In this paper we address the abnormality detection problem in crowded scenes. We propose to use Generative Adversarial Nets (GANs), which are trained using normal frames and corresponding ...optical-flow images in order to learn an internal representation of the scene normality. Since our GANs are trained with only normal data, they are not able to generate abnormal events. At testing time the real data are compared with both the appearance and the motion representations reconstructed by our GANs and abnormal areas are detected by computing local differences. Experimental results on challenging abnormality detection datasets show the superiority of the proposed method compared to the state of the art in both frame-level and pixel-level abnormality detection tasks.
Bioprinting, within the emerging field of biofabrication, aims at the fabrication of functional biomimetic constructs. Different 3D bioprinting techniques have been adapted to bioprint cell‐laden ...bioinks. However, single‐material bioprinting techniques oftentimes fail to reproduce the complex compositions and diversity of native tissues. Multi‐material bioprinting as an emerging approach enables the fabrication of heterogeneous multi‐cellular constructs that replicate their host microenvironments better than single‐material approaches. Here, bioprinting modalities are reviewed, their being adapted to multi‐material bioprinting is discussed, and their advantages and challenges, encompassing both custom‐designed and commercially available technologies are analyzed. A perspective of how multi‐material bioprinting opens up new opportunities for tissue engineering, tissue model engineering, therapeutics development, and personalized medicine is offered.
A comprehensive overview of the available 3D bioprinting technologies for fabricating multi‐material constructs is presented. The technologies are classified into four major categories, and their advantages and shortcomings are compared. Available multi‐material commercial bioprinters are reviewed, concluding with a perspective of the future path for developing multi‐material technologies.
The E-health care systems allow patients to gain the health monitoring facility and access medical services remotely. A secure mechanism for mutual authentication and session key agreement is the ...most important requirements for E-Health Care Systems. Recently, Amin et al.’s proposed a mutual authentication and session key agreement protocol and claimed that their scheme is secure against all possible attacks. In this paper, we show that not only their scheme is vulnerable to privileged-insider attack, replay attack, session key disclosure attack, but also does not provide patient untraceability and backward secrecy. In order to withstand the mentioned security weaknesses, we propose an efficient remote mutual authentication scheme for the systems which are using
ECC
and Fuzzy Extractor. The proposed scheme not only resists against different security attacks, but it also provides an efficient registration, login, mutual authentication, session key agreement, and password and biometric update phases. During the experimentation, it has been observed that the proposed scheme is secure against various known attacks. Beside, our scheme is robust against privileged-insider attack that it rarely checked in security analysis. The informal analysis will ensure that our scheme provides well security protection against the different security attacks. Furthermore, we analyzed the security of the scheme using
AVISPA
software and Random Oracle Model. The formal analysis results and performance evaluation vouch that our scheme is also secure and efficient in computation and communication cost.
The development of accurate methods for multi-label classification (MLC) of remote sensing (RS) images is one of the most important research topics in RS. The MLC methods based on convolutional ...neural networks (CNNs) have shown strong performance gains in RS. However, they usually require a high number of reliable training images annotated with multiple land-cover class labels. Collecting such data is time-consuming and costly. To address this problem, the publicly available thematic products, which can include noisy labels, can be used to annotate RS images with zero-labeling cost. However, multi-label noise (which can be associated with wrong and missing label annotations) can distort the learning process of the MLC methods. To address this problem, we propose a novel multi-label noise robust collaborative learning (RCML) method to alleviate the negative effects of multi-label noise during the training phase of a CNN model. RCML identifies, ranks, and excludes noisy multi-labels in RS images based on three main modules: 1) the discrepancy module; 2) the group lasso module; and 3) the swap module. The discrepancy module ensures that the two networks learn diverse features, while producing the same predictions. The task of the group lasso module is to detect the potentially noisy labels assigned to multi-labeled training images, while the swap module is devoted to exchange the ranking information between two networks. Unlike the existing methods that make assumptions about noise distribution, our proposed RCML does not make any prior assumption about the type of noise in the training set. The experiments conducted on two multi-label RS image archives confirm the robustness of the proposed RCML under extreme multi-label noise rates. Our code is publicly available at: https://www.noisy-labels-in-rs.org .
In the present work, heat transfer and fluid flow in simple tube geometry, star-shaped tube geometry, and turbulator inserted geometry have been investigated and compared. Also, it is located in a ...double tube heat exchanger to use in a residential gas fire water heater. The most critical parameters are considered including temperature distribution, Nusselt number, convective heat transfer coefficient, coefficient of friction, and pressure drop. The simulation is 3D, and the SIMPLE algorithm is used for numerical solution based on the finite volume method. Then, by considering two methods of changing the geometry of the tube and using a turbulator in the flow path to increase the efficiency of a double tube heat exchanger and comparing them with each other, the most optimal case is presented. The validation is shown acceptable agreement by the absolute average deviation (AAD) error of 7.13% compared to the experimental data and numerical results. In the 200 ≤ Re ≤ 1800 for cold flow and the constant Reynolds number equal to 1800 for hot flow, the results show that when using heat exchanger geometries with turbulator and star-shaped tube instead of the simple heat exchanger geometry, the Nusselt number on either the hot or cold side of the heat exchanger has improved up to 146% and 50%, respectively. For cold flow in turbulator inserted geometry, in the best result, the Nusselt number increased 2.4 times to 6.107, and for star-shaped tube geometry up 1.5 times to 3.939. For hot flow in turbulator inserted geometry, the Nusselt number has increased up to 48.05, and for star-shaped, tube geometry decreased to 16.3 in comparison to simple geometry. In addition, the pressure drop for the cold side of the flow in the mode of the simple double tube and the coiled wire double tube is approximately identical (maximum 1818.06 for Re = 1800), while the pressure drop in the double star-shaped tubes is reduced by up to 50% compared to the other two modes and its best value at Re = 1800 is 1419.94pa. Finally, by using the Topsis method, as a multi-objective optimization technique, and according to the two criteria with different mass, including pressure drop, as an undesirable criterion, and Nusselt number, as a desirable criterion, the optimal Reynolds number for cold flow was determined.
ABSTRACT
One of the critical challenges facing imaging studies of the 21-cm signal at the Epoch of Reionization (EoR) is the separation of astrophysical foreground contamination. These foregrounds ...are known to lie in a wedge-shaped region of (k⊥, k∥) Fourier space. Removing these Fourier modes excises the foregrounds at grave expense to image fidelity, since the cosmological information at these modes is also removed by the wedge filter. However, the 21-cm EoR signal is non-Gaussian, meaning that the lost wedge modes are correlated to the surviving modes by some covariance matrix. We have developed a machine learning-based method that exploits this information to identify ionized regions within a wedge-filtered image. Our method reliably identifies the largest ionized regions and can reconstruct their shape, size, and location within an image. We further demonstrate that our method remains viable when instrumental effects are accounted for, using the Hydrogen EoR Array and the Square Kilometre Array as fiducial instruments. The ability to recover spatial information from wedge-filtered images unlocks the potential for imaging studies using current- and next-generation instruments without relying on detailed models of the astrophysical foregrounds themselves.
In the present work, thermodynamic and economic modeling of a single-effect absorption chiller cycle to a photovoltaic solar system has been investigated. Modeling with three perspectives of optical ...analysis, computational fluid dynamics, and thermodynamics is considered to be coupled together. Solar energy has been used to drive the absorption chiller cycle and production of cooling for residential buildings. Solar centralization system including solar panels, fluid flow is used to generate and store electricity, usage in the absorption cycle, respectively. In the numerical simulation, the pressure drop and temperature of the system outlet are investigated. In the thermodynamic simulation, the performance coefficient of the absorption chiller cycle, the efficiency of the second law of thermodynamics, the cooling load, and the temperature of cooling flow is investigated. The results are validated under the same conditions for optical analysis and numerical solution; Based on this, the values obtained from the simulation is shown a maximum of 7.6% error compared to the results of the reference paper. The maximum heat flux transferred to water flow is equal to 11884 (W/m2) in June, which was obtained using numerical simulation, the maximum value Tout,CPVT=368.8(K). According to the thermodynamic modeling of the system, the minimum flow rate of CPVT was obtained m˙CPVT=0.15(kg/s) and according to the performance coefficient, exergy efficiency, and total cost rate was selected as the optimal flow rate that produces a cooling load equal to Q˙Eva=8.509(kW) the production coefficient and efficiency. Exergy and overall start-up costs are 0.2714, 0.729 and 0.0424 ($/hr), respectively.
Enhancing the performance of domestic gas-fired water heaters, due to their extensive usage, will significantly reduce their energy consumption and greenhouse gas emissions. Therefore, a numerical ...investigation, comparison, and optimization of three different fins of the heat exchangers used in the domestic gas-fired water heaters have been performed. The variations of thermal and flow parameters, including Nusselt number (Nu), Colburn factor (j), and Friction factor (f) for every proposed geometry, have been studied numerically. Besides, the effect of parameters including separator angle (α) in the first geometry (G1), nondimensional distance of circular vortex generator from the fin base (L*) in the second geometry (G2), and the nondimensional distance of winglets from the center of pipes' cross section (R*) in the third geometry (G3) on the fluid flow and heat transfer was investigated. Results revealed that the best hydrothermal performance is obtained in G1, G2, and G3 with the specifications of α = 40°, L* = 0.26, and R* = 1.74, respectively. Besides, compared with plain geometry, the maximum enhancement (11.2%) was achieved in G2 with L* = 0.26. The entropy generation (S
g
) for each geometry was studied to analyze the performance of the designed fins. It was found that the G2 with L* = 0.13 shows the minimum
S
g
. The TOPSIS multi-objective optimization results showed that by increasing the Reynolds number (Re), the G2 with L* = 0.13 showed the best performance and was chosen as the best geometry.
Graphical Abstract
This paper presents an automatic building detection technique using LIDAR data and multispectral imagery. Two masks are obtained from the LIDAR data: a ‘primary building mask’ and a ‘secondary ...building mask’. The primary building mask indicates the
void areas where the laser does not reach below a certain height threshold. The secondary building mask indicates the
filled areas, from where the laser reflects, above the same threshold. Line segments are extracted from around the void areas in the primary building mask. Line segments around trees are removed using the normalized difference vegetation index derived from the orthorectified multispectral images. The initial building positions are obtained based on the remaining line segments. The complete buildings are detected from their initial positions using the two masks and multispectral images in the YIQ colour system. It is experimentally shown that the proposed technique can successfully detect urban residential buildings, when assessed in terms of 15 indices including
completeness,
correctness and
quality.
The development of accurate methods for multi-label scene classification (MLC) of remote sensing (RS) images is one of the most important research topics in RS. To address MLC problems, the use of ...deep neural networks that require a high number of reliable training images annotated by multiple land-cover class labels (multi-labels) has been found popular in RS. However, collecting such annotations is time consuming and costly. A common procedure to obtain annotations at zero labeling cost is to rely on thematic products or crowdsourced labels. As a drawback, these procedures come with the risk of label noise that can distort the learning process of the MLC algorithms. In the literature, most label noise robust methods are designed for single-label classification (SLC) problems in computer vision (CV), where each image is annotated by a single label. Unlike SLC, label noise in MLC can be associated with: 1) subtractive label noise (a land cover class label is not assigned to an image while that class is present in the image); 2) additive label noise (a land cover class label is assigned to an image, although that class is not present in the given image); and 3) mixed label noise (a combination of both). In this article, we investigate three different noise robust CV SLC methods (self-adaptive training (SAT), early-learning regularization, and joint co-regularized training) and adapt them to be robust for multi-label noise scenarios in RS. During experiments, we study the effects of different types of multi-label noise and evaluate the adapted methods rigorously. To this end, we also introduce a synthetic multi-label noise injection strategy that is more adequate to simulate operational scenarios compared to the uniform label noise injection strategy, in which the labels of absent and present classes are flipped at uniform probability. Further, we study the relevance of different evaluation metrics in MLC problems under noisy multi-labels. On the basis of the theoretical and experimental analyses, some guidelines for a proper design of label noise robust MLC methods are derived.