Search results for: multi-resolution feature fusion

Authors: Mansouri Nabila, Ben Jemaa Yousra, Motamed Cina, Watelain Eric

Abstract:

Research and development efforts in intelligent Advanced Driver Assistance Systems (ADAS) seek to save lives and reduce the number of on-road fatalities. For traffic and emergency monitoring, the essential but challenging task is vehicle detection and tracking in reasonably short time. This purpose needs first of all a powerful dynamic car detector model. In fact, this paper presents an optimized HOG process based on shape and motion parameters fusion. Our proposed approach mains to compute HOG by bloc feature from foreground blobs using configurable research window and pathway in order to overcome the shortcoming in term of computing time of HOG descriptor and improve their dynamic application performance. Indeed we prove in this paper that HOG by bloc descriptor combined with motion parameters is a very suitable car detector which reaches in record time a satisfactory recognition rate in dynamic outside area and bypasses several popular works without using sophisticated and expensive architectures such as GPU and FPGA.

Keywords: car-detector, HOG, motion, computing time

Procedia PDF Downloads 292

Authors: Rodrigo Antunes, Olga Borisevich, David Demange

Abstract:

In future nuclear fusion reactors, tritium self-sufficiency will be ensured by tritium (3H) production via reactions between the fusion neutrons and lithium. To favor tritium breeding, a neutron multiplier must also be used. Both tritium breeder and neutron multiplier will be placed in the so-called Breeding Blanket (BB). For the European Helium-Cooled Pebble Bed (HCPB) BB concept, the tritium production and neutron multiplication will be ensured by neutron bombardment of Li4SiO4 and Be pebbles, respectively. The produced tritium is extracted from the pebbles by purging them with large flows of He (~ 104 Nm3h-1), doped with small amounts of H2 (~ 0.1 vol%) to promote tritium extraction via isotopic exchange (producing HT). Due to the presence of oxygen in the pebbles, production of tritiated water is unavoidable. Therefore, the purging gas downstream of the BB will be composed by Q2/Q2O/He (Q = 1H, 2H, 3H), with Q2/Q2O down to ppm levels, which must be further processed for tritium recovery. A two-stage continuous approach, where zeolite membranes (ZMs) are followed by a catalytic membrane reactor (CMR), has been recently proposed to fulfil this task. The tritium recovery from Q2/Q2O/He is ensured by the CMR, that requires a reduction of the gas flow coming from the BB and a pre-concentration of Q2 and Q2O to be efficient. For this reason, and to keep this stage with reasonable dimensions, ZMs are required upfront to reduce as much as possible the He flows and concentrate the Q2/Q2O species. Therefore, experimental activities have been carried out at the Tritium Laboratory Karlsruhe (TLK) to test the separation performances of different zeolite membranes for H2/H2O/He. First experiments have been performed with binary mixtures of H2/He and H2O/He with commercial MFI-ZSM5 and NaA zeolite-type membranes. Only the MFI-ZSM5 demonstrated selectivity towards H2, with a separation factor around 1.5, and H2 permeances around 0.72 µmolm-2s-1Pa-1, rather independent for feed concentrations in the range 0.1 vol%-10 vol% H2/He. The experiments with H2O/He have demonstrated that the separation factor towards H2O is highly dependent on the feed concentration and temperature. For instance, at 0.2 vol% H2O/He the separation factor with NaA is below 2 and around 1000 at 5 vol% H2O/He, at 30°C. Overall, both membranes demonstrated complementary results at equivalent temperatures. In fact, at low feed concentrations ( ≤ 1 vol% H2O/He) MFI-ZSM5 separates better than NaA, whereas the latter has higher separation factors for higher inlet water content ( ≥ 5 vol% H2O/He). In this contribution, the results obtained with both MFI-ZSM5 and NaA membranes for H2/He and H2O/H2 mixtures at different concentrations and temperatures are compared and discussed.

Keywords: nuclear fusion, gas separation, tritium processes, zeolite membranes

Procedia PDF Downloads 266

Authors: Tawfik Thelaidjia, Salah Chenikher

Abstract:

Bearing fault diagnosis has attracted significant attention over the past few decades. It consists of two major parts: vibration signal feature extraction and condition classification for the extracted features. In this paper, feature extraction from faulty bearing vibration signals is performed by a combination of the signal’s Kurtosis and features obtained through the preprocessing of the vibration signal samples using Db2 discrete wavelet transform at the fifth level of decomposition. In this way, a 7-dimensional vector of the vibration signal feature is obtained. After feature extraction from vibration signal, the support vector machine (SVM) was applied to automate the fault diagnosis procedure. To improve the classification accuracy for bearing fault prediction, particle swarm optimization (PSO) is employed to simultaneously optimize the SVM kernel function parameter and the penalty parameter. The results have shown feasibility and effectiveness of the proposed approach

Keywords: condition monitoring, discrete wavelet transform, fault diagnosis, kurtosis, machine learning, particle swarm optimization, roller bearing, rotating machines, support vector machine, vibration measurement

Procedia PDF Downloads 408

Authors: N. Dahraoui, M. Boulakroune, D. Benatia

Abstract:

In this paper, the improvement by deconvolution of the depth resolution in Secondary Ion Mass Spectrometry (SIMS) analysis is considered. Indeed, we have developed a new Tikhonov-Miller deconvolution algorithm where a priori model of the solution is included. This is a denoisy and pre-deconvoluted signal obtained from: firstly, by the application of wavelet shrinkage algorithm, secondly by the introduction of the obtained denoisy signal in an iterative deconvolution algorithm. In particular, we have focused the light on the effect of the iterations number on the evolution of the deconvoluted signals. The SIMS profiles are multilayers of Boron in Silicon matrix.

Keywords: DRF, in-depth resolution, multiresolution deconvolution, SIMS, wavelet shrinkage

Procedia PDF Downloads 386

Authors: Deepa Das, Susmita Das

Abstract:

Cognitive Radio (CR) is an emerging technology to combat the spectrum scarcity issues. This is achieved by consistently sensing the spectrum, and detecting the under-utilized frequency bands without causing undue interference to the primary user (PU). In soft decision fusion (SDF) based cooperative spectrum sensing, various evolutionary algorithms have been discussed, which optimize the weight coefficient vector for maximizing the detection performance. In this paper, we propose the hybrid invasive weed optimization and particle swarm optimization (IWO/PSO) algorithm as a fast and global optimization method, which improves the detection probability with a lesser sensing time. Then, the efficiency of this algorithm is compared with the standard invasive weed optimization (IWO), particle swarm optimization (PSO), genetic algorithm (GA) and other conventional SDF based methods on the basis of convergence and detection probability.

Keywords: cognitive radio, spectrum sensing, soft decision fusion, GA, PSO, IWO, hybrid IWO/PSO

Procedia PDF Downloads 427

Authors: Peyman Sheikholharam Mashhadi

Abstract:

Difficulties in analyzing real world images in classical image processing and machine vision framework have motivated researchers towards considering the biology-based vision. It is a common belief that mammalian visual cortex has been adapted to the statistics of the real world images through the evolution process. There are two well-known successful models of mammalian visual cortical cells: Independent Component Analysis (ICA) and Independent Subspace Analysis (ISA). In this paper, we statistically analyze the dependencies which remain in the components after applying these models to the natural images. Also, we investigate the response of feature detectors to gratings with various parameters in order to find optimal parameters of the feature detectors. Finally, the selectiveness of feature detectors to phase, in both models is considered.

Keywords: statistics, independent component analysis, independent subspace analysis, phase, natural images

Procedia PDF Downloads 318

Authors: Adel Sabry Eesa, Adnan Mohsin Abdulazeez Brifcani, Zeynep Orman

Abstract:

Feature selection has been used in many fields such as classification, data mining and object recognition and proven to be effective for removing irrelevant and redundant features from the original data set. In this paper, a new design of distributed intrusion detection system using a combination feature selection model based on bees and decision tree. Bees algorithm is used as the search strategy to find the optimal subset of features, whereas decision tree is used as a judgment for the selected features. Both the produced features and the generated rules are used by Decision Making Mobile Agent to decide whether there is an attack or not in the networks. Decision Making Mobile Agent will migrate through the networks, moving from node to another, if it found that there is an attack on one of the nodes, it then alerts the user through User Interface Agent or takes some action through Action Mobile Agent. The KDD Cup 99 data set is used to test the effectiveness of the proposed system. The results show that even if only four features are used, the proposed system gives a better performance when it is compared with the obtained results using all 41 features.

Keywords: distributed intrusion detection system, mobile agent, feature selection, bees algorithm, decision tree

Procedia PDF Downloads 367

Authors: Awais Ahmad Khan, Emad Abouel Nasr, H. M. A. Hussein, Abdulrahman Al-Ahmari

Abstract:

Sheet-metal parts have been widely applied in electronics, communication and mechanical industries in recent decades; but the advancement in sheet-metal part design and manufacturing is still behind in comparison with the increasing importance of sheet-metal parts in modern industry. This paper presents a methodology for automatic extraction of some common 2D internal sheet metal features. The features used in this study are taken from Unipunch ™ catalogue. The extraction process starts with the data extraction from STEP file using an object oriented approach and with the application of suitable algorithms and rules, all features contained in the catalogue are automatically extracted. Since the extracted features include geometry and engineering information, they will be effective for downstream application such as feature rebuilding and process planning.

Keywords: feature extraction, internal features, punch shapes, sheet metal

Procedia PDF Downloads 587

Authors: Robnier Reyes, Andrew J. P. Marques, Joel Ramjist, Chris R. Pasarikovski, Victor X. D. Yang

Abstract:

Over the past three decades, surgical robotic systems have demonstrated their ability to improve surgical outcomes. The LBR Med is a collaborative robotic arm that is meant to work with a surgeon to streamline surgical workflow. It has 7 degrees of freedom and thus can be easily oriented. Position and torque sensors at each joint allow it to maintain a position accuracy of 150 µm with real-time force and torque feedback, making it ideal for complex surgical procedures. Spinal fusion procedures involve the placement of as many as 20 pedicle screws, requiring a great deal of accuracy due to proximity to the spinal canal and surrounding vessels. Any deviation from intended path can lead to major surgical complications. Assistive surgical robotic systems are meant to serve as collaborative devices easing the workload of the surgeon, thereby improving pedicle screw placement by mitigating fatigue related inaccuracies. Moreover, robotic spinal systems have shown marked improvements over conventional freehanded techniques in both screw placement accuracy and fusion quality and have greatly reduced the need for screw revision, intraoperatively and post-operatively. However, current assistive spinal fusion robots, such as the ROSA Spine, are limited in functionality to positioning surgical instruments. While they offer a small degree of improvement in pedicle screw placement accuracy, they do not alleviate surgeon fatigue, nor do they provide real-time force and torque feedback during screw insertion. We propose a semi-autonomous surgical robot workflow for spinal fusion where the surgeon guides the robot to its initial position and orientation, and the robot drives the pedicle screw accurately into the vertebra. Here, we demonstrate feasibility by inserting pedicle screws into ex-vivo bovine rib bone. The robot monitors position, force and torque with respect to predefined values selected by the surgeon to ensure the highest possible spinal fusion quality. The workflow alleviates the strain on the surgeon by having the robot perform the screw placement while the ability to monitor the process in real-time keeps the surgeon in the system loop. The approach we have taken in terms of level autonomy for the robot reflects its ability to safely collaborate with the surgeon in the operating room without external navigation systems.

Keywords: ex vivo bovine bone, pedicle screw, surgical robot, surgical workflow

Procedia PDF Downloads 128

Authors: Kasra Majbouri Yazdi, Adel Majbouri Yazdi, Saeid Khodayi, Jingyu Hou, Wanlei Zhou, Saeed Saedy

Abstract:

Fake news and false information are big challenges of all types of media, especially social media. There is a lot of false information, fake likes, views and duplicated accounts as big social networks such as Facebook and Twitter admitted. Most information appearing on social media is doubtful and in some cases misleading. They need to be detected as soon as possible to avoid a negative impact on society. The dimensions of the fake news datasets are growing rapidly, so to obtain a better result of detecting false information with less computation time and complexity, the dimensions need to be reduced. One of the best techniques of reducing data size is using feature selection method. The aim of this technique is to choose a feature subset from the original set to improve the classification performance. In this paper, a feature selection method is proposed with the integration of K-means clustering and Support Vector Machine (SVM) approaches which work in four steps. First, the similarities between all features are calculated. Then, features are divided into several clusters. Next, the final feature set is selected from all clusters, and finally, fake news is classified based on the final feature subset using the SVM method. The proposed method was evaluated by comparing its performance with other state-of-the-art methods on several specific benchmark datasets and the outcome showed a better classification of false information for our work. The detection performance was improved in two aspects. On the one hand, the detection runtime process decreased, and on the other hand, the classification accuracy increased because of the elimination of redundant features and the reduction of datasets dimensions.

Keywords: clustering, fake news detection, feature selection, machine learning, social media, support vector machine

Procedia PDF Downloads 144

Authors: Hassan Masoumi, Ahad Salimi, Nazanin Barhemmat, Babak Gholami

Abstract:

Artificial neural networks have gained a lot of interest as empirical models for their powerful representational capacity, multi input and output mapping characteristics. In fact, most feed-forward networks with nonlinear nodal functions have been proved to be universal approximates. In this paper, we propose a new supervised method for color image classification based on self organizing feature maps (SOFM). This algorithm is based on competitive learning. The method partitions the input space using self-organizing feature maps to introduce the concept of local neighborhoods. Our image classification system entered into RGB image. Experiments with simulated data showed that separability of classes increased when increasing training time. In additional, the result shows proposed algorithms are effective for color image classification.

Keywords: classification, SOFM algorithm, neural network, neighborhood, RGB image

Procedia PDF Downloads 442

Authors: Mehdi Brahimi, Kamal Medjaher, Noureddine Zerhouni, Mohammed Leouatni

Abstract:

The Prognostics and Health Management is a system engineering discipline which provides solutions and models to the implantation of a predictive maintenance. The approach is based on extracting useful information from monitoring data to assess the “health” state of an industrial equipment or an asset. In this paper, we examine multiple extracted features from Pantograph-Catenary contact force in order to select the most relevant ones to achieve a diagnostics function. The feature extraction methodology is based on simulation data generated thanks to a Pantograph-Catenary simulation software called INPAC and measurement data. The feature extraction method is based on both statistical and signal processing analyses. The feature selection method is based on statistical criteria.

Keywords: catenary/pantograph interaction, diagnostics, Prognostics and Health Management (PHM), quality of current collection

Procedia PDF Downloads 260

Authors: H. G. C. P. Dinesh, G. Tharshini, M. P. B. Ekanayake, G. M. R. I. Godaliyadda

Abstract:

This paper presents a new spatial feature extraction method based on principle component analysis (PCA) and Fisher Discernment Analysis (FDA) for facial expression recognition. It not only extracts reliable features for classification, but also reduces the feature space dimensions of pattern samples. In this method, first each gray scale image is considered in its entirety as the measurement matrix. Then, principle components (PCs) of row vectors of this matrix and variance of these row vectors along PCs are estimated. Therefore, this method would ensure the preservation of spatial information of the facial image. Afterwards, by incorporating the spectral information of the eigen-filters derived from the PCs, a feature vector was constructed, for a given image. Finally, FDA was used to define a set of basis in a reduced dimension subspace such that the optimal clustering is achieved. The method of FDA defines an inter-class scatter matrix and intra-class scatter matrix to enhance the compactness of each cluster while maximizing the distance between cluster marginal points. In order to matching the test image with the training set, a cosine similarity based Bayesian classification was used. The proposed method was tested on the Cohn-Kanade database and JAFFE database. It was observed that the proposed method which incorporates spatial information to construct an optimal feature space outperforms the standard PCA and FDA based methods.

Keywords: facial expression recognition, principle component analysis (PCA), fisher discernment analysis (FDA), eigen-filter, cosine similarity, bayesian classifier, f-measure

Procedia PDF Downloads 400

Authors: B. R. S. Babu, E. Prasad, P. V. Laveen, A. M. Vinodkumar

Abstract:

Searching the “Island of stability” is a topic of extreme interest in theoretical as well as experimental modern physics today. This “island of stability” is spanned by superheavy elements (SHE's) that are produced in the laboratory. SHE's are believed to exist primarily due to the “magic” stabilizing effects of nuclear shell structure. SHE synthesis is extremely difficult due to their very low production cross section, often of the order of pico barns or less. Stabilizing effects of shell closures at proton number Z=82 and neutron number N=126 are predicted theoretically. Though stabilizing effects of Z=82 have been experimentally verified, no concluding observations have been made with N=126, so far. We measured and analyzed the total evaporation residue (ER) cross sections for a number of systems with neutron number around 126 to explore possible shell closure effects in ER cross sections, in this work.

Keywords: super heavy elements, fusion, evaporation residue, compund nucleus

Procedia PDF Downloads 446

Authors: LuoJiaoyang, Yu Hongyang

Abstract:

In this paper, we experimented with a new approach to multimodal identification using RGB, RGB-D and voice data. The multimodal combination of RGB and voice data has been applied in tasks such as emotion recognition and has shown good results and stability, and it is also the same in identity recognition tasks. We believe that the data of different modalities can enhance the effect of the model through mutual reinforcement. We try to increase the three modalities on the basis of the dual modalities and try to improve the effectiveness of the network by increasing the number of modalities. We also implemented the single-modal identification system separately, tested the data of these different modalities under clean and noisy conditions, and compared the performance with the multimodal model. In the process of designing the multimodal model, we tried a variety of different fusion strategies and finally chose the fusion method with the best performance. The experimental results show that the performance of the multimodal system is better than that of the single modality, especially in dealing with noise, and the multimodal system can achieve an average improvement of 5%.

Keywords: multimodal, three modalities, RGB-D, identity verification

Procedia PDF Downloads 46

Authors: Long Wang, Yongjin Feng, Xiaofang Luo

Abstract:

Tritium permeation through structural materials is a significant issue for fusion demonstration (DEMO) reactor blankets in terms of fuel cycle efficiency and radiological safety. Reduced activation ferritic (RAFM) steel CLF-1 is a prime candidate for the China’s CFETR blanket structural material, facing high permeability of hydrogen isotopes at reactor operational temperature. To confine tritium as much as possible in the reactor, surface modification of the steels including fabrication of tritium permeation barrier (TPB) attracts much attention. As a new alloy system, high entropy alloy (HEA) contains at least five principal elements, each of which ranges from 5 at% to 35 at%. This high mixing effect entitles HEA extraordinary comprehensive performance. So it is attractive to lead HEA into surface alloying for protective use. At present, studies on the hydrogen isotope permeability of HEA coatings is still insufficient and corresponding mechanism isn’t clear. In our study, we prepared three kinds of HEA coatings, including AlCrTaTiZr, (AlCrTaTiZr)N and (AlCrTaTiZr)O. After comprehensive characterization of SEM, XPS, AFM, XRD and TEM, the structure and composition of the HEA coatings were obtained. Deuterium permeation tests were conducted to evaluate the hydrogen isotope permeability of AlCrTaTiZr, (AlCrTaTiZr)N and (AlCrTaTiZr)O HEA coatings. Results proved that the (AlCrTaTiZr)N and (AlCrTaTiZr)O HEA coatings had better hydrogen isotope permeation resistance. Through analyzing and characterizing the hydrogen isotope permeation results of the corroded samples, an internal link between hydrogen isotope permeation behavior and structure of HEA coatings was established. The results provide valuable reference in engineering design of structural and TPB materials for future fusion device.

Keywords: high entropy alloy, hydrogen isotope permeability, tritium permeation barrier, fusion demonstration reactor

Procedia PDF Downloads 142

Authors: Pei-Jyun Hsieh, Cheng-Hsuan Li, Bor-Chen Kuo

Abstract:

For hyperspectral image classification, feature reduction is an important pre-processing for avoiding the Hughes phenomena due to the difficulty for collecting training samples. Hence, lots of researches developed feature selection methods such as F-score, HSIC (Hilbert-Schmidt Independence Criterion), and etc., to improve hyperspectral image classification. However, most of them only consider the class separability in the original space, i.e., a linear class separability. In this study, we proposed a nonlinear class separability measure based on kernel trick for selecting an appropriate feature subset. The proposed nonlinear class separability was formed by a generalized RBF kernel with different bandwidths with respect to different features. Moreover, it considered the within-class separability and the between-class separability. A genetic algorithm was applied to tune these bandwidths such that the smallest with-class separability and the largest between-class separability simultaneously. This indicates the corresponding feature space is more suitable for classification. In addition, the corresponding nonlinear classification boundary can separate classes very well. These optimal bandwidths also show the importance of bands for hyperspectral image classification. The reciprocals of these bandwidths can be viewed as weights of bands. The smaller bandwidth, the larger weight of the band, and the more importance for classification. Hence, the descending order of the reciprocals of the bands gives an order for selecting the appropriate feature subsets. In the experiments, three hyperspectral image data sets, the Indian Pine Site data set, the PAVIA data set, and the Salinas A data set, were used to demonstrate the selected feature subsets by the proposed nonlinear feature selection method are more appropriate for hyperspectral image classification. Only ten percent of samples were randomly selected to form the training dataset. All non-background samples were used to form the testing dataset. The support vector machine was applied to classify these testing samples based on selected feature subsets. According to the experiments on the Indian Pine Site data set with 220 bands, the highest accuracies by applying the proposed method, F-score, and HSIC are 0.8795, 0.8795, and 0.87404, respectively. However, the proposed method selects 158 features. F-score and HSIC select 168 features and 217 features, respectively. Moreover, the classification accuracies increase dramatically only using first few features. The classification accuracies with respect to feature subsets of 10 features, 20 features, 50 features, and 110 features are 0.69587, 0.7348, 0.79217, and 0.84164, respectively. Furthermore, only using half selected features (110 features) of the proposed method, the corresponding classification accuracy (0.84168) is approximate to the highest classification accuracy, 0.8795. For other two hyperspectral image data sets, the PAVIA data set and Salinas A data set, we can obtain the similar results. These results illustrate our proposed method can efficiently find feature subsets to improve hyperspectral image classification. One can apply the proposed method to determine the suitable feature subset first according to specific purposes. Then researchers can only use the corresponding sensors to obtain the hyperspectral image and classify the samples. This can not only improve the classification performance but also reduce the cost for obtaining hyperspectral images.

Keywords: hyperspectral image classification, nonlinear feature selection, kernel trick, support vector machine

Procedia PDF Downloads 240

Authors: Arwa Alzughaibi

Abstract:

Human Motion detection is a challenging task due to a number of factors including variable appearance, posture and a wide range of illumination conditions and background. So, the first need of such a model is a reliable feature set that can discriminate between a human and a non-human form with a fair amount of confidence even under difficult conditions. By having richer representations, the classification task becomes easier and improved results can be achieved. The Aim of this paper is to investigate the reliable and accurate human motion detection models that are able to detect the human motions accurately under varying illumination levels and backgrounds. Different sets of features are tried and tested including Histogram of Oriented Gradients (HOG), Deformable Parts Model (DPM), Local Decorrelated Channel Feature (LDCF) and Aggregate Channel Feature (ACF). However, we propose an efficient and reliable human motion detection approach by combining Histogram of oriented gradients (HOG) and local phase quantization (LPQ) as the feature set, and implementing search pruning algorithm based on optical flow to reduce the number of false positive. Experimental results show the effectiveness of combining local phase quantization descriptor and the histogram of gradient to perform perfectly well for a large range of illumination conditions and backgrounds than the state-of-the-art human detectors. Areaunder th ROC Curve (AUC) of the proposed method achieved 0.781 for UCF dataset and 0.826 for CDW dataset which indicates that it performs comparably better than HOG, DPM, LDCF and ACF methods.

Keywords: human motion detection, histograms of oriented gradient, local phase quantization, local phase quantization

Procedia PDF Downloads 229

Authors: Belkacem Soundes, Guezouli Larbi

Abstract:

This paper presents a robust and accurate method for text detection and localization over lecture videos. Frame regions are classified into text or background based on visual feature analysis. However, lecture video shows significant degradation mainly related to acquisition conditions, camera motion and environmental changes resulting in low quality videos. Hence, affecting feature extraction and description efficiency. Moreover, traditional text detection methods cannot be directly applied to lecture videos. Therefore, robust feature extraction methods dedicated to this specific video genre are required for robust and accurate text detection and extraction. Method consists of a three-step process: Slide region detection and segmentation; Feature extraction and non-text filtering. For robust and effective features extraction moment functions are used. Two distinct types of moments are used: orthogonal and non-orthogonal. For orthogonal Zernike Moments, both Pseudo Zernike moments are used, whereas for non-orthogonal ones Hu moments are used. Expressivity and description efficiency are given and discussed. Proposed approach shows that in general, orthogonal moments show high accuracy in comparison to the non-orthogonal one. Pseudo Zernike moments are more effective than Zernike with better computation time.

Keywords: text detection, text localization, lecture videos, pseudo zernike moments

Procedia PDF Downloads 122

Authors: I. Nyoman Mahayasa Adiputra

Abstract:

Data in the field of health can be useful for the purposes of data analysis, one example of health data is disease data. Disease data is usually in a geographical plot in accordance with the area. Where the data was collected, in the city of Denpasar, Bali. Disease data report is still published in tabular form, disease information has not been mapped in GIS form. In this research, disease information in Denpasar city will be digitized in the form of a geographic information system with the smallest administrative area in the form of district. Denpasar City consists of 4 districts of North Denpasar, East Denpasar, West Denpasar and South Denpasar. In this research, we use Google fusion table technology for map digitization process, where this technology can facilitate from the administrator and from the recipient information. From the administrator side of the input disease, data can be done easily and quickly. From the receiving end of the information, the resulting GIS application can be published in a website-based application so that it can be accessed anywhere and anytime. In general, the results obtained in this study, divided into two, namely: (1) Geolocation of Denpasar and all of Denpasar districts, the process of digitizing the map of Denpasar city produces a polygon geolocation of each - district of Denpasar city. These results can be utilized in subsequent GIS studies if you want to use the same administrative area. (2) Dengue fever mapping in 2014 and 2015. Disease data used in this study is dengue fever case data taken in 2014 and 2015. Data taken from the profile report Denpasar Health Department 2015 and 2016. This mapping can be useful for the analysis of the spread of dengue hemorrhagic fever in the city of Denpasar.

Keywords: geographic information system, Google fusion table technology, delivery of disease data information, Denpasar city

Procedia PDF Downloads 104

Authors: Ezzeddin Anawa, Abdol-Ghane Olabi

Abstract:

The dissimilar joint between aluminum /titanium alloys (Al 6082 and Ti G2) alloys were successfully achieved by CO2 laser welding with a single pass and without filler material using the overlap joint design. Laser welding parameters ranges combinations were experimentally determined using Taguchi approach with the objective of producing welded joint with acceptable welding profile and high quality of mechanical properties. In this study a joining of dissimilar Al 6082 / Ti G2 was result in three distinct regions fusion area (FA), heat-affected zone (HAZ), and the unaffected base metal (BM) in the weldment. These regions are studied in terms of its microstructural characteristics and microhardness which are directly affecting the welding quality. The weld metal was mainly composed of martensite alpha prime. In two different metals in the two different sides of joint HAZ, grain growth was detected. The microhardness of the joint distribution also has shown microhardness increasing in the HAZ of two base metals and a varying microhardness in fusion zone.

Keywords: microharness , microstructure, laser welding and dissimilar jointed materials.

Procedia PDF Downloads 349

Authors: Bhalke D. G., Bormane D. S., Kharate G. K.

Abstract:

This paper presents classification of musical instrument using machine learning techniques. The classification has been carried out using temporal, spectral, cepstral and wavelet features. Detail feature analysis is carried out using separate and combined features. Further, instrument model has been developed using K-Nearest Neighbor and Support Vector Machine (SVM). Benchmarked McGill university database has been used to test the performance of the system. Experimental result shows that SVM performs better as compared to KNN classifier.

Keywords: feature extraction, SVM, KNN, musical instruments

Procedia PDF Downloads 454

Authors: Fadwa Alaskar, Fang-Chieh Chou, Carlos Flores, Xiao-Yun Lu, Alexandre M. Bayen

Abstract:

This article proposes a perception model for enhancing the accuracy and stability of car-following control of a longitudinally automated truck. We applied a fusion-based tracking algorithm on measurements of a single preceding vehicle needed for car-following control. This algorithm fuses two types of data, radar and LiDAR data, to obtain more accurate and robust longitudinal perception of the subject vehicle in various weather conditions. The filter’s resulting signals are fed to the gap control algorithm at every tracking loop composed by a high-level gap control and lower acceleration tracking system. Several highway tests have been performed with two trucks. The tests show accurate and fast tracking of the target, which impacts on the gap control loop positively. The experiments also show the fulfilment of control design requirements, such as fast speed variations tracking and robust time gap following.

Keywords: object tracking, perception, sensor fusion, adaptive cruise control, cooperative adaptive cruise control

Procedia PDF Downloads 200

Authors: Huinan Zhang, Wenjie Jiang

Abstract:

Accurate estimation of tropical cyclone intensity is of great importance for disaster prevention and mitigation. Existing techniques are largely based on satellite imagery data, and research and utilization of the inner thermal core structure characteristics of tropical cyclones still pose challenges. This paper presents a two-stage tropical cyclone intensity estimation network based on the fusion of coarse and fine-grained features from microwave brightness temperature data. The data used in this network are obtained from the thermal core structure of tropical cyclones through the Advanced Technology Microwave Sounder (ATMS) inversion. Firstly, the thermal core information in the pressure direction is comprehensively expressed through the maximal intensity projection (MIP) method, constructing coarse-grained thermal core images that represent the tropical cyclone. These images provide a coarse-grained feature range wind speed estimation result in the first stage. Then, based on this result, fine-grained features are extracted by combining thermal core information from multiple view profiles with a distributed network and fused with coarse-grained features from the first stage to obtain the final two-stage network wind speed estimation. Furthermore, to better capture the long-tail distribution characteristics of tropical cyclones, focal loss is used in the coarse-grained loss function of the first stage, and ordinal regression loss is adopted in the second stage to replace traditional single-value regression. The selection of tropical cyclones spans from 2012 to 2021, distributed in the North Atlantic (NA) regions. The training set includes 2012 to 2017, the validation set includes 2018 to 2019, and the test set includes 2020 to 2021. Based on the Saffir-Simpson Hurricane Wind Scale (SSHS), this paper categorizes tropical cyclone levels into three major categories: pre-hurricane, minor hurricane, and major hurricane, with a classification accuracy rate of 86.18% and an intensity estimation error of 4.01m/s for NA based on this accuracy. The results indicate that thermal core data can effectively represent the level and intensity of tropical cyclones, warranting further exploration of tropical cyclone attributes under this data.

Keywords: Artificial intelligence, deep learning, data mining, remote sensing

Procedia PDF Downloads 23

Authors: Majid Habib Khan, Jinwei Zhao, Xinhong Hei, Liu Jiedong, Rana Shahzad Noor, Muhammad Imran

Abstract:

Deep learning is increasingly employed in image classification, yet the scarcity and high cost of labeled data for training remain a challenge. Limited samples often lead to overfitting due to biased sample distribution. This paper introduces a dynamic distribution calibration method for few-shot learning. Initially, base and new class samples undergo normalization to mitigate disparate feature magnitudes. A pre-trained model then extracts feature vectors from both classes. The method dynamically selects distribution characteristics from base classes (both adjacent and remote) in the embedding space, using a threshold value approach for new class samples. Given the propensity of similar classes to share feature distributions like mean and variance, this research assumes a Gaussian distribution for feature vectors. Subsequently, distributional features of new class samples are calibrated using a corrected hyperparameter, derived from the distribution features of both adjacent and distant base classes. This calibration augments the new class sample set. The technique demonstrates significant improvements, with up to 4% accuracy gains in few-shot classification challenges, as evidenced by tests on miniImagenet and CUB datasets.

Keywords: deep learning, computer vision, image classification, few-shot learning, threshold

Procedia PDF Downloads 27

Authors: Charbel Aoun, Loic Lagadec

Abstract:

A Sensor Network (SN) is considered as an operation of two phases: (1) the observation/measuring, which means the accumulation of the gathered data at each sensor node; (2) transferring the collected data to some processing center (e.g., Fusion Servers) within the SN. Therefore, an underwater sensor network can be defined as a sensor network deployed underwater that monitors underwater activity. The deployed sensors, such as Hydrophones, are responsible for registering underwater activity and transferring it to more advanced components. The process of data exchange between the aforementioned components perfectly defines the Marine Observatory (MO) concept which provides information on ocean state, phenomena and processes. The first step towards the implementation of this concept is defining the environmental constraints and the required tools and components (Marine Cables, Smart Sensors, Data Fusion Server, etc). The logical and physical components that are used in these observatories perform some critical functions such as the localization of underwater moving objects. These functions can be orchestrated with other services (e.g. military or civilian reaction). In this paper, we present an extension to our MO meta-model that is used to generate a design tool (ArchiMO). We propose new constraints to be taken into consideration at design time. We illustrate our proposal with an example from the MO domain. Additionally, we generate the corresponding simulation code using our self-developed domain-specific model compiler. On the one hand, this illustrates our approach in relying on Enterprise Architecture (EA) framework that respects: multiple views, perspectives of stakeholders, and domain specificity. On the other hand, it helps reducing both complexity and time spent in design activity, while preventing from design modeling errors during porting this activity in the MO domain. As conclusion, this work aims to demonstrate that we can improve the design activity of complex system based on the use of MDE technologies and a domain-specific modeling language with the associated tooling. The major improvement is to provide an early validation step via models and simulation approach to consolidate the system design.

Keywords: smart sensors, data fusion, distributed fusion architecture, sensor networks, domain specific modeling language, enterprise architecture, underwater moving object, localization, marine observatory, NS-3, IMS

Procedia PDF Downloads 144

Authors: Amal Khalifa, Nicolas Vana Santos

Abstract:

Steganography has been known for centuries as an efficient approach for covert communication. Due to its popularity and ease of access, image steganography has attracted researchers to find secure techniques for hiding information within an innocent looking cover image. In this research, we propose a novel deep-learning approach to digital image steganography. The proposed method, DeepWaveletFusion, uses convolutional neural networks (CNN) to hide a secret image into a cover image of the same size. Two CNNs are trained back-to-back to merge the Discrete Wavelet Transform (DWT) of both colored images and eventually be able to blindly extract the hidden image. Based on two different image similarity metrics, a weighted gain function is used to guide the learning process and maximize the quality of the retrieved secret image and yet maintaining acceptable imperceptibility. Experimental results verified the high recoverability of DeepWaveletFusion which outperformed similar deep-learning-based methods.

Keywords: deep learning, steganography, image, discrete wavelet transform, fusion

Procedia PDF Downloads 42

Authors: Jitendar Kumar Tiwari, Ajay Mandal, N. Sathish, A. K. Srivastava

Abstract:

Since the last decade, graphene achieved great attention toward the progress of multifunction metal matrix composites, which are highly demanded in industries to develop energy-efficient systems. This study covers the two advanced aspects of the latest scientific endeavor, i.e., graphene as reinforcement in metallic materials and additive manufacturing (AM) as a processing technology. Herein, high-quality graphene and AlSi10Mg powder mechanically mixed by very low energy ball milling with 0.1 wt. % and 0.2 wt. % graphene. Mixed powder directly subjected to the powder bed fusion process, i.e., an AM technique to produce composite samples along with bare counterpart. The effects of graphene on porosity, microstructure, and mechanical properties were examined in this study. The volumetric distribution of pores was observed under X-ray computed tomography (CT). On the basis of relative density measurement by X-ray CT, it was observed that porosity increases after graphene addition, and pore morphology also transformed from spherical pores to enlarged flaky pores due to improper melting of composite powder. Furthermore, the microstructure suggests the grain refinement after graphene addition. The columnar grains were able to cross the melt pool boundaries in case of the bare sample, unlike composite samples. The smaller columnar grains were formed in composites due to heterogeneous nucleation by graphene platelets during solidification. The tensile properties get affected due to induced porosity irrespective of graphene reinforcement. The optimized tensile properties were achieved at 0.1 wt. % graphene. The increment in yield strength and ultimate tensile strength was 22% and 10%, respectively, for 0.1 wt. % graphene reinforced sample in comparison to bare counterpart while elongation decreases 20% for the same sample. The hardness indentations were taken mostly on the solid region in order to avoid the collapse of the pores. The hardness of the composite was increased progressively with graphene content. Around 30% of increment in hardness was achieved after the addition of 0.2 wt. % graphene. Therefore, it can be concluded that powder bed fusion can be adopted as a suitable technique to develop graphene reinforced AlSi10Mg composite. Though, some further process modification required to avoid the induced porosity after the addition of graphene, which can be addressed in future work.

Keywords: graphene, hardness, porosity, powder bed fusion, tensile properties

Procedia PDF Downloads 101

Authors: John Hardy

Abstract:

The expansion of special operations forces (SOF) in the twenty-first century is often discussed in terms of the size and disposition of SOF units. Research regarding the number SOF personnel, the equipment SOF units procure, and the variety of roles and mission that SOF fulfill in contemporary conflicts paints a fascinating picture of changing expectations for the use of force. A strong indicator of the changing nature of SOF in contemporary conflicts is the fusion of strike and intelligence functions in the SOF in many countries. What were once more distinct roles on the kind of battlefield generally associated with the concept of conventional warfare have become intermingled in the era of persistent conflict which SOF face. This study presents a historical analysis of the co-evolution of the intelligence and direct action functions carried out by SOF in counterterrorism, counterinsurgency, and training and mentoring missions between 2004 and 2016. The study focuses primarily on innovation in the US military and the diffusion of key concepts to US allies first, and then more broadly afterward. The findings show that there were three key phases of evolution throughout the period of study, each coinciding with a process of innovation and doctrinal adaptation. The first phase was characterized by the fusion of intelligence at the tactical and operational levels. The second phase was characterized by the industrial counterterrorism campaigns used by US SOF against irregular enemies in Iraq and Afghanistan. The third phase was characterized by increasing forward collection of actionable intelligence by SOF force elements in the course of direct action raids. The evolution of strike and intelligence functions in SOF operations between 2004 and 2016 was significantly influenced by reciprocity. Intelligence fusion led to more effective targeting, which then increased intelligence collection. Strike and intelligence functions were then enhanced by greater emphasis on intelligence exploitation during operations, which further increased the effectiveness of both strike and intelligence operations.

Keywords: counterinsurgency, counterterrorism, intelligence, irregular warfare, military operations, special operations forces

Procedia PDF Downloads 235

Authors: Kyugneun Lee, Ikjin Lee

Abstract:

Parameter estimation with inverse problem often suffers from unfavorable conditions in the real world. Useless data and many input parameters make the problem complicated or insoluble. Data refinement and reformulation of the problem can solve that kind of difficulties. In this research, a method to solve the rank deficient inverse problem is suggested. A multi-physics system which has rank deficiency caused by response correlation is treated. Impeditive information is removed and the problem is reformulated to sequential estimations using Bayesian network (BN) and subset groups. At first, subset grouping of the responses is performed. Feature selection with singular value decomposition (SVD) is used for the grouping. Next, BN inference is used for sequential conditional estimation according to the group hierarchy. Directed acyclic graph (DAG) structure is organized to maximize the estimation ability. Variance ratio of response to noise is used to pairing the estimable parameters by each response.

Keywords: Bayesian network, feature selection, rank deficiency, statistical inverse analysis

Procedia PDF Downloads 282