A Cost-Effective Method for Bulge Prediction in Two Point Incremental Forming

Accurate prediction of the defects occurring in incrementally formed parts has been gaining attention in recent years. This interest is because accurate predictions can overcome the limitation in the advancement of incremental forming in industrial-scale implementation, which has been held back by the increase in the cost and development time due to trial and error methods. The finite element method has been widely utilized to predict the defects in the formed part, e.g., bulge. However, the computation time of running these models and their mesh-size dependency in predicting the forming defects represent barriers in adopting these models as part of CAD-FEM-CAE platforms. Thus, robust analytical and data-driven algorithms must be developed for a cost-effective design of complex parts. In this paper, a new analytical model is proposed to predict the bulge location and geometry in two point incremental forming of an aerospace aluminum alloy AA7075-O for a 67° truncated cone. First, the algorithm calculates the region of interest based on the part geometry. A novel shape function and weighted summation method are then utilized to calculate the amplitude of the instability produced by material accumulation during forming, leading to a bulge on the unformed portion of the sample. It was found that the geometric profile of the part influences the shape function, which is a function created to incorporate the effects of process parameter and boundary condition. The calculated profile in each direction is finalized into one 3-dimensional profile, compared with the experimental results for validation. The proposed model has proven to predict an accurate bulge profile with 95% accuracy comparing with experiments with less than 5% computational cost of FEM modeling.

Download Full-text

A MACH Filter-Based Reconstruction-Free Target Detector and Tracker for Compressive Sensing Cameras

International Journal of Smart Security Technologies ◽

10.4018/ijsst.2020070101 ◽

2020 ◽

Vol 7 (2) ◽

pp. 1-21

Author(s):

Henry Braun ◽

Sameeksha Katoch ◽

Pavan Turaga ◽

Andreas Spanias ◽

Cihan Tepedelenlioglu

Keyword(s):

Compressive Sensing ◽

Tracking System ◽

Video Quality ◽

Computational Cost ◽

Computation Time ◽

Visible Spectrum ◽

Cost Effective ◽

Sensor Data ◽

Image Reconstructions ◽

Mach Filter

Compressive sensing cameras hold the promise of cost-effective hardware, lower data rates, and improved video quality, particularly outside the visible spectrum. However, these improvements involve significant computational cost, as sensor output must be reconstructed in order to form an image viewable by a human. This paper describes a prototype automated detection and tracking system using a compressive sensing camera that does not rely on computationally costly image reconstructions. It operates on raw sensor data for an approximately ten-fold improvement in computation time over a comparable reconstruct-then-track algorithm. The detector is successful at a sensing rate of 0.3, comparable to that required for high-quality image reconstructions. If initialized with the location of a target, the tracker holds the target at a sensing rate of 0.005, below the boundary where reconstruction breaks down. These results show not only that direct tracking from compressive cameras is possible, but also give support to the pursuit of direct inference from compressive sensors of all types.

Download Full-text

Updated Kriging-Assisted Shape Optimization of a Gravity Dam

Water ◽

10.3390/w13010087 ◽

2021 ◽

Vol 13 (1) ◽

pp. 87

Author(s):

Yongqiang Wang ◽

Ye Liu ◽

Xiaoyi Ma

Keyword(s):

Surrogate Model ◽

Computational Cost ◽

Region Of Interest ◽

Optimization Procedure ◽

Optimal Shape ◽

Small Sample ◽

Gravity Dam ◽

Kriging Surrogate Model ◽

Gravity Dams ◽

Sample Set

The numerical simulation of the optimal design of gravity dams is computationally expensive. Therefore, a new optimization procedure is presented in this study to reduce the computational cost for determining the optimal shape of a gravity dam. Optimization was performed using a combination of the genetic algorithm (GA) and an updated Kriging surrogate model (UKSM). First, a Kriging surrogate model (KSM) was constructed with a small sample set. Second, the minimizing the predictor strategy was used to add samples in the region of interest to update the KSM in each updating cycle until the optimization process converged. Third, an existing gravity dam was used to demonstrate the effectiveness of the GA–UKSM. The solution obtained with the GA–UKSM was compared with that obtained using the GA–KSM. The results revealed that the GA–UKSM required only 7.53% of the total number of numerical simulations required by the GA–KSM to achieve similar optimization results. Thus, the GA–UKSM can significantly improve the computational efficiency. The method adopted in this study can be used as a reference for the optimization of the design of gravity dams.

Download Full-text

Practical Cross-Layer Radio Frequency-Based Authentication Scheme for Internet of Things

Sensors ◽

10.3390/s21124034 ◽

2021 ◽

Vol 21 (12) ◽

pp. 4034

Author(s):

Arie Haenel ◽

Yoram Haddad ◽

Maryline Laurent ◽

Zonghua Zhang

Keyword(s):

Internet Of Things ◽

Radio Frequency ◽

Real Life ◽

Computation Time ◽

Cost Effective ◽

Battery Life ◽

Cross Layer ◽

Security Level ◽

Cost Of Energy ◽

Iot Devices

The Internet of Things world is in need of practical solutions for its security. Existing security mechanisms for IoT are mostly not implemented due to complexity, budget, and energy-saving issues. This is especially true for IoT devices that are battery powered, and they should be cost effective to be deployed extensively in the field. In this work, we propose a new cross-layer approach combining existing authentication protocols and existing Physical Layer Radio Frequency Fingerprinting technologies to provide hybrid authentication mechanisms that are practically proved efficient in the field. Even though several Radio Frequency Fingerprinting methods have been proposed so far, as a support for multi-factor authentication or even on their own, practical solutions are still a challenge. The accuracy results achieved with even the best systems using expensive equipment are still not sufficient on real-life systems. Our approach proposes a hybrid protocol that can save energy and computation time on the IoT devices side, proportionally to the accuracy of the Radio Frequency Fingerprinting used, which has a measurable benefit while keeping an acceptable security level. We implemented a full system operating in real time and achieved an accuracy of 99.8% for the additional cost of energy, leading to a decrease of only ~20% in battery life.

Download Full-text

Data-Informed Decomposition for Localized Uncertainty Quantification of Dynamical Systems

Vibration ◽

10.3390/vibration4010004 ◽

2020 ◽

Vol 4 (1) ◽

pp. 49-63

Author(s):

Waad Subber ◽

Sayan Ghosh ◽

Piyush Pandita ◽

Yiming Zhang ◽

Liping Wang

Keyword(s):

Dynamical Systems ◽

Computational Cost ◽

Three Dimensional ◽

Region Of Interest ◽

System Response ◽

Computational Domain ◽

User Interest ◽

Numerical Resolution ◽

Multi Scale ◽

Operation Conditions

Industrial dynamical systems often exhibit multi-scale responses due to material heterogeneity and complex operation conditions. The smallest length-scale of the systems dynamics controls the numerical resolution required to resolve the embedded physics. In practice however, high numerical resolution is only required in a confined region of the domain where fast dynamics or localized material variability is exhibited, whereas a coarser discretization can be sufficient in the rest majority of the domain. Partitioning the complex dynamical system into smaller easier-to-solve problems based on the localized dynamics and material variability can reduce the overall computational cost. The region of interest can be specified based on the localized features of the solution, user interest, and correlation length of the material properties. For problems where a region of interest is not evident, Bayesian inference can provide a feasible solution. In this work, we employ a Bayesian framework to update the prior knowledge of the localized region of interest using measurements of the system response. Once, the region of interest is identified, the localized uncertainty is propagate forward through the computational domain. We demonstrate our framework using numerical experiments on a three-dimensional elastodynamic problem.

Download Full-text

Comparison between an Advanced Numerical Simulation of Sheet Incremental Forming Using Adaptive Remeshing and Experimental Results

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.554-557.1375 ◽

2013 ◽

Vol 554-557 ◽

pp. 1375-1381 ◽

Cited By ~ 5

Author(s):

Laurence Giraud-Moreau ◽

Abel Cherouat ◽

Jie Zhang ◽

Houman Borouchaki

Keyword(s):

Numerical Simulation ◽

Numerical Model ◽

Sheet Metal ◽

Metal Forming ◽

Tool Path ◽

Incremental Forming ◽

Computation Time ◽

Experimental Results ◽

Forming Process ◽

Adaptive Remeshing

Recently, new sheet metal forming technique, incremental forming has been introduced. It is based on using a single spherical tool, which is moved along CNC controlled tool path. During the incremental forming process, the sheet blank is fixed in sheet holder. The tool follows a certain tool path and progressively deforms the sheet. Nowadays, numerical simulations of metal forming are widely used by industry to predict the geometry of the part, stresses and strain during the forming process. Because incremental forming is a dieless process, it is perfectly suited for prototyping and small volume production [1, 2]. On the other hand, this process is very slow and therefore it can only be used when a slow series production is required. As the sheet incremental forming process is an emerging process which has a high industrial interest, scientific efforts are required in order to optimize the process and to increase the knowledge of this process through experimental studies and the development of accurate simulation models. In this paper, a comparison between numerical simulation and experimental results is realized in order to assess the suitability of the numerical model. The experimental investigation is realized using a three-axis CNC milling machine. The forming tool consists in a cylindrical rotating punch with a hemispherical head. A subroutine has been developed to describe the tool path from CAM procedure. A numerical model has been developed to simulate the sheet incremental forming process. The finite element code Abaqus explicit has been used. The simulation of the incremental forming process stays a complex task and the computation time is often prohibitive for many reasons. During this simulation, the blank is deformed by a sequence of small increments that requires many numerical increments to be performed. Moreover, the size of the tool diameter is generally very small compared to the size of the metal sheet and thus the contact zone between the tool and the sheet is limited. As the tool deforms almost every part of the sheet, small elements are required everywhere in the sheet resulting in a very high computation time. In this paper, an adaptive remeshing method has been used to simulate the incremental forming process. This strategy, based on adaptive refinement and coarsening procedures avoids having an initially fine mesh, resulting in an enormous computing time. Experiments have been carried out using aluminum alloy sheets. The final geometrical shape and the thickness profile have been measured and compared with the numerical results. These measurements have allowed validating the proposed numerical model. References [1] M. Yamashita, M. Grotoh, S.-Y. Atsumi, Numerical simulation of incremental forming of sheet metal, J. Processing Technology, No. 199 (2008), p. 163 172. [2] C. Henrard, A.M. Hbraken, A. Szekeres, J.R. Duflou, S. He, P. Van Houtte, Comparison of FEM Simulations for the Incremental Forming Process, Advanced Materials Research, 6-8 (2005), p. 533-542.

Download Full-text

Accelerated 3D blind separation of convolved mixtures based on the fast iterative shrinkage thresholding algorithm for adaptive multiple subtraction

Geophysics ◽

10.1190/geo2016-0384.1 ◽

2018 ◽

Vol 83 (2) ◽

pp. V99-V113 ◽

Cited By ~ 7

Author(s):

Zhong-Xiao Li ◽

Zhen-Chun Li

Keyword(s):

Field Data ◽

Optimization Problem ◽

Computational Cost ◽

Computation Time ◽

Blind Separation ◽

L1 Norm ◽

Norm Minimization ◽

Iterative Shrinkage ◽

Thresholding Algorithm ◽

Iterative Shrinkage Thresholding

After multiple prediction, adaptive multiple subtraction is essential for the success of multiple removal. The 3D blind separation of convolved mixtures (3D BSCM) method, which is effective in conducting adaptive multiple subtraction, needs to solve an optimization problem containing L1-norm minimization constraints on primaries by the iterative reweighted least-squares (IRLS) algorithm. The 3D BSCM method can better separate primaries and multiples than the 1D/2D BSCM method and the method with energy minimization constraints on primaries. However, the 3D BSCM method has high computational cost because the IRLS algorithm achieves nonquadratic optimization with an LS optimization problem solved in each iteration. In general, it is good to have a faster 3D BSCM method. To improve the adaptability of field data processing, the fast iterative shrinkage thresholding algorithm (FISTA) is introduced into the 3D BSCM method. The proximity operator of FISTA can solve the L1-norm minimization problem efficiently. We demonstrate that our FISTA-based 3D BSCM method achieves similar accuracy of estimating primaries as that of the reference IRLS-based 3D BSCM method. Furthermore, our FISTA-based 3D BSCM method reduces computation time by approximately 60% compared with the reference IRLS-based 3D BSCM method in the synthetic and field data examples.

Download Full-text

Plant Leaf Disease Recognition Using Depth-Wise Separable Convolution-Based Models

Symmetry ◽

10.3390/sym13030511 ◽

2021 ◽

Vol 13 (3) ◽

pp. 511

Author(s):

Syed Mohammad Minhaz Hossain ◽

Kaushik Deb ◽

Pranab Kumar Dhar ◽

Takeshi Koshiba

Keyword(s):

State Of The Art ◽

Computational Cost ◽

Region Of Interest ◽

Number Of Clusters ◽

Plant Leaf ◽

Leaf Disease ◽

Automatic Initialization ◽

Adequate Accuracy ◽

Model Size ◽

High Computational Cost

Proper plant leaf disease (PLD) detection is challenging in complex backgrounds and under different capture conditions. For this reason, initially, modified adaptive centroid-based segmentation (ACS) is used to trace the proper region of interest (ROI). Automatic initialization of the number of clusters (K) using modified ACS before recognition increases tracing ROI’s scalability even for symmetrical features in various plants. Besides, convolutional neural network (CNN)-based PLD recognition models achieve adequate accuracy to some extent. However, memory requirements (large-scaled parameters) and the high computational cost of CNN-based PLD models are burning issues for the memory restricted mobile and IoT-based devices. Therefore, after tracing ROIs, three proposed depth-wise separable convolutional PLD (DSCPLD) models, such as segmented modified DSCPLD (S-modified MobileNet), segmented reduced DSCPLD (S-reduced MobileNet), and segmented extended DSCPLD (S-extended MobileNet), are utilized to represent the constructive trade-off among accuracy, model size, and computational latency. Moreover, we have compared our proposed DSCPLD recognition models with state-of-the-art models, such as MobileNet, VGG16, VGG19, and AlexNet. Among segmented-based DSCPLD models, S-modified MobileNet achieves the best accuracy of 99.55% and F1-sore of 97.07%. Besides, we have simulated our DSCPLD models using both full plant leaf images and segmented plant leaf images and conclude that, after using modified ACS, all models increase their accuracy and F1-score. Furthermore, a new plant leaf dataset containing 6580 images of eight plants was used to experiment with several depth-wise separable convolution models.

Download Full-text

Multi-Scale Convolutional Neural Network for Accurate Corneal Segmentation in Early Detection of Fungal Keratitis

Journal of Fungi ◽

10.3390/jof7100850 ◽

2021 ◽

Vol 7 (10) ◽

pp. 850

Author(s):

Veena Mayya ◽

Sowmya Kamath Shevgoor ◽

Uma Kulkarni ◽

Manali Hazarika ◽

Prabal Datta Barua ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Region Of Interest ◽

Cost Effective ◽

Fungal Keratitis ◽

Contact Lens Wear ◽

Multi Scale ◽

Effective Interventions ◽

Prolonged Contact ◽

Segmented Images

Microbial keratitis is an infection of the cornea of the eye that is commonly caused by prolonged contact lens wear, corneal trauma, pre-existing systemic disorders and other ocular surface disorders. It can result in severe visual impairment if improperly managed. According to the latest World Vision Report, at least 4.2 million people worldwide suffer from corneal opacities caused by infectious agents such as fungi, bacteria, protozoa and viruses. In patients with fungal keratitis (FK), often overt symptoms are not evident, until an advanced stage. Furthermore, it has been reported that clear discrimination between bacterial keratitis and FK is a challenging process even for trained corneal experts and is often misdiagnosed in more than 30% of the cases. However, if diagnosed early, vision impairment can be prevented through early cost-effective interventions. In this work, we propose a multi-scale convolutional neural network (MS-CNN) for accurate segmentation of the corneal region to enable early FK diagnosis. The proposed approach consists of a deep neural pipeline for corneal region segmentation followed by a ResNeXt model to differentiate between FK and non-FK classes. The model trained on the segmented images in the region of interest, achieved a diagnostic accuracy of 88.96%. The features learnt by the model emphasize that it can correctly identify dominant corneal lesions for detecting FK.

Download Full-text

Mobile Agent-Based Collaborative Computing Framework for Handling Constraint Resources

Ubiquitous Multimedia and Mobile Agents ◽

10.4018/978-1-61350-107-8.ch005 ◽

2012 ◽

pp. 113-134

Author(s):

Anil Kakarla ◽

Sanjeev Agarwal ◽

Sanjay Kumar Madria

Keyword(s):

Information Processing ◽

Distributed Computing ◽

Mobile Agent ◽

Computational Cost ◽

Computation Time ◽

Distributed Network ◽

Collaborative Computing ◽

Agent Based ◽

Computing Framework ◽

Viable System

Information processing and collaborative computing using agents over a distributed network of heterogeneous platforms are important for many defense and civil applications. In this chapter, a mobile agent based collaborative and distributed computing framework for network centric information processing is presented using a military application. In this environment, the challenge is to continue processing efficiently while satisfying multiple constraints like computational cost, communication bandwidth, and energy in a distributed network. The authors use mobile agent technology for distributed computing to speed up data processing using the available systems resources in the network. The proposed framework provides a mechanism to bridge the gap between computation resources and dispersed data sources under variable bandwidth constraints. For every computation task raised in the network, a viable system that has resources and data to compute the task is identified and sent to the viable system for completion. Experimental evaluation under the real platform is reported. It shows that in spite of an increase of the communication load in comparison with other solutions the proposed framework leads to a decrease of the computation time.

Download Full-text

Classification of Mammograms Using Texture and CNN Based Extracted Features

Journal of Biomimetics Biomaterials and Biomedical Engineering ◽

10.4028/www.scientific.net/jbbbe.42.79 ◽

2019 ◽

Vol 42 ◽

pp. 79-97 ◽

Cited By ~ 2

Author(s):

Taye Girma Debelee ◽

Abrham Gebreselasie ◽

Friedhelm Schwenker ◽

Mohammadreza Amirian ◽

Dereje Yohannes

Keyword(s):

Feature Fusion ◽

Region Of Interest ◽

Computation Time ◽

Texture Features ◽

The Public ◽

Gabor Features ◽

Analysis Society ◽

Public Datasets ◽

Mlp Classifier ◽

Sensitivity Specificity

In this paper, a modified adaptive K-means (MAKM) method is proposed to extract the region of interest (ROI) from the local and public datasets. The local image datasets are collected from Bethezata General Hospital (BGH) and the public datasets are from Mammographic Image Analysis Society (MIAS). The same image number is used for both datasets, 112 are abnormal and 208 are normal. Two texture features (GLCM and Gabor) from ROIs and one CNN based extracted features are considered in the experiment. CNN features are extracted using Inception-V3 pre-trained model after simple preprocessing and cropping. The quality of the features are evaluated individually and by fusing features to one another and five classifiers (SVM, KNN, MLP, RF, and NB) are used to measure the descriptive power of the features using cross-validation. The proposed approach was first evaluated on the local dataset and then applied to the public dataset. The results of the classifiers are measured using accuracy, sensitivity, specificity, kappa, computation time and AUC. The experimental analysis made using GLCM features from the two datasets indicates that GLCM features from BGH dataset outperformed that of MIAS dataset in all five classifiers. However, Gabor features from the two datasets scored the best result with two classifiers (SVM and MLP). For BGH and MIAS, SVM scored an accuracy of 99%, 97.46%, the sensitivity of 99.48%, 96.26% and specificity of 98.16%, 100% respectively. And MLP achieved an accuracy of 97%, 87.64%, the sensitivity of 97.40%, 96.65% and specificity of 96.26%, 75.73% respectively. Relatively maximum performance is achieved for feature fusion between Gabor and CNN based extracted features using MLP classifier. However, KNN, MLP, RF, and NB classifiers achieved almost 100% performance for GLCM texture features and SVM scored an accuracy of 96.88%, the sensitivity of 97.14% and specificity of 96.36%. As compared to other classifiers, NB has scored the least computation time in all experiments.

Download Full-text