Search results for: hyperspectral image classification using tree search algorithm

Authors: Shaira L. Kee, Michael Aaron G. Sy, Myles Joshua T. Tan, Hezerul Abdul Karim, Nouar AlDahoul

Abstract:

Skin diseases are considered the fourth most common disease, with melanoma and non-melanoma skin cancer as the most common type of cancer in Caucasians. The alarming increase in Skin Cancer cases shows an urgent need for further research to improve diagnostic methods, as early diagnosis can significantly improve the 5-year survival rate. Machine Learning algorithms for image pattern analysis in diagnosing skin lesions can dramatically increase the accuracy rate of detection and decrease possible human errors. Several studies have shown the diagnostic performance of computer algorithms outperformed dermatologists. However, existing methods still need improvements to reduce diagnostic errors and generate efficient and accurate results. Our paper proposes an ensemble method to classify dermoscopic images into benign and malignant skin lesions. The experiments were conducted using the International Skin Imaging Collaboration (ISIC) image samples. The dataset contains 3,297 dermoscopic images with benign and malignant categories. The results show improvement in performance with an accuracy of 88% and an F1 score of 87%, outperforming other existing models such as support vector machine (SVM), Residual network (ResNet50), EfficientNetB0, EfficientNetB4, and VGG16.

Keywords: deep learning - VGG16 - efficientNet - CNN – ensemble – dermoscopic images - melanoma

Procedia PDF Downloads 82

Authors: Sarita Agarwal, Deepika Delsa Dean

Abstract:

Like the task of transferring photo images to artistic images, image-to-image translation aims to translate the data to the imitated data which belongs to the target domain. Neural Style Transfer and CycleGAN are two well-known deep learning architectures used for photo image-to-art image transfer. However, studies involving these two models concentrate on one-to-one domain translation, not one-to-multi domains translation. Our study tries to investigate deep learning architectures, which can be controlled to yield multiple artistic style translation only by adding a conditional vector. We have expanded CycleGAN and constructed Conditional CycleGAN for 5 kinds of categories translation. Our study found that the architecture inserting conditional vector into the middle layer of the Generator could output multiple artistic images.

Keywords: genetic counseling, FMR1 gene, fragile x-associated primary ovarian insufficiency, premutation

Procedia PDF Downloads 131

Authors: Nidal F. Shilbayeh, Belal AbuHaija, Zainab N. Al-Qudsy

Abstract:

In this paper, a hybrid blind digital watermarking system using Discrete Wavelet Transform (DWT) and Contourlet Transform (CT) has been implemented and tested. The implemented combined digital watermarking system has been tested against five common types of image attacks. The performance evaluation shows improved results in terms of imperceptibility, robustness, and high tolerance against these attacks; accordingly, the system is very effective and applicable.

Keywords: discrete wavelet transform (DWT), contourlet transform (CT), digital image watermarking, copyright protection, geometric attack

Procedia PDF Downloads 396

Authors: Nkechi Neboh, Josiah Adeyemo, Abimbola Enitan, Oludayo Olugbara

Abstract:

Evolutionary algorithms are techniques extensively used in the planning and management of water resources and systems. It is useful in finding optimal solutions to water resources problems considering the complexities involved in the analysis. River basin management is an essential area that involves the management of upstream, river inflow and outflow including downstream aspects of a reservoir. Water as a scarce resource is needed by human and the environment for survival and its management involve a lot of complexities. Management of this scarce resource is necessary for proper distribution to competing users in a river basin. This presents a lot of complexities involving many constraints and conflicting objectives. Evolutionary algorithms are very useful in solving this kind of complex problems with ease. Evolutionary algorithms are easy to use, fast and robust with many other advantages. Many applications of evolutionary algorithms, which are population based search algorithm, are discussed. Different methodologies involved in the modeling and simulation of water management problems in river basins are explained. It was found from this work that different evolutionary algorithms are suitable for different problems. Therefore, appropriate algorithms are suggested for different methodologies and applications based on results of previous studies reviewed. It is concluded that evolutionary algorithms, with wide applications in water resources management, are viable and easy algorithms for most of the applications. The results suggested that evolutionary algorithms, applied in the right application areas, can suggest superior solutions for river basin management especially in reservoir operations, irrigation planning and management, stream flow forecasting and real-time applications. The future directions in this work are suggested. This study will assist decision makers and stakeholders on the best evolutionary algorithm to use in varied optimization issues in water resources management.

Keywords: evolutionary algorithm, multi-objective, reservoir operation, river basin management

Procedia PDF Downloads 491

Authors: Dumont Maxime, Correia Carlos, Sauvage Jean-François, Schwartz Noah, Gray Morgan

Abstract:

Context: The concept of the segmented telescope is unavoidable to build extremely large telescopes (ELT) in the quest for spatial resolution, but it also allows one to fit a large telescope within a reduced volume of space (JWST) or into an even smaller volume (Standard Cubesat). Cubesats have tight constraints on the computational burden available and the small payload volume allowed. At the same time, they undergo thermal gradients leading to large and evolving optical aberrations. The pupil segmentation comes nevertheless with an obvious difficulty: to co-phase the different segments. The CubeSat constraints prevent the use of a dedicated wavefront sensor (WFS), making the focal-plane images acquired by the science detector the most practical alternative. Yet, one of the challenges for the wavefront sensing is the non-linearity between the image intensity and the phase aberrations. Plus, for Earth observation, the object is unknown and unrepeatable. Recently, several studies have suggested Neural Networks (NN) for wavefront sensing; especially convolutional NN, which are well known for being non-linear and image-friendly problem solvers. Aims: We study in this paper the prospect of using NN to measure the phasing aberrations of a segmented pupil from the focal-plane image directly without a dedicated wavefront sensing. Methods: In our application, we take the case of a deployable telescope fitting in a CubeSat for Earth observations which triples the aperture size (compared to the 10cm CubeSat standard) and therefore triples the angular resolution capacity. In order to reach the diffraction-limited regime in the visible wavelength, typically, a wavefront error below lambda/50 is required. The telescope focal-plane detector, used for imaging, will be used as a wavefront-sensor. In this work, we study a point source, i.e. the Point Spread Function [PSF] of the optical system as an input of a VGG-net neural network, an architecture designed for image regression/classification. Results: This approach shows some promising results (about 2nm RMS, which is sub lambda/50 of residual WFE with 40-100nm RMS of input WFE) using a relatively fast computational time less than 30 ms which translates a small computation burder. These results allow one further study for higher aberrations and noise.

Keywords: wavefront sensing, deep learning, deployable telescope, space telescope

Procedia PDF Downloads 106

Authors: Sedat Aktas, Egemen Ulusoy, Remzi Yildirim

Abstract:

This article explains how to get a ram image from a computer with a Linux operating system and what steps should be followed while getting it. What we mean by taking a ram image is the process of dumping the physical memory instantly and writing it to a file. This process can be likened to taking a picture of everything in the computer’s memory at that moment. This process is very important for tools that analyze ram images. Volatility can be given as an example because before these tools can analyze ram, images must be taken. These tools are used extensively in the forensic world. Forensic, on the other hand, is a set of processes for digitally examining the information on any computer or server on behalf of official authorities. In this article, the protected mode architecture in the Linux operating system is examined, and the way to save the image sample of the kernel driver and system memory to disk is followed. Tables and access methods to be used in the operating system are examined based on the basic architecture of the operating system, and the most appropriate methods and application methods are transferred to the article. Since there is no article directly related to this study on Linux in the literature, it is aimed to contribute to the literature with this study on obtaining ram images. LIME can be mentioned as a similar tool, but there is no explanation about the memory dumping method of this tool. Considering the frequency of use of these tools, the contribution of the study in the field of forensic medicine has been the main motivation of the study due to the intense studies on ram image in the field of forensics.

Keywords: linux, paging, addressing, ram-image, memory dumping, kernel modules, forensic

Procedia PDF Downloads 119

Authors: Larbi Guezouli, Imane Azzouz

Abstract:

This work is located in the domain of distributed information retrieval ‘DIR’. A simplified view of the DIR requires a multi-search in a set of collections, which forces the system to analyze results found in these collections, and merge results back before sending them to the user in a single list. Our work is to find a fusion method based on the relevance score of each result received from collections and the relevance of the local search engine of each collection.

Keywords: information retrieval, distributed IR systems, merging results, datamining

Procedia PDF Downloads 338

Authors: Seyed-Yaser Nabavi-Chashmi, Davood Asadi, Karim Ahmadi, Eren Demir

Abstract:

The landing phase of a UAV is very critical as there are many uncertainties in this phase, which can easily entail a hard landing or even a crash. In this paper, the estimation of relative distance and velocity to the ground, as one of the most important processes during the landing phase, is studied. Using accurate measurement sensors as an alternative approach can be very expensive for sensors like LIDAR, or with a limited operational range, for sensors like ultrasonic sensors. Additionally, absolute positioning systems like GPS or IMU cannot provide distance to the ground independently. The focus of this paper is to determine whether we can measure the relative distance and velocity of UAV and ground in the landing phase using just low-resolution images taken by a monocular camera. The Lucas-Konda feature detection technique is employed to extract the most suitable feature in a series of images taken during the UAV landing. Two different approaches based on Extended Kalman Filters (EKF) have been proposed, and their performance in estimation of the relative distance and velocity are compared. The first approach uses the kinematics of the UAV as the process and the calculated optical flow as the measurement; On the other hand, the second approach uses the feature’s projection on the camera plane (pixel position) as the measurement while employing both the kinematics of the UAV and the dynamics of variation of projected point as the process to estimate both relative distance and relative velocity. To verify the results, a sequence of low-quality images taken by a camera that is moving on a specifically developed testbed has been used to compare the performance of the proposed algorithm. The case studies show that the quality of images results in considerable noise, which reduces the performance of the first approach. On the other hand, using the projected feature position is much less sensitive to the noise and estimates the distance and velocity with relatively high accuracy. This approach also can be used to predict the future projected feature position, which can drastically decrease the computational workload, as an important criterion for real-time applications.

Keywords: altitude estimation, drone, image processing, trajectory planning

Procedia PDF Downloads 113

Authors: Bundit Pungnirund

Abstract:

This research aimed to investigate the relationship between attitude towards marketing mix, brand image and consumer behavior of the passengers of low-cost airlines service. This study employed by quantitative research and the questionnaire was used to collect the data from 400 sampled of the passengers who have ever used the low-cost airline services based in Bangkok, Thailand. The descriptive statistics and Pearson’s correlation analysis were used to analyze data. The research results revealed that the attitude of the marketing mix of the low-cost airline services including product, price, place, promotion and process had related to the consumer behavior on the aspects of duration of service and frequency of service. While, the brand image of the low cost airline including the characteristics of organization, service quality and company identity had related to the consumer behavior on duration of service, frequency of service and cost of service at the significant statistically acceptable levels.

Keywords: brand image, consumer behavior, low-cost airline, marketing mix

Procedia PDF Downloads 316

Authors: Amit Verma, Pardeep Kaur

Abstract:

In software development organizations, Component based Software engineering (CBSE) is emerging paradigm for software development and gained wide acceptance as it often results in increase quality of software product within development time and budget. In component reusability, main challenges are the right component identification from large repositories at right time. The major objective of this work is to provide efficient algorithm for storage and effective retrieval of components using neural network and parameters based on user choice through clustering. This research paper aims to propose an algorithm that provides error free and automatic process (for retrieval of the components) while reuse of the component. In this algorithm, keywords (or components) are extracted from software document, after by applying k mean clustering algorithm. Then weights assigned to those keywords based on their frequency and after assigning weights, ANN predicts whether correct weight is assigned to keywords (or components) or not, otherwise it back propagates in to initial step (re-assign the weights). In last, store those all keywords into repositories for effective retrieval. Proposed algorithm is very effective in the error correction and detection with user base choice while choice of component for reusability for efficient retrieval is there.

Keywords: component based development, clustering, back propagation algorithm, keyword based retrieval

Procedia PDF Downloads 379

Authors: Yuan-Hsiang Chang, Zhong-Xian Peng, Li-Der Jeng

Abstract:

Music has always been an integral part of human’s daily lives. But, for the most people, reading musical score and turning it into melody is not easy. This study aims to develop an Automatic music score recognition system using digital image processing, which can be used to read and analyze musical score images automatically. The technical approaches included: (1) staff region segmentation; (2) image preprocessing; (3) note recognition; and (4) accidental and rest recognition. Digital image processing techniques (e.g., horizontal /vertical projections, connected component labeling, morphological processing, template matching, etc.) were applied according to musical notes, accidents, and rests in staff notations. Preliminary results showed that our system could achieve detection and recognition rates of 96.3% and 91.7%, respectively. In conclusion, we presented an effective automated musical score recognition system that could be integrated in a system with a media player to play music/songs given input images of musical score. Ultimately, this system could also be incorporated in applications for mobile devices as a learning tool, such that a music player could learn to play music/songs.

Keywords: connected component labeling, image processing, morphological processing, optical musical recognition

Procedia PDF Downloads 421

Authors: Fatimah Zawani Abdullah, Shereena Mohd Arif, Nurul Malim

Abstract:

The study of molecular similarity search in chemical database is increasingly widespread, especially in the area of drug discovery. Similarity search is an application in the field of Chemoinformatics to measure the similarity between the molecular structure which is known as the query and the structure of chemical compounds in the database. Similarity search is also one of the approaches in virtual screening which involves computational techniques and scoring the probabilities of activity. The main objective of this work is to determine the best fingerprint when compared to the other five fingerprints selected in this study using PubChem chemical dataset. This paper will discuss the similarity searching process conducted using 6 types of descriptors, which are ECFP4, ECFC4, FCFP4, FCFC4, SRECFC4 and SRFCFC4 on 15 activity classes of PubChem dataset using Tanimoto coefficient to calculate the similarity between the query structures and each of the database structure. The results suggest that ECFP4 performs the best to be used with Tanimoto coefficient in the PubChem dataset.

Keywords: 2D fingerprints, Tanimoto, PubChem, similarity searching, chemoinformatics

Procedia PDF Downloads 294

Authors: Sudha T., Naveen C.

Abstract:

Dengue is a serious public health issue that causes significant annual economic and welfare burdens on nations. However, enhanced optimization techniques and quantitative modeling approaches can predict the incidence of dengue. By advocating for a data-driven approach, public health officials can make informed decisions, thereby improving the overall effectiveness of sudden disease outbreak control efforts. The National Oceanic and Atmospheric Administration and the Centers for Disease Control and Prevention are two of the U.S. Federal Government agencies from which this study uses environmental data. Based on environmental data that describe changes in temperature, precipitation, vegetation, and other factors known to affect dengue incidence, many predictive models are constructed that use different machine learning methods to estimate weekly dengue cases. The first step involves preparing the data, which includes handling outliers and missing values to make sure the data is prepared for subsequent processing and the creation of an accurate forecasting model. In the second phase, multiple feature selection procedures are applied using various machine learning models and optimization techniques. During the third phase of the research, machine learning models like the Huber Regressor, Support Vector Machine, Gradient Boosting Regressor (GBR), and Support Vector Regressor (SVR) are compared with several optimization techniques for feature selection, such as Harmony Search and Genetic Algorithm. In the fourth stage, the model's performance is evaluated using Mean Square Error (MSE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) as assistance. Selecting an optimization strategy with the least number of errors, lowest price, biggest productivity, or maximum potential results is the goal. In a variety of industries, including engineering, science, management, mathematics, finance, and medicine, optimization is widely employed. An effective optimization method based on harmony search and an integrated genetic algorithm is introduced for input feature selection, and it shows an important improvement in the model's predictive accuracy. The predictive models with Huber Regressor as the foundation perform the best for optimization and also prediction.

Keywords: deep learning model, dengue fever, prediction, optimization

Procedia PDF Downloads 67

Authors: Md Shohidul Islam, Jongmyon Kim, Ui-pil Chong

Abstract:

Medical image is an integral part of e-health care and e-diagnosis system. Medical image watermarking is widely used to protect patients’ information from malicious alteration and manipulation. The watermarked medical images are transmitted over the internet among patients, primary and referred physicians. The images are highly prone to corruption in the wireless transmission medium due to various noises, deflection, and refractions. Distortion in the received images leads to faulty watermark detection and inappropriate disease diagnosis. To address the issue, this paper utilizes error correction code (ECC) with (8, 4) Hamming code in an existing watermarking system. In addition, we implement the high complex ECC on a graphics processing units (GPU) to accelerate and support real-time requirement. Experimental results show that GPU achieves considerable speedup over the sequential CPU implementation, while maintaining 100% ECC efficiency.

Keywords: medical image watermarking, e-health system, error correction, Hamming code, GPU

Procedia PDF Downloads 292

Authors: Gianna Zou

Abstract:

Propensity score matching (PSM), introduced by Paul R. Rosenbaum and Donald Rubin in 1983, is a popular statistical matching technique which tries to estimate the treatment effects by taking into account covariates that could impact the efficacy of study medication in clinical trials. PSM can be used to reduce the bias due to confounding variables. However, PSM assumes that the response values are normally distributed. In some cases, this assumption may not be held. In this paper, a machine learning method - Bayesian Additive Regression Tree (BART), is used as a more robust method of matching. BART can work well when models are misspecified since it can be used to model heterogeneous treatment effects. Moreover, it has the capability to handle non-linear main effects and multiway interactions. In this research, a BART Matching Method (BMM) is proposed to provide a more reliable matching method over PSM. By comparing the analysis results from PSM and BMM, BMM can perform well and has better prediction capability when the response values are not normally distributed.

Keywords: BART, Bayesian, matching, regression

Procedia PDF Downloads 149

Authors: Guezouli Larbi, Belkacem Soundes

Abstract:

The automation of the text detection process can help the human in his driving task. Its application can be very useful to help drivers to have more information about their environment by facilitating the reading of road signs such as directional signs, events, stores, etc. In this paper, a system consisting of two stages has been proposed. In the first one, we used pseudo-Zernike moments to pinpoint areas of the image that may contain text. The architecture of this part is based on three main steps, region of interest (ROI) detection, text localization, and non-text region filtering. Then, in the second step, we present a convolutional neural network architecture (On-Road Text Detection Network - ORTDN) which is considered a classification phase. The results show that the proposed framework achieved ≈ 35 fps and an mAP of ≈ 90%, thus a low computational time with competitive accuracy.

Keywords: text detection, CNN, PZM, deep learning

Procedia PDF Downloads 84

Authors: Mohmmad A. Obeidat, Amjed Al Fahoum, Ayman M. Mansour

Abstract:

The recognition of an abnormal activity of the brain functionality is a vital issue. To determine the type of the abnormal activity either a brain image or brain signal are usually considered. Imaging localizes the defect within the brain area and relates this area with somebody functionalities. However, some functions may be disturbed without affecting the brain as in epilepsy. In this case, imaging may not provide the symptoms of the problem. A cheaper yet efficient approach that can be utilized to detect abnormal activity is the measurement and analysis of the electroencephalogram (EEG) signals. The main goal of this work is to come up with a new method to facilitate the classification of the abnormal and disorder activities within the brain directly using EEG signal processing, which makes it possible to be applied in an on-line monitoring system.

Keywords: EEG, wavelet, epilepsy, detection

Procedia PDF Downloads 538

Authors: Yang Yi-Fei, Luo Min-Zhou, Zhang Fu-Chun, He Nai-Bao, Xing Shao-Bang

Abstract:

This paper presents an electromagnetic finite element model of permanent magnet synchronous linear motor and distortion rate of the air gap flux density waveform is analyzed in detail. By designing the sample space of the parameters, nonlinear regression modeling of the orthogonal experimental design is introduced. We put forward for possible air gap flux density waveform sine electromagnetic scheme. Parameters optimization of the permanent magnet synchronous linear motor is also introduced which is based on chaotic search and adaptation function. Simulation results prove that the pole shifting does not affect the motor back electromotive symmetry based on the structural parameters, it provides a novel way for the optimum design of permanent magnet synchronous linear motor and other engineering.

Keywords: permanent magnet synchronous linear motor, finite element analysis, chaotic search, optimization design

Procedia PDF Downloads 418

Authors: Ashwini Mohan, Haris Batley

Abstract:

An orthodontic index is used to rate or categorise an individual’s occlusion using a numeric or alphanumeric score. Indexing of malocclusions and their correction is important in epidemiology, diagnosis, communication between clinicians as well as their patients and assessing treatment outcomes. Many useful indices have been put forward, but to the author’s best knowledge, no one method to this day appears to be equally suitable for the use of epidemiologists, public health program planners and clinicians. This article describes the common clinical orthodontic indices and classifications used in United Kingdom.

Keywords: classification, indices, orthodontics, validity

Procedia PDF Downloads 154

Authors: M. Nadeem, Y. K. Chang, C. Diallo, U. Venkatadri, P. Havard, T. Nguyen-Quang

Abstract:

Uniform distribution of agro-chemicals is highly important because there is a significant loss of agro-chemicals, for example from pesticide, during spraying due to non-uniformity of droplet and off-target drift. Improving the efficiency of spray pattern for different cropping systems would reduce energy, costs and to minimize environmental pollution. In this paper, we examine the water jet patterns in order to study the performance and uniformity of water distribution during the spraying process. We present a method to quantify the water amount from a sprayer jet by using the Particle Image Velocimetry (PIV) system. The results of the study will be used to optimize sprayer or nozzles design for chemical application. For this study, ten sets of images were acquired by using the following PIV system settings: double frame mode, trigger rate is 4 Hz, and time between pulsed signals is 500 µs. Each set of images contained different numbers of double-framed images: 10, 20, 30, 40, 50, 60, 70, 80, 90 and 100 at eight different pressures 25, 50, 75, 100, 125, 150, 175 and 200 kPa. The PIV images obtained were analysed using custom-made image processing software for droplets and volume calculations. The results showed good agreement of both manual and PIV measurements and suggested that the PIV technique coupled with image processing can be used for a precise quantification of flow through nozzles. The results also revealed that the method of measuring fluid flow through PIV is reliable and accurate for sprayer patterns.

Keywords: image processing, PIV, quantifying the water volume from nozzle, spraying pattern

Procedia PDF Downloads 238

Authors: Naser Safdarian, Nader Jafarnia Dabanloo

Abstract:

In this paper we used four features i.e. Q-wave integral, QRS complex integral, T-wave integral and total integral as extracted feature from normal and patient ECG signals to detection and localization of myocardial infarction (MI) in left ventricle of heart. In our research we focused on detection and localization of MI in standard ECG. We use the Q-wave integral and T-wave integral because this feature is important impression in detection of MI. We used some pattern recognition method such as Artificial Neural Network (ANN) to detect and localize the MI. Because these methods have good accuracy for classification of normal and abnormal signals. We used one type of Radial Basis Function (RBF) that called Probabilistic Neural Network (PNN) because of its nonlinearity property, and used other classifier such as k-Nearest Neighbors (KNN), Multilayer Perceptron (MLP) and Naive Bayes Classification. We used PhysioNet database as our training and test data. We reached over 80% for accuracy in test data for localization and over 95% for detection of MI. Main advantages of our method are simplicity and its good accuracy. Also we can improve accuracy of classification by adding more features in this method. A simple method based on using only four features which extracted from standard ECG is presented which has good accuracy in MI localization.

Keywords: ECG signal processing, myocardial infarction, features extraction, pattern recognition

Procedia PDF Downloads 457

Authors: Nkechinyere Joy Olawuyi, Babajide Samuel Afolabi, Bola Ibitoye

Abstract:

This study collected a preprocessed dataset of chest radiographs and formulated a deep neural network model for detecting abnormalities. It also evaluated the performance of the formulated model and implemented a prototype of the formulated model. This was with the view to developing a deep neural network model to automatically classify abnormalities in chest radiographs. In order to achieve the overall purpose of this research, a large set of chest x-ray images were sourced for and collected from the CheXpert dataset, which is an online repository of annotated chest radiographs compiled by the Machine Learning Research Group, Stanford University. The chest radiographs were preprocessed into a format that can be fed into a deep neural network. The preprocessing techniques used were standardization and normalization. The classification problem was formulated as a multi-label binary classification model, which used convolutional neural network architecture to make a decision on whether an abnormality was present or not in the chest radiographs. The classification model was evaluated using specificity, sensitivity, and Area Under Curve (AUC) score as the parameter. A prototype of the classification model was implemented using Keras Open source deep learning framework in Python Programming Language. The AUC ROC curve of the model was able to classify Atelestasis, Support devices, Pleural effusion, Pneumonia, A normal CXR (no finding), Pneumothorax, and Consolidation. However, Lung opacity and Cardiomegaly had a probability of less than 0.5 and thus were classified as absent. Precision, recall, and F1 score values were 0.78; this implies that the number of False Positive and False Negative is the same, revealing some measure of label imbalance in the dataset. The study concluded that the developed model is sufficient to classify abnormalities present in chest radiographs into present or absent.

Keywords: transfer learning, convolutional neural network, radiograph, classification, multi-label

Procedia PDF Downloads 130

Authors: Sidney A. Lima, Hermann J. H. Kux, Elcio H. Shiguemori

Abstract:

The Unmanned Aircraft Systems (UAS) usually navigate through the Global Navigation Satellite System (GNSS) associated with an Inertial Navigation System (INS). However, GNSS can have its accuracy degraded at any time or even turn off the signal of GNSS. In addition, there is the possibility of malicious interferences, known as jamming. Therefore, the image navigation system can solve the autonomy problem, because if the GNSS is disabled or degraded, the image navigation system would continue to provide coordinate information for the INS, allowing the autonomy of the system. This work aims to evaluate the accuracy of the positioning though photogrammetry concepts. The methodology uses orthophotos and Digital Surface Models (DSM) as a reference to represent the object space and photograph obtained during the flight to represent the image space. For the calculation of the coordinates of the perspective center and camera attitudes, it is necessary to know the coordinates of homologous points in the object space (orthophoto coordinates and DSM altitude) and image space (column and line of the photograph). So if it is possible to automatically identify in real time the homologous points the coordinates and attitudes can be calculated whit their respective accuracies. With the methodology applied in this work, it is possible to verify maximum errors in the order of 0.5 m in the positioning and 0.6º in the attitude of the camera, so the navigation through the image can reach values equal to or higher than the GNSS receivers without differential correction. Therefore, navigating through the image is a good alternative to enable autonomous navigation.

Keywords: autonomy, navigation, security, photogrammetry, remote sensing, spatial resection, UAS

Procedia PDF Downloads 193

Authors: Anthony D. Rhodes, Manan Goel

Abstract:

We provide a high fidelity deep learning algorithm (HyperSeg) for interactive video segmentation tasks using a dense convolutional network with context-aware skip connections and compressed, 'hypercolumn' image features combined with a convolutional tessellation procedure. In order to maintain high output fidelity, our model crucially processes and renders all image features in high resolution, without utilizing downsampling or pooling procedures. We maintain this consistent, high grade fidelity efficiently in our model chiefly through two means: (1) we use a statistically-principled, tensor decomposition procedure to modulate the number of hypercolumn features and (2) we render these features in their native resolution using a convolutional tessellation technique. For improved pixel-level segmentation results, we introduce a boundary loss function; for improved temporal coherence in video data, we include temporal image information in our model. Through experiments, we demonstrate the improved accuracy of our model against baseline models for interactive segmentation tasks using high resolution video data. We also introduce a benchmark video segmentation dataset, the VFX Segmentation Dataset, which contains over 27,046 high resolution video frames, including green screen and various composited scenes with corresponding, hand-crafted, pixel-level segmentations. Our work presents a improves state of the art segmentation fidelity with high resolution data and can be used across a broad range of application domains, including VFX pipelines and medical imaging disciplines.

Keywords: computer vision, object segmentation, interactive segmentation, model compression

Procedia PDF Downloads 120

Authors: Jude K. Safo

Abstract:

Knowledge Graphs KG) and their relation to Graph Embeddings (GE) represent a unique data structure in the landscape of machine learning (relative to image, text and acoustic data). Unlike the latter, GEs are the only data structure sufficient for representing hierarchically dense, semantic information needed for use-cases like supply chain data and protein folding where the search space exceeds the limits traditional search methods (e.g. page-rank, Dijkstra, etc.). While GEs are effective for compressing low rank tensor data, at scale, they begin to introduce a new problem of ’data retreival’ which we observe in Large Language Models. Notable attempts by transE, TransR and other prominent industry standards have shown a peak performance just north of 57% on WN18 and FB15K benchmarks, insufficient practical industry applications. They’re also limited, in scope, to next node/link predictions. Traditional linear methods like Tucker, CP, PARAFAC and CANDECOMP quickly hit memory limits on tensors exceeding 6.4 million nodes. This paper outlines a topological framework for linear mapping between concepts in KG space and GE space that preserve cardinality. Most importantly we introduce a traceable framework for composing dense linguistic strcutures. We demonstrate performance on WN18 benchmark this model hits. This model does not rely on Large Langauge Models (LLM) though the applications are certainy relevant here as well.

Keywords: representation theory, large language models, graph embeddings, applied algebraic topology, applied knot theory, combinatorics

Procedia PDF Downloads 68

Authors: Mohammadreza Hedyehzadeh, Mahdi Yousefi

Abstract:

Colon cancer is one of the most common cancer, which predicted to increase its prevalence due to the bad eating habits of peoples. Nowadays, due to the busyness of people, the use of fast foods is increasing, and therefore, diagnosis of this disease and its treatment are of particular importance. To determine the best treatment approach for each specific colon cancer patients, the oncologist should be known the stage of the tumor. The most common method to determine the tumor stage is TNM staging system. In this system, M indicates the presence of metastasis, N indicates the extent of spread to the lymph nodes, and T indicates the size of the tumor. It is clear that in order to determine all three of these parameters, an imaging method must be used, and the gold standard imaging protocols for this purpose are CT and PET/CT. In CT imaging, due to the use of X-rays, the risk of cancer and the absorbed dose of the patient is high, while in the PET/CT method, there is a lack of access to the device due to its high cost. Therefore, in this study, we aimed to estimate the tumor size and the extent of its spread to the lymph nodes using MR images. More than 1300 MR images collected from the TCIA portal, and in the first step (pre-processing), histogram equalization to improve image qualities and resizing to get the same image size was done. Two expert radiologists, which work more than 21 years on colon cancer cases, segmented the images and extracted the tumor region from the images. The next step is feature extraction from segmented images and then classify the data into three classes: T0N0، T3N1 و T3N2. In this article, the VGG-16 convolutional neural network has been used to perform both of the above-mentioned tasks, i.e., feature extraction and classification. This network has 13 convolution layers for feature extraction and three fully connected layers with the softmax activation function for classification. In order to validate the proposed method, the 10-fold cross validation method used in such a way that the data was randomly divided into three parts: training (70% of data), validation (10% of data) and the rest for testing. It is repeated 10 times, each time, the accuracy, sensitivity and specificity of the model are calculated and the average of ten repetitions is reported as the result. The accuracy, specificity and sensitivity of the proposed method for testing dataset was 89/09%, 95/8% and 96/4%. Compared to previous studies, using a safe imaging technique (MRI) and non-use of predefined hand-crafted imaging features to determine the stage of colon cancer patients are some of the study advantages.

Keywords: colon cancer, VGG-16, magnetic resonance imaging, tumor size, lymph node metastasis

Procedia PDF Downloads 61

Authors: Chun-Shien Lu

Abstract:

Privacy-preserving query has recently received considerable attention in the signal processing and multimedia community. It is also a critical step in wireless sensor network for retrieval of sensitive data. The purposes of privacy-preserving query in both the areas of signal processing and sensor network are the same, but the similarity and difference of the adopted technologies are not fully explored. In this paper, we first review the recently developed methods of privacy-preserving query, and then describe in a comprehensive manner what we can learn from the mutual of both areas.

Keywords: encryption, privacy-preserving, search, security

Procedia PDF Downloads 257

Authors: Djamel Fawzi Hadj Sadok, Marrone Silvério Melo Dantas Pedro Henrique Dreyer, Gabriel Fonseca Reis de Souza, Daniel Bezerra, Ricardo Souza, Silvia Lins, Judith Kelner

Abstract:

A radio base station (RBS), part of the radio access network, is a particular type of equipment that supports the connection between a wide range of cellular user devices and an operator network access infrastructure. Nowadays, most of the RBS maintenance is carried out manually, resulting in a time consuming and costly task. A suitable candidate for RBS maintenance automation is repairing faulty links between devices caused by missing or unplugged connectors. A suitable candidate for RBS maintenance automation is repairing faulty links between devices caused by missing or unplugged connectors. This paper proposes and compares two deep learning solutions to identify attached RJ45 connectors on network ports. We named connector detection, the solution based on object detection, and connector classification, the one based on object classification. With the connector detection, we get an accuracy of 0:934, mean average precision 0:903. Connector classification, get a maximum accuracy of 0:981 and an AUC of 0:989. Although connector detection was outperformed in this study, this should not be viewed as an overall result as connector detection is more flexible for scenarios where there is no precise information about the environment and the possible devices. At the same time, the connector classification requires that information to be well-defined.

Keywords: radio base station, maintenance, classification, detection, deep learning, automation

Procedia PDF Downloads 203

Authors: Ming-Yen Chang, Sheng-Hung Ke

Abstract:

This research focuses on the development of a speed bump identification system for real-time control of adjustable shock absorbers in vehicular suspension systems. The study initially involved the collection of images of various speed bumps, and rubber speed bump profiles found on roadways. These images were utilized for training and recognition purposes through the deep learning object detection algorithm YOLOv5. Subsequently, the trained speed bump identification program was integrated with an in-vehicle camera system for live image capture during driving. These images were instantly transmitted to a computer for processing. Using the principles of monocular vision ranging, the distance between the vehicle and an approaching speed bump was determined. The appropriate control distance was established through both practical vehicle measurements and theoretical calculations. Collaboratively, with the electronically adjustable shock absorbers equipped in the vehicle, a shock absorber control system was devised to dynamically adapt the damping force just prior to encountering a speed bump. This system effectively mitigates passenger discomfort and enhances ride quality.

Keywords: adjustable shock absorbers, image recognition, monocular vision ranging, ride

Procedia PDF Downloads 67

Authors: Khader S. Al-Aidmat, Venus W. Samawi

Abstract:

Blurred vision in the misty atmosphere is essential problem which needs to be resolved. To solve this problem, we developed a technique to restore foggy degraded image from its original version using Back-propagation neural network (BP-NN). The suggested technique is based on mapping between foggy scene and its corresponding original scene. Seven different approaches are suggested based on type of features used in image restoration. Features are extracted from spatial and spatial-frequency domain (using DCT). Each of these approaches comes with its own BP-NN architecture depending on type and number of used features. The weight matrix resulted from training each BP-NN represents a fog filter. The performance of these filters are evaluated empirically (using PSNR), and perceptually. By comparing the performance of these filters, the effective features that suits BP-NN technique for restoring foggy images is recognized. This system proved its effectiveness and success in restoring moderate foggy images.

Keywords: artificial neural network, discrete cosine transform, feed forward neural network, foggy image restoration

Procedia PDF Downloads 384