Search results for: sparse autoencoder

Authors: Fares Hedayatit, Arnauld Joly, Panagiotis Papadimitriou

Abstract:

Many machine learning tasks such as text annotation usually require training over very big datasets, e.g., millions of web documents, that can be represented in a sparse input space. State-of the-art tree-based ensemble algorithms cannot scale to such datasets, since they include operations whose running time is a function of the input space size rather than a function of the non-zero input elements. In this paper, we propose an efficient splitting algorithm to leverage input sparsity within decision tree methods. Our algorithm improves training time over sparse datasets by more than two orders of magnitude and it has been incorporated in the current version of scikit-learn.org, the most popular open source Python machine learning library.

Keywords: big data, sparsely representable data, tree-based models, scalable learning

Procedia PDF Downloads 236

Authors: Dacheng Li, Bo Huang, Qinjin Han, Ming Li

Abstract:

Remotely sensed imagery with the high spatial and temporal characteristics, which it is hard to acquire under the current land observation satellites, has been considered as a key factor for monitoring environmental changes over both global and local scales. On a basis of the limited high spatial-resolution observations, challenged studies called spatiotemporal fusion have been developed for generating high spatiotemporal images through employing other auxiliary low spatial-resolution data while with high-frequency observations. However, a majority of spatiotemporal fusion approaches yield to satisfactory assumption, empirical but unstable parameters, low accuracy or inefficient performance. Although the spatiotemporal fusion methodology via sparse representation theory has advantage in capturing reflectance changes, stability and execution efficiency (even more efficient when overcomplete dictionaries have been pre-trained), the retrieval of high-accuracy dictionary and its response to fusion results are still pending issues. In this paper, we employ additional image pairs (here each image-pair includes a Landsat Operational Land Imager and a Moderate Resolution Imaging Spectroradiometer acquisitions covering the partial area of Baotou, China) only into the coupled dictionary training process based on K-SVD (K-means Singular Value Decomposition) algorithm, and attempt to improve the fusion results of two existing sparse representation based fusion models (respectively utilizing one and two available image-pair). The results show that more eligible image pairs are probably related to a more accurate overcomplete dictionary, which generally indicates a better image representation, and is then contribute to an effective fusion performance in case that the added image-pair has similar seasonal aspects and image spatial structure features to the original image-pair. It is, therefore, reasonable to construct multi-dictionary training pattern for generating a series of high spatial resolution images based on limited acquisitions.

Keywords: spatiotemporal fusion, sparse representation, K-SVD algorithm, dictionary learning

Procedia PDF Downloads 231

Authors: Qingsong Xiong, Cheng Yuan, Qingzhao Kong, Haibei Xiong

Abstract:

Deep-learning-driven approaches based on vibration responses have attracted larger attention in rapid structural condition assessment while obtaining sufficient measured training data with corresponding labels is relevantly costly and even inaccessible in practical engineering. This study proposes an integrated label propagation network for structural condition assessment, which is able to diffuse the labels from continuously-generating measurements by intact structure to those of missing labels of damage scenarios. The integrated network is embedded with damage-sensitive features extraction by deep autoencoder and pseudo-labels propagation by optimized fuzzy clustering, the architecture and mechanism which are elaborated. With a sophisticated network design and specified strategies for improving performance, the present network achieves to extends the superiority of self-supervised representation learning, unsupervised fuzzy clustering and supervised classification algorithms into an integration aiming at assessing damage conditions. Both numerical simulations and full-scale laboratory shaking table tests of a two-story building structure were conducted to validate its capability of detecting post-earthquake damage. The identifying accuracy of a present network was 0.95 in numerical validations and an average 0.86 in laboratory case studies, respectively. It should be noted that the whole training procedure of all involved models in the network stringently doesn’t rely upon any labeled data of damage scenarios but only several samples of intact structure, which indicates a significant superiority in model adaptability and feasible applicability in practice.

Keywords: autoencoder, condition assessment, fuzzy clustering, label propagation

Procedia PDF Downloads 73

Authors: Jianhong Xiang, Hao Xiang, Linyu Wang

Abstract:

Compressed sensing (CS) has a wide range of applications in sparse signal reconstruction. Aiming at the problems of low recovery accuracy and long reconstruction time of existing reconstruction algorithms in medical imaging, this paper proposes a corrected smoothing L0 algorithm based on compressed sensing (CSL0). First, an approximate hyperbolic tangent function (AHTF) that is more similar to the L0 norm is proposed to approximate the L0 norm. Secondly, in view of the "sawtooth phenomenon" in the steepest descent method and the problem of sensitivity to the initial value selection in the modified Newton method, the use of the steepest descent method and the modified Newton method are jointly optimized to improve the reconstruction accuracy. Finally, the CSL0 algorithm is simulated on various images. The results show that the algorithm proposed in this paper improves the reconstruction accuracy of the test image by 0-0. 98dB.

Keywords: smoothed L0, compressed sensing, image processing, sparse reconstruction

Procedia PDF Downloads 90

Authors: Krzysztof Malczewski

Abstract:

Magnetic Resonance Imaging (MRI) reconstruction algorithm using compressed sensing is presented in this paper. It is exhibited that the offered approach improves MR images spatial resolution in circumstances when highly undersampled k-space trajectories are applied. Compressed Sensing (CS) aims at signal and images reconstructing from significantly fewer measurements than were conventionally assumed necessary. Magnetic Resonance Imaging (MRI) is a fundamental medical imaging method struggles with an inherently slow data acquisition process. The use of CS to MRI has the potential for significant scan time reductions, with visible benefits for patients and health care economics. In this study the objective is to combine super-resolution image enhancement algorithm with CS framework benefits to achieve high resolution MR output image. Both methods emphasize on maximizing image sparsity on known sparse transform domain and minimizing fidelity. The presented algorithm considers the cardiac and respiratory movements.

Keywords: super-resolution, MRI, compressed sensing, sparse-sense, image enhancement

Procedia PDF Downloads 397

Authors: Hozaifa Zaki, Ghada Soliman

Abstract:

In this paper, we introduced an approach for Automated Dotted Arabic Expiration Date Extraction using Optimized Convolutional Autoencoder (ARABEX) with bidirectional LSTM. This approach is used for translating the Arabic dot-matrix expiration dates into their corresponding filled-in dates. A custom lightweight Convolutional Recurrent Neural Network (CRNN) model is then employed to extract the expiration dates. Due to the lack of available dataset images for the Arabic dot-matrix expiration date, we generated synthetic images by creating an Arabic dot-matrix True Type Font (TTF) matrix to address this limitation. Our model was trained on a realistic synthetic dataset of 3287 images, covering the period from 2019 to 2027, represented in the format of yyyy/mm/dd. We then trained our custom CRNN model using the generated synthetic images to assess the performance of our model (ARABEX) by extracting expiration dates from the translated images. Our proposed approach achieved an accuracy of 99.4% on the test dataset of 658 images, while also achieving a Structural Similarity Index (SSIM) of 0.46 for image translation on our dataset. The ARABEX approach demonstrates its ability to be applied to various downstream learning tasks, including image translation and reconstruction. Moreover, this pipeline (ARABEX+CRNN) can be seamlessly integrated into automated sorting systems to extract expiry dates and sort products accordingly during the manufacturing stage. By eliminating the need for manual entry of expiration dates, which can be time-consuming and inefficient for merchants, our approach offers significant results in terms of efficiency and accuracy for Arabic dot-matrix expiration date recognition.

Keywords: computer vision, deep learning, image processing, character recognition

Procedia PDF Downloads 48

Authors: Ho Jeong Jin, Chang Won Seo, Choon Sik Cho, Bong Yong Choi, Kwang Kyun Na, Sang Rok Lee

Abstract:

In this paper, a radar signal processing technique using the LFM-FSK (Linear Frequency Modulation-Frequency Shift Keying) is proposed for reducing the false alarm rate based on the compressive sensing. The LFM-FSK method combines FMCW (Frequency Modulation Continuous Wave) signal with FSK (Frequency Shift Keying). This shows an advantage which can suppress the ghost phenomenon without the complicated CFAR (Constant False Alarm Rate) algorithm. Moreover, the parametric sparse algorithm applying the compressive sensing that restores signals efficiently with respect to the incomplete data samples is also integrated, leading to reducing the burden of ADC in the receiver of radars. 24 GHz FMCW signal is applied and tested in the real environment with FSK modulated data for verifying the proposed algorithm along with the compressive sensing.

Keywords: compressive sensing, LFM-FSK radar, radar signal processing, sparse algorithm

Procedia PDF Downloads 444

Authors: Fuad Noman, Sh-Hussain Salleh, Chee-Ming Ting, Hadri Hussain, Syed Rasul

Abstract:

In this paper, a data-driven dictionary approach is proposed for the automatic detection and classification of cardiovascular abnormalities. Electrocardiography (ECG) signal is represented by the trained complete dictionaries that contain prototypes or atoms to avoid the limitations of pre-defined dictionaries. The data-driven trained dictionaries simply take the ECG signal as input rather than extracting features to study the set of parameters that yield the most descriptive dictionary. The approach inherently learns the complicated morphological changes in ECG waveform, which is then used to improve the classification. The classification performance was evaluated with ECG data under two different preprocessing environments. In the first category, QT-database is baseline drift corrected with notch filter and it filters the 60 Hz power line noise. In the second category, the data are further filtered using fast moving average smoother. The experimental results on QT database confirm that our proposed algorithm shows a classification accuracy of 92%.

Keywords: electrocardiogram, dictionary learning, sparse coding, classification

Procedia PDF Downloads 352

Authors: M. S. Jimah, A. C. Achuenu, M. Momodu

Abstract:

Group communications over public infrastructure are prone to a lot of security issues. Existing network protocols like Protocol Independent Multicast Sparse Mode (PIM SM) and Protocol Independent Multicast Dense Mode (PIM DM) do not have inbuilt security features. Therefore, any user or node can easily access the group communication as long as the user can send join message to the source nodes, the source node then adds the user to the network group. In this research, a hybrid method of salting and hashing to encrypt information in the source and stub node was designed, and when stub nodes need to connect, they must have the appropriate key to join the group network. Object oriented analysis design (OOAD) was the methodology used, and the result shows that no extra controlled bandwidth overhead cost was added by encrypting and the hybrid model was more securing than the existing PIM SM, PIM DM and Zhang secure PIM SM.

Keywords: group communications, multicast, PIM SM, PIM DM, encryption

Procedia PDF Downloads 135

Authors: Hyeongbok Kim, Lingling Zhao, Xiaohong Su

Abstract:

Deep reinforcement learning has been applied to address various problems in robotics, such as autonomous driving and unmanned aerial vehicle. However, because of the sparse reward penalty for a collision with obstacles during the navigation mission, the agent fails to learn the optimal policy or requires a long time for convergence. Therefore, using obstacles and enemy agents, in this paper, we present a curriculum-based boost learning method to effectively train compound skills during multi-agent reinforcement learning. First, to enable the agents to solve challenging tasks, we gradually increased learning difficulties by adjusting reward shaping instead of constructing different learning environments. Then, in a benchmark environment with static obstacles and moving enemy agents, the experimental results showed that the proposed curriculum learning strategy enhanced cooperative navigation and compound collision avoidance skills in uncertain environments while improving learning efficiency.

Keywords: curriculum learning, hard exploration, multi-agent reinforcement learning, robotic navigation, sparse reward

Procedia PDF Downloads 65

Authors: Debajyoti Mukherjee, Arathy B. S., Arpita Sahu, Saranga P. Pogula

Abstract:

A functional model to mimic the functional correctness of a neural network compute accelerator IP is very crucial for design validation. Neural network workloads are based on a Brain Floating Point (BF-16) data type. The major challenge we were facing was the incompatibility of GCC compilers to the BF-16 datatype, which we addressed with a native BF-16 generator integrated into our functional model. Moreover, working with big GEMM (General Matrix Multiplication) or SpMM (Sparse Matrix Multiplication) Work Loads (Dense or Sparse) and debugging the failures related to data integrity is highly painstaking. In this paper, we are addressing the quality challenge of such a complex neural network accelerator design by proposing a functional model-based scoreboard or software model using SystemC. The proposed functional model executes the assembly code based on the ISA of the processor IP, decodes all instructions, and executes as expected to be done by the DUT. The said model would give a lot of visibility and debug capability in the DUT, bringing up micro-steps of execution.

Keywords: ISA, neural network, Brain Float-16, DUT

Procedia PDF Downloads 61

Authors: Yadpiroon Onmek, Jean Triboulet, Sebastien Druon, Bruno Jouvencel

Abstract:

The objective of this paper is to develop the 3D underwater reconstruction of archaeology object, which is based on the fusion between a sonar system and stereo camera system. The underwater images are obtained from a calibrated camera system. The multiples image pairs are input, and we first solve the problem of image processing by applying the well-known filter, therefore to improve the quality of underwater images. The features of interest between image pairs are selected by well-known methods: a FAST detector and FLANN descriptor. Subsequently, the RANSAC method is applied to reject outlier points. The putative inliers are matched by triangulation to produce the local sparse point clouds in 3D space, using a pinhole camera model and Euclidean distance estimation. The SFM technique is used to carry out the global sparse point clouds. Finally, the ICP method is used to fusion the sonar information with the stereo model. The final 3D models have a précised by measurement comparing with the real object.

Keywords: 3D reconstruction, archaeology, fusion, stereo system, sonar system, underwater

Procedia PDF Downloads 280

Authors: Hebert Montegranario, Mauricio Londoño

Abstract:

Solutions of Helmholtz equation are essential in seismic imaging methods like full wave inversion, which needs to solve many times the wave equation. Traditional methods like Finite Element Method (FEM) or Finite Differences (FD) have sparse matrices but may suffer the so called pollution effect in the numerical solutions of Helmholtz equation for large values of the wave number. On the other side, global radial basis functions have a better accuracy but produce full matrices that become unstable. In this research we combine the virtues of both approaches to find numerical solutions of Helmholtz equation, by applying a meshless method that produce sparse matrices by local radial basis functions. We solve the equation with absorbing boundary conditions of the kind Clayton-Enquist and PML (Perfect Matched Layers) and compared with results in standard literature, showing a promising performance by tackling both the pollution effect and matrix instability.

Keywords: Helmholtz equation, meshless methods, seismic imaging, wavefield inversion

Procedia PDF Downloads 516

Authors: Javad Khazaei, Rick Blum

Abstract:

Distributed control is an efficient and flexible approach for coordination of multi-agent systems. One of the main challenges in designing a distributed controller is identifying the governing dynamics of the dynamical systems. Data-driven system identification is currently undergoing a revolution. With the availability of high-fidelity measurements and historical data, model-free identification of dynamical systems can facilitate the control design without tedious modeling of high-dimensional and/or nonlinear systems. This paper develops a distributed control design using consensus theory for linear and nonlinear dynamical systems using sparse identification of system dynamics. Compared with existing consensus designs that heavily rely on knowing the detailed system dynamics, the proposed model-free design can accurately capture the dynamics of the system with available measurements and input data and provide guaranteed performance in consensus and tracking problems. Heterogeneous damped oscillators are chosen as examples of dynamical system for validation purposes.

Keywords: consensus tracking, distributed control, model-free control, sparse identification of dynamical systems

Procedia PDF Downloads 230

Authors: Debajyoti Mukherjee, Arathy B. S., Arpita Sahu, Saranga P. Pogula

Abstract:

A Functional Model to mimic the functional correctness of a Neural Network Compute Accelerator IP is very crucial for design validation. Neural network workloads are based on a Brain Floating Point (BF-16) data type. The major challenge we were facing was the incompatibility of gcc compilers to BF-16 datatype, which we addressed with a native BF-16 generator integrated to our functional model. Moreover, working with big GEMM (General Matrix Multiplication) or SpMM (Sparse Matrix Multiplication) Work Loads (Dense or Sparse) and debugging the failures related to data integrity is highly painstaking. In this paper, we are addressing the quality challenge of such a complex Neural Network Accelerator design by proposing a Functional Model-based scoreboard or Software model using SystemC. The proposed Functional Model executes the assembly code based on the ISA of the processor IP, decodes all instructions, and executes as expected to be done by the DUT. The said model would give a lot of visibility and debug capability in the DUT bringing up micro-steps of execution.

Keywords: ISA (instruction set architecture), NN (neural network), TLM (transaction-level modeling), GEMM (general matrix multiplication)

Procedia PDF Downloads 48

Authors: Israa Sh. Tawfic, Sema Koc Kayhan

Abstract:

Given a large sparse signal, great wishes are to reconstruct the signal precisely and accurately from lease number of measurements as possible as it could. Although this seems possible by theory, the difficulty is in built an algorithm to perform the accuracy and efficiency of reconstructing. This paper proposes a new proved method to reconstruct sparse signal depend on using new method called Least Support Matching Pursuit (LS-OMP) merge it with the theory of Partial Knowing Support (PSK) given new method called Partially Knowing of Least Support Orthogonal Matching Pursuit (PKLS-OMP). The new methods depend on the greedy algorithm to compute the support which depends on the number of iterations. So to make it faster, the PKLS-OMP adds the idea of partial knowing support of its algorithm. It shows the efficiency, simplicity, and accuracy to get back the original signal if the sampling matrix satisfies the Restricted Isometry Property (RIP). Simulation results also show that it outperforms many algorithms especially for compressible signals.

Keywords: compressed sensing, lest support orthogonal matching pursuit, partial knowing support, restricted isometry property, signal reconstruction

Procedia PDF Downloads 215

Authors: Radhika Ranjan Roy

Abstract:

Deployment of machine learning (ML)/deep learning (DL) algorithms for cyberattack detection in operational communications networks (wireless and/or wire-line) is being delayed because of low-performance parameters (e.g., recall, precision, and f₁-score). If datasets become imbalanced, which is the usual case for communications networks, the performance tends to become worse. Complexities in handling reducing dimensions of the feature sets for increasing performance are also a huge problem. Mahalanobis algorithms have been widely applied in scientific research because Mahalanobis distance metric learning is a successful framework. In this paper, we have investigated the Mahalanobis binary classifier algorithm for increasing cyberattack detection performance over communications networks as a proof of concept. We have also found that high-dimensional information in intermediate features that are not utilized as much for classification tasks in ML/DL algorithms are the main contributor to the state-of-the-art of improved performance of the Mahalanobis method, even for imbalanced and sparse datasets. With no feature reduction, MD offers uniform results for precision, recall, and f₁-score for unbalanced and sparse NSL-KDD datasets.

Keywords: Mahalanobis distance, machine learning, deep learning, NS-KDD, local intrinsic dimensionality, chi-square, positive semi-definite, area under the curve

Procedia PDF Downloads 50

Authors: Shubham Gogri, Lucia Florescu

Abstract:

Medical diagnosis and radiotherapy treatment planning using Computed Tomography (CT) rely on the quantitative accuracy and quality of the CT images. At the same time, requirements for CT imaging include reducing the radiation dose exposure to patients and minimizing scanning time. A solution to this is the sparse-view CT technique, based on a reduced number of projection views. This, however, introduces a new problem— the incomplete projection data results in lower quality of the reconstructed images. To tackle this issue, deep learning methods have been applied to enhance the quality of the sparse-view CT images. A first approach involved employing Mir-Net, a dedicated deep neural network designed for image enhancement. This showed promise, utilizing an intricate architecture comprising encoder and decoder networks, along with the incorporation of the Charbonnier Loss. However, this approach was computationally demanding. Subsequently, a specialized Generative Adversarial Network (GAN) architecture, rooted in the Pix2Pix framework, was implemented. This GAN framework involves a U-Net-based Generator and a Discriminator based on Convolutional Neural Networks. To bolster the GAN's performance, both Charbonnier and Wasserstein loss functions were introduced, collectively focusing on capturing minute details while ensuring training stability. The integration of the perceptual loss, calculated based on feature vectors extracted from the VGG16 network pretrained on the ImageNet dataset, further enhanced the network's ability to synthesize relevant images. A series of comprehensive experiments with clinical CT data were conducted, exploring various GAN loss functions, including Wasserstein, Charbonnier, and perceptual loss. The outcomes demonstrated significant image quality improvements, confirmed through pertinent metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) between the corrected images and the ground truth. Furthermore, learning curves and qualitative comparisons added evidence of the enhanced image quality and the network's increased stability, while preserving pixel value intensity. The experiments underscored the potential of deep learning frameworks in enhancing the visual interpretation of CT scans, achieving outcomes with SSIM values close to one and PSNR values reaching up to 76.

Keywords: generative adversarial networks, sparse view computed tomography, CT image correction, Mir-Net

Procedia PDF Downloads 116

Authors: Jonathan Gong

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deep learning, image processing, machine learning

Procedia PDF Downloads 96

Authors: Prittesh Patel, Ramar Krishnamurthy

Abstract:

In the present study, nine strains of C. falcatum obtained from different places and cultivars were characterized for sporulation, growth rate, and 18S rRNA gene sequence. All isolates had characteristic fast-growing sparse and fleecy aerial mycelia on potato dextrose agar with sickle shape conidia (length x width: varied from 20.0 X 3.89 to 25.52 X 5.34 μm) and blackish to orange acervuli with setae (length x width: varied from 112.37X 2.78 to 167.66 X 6.73 μm). They could be divided into two groups on the base of morphology; P1, dense mycelia with concentric growth and P2, sparse mycelia with uneven growth. Genomic DNA isolation followed by PCR amplification with ITS1 and ITS4 primer produced ~550bp amplicons for all isolates. Phylogeny generated by 18S rRNA gene sequence confirmed the variation in isolates and mainly grouped into two clusters; cluster 1 contained CoC671 isolates (cfNAV and cfPAR) and Co86002 isolate (cfTIM). Other isolates cfMAD, cfKAM, and cfMAR were grouped into cluster 2. Remaining isolates did not fall into any cluster. Isolate cfGAN, collected from Co86032 was found highly diverse of all the nine isolates. In a nutshell, we found considerable genetic divergence and morphological variation within C. falcatum accessions collected from different areas of south Gujarat, India and these can be used for the breeding program.

Keywords: Colletotrichum falcatum, ITS, morphology, red rot, sugarcane

Procedia PDF Downloads 99

Authors: Sandeep Santosh, O. P. Sahu

Abstract:

In this paper, performance comparison of wideband covariance matrix sparse representation (W-CMSR) method with other existing wideband Direction of Arrival (DOA) estimation methods has been made.W-CMSR relies less on a priori information of the incident signal number than the ordinary subspace based methods.Consider the perturbation free covariance matrix of the wideband array output. The diagonal covariance elements are contaminated by unknown noise variance. The covariance matrix of array output is conjugate symmetric i.e its upper right triangular elements can be represented by lower left triangular ones.As the main diagonal elements are contaminated by unknown noise variance,slide over them and align the lower left triangular elements column by column to obtain a measurement vector.Simulation results for W-CMSR are compared with simulation results of other wideband DOA estimation methods like Coherent signal subspace method (CSSM), Capon, l1-SVD, and JLZA-DOA. W-CMSR separate two signals very clearly and CSSM, Capon, L1-SVD and JLZA-DOA fail to separate two signals clearly and an amount of pseudo peaks exist in the spectrum of L1-SVD.

Keywords: W-CMSR, wideband direction of arrival (DOA), covariance matrix, electrical and computer engineering

Procedia PDF Downloads 437

Authors: Tal Remez, Or Litany, Alex Bronstein

Abstract:

The pursuit of smaller pixel sizes at ever increasing resolution in digital image sensors is mainly driven by the stringent price and form-factor requirements of sensors and optics in the cellular phone market. Recently, Eric Fossum proposed a novel concept of an image sensor with dense sub-diffraction limit one-bit pixels (jots), which can be considered a digital emulation of silver halide photographic film. This idea has been recently embodied as the EPFL Gigavision camera. A major bottleneck in the design of such sensors is the image reconstruction process, producing a continuous high dynamic range image from oversampled binary measurements. The extreme quantization of the Poisson statistics is incompatible with the assumptions of most standard image processing and enhancement frameworks. The recently proposed maximum-likelihood (ML) approach addresses this difficulty, but suffers from image artifacts and has impractically high computational complexity. In this work, we study a variant of a sensor with binary threshold pixels and propose a reconstruction algorithm combining an ML data fitting term with a sparse synthesis prior. We also show an efficient hardware-friendly real-time approximation of this inverse operator. Promising results are shown on synthetic data as well as on HDR data emulated using multiple exposures of a regular CMOS sensor.

Keywords: binary pixels, maximum likelihood, neural networks, sparse coding

Procedia PDF Downloads 172

Authors: Damir Latypov

Abstract:

A hybrid classical-quantum algorithm to solve boundary integral equations (BIE) arising in problems of electromagnetic and acoustic scattering is proposed. The quantum speed-up is due to a Quantum Linear System Algorithm (QLSA). The original QLSA of Harrow et al. provides an exponential speed-up over the best-known classical algorithms but only in the case of sparse systems. Due to the non-local nature of integral operators, matrices arising from discretization of BIEs, are, however, dense. A QLSA for dense matrices was introduced in 2017. Its runtime as function of the system's size N is bounded by O(√Npolylog(N)). The run time of the best-known classical algorithm for an arbitrary dense matrix scales as O(N².³⁷³). Instead of exponential as in case of sparse matrices, here we have only a polynomial speed-up. Nevertheless, sufficiently high power of this polynomial, ~4.7, should make QLSA an appealing alternative. Unfortunately for the QLSA, the asymptotic separability of the Green's function leads to high compressibility of the BIEs matrices. Classical fast algorithms such as Multilevel Fast Multipole Method (MLFMM) take advantage of this fact and reduce the runtime to O(Nlog(N)), i.e., the QLSA is only quadratically faster than the MLFMM. To be truly impactful for computational electromagnetics and acoustics engineers, QLSA must provide more substantial advantage than that. We propose a computational scheme which combines elements of the classical fast algorithms with the QLSA to achieve the required performance.

Keywords: quantum linear system algorithm, boundary integral equations, dense matrices, electromagnetic scattering theory

Procedia PDF Downloads 118

Authors: Keisuke Takahata, Hiroshi Suetsugu

Abstract:

Forest height is an important parameter for forest biomass estimation, and precise elevation data is essential for accurate forest height estimation. There are several globally or nationally available digital elevation models (DEMs) like SRTM and ASTER. However, its accuracy is reported to be low particularly in mountainous areas where there are closed canopy or steep slope. Recently, space-borne LiDAR, such as the Global Ecosystem Dynamics Investigation (GEDI), have started to provide sparse but accurate ground elevation and canopy height estimates. Several studies have reported the high degree of accuracy in their elevation products on their exact footprints, while it is not clear how this sparse information can be used for wider area. In this study, we developed a digital terrain model correction algorithm by spatially interpolating the difference between existing DEMs and GEDI elevation products by using Gaussian Process (GP) regression model. The result shows that our GP-based methodology can reduce the mean bias of the elevation data from 3.7m to 0.3m when we use airborne LiDAR-derived elevation information as ground truth. Our algorithm is also capable of quantifying the elevation data uncertainty, which is critical requirement for biomass inventory. Upcoming satellite-LiDAR missions, like MOLI (Multi-footprint Observation Lidar and Imager), are expected to contribute to the more accurate digital terrain model generation.

Keywords: digital terrain model, satellite LiDAR, gaussian processes, uncertainty quantification

Procedia PDF Downloads 143

Authors: Wen Shyong Hsieh, Chih Hsueh Lin

Abstract:

In this paper, we combine the concepts of chameleon hash function (CHF) and identification based cryptography (IBC) to build a message authentication environment for VANET under sparse RSUs. Based on the CHF, TA keeps two common secrets that will be embedded to all identities to be as the evidence of mutual trusting. TA will issue one original identity to every RSU and vehicle. An identity contains one public ID and one private key. The public ID, includes three components: pseudonym, random key, and public key, is used to present one entity and can be verified to be a legal one. The private key is used to claim the ownership of the public ID. Based on the concept of IBC, without any negotiating process, a CHF pairing key multiplied by one private key and other’s public key will be used for mutually trusting and to be utilized as the session key of secure communicating between RSUs and vehicles. To help the vehicles to do message authenticating, the RSUs are assigned to response the vehicle’s temple identity request using two short time secretes that are broadcasted by TA. To light the loading of request information, one day is divided into M time slots. At every time slot, TA will broadcast two short time secretes to all valid RSUs for that time slot. Any RSU can response the temple identity request from legal vehicles. With the collected announcement of public IDs from the neighbor vehicles, a vehicle can set up its neighboring set, which includes the information about the neighbor vehicle’s temple public ID and temple CHF pairing key that can be derived by the private key and neighbor’s public key and will be used to do message authenticating or secure communicating without the help of RSU.

Keywords: Internet of Vehicles (IOV), Vehicular Ad-hoc Networks (VANETs), Chameleon Hash Function (CHF), message authentication

Procedia PDF Downloads 359

Authors: Jun Ming Moey, Zhiyaun Chen, David Nicholson

Abstract:

Bad actors are often hard to detect in data that imprints their behaviour patterns because they are comparatively rare events embedded in non-bad actor data. An unsupervised machine learning framework is applied here to detect bad actors in financial crime datasets that record millions of transactions undertaken by hundreds of actors (<0.01% bad). Specifically, the framework combines ‘shallow’ (PCA, Isolation Forest) and ‘deep’ (Autoencoder) methods to detect outlier patterns. Detection performance analysis for both the individual methods and their combination is reported.

Keywords: detection, machine learning, deep learning, unsupervised, outlier analysis, data science, fraud, financial crime

Procedia PDF Downloads 66

Authors: Varun Agarwal

Abstract:

Introduction: With the advent of personalized medicine, histopathological review of whole slide images (WSIs) for cancer diagnosis presents an exceedingly time-consuming, complex task. Specifically, detecting metastatic regions in WSIs of sentinel lymph node biopsies necessitates a full-scanned, holistic evaluation of the image. Thus, digital pathology, low-level image manipulation algorithms, and machine learning provide significant advancements in improving the efficiency and accuracy of WSI analysis. Using Camelyon16 data, this paper proposes a deep learning pipeline to automate and ameliorate breast cancer metastasis localization and WSI classification. Methodology: The model broadly follows five stages -region of interest detection, WSI partitioning into image tiles, convolutional neural network (CNN) image-segment classifications, probabilistic mapping of tumor localizations, and further processing for whole WSI classification. Transfer learning is applied to the task, with the implementation of Inception-ResNetV2 - an effective CNN classifier that uses residual connections to enhance feature representation, adding convolved outputs in the inception unit to the proceeding input data. Moreover, in order to augment the performance of the transfer learning CNN, a stack of convolutional denoising autoencoders (CDAE) is applied to produce embeddings that enrich image representation. Through a saliency-detection algorithm, visual training segments are generated, which are then processed through a denoising autoencoder -primarily consisting of convolutional, leaky rectified linear unit, and batch normalization layers- and subsequently a contrast-normalization function. A spatial pyramid pooling algorithm extracts the key features from the processed image, creating a viable feature map for the CNN that minimizes spatial resolution and noise. Results and Conclusion: The simplified and effective architecture of the fine-tuned transfer learning Inception-ResNetV2 network enhanced with the CDAE stack yields state of the art performance in WSI classification and tumor localization, achieving AUC scores of 0.947 and 0.753, respectively. The convolutional feature retention and compilation with the residual connections to inception units synergized with the input denoising algorithm enable the pipeline to serve as an effective, efficient tool in the histopathological review of WSIs.

Keywords: breast cancer, convolutional neural networks, metastasis mapping, whole slide images

Procedia PDF Downloads 105

Authors: Chen Zhang, Nan Chen

Abstract:

High-dimensional process monitoring becomes increasingly important in many application domains, where usually the process distribution is unknown and much more complicated than the normal distribution, and the between-stream correlation can not be neglected. However, since the process dimension is generally much bigger than the reference sample size, most traditional nonparametric multivariate control charts fail in high-dimensional cases due to the curse of dimensionality. Furthermore, when the process goes out of control, the influenced variables are quite sparse compared with the whole dimension, which increases the detection difficulty. Targeting at these issues, this paper proposes a new nonparametric monitoring scheme for high-dimensional processes. This scheme first projects the high-dimensional process into several subprocesses using random projections for dimension reduction. Then, for every subprocess with the dimension much smaller than the reference sample size, a local nonparametric control chart is constructed based on the spatial rank test to detect changes in this subprocess. Finally, the results of all the local charts are fused together for decision. Furthermore, after an out-of-control (OC) alarm is triggered, a diagnostic framework is proposed. using the square-root LASSO. Numerical studies demonstrate that the chart has satisfactory detection power for sparse OC changes and robust performance for non-normally distributed data, The diagnostic framework is also effective to identify truly changed variables. Finally, a real-data example is presented to demonstrate the application of the proposed method.

Keywords: random projection, high-dimensional process control, spatial rank, sequential change detection

Procedia PDF Downloads 274

Authors: N. Anjana

Abstract:

Worldwide, the prevalence of mental illnesses is increasing. The issues of persons with mental illness and their caregivers have been well documented in the literature. However, data regarding the factors affecting the caregiving experience of children with parental mental illnesses is sparse. This systematic review aimed to examine the existing literature of the factors affecting the caregiving experience of children of parents with mental illnesses. A comprehensive search of databases such as PubMed, EBSCO, JSTOR, ProQuest Central, Taylor and Francis Online, and Google Scholar were performed to identify peer-reviewed papers examining the factors associated with caregiving experiences of children with parental mental illnesses such as schizophrenia and major depression, for the 10-year period ending November 2019. Two researchers screened studies for eligibility. One researcher extracted data from eligible studies while a second performed verification of results for accuracy and completeness. Quality appraisal was conducted by both reviewers. Data describing major factors associated with caregiving experiences of children with parental mental illnesses were synthesized and reported in narrative form. Five studies were considered eligible and included in this review. Findings are organized under major themes such as the impact of parental mental illness on children’s daily life, how children provide care to their mentally ill parents as primary carers, social and relationship factors associated with their caregiving, positive and negative experiences in caregiving and how children cope with their experiences with parental mental illnesses. Literature relating to the caregiving experiences of children with parental mental illnesses is sparse. More research is required to better understand the children’s caregiving experiences related to parental mental illnesses so as to better inform management for enhancing their mental health, wellbeing, and caregiving practice.

Keywords: caregiving experience, children, parental mental illnesses, wellbeing

Procedia PDF Downloads 113

Authors: Sai Maniveer Adapa, Sai Guptha Perla, Adithya Reddy P.

Abstract:

Thyroid nodules can often be diagnosed with ultrasound imaging, although differentiating between benign and malignant nodules can be challenging for medical professionals. This work suggests a novel approach to increase the precision of thyroid nodule identification by combining machine learning and deep learning. The new approach first extracts information from the ultrasound pictures using a deep learning method known as a convolutional autoencoder. A support vector machine, a type of machine learning model, is then trained using these features. With an accuracy of 92.52%, the support vector machine can differentiate between benign and malignant nodules. This innovative technique may decrease the need for pointless biopsies and increase the accuracy of thyroid nodule detection.

Keywords: thyroid tumor diagnosis, ultrasound images, deep learning, machine learning, convolutional auto-encoder, support vector machine

Procedia PDF Downloads 20