinopyridine-3-carboxylic acid (HYNIC)-Tyr(8)-Met(O)(11)-SP] was synthesized and radiolabeled with (99m)Tc using ethylenediamine-N,N'-diacetic acid (EDDA)and Tricine as coligands. Common physicochemical properties of radioconjugate were studied and in-vitro cell line biological tests were accomplished to determine the receptor mediated characteristics. In-vivo biodistribution in normal and tumor bearingnude mice was also assessed. The cold peptide was prepared in high purity (>99%) and radiolabeled with (99m)Tc at high specific activities (84-112GBq/µmol) with an acceptable labeling yield (>95%). The radioconjugate was stable in-vitro in the presence of human serum and showed 44% protein binding to human serumalbumin. In-vitro cell line studies on U373MG cells showed an acceptable uptake up to 4.91 ± 0.22% with the ratio of 60.21 ± 1.19% for its specific fraction and increasing specific internalization during 4 h. Receptor binding assays on U373MG cells indicated a mean Kd of 2.46 ± 0.43 nM and Bmax of 128925 ± 8145 sites/cell. In-vivo investigations determined the specific tumor uptake in 3.36 percent of injected dose per gram (%ID/g) for U373MG cells and noticeable accumulations of activity in the intestines and lung. Predominant renal excretion pathway was demonstrated. Therefore, this new radiolabeled peptide could be a promising radiotracer for detection of NK1R positive primary or secondary tumors.

Copy-move forgery detection using multiresolution local binary patterns.

Copy-move forgery is one of the most popular tampering artifacts in digital images. In this paper, we present an efficient method for copy-move forgery detection using Multiresolution Local Binary Patterns (MLBP). The proposed method is robust to geometric distortions and illumination variations of duplicated regions. Furthermore, the proposed block-based method recovers parameters of the geometric transformations. First, the image is divided into overlapping blocks and feature vectors for each block are extracted using LBP operators. The feature vectors are sorted based on lexicographical order. Duplicated image blocks are determined in the block matching step using k-d tree for more time reduction. Finally, in order to both determine the parameters of geometric transformations and remove the possible false matches, RANSAC (RANdom SAmple Consensus) algorithm is used. Experimental results show that the proposed approach is able to precisely detect duplicated regions even after distortions such as rotation, scaling, JPEG compression, blurring and noise adding.

Face verification using local binary pattern-unconstrained minimum average correlation energy correlation filters.

In this paper, we present a novel approach for face verification using local binary pattern (LBP) operators and optical correlation filters. Due to selected filter type and LBP method, different performances would have been expected. We let LBP operate on training images to form local binary pattern-unconstrained minimum average correlation energy (LBP-UMACE) filters as an optical correlation filter to enhance recognition rates and reduce error rates simultaneously. As a result, we demonstrate that the designed filters have better performance compared with UMACE filters. Moreover, the proposed filters are easy to implement and can be used in fast and reliable face verification systems.