Search results for: angle classification

Authors: Ali J. Ghandour, Houssam A. Krayem, Abedelkarim A. Jezzini

Abstract:

High-resolution satellite images and remote sensing can provide global information in a fast way compared to traditional methods of data collection. Under such high resolution, a road is not a thin line anymore. Objects such as cars and trees are easily identifiable. Automatic vehicles enumeration can be considered one of the most important applications in traffic management. In this paper, autonomous vehicle detection and classification approach in highway environment is proposed. This approach consists mainly of three stages: (i) first, a set of preprocessing operations are applied including soil, vegetation, water suppression. (ii) Then, road networks detection and delineation is implemented using built-up area index, followed by several morphological operations. This step plays an important role in increasing the overall detection accuracy since vehicles candidates are objects contained within the road networks only. (iii) Multi-level Otsu segmentation is implemented in the last stage, resulting in vehicle detection and classification, where detected vehicles are classified into cars and trucks. Accuracy assessment analysis is conducted over different study areas to show the great efficiency of the proposed method, especially in highway environment.

Keywords: remote sensing, object identification, vehicle and road extraction, vehicle and road features-based classification

Procedia PDF Downloads 222

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 54

Authors: Hooman Dabirmanesh, Mahmoud Ghazavi, Kazem Barkhordari

Abstract:

A finite element modeling for determination of the bearing capacity of caissons subjected to inclined loads is presented in this paper. The model investigates the uplift capacity of the caisson with varying cross sectional area. To this aim, the behavior of the soil is assumed to be elasto-plastic, and its failure is controlled by Modified Cam-Clay failure criterion. The simulation takes into account the couple analysis. The approach is verified using available data from other research work especially centrifuge data. Parametric studies are subsequently performed to investigate the effect of contributing parameters such as aspect ratio of the caisson, the loading rate, the loading direction angle, and points where the external load is applied. In addition, the influence of the caisson geometry is taken into account. The results show the bearing capacity of the caisson increases with increasing the taper angle. Hence, the pullout capacity will increase using the same material. In addition, the bearing capacity of caissons strongly depends on the suction that is generated at tip and in sealed surface on top of caisson. Other results concerning the influencing factors will be presented.

Keywords: aspect ratio, finite element method, inclined load, modified Cam clay, taper angle, undrained condition

Procedia PDF Downloads 250

Authors: Mekamı Hayet, Bounoua Nacer, Benabderrahmane Sidahmed, Taleb Ahmed

Abstract:

Pose estimation is an important task in computer vision. Though the majority of the existing solutions provide good accuracy results, they are often overly complex and computationally expensive. In this perspective, we propose the use of dimensionality reduction techniques to address the problem of facial pose estimation. Firstly, a face image is converted into one-dimensional time series using Hilbert space filling curve, then the approach converts these time series data to a symbolic representation. Furthermore, a distance matrix is calculated between symbolic series of an input learning dataset of images, to generate classifiers of frontal vs. profile face pose. The proposed method is evaluated with three public datasets. Experimental results have shown that our approach is able to achieve a correct classification rate exceeding 97% with K-NN algorithm.

Keywords: machine learning, pattern recognition, facial pose classification, time series

Procedia PDF Downloads 342

Authors: Divyanshoo Singh, Hemant Kumar Singh, Kumar Nilankar

Abstract:

Major engineering constructions and foundations (e.g., dams, tunnels, bridges, underground caverns, etc.) in and around the Himalayan region of Uttarakhand are not only confined within hard and crystalline rocks but also stretched within weak and anisotropic rocks. While constructing within such anisotropic rocks, engineers more often encounter geotechnical complications such as structural instability, slope failure, and excessive deformation. These severities/complexities arise mainly due to inherent anisotropy such as layering/foliations, preferred mineral orientations, and geo-mechanical anisotropy present within rocks and vary when measured in different directions. Of all the inherent anisotropy present within the rocks, major geotechnical complexities mainly arise due to the inappropriate orientation of weak planes (bedding/foliation). Thus, Orientations of such weak planes highly affect the fracture patterns, failure mechanism, and strength of rocks. This has led to an improved understanding of the physico-mechanical behavior of anisotropic rocks with different orientations of weak planes. Therefore, in this study, block samples of phyllite belonging to the Chandpur Group of Lesser Himalaya were collected from the Srinagar area of Uttarakhand, India, to investigate the effect of foliation angles on physico-mechanical properties of the rock. Further, collected block samples were core drilled of diameter 50 mm at different foliation angles, β (angle between foliation plane and drilling direction), i.e., 0⁰, 30⁰, 60⁰, and 90⁰, respectively. Before the test, drilled core samples were oven-dried at 110⁰C to achieve uniformity. Physical and mechanical properties such as Seismic wave velocity, density, uniaxial compressive strength (UCS), point load strength (PLS), and Brazilian tensile strength (BTS) test were carried out on prepared core specimens. The results indicate that seismic wave velocities (P-wave and S-wave) decrease with increasing β angle. As the β angle increases, the number of foliation planes that the wave needs to pass through increases and thus causes the dissipation of wave energy with increasing β. Maximum strength for UCS, PLS, and BTS was found to be at β angle of 90⁰. However, minimum strength for UCS and BTS was found to be at β angle of 30⁰, which differs from PLS, where minimum strength was found at 0⁰ β angle. Furthermore, failure modes also correspond to the strength of the rock, showing along foliation and non-central failure as characteristics of low strength values, while multiple fractures and central failure as characteristics of high strength values. Thus, this study will provide a better understanding of the anisotropic features of phyllite for the purpose of major engineering construction and foundations within the Himalayan Region.

Keywords: anisotropic rocks, foliation angle, Physico-mechanical properties, phyllite, Himalayan region

Procedia PDF Downloads 51

Authors: Wakayama Shunya, Okubo Kazuya, Fujii Toru, Sakata Daisuke, Kado Noriyuki, Furutachi Hiroshi

Abstract:

The purpose of this study is to propose an effective method to improve frictional coefficient of modified shoe rubber soles with added glass fibers onto the icy and snowy road surfaces in order to prevent slip-and-fall accidents by the users. Added fibers in the rubber were uniformly tilted to the perpendicular direction of the frictional surface, where tilting angle was -60, -30, +30, +60, 90 degrees and 0 for usual specimen, respectively. It was found that horizontal arraignment was effective to improve the frictional coefficient when glass fibers were embedded in the shoe rubber, while the standing in normal direction of the embedded glass fibers on the shoe surface was also effective to do that once after they were exposed from the shoe rubber with its abrasion. These improvements were explained by the increase of stiffness against the shear deformation of the rubber at the critical frictional state and the enlargement of resistance force for extracting exposed fibers from the ice and snow, respectively. Current study suggested that effective arraignments in the tilting angle of the added fibers should be applied in designing rubber shoe soles to keep the safeties for uses in regions of cold climates.

Keywords: frictional coefficient, shoe soles, icy and snowy road, glass fibers, tilting angle

Procedia PDF Downloads 487

Authors: Kenan Morani, Esra Kaya Ayana

Abstract:

This study aimed to develop a novel pipeline for COVID-19 detection using a large and rigorously annotated database of computed tomography (CT) images. The pipeline consists of UNet-based segmentation, lung extraction, and a classification part, with the addition of optional slice removal techniques following the segmentation part. In this work, a batch normalization was added to the original UNet model to produce lighter and better localization, which is then utilized to build a full pipeline for COVID-19 diagnosis. To evaluate the effectiveness of the proposed pipeline, various segmentation methods were compared in terms of their performance and complexity. The proposed segmentation method with batch normalization outperformed traditional methods and other alternatives, resulting in a higher dice score on a publicly available dataset. Moreover, at the slice level, the proposed pipeline demonstrated high validation accuracy, indicating the efficiency of predicting 2D slices. At the patient level, the full approach exhibited higher validation accuracy and macro F1 score compared to other alternatives, surpassing the baseline. The classification component of the proposed pipeline utilizes a convolutional neural network (CNN) to make final diagnosis decisions. The COV19-CT-DB dataset, which contains a large number of CT scans with various types of slices and rigorously annotated for COVID-19 detection, was utilized for classification. The proposed pipeline outperformed many other alternatives on the dataset.

Keywords: classification, computed tomography, lung extraction, macro F1 score, UNet segmentation

Procedia PDF Downloads 122

Authors: Guoliang Lu, Changhou Lu, Xueyong Li

Abstract:

In action recognition, previous studies have demonstrated the effectiveness of using multiple features to improve the recognition performance. We focus on two practical issues: i) most studies use a direct way of concatenating/accumulating multi features to evaluate the similarity between two actions. This way could be too strong since each kind of feature can include different dimensions, quantities, etc; ii) in many studies, the employed classification methods lack of a flexible and effective mechanism to add new feature(s) into classification. In this paper, we explore an unified scheme based on recently-proposed multi-dimensional dynamic time warping (MD-DTW). Experiments demonstrated the scheme's effectiveness of combining multi-feature and the flexibility of adding new feature(s) to increase the recognition performance. In addition, the explored scheme also provides us an open architecture for using new advanced classification methods in the future to enhance action recognition.

Keywords: action recognition, multi features, dynamic time warping, feature combination

Procedia PDF Downloads 432

Authors: Vera Karla S. Caingles, Glen A. Lorenzo

Abstract:

Soil, as the main material of landslides, plays a vital role in landslide assessment. An efficient and accurate method of doing an assessment is significantly important to prevent damage of properties and loss of lives. The study has two phases: to establish an empirical correlation of the residual soil thickness with the slope angle and to investigate the geotechnical characteristics of residual soil. Digital Elevation Model (DEM) in Geographic Information System (GIS) was used to establish the slope map and to program sampling points for field investigation. Physical and index property tests were undertaken on the 20 soil samples obtained from the area with Pliocene-Pleistocene geology and different slope angle in Kibawe, Bukidnon. The regression analysis result shows that the best fitting model that can describe the soil thickness-slope angle relationship is an exponential function. The physical property results revealed that soils contain a high percentage of clay and silts ranges from 41% - 99.52%. Based on the index properties test results, the soil exhibits a high degree of plasticity and expansion but not collapsible. It is deemed that this compendium will serve as primary data for slope stability analysis and deterministic landslide assessment.

Keywords: collapsibility, correlation, expansiveness, landslide, plasticity

Procedia PDF Downloads 150

Authors: Evgeniya Orlova, Dmitriy Feoktistov, Geniy Kuznetsov

Abstract:

Spreading of a droplet over a solid substrate is a key phenomenon observed in the following engineering applications: thin film coating, oil extraction, inkjet printing, and spray cooling of heated surfaces. Droplet cooling systems are known to be more effective than film or rivulet cooling systems. It is caused by the greater evaporation surface area of droplets compared with the film of the same mass and wetting surface. And the greater surface area of droplets is connected with the curvature of the interface. Location of the droplets on the cooling surface influences on the heat transfer conditions. The close distance between the droplets provides intensive heat removal, but there is a possibility of their coalescence in the liquid film. The long distance leads to overheating of the local areas of the cooling surface and the occurrence of thermal stresses. To control the location of droplets is possible by changing the roughness, structure and chemical composition of the surface. Thus, control of spreading can be implemented. The most important characteristic of spreading of droplets on solid surfaces is a dynamic contact angle, which is a function of the contact line speed or capillary number. However, there is currently no universal equation, which would describe the relationship between these parameters. This paper presents the results of the experimental studies of water droplet spreading on metal substrates with different surface roughness. The effect of the droplet growth rate and the surface roughness on spreading characteristics was studied at low capillary numbers. The shadow method using high speed video cameras recording up to 10,000 frames per seconds was implemented. A droplet profile was analyzed by Axisymmetric Drop Shape Analyses techniques. According to change of the dynamic contact angle and the contact line speed three sequential spreading stages were observed: rapid increase in the dynamic contact angle; monotonous decrease in the contact angle and the contact line speed; and form of the equilibrium contact angle at constant contact line. At low droplet growth rate, the dynamic contact angle of the droplet spreading on the surfaces with the maximum roughness is found to increase throughout the spreading time. It is due to the fact that the friction force on such surfaces is significantly greater than the inertia force; and the contact line is pinned on microasperities of a relief. At high droplet growth rate the contact angle decreases during the second stage even on the surfaces with the maximum roughness, as in this case, the liquid does not fill the microcavities, and the droplet moves over the “air cushion”, i.e. the interface is a liquid/gas/solid system. Also at such growth rates pulsation of liquid flow was detected; and the droplet oscillates during the spreading. Thus, obtained results allow to conclude that it is possible to control spreading by using the surface roughness and the growth rate of droplets on surfaces as varied factors. Also, the research findings may be used for analyzing heat transfer in rivulet and drop cooling systems of high energy equipment.

Keywords: contact line speed, droplet growth rate, dynamic contact angle, shadow system, spreading

Procedia PDF Downloads 321

Authors: S. Chandrakaran, G. Govind

Abstract:

Stone columns are effectively used to improve bearing strength of soils and also for many geotechnical applications. In soft soils when stone columns are loaded they undergo large settlements due to insufficient lateral confinement. Use of geosynthetics encasement has proved to be a solution for this problem. In this paper, results of a laboratory experimental study carried out with model stone columns with and without encasement. Sand was used for making test beds, and grain size of soil varies from 0.075mm to 4.75mm. Woven geotextiles produced by Gareware ropes India with mass per unit area of 240gm/M2 and having tensile strength of 52KN/m is used for the present investigation. Tests were performed with large scale direct shear box and also using scaled laboratory plate load tests. Stone column of 50mm and 75mm is used for the present investigation. Diameter of stone column, size of stones used for making stone columns is varied in making stone column in the present study. Two types of stone were used namely small and bigger in size. Results indicate that there is an increase in angle of internal friction and also an increase in the shear strength of soil when stone columns are encased. With stone columns with 50mm dia, an average increase of 7% in shear strength and 4.6 % in angle of internal friction was achieved. When large stones were used increase in the shear strength was 12.2%, and angle of internal friction was increased to 5.4%. When the stone column diameter has increased to 75mm increase in shear strength and angle of internal friction was increased with smaller size of stones to 7.9 and 7.5%, and with large size stones, it was 7.7 and 5.48% respectively. Similar results are obtained in plate load tests, also.

Keywords: stone columns, encasement, shear strength, plate load test

Procedia PDF Downloads 228

Authors: Faci Youcef

Abstract:

In the present work, an experimental study is carried out using the digital image correlation (DIC) technique to analyze the damage and behavior of woven composite carbon/epoxy under tensile loading. The tension mechanisms associated with failure modes of bolted joints in advanced composites are studied, as well as displacement distribution and strain distribution. The evolution value of bolt angle inclination during tensile tests was studied. In order to compare the distribution of displacements and strains along the surface, figures of image mapping are made. Several factors that are responsible for the failure of fiber-reinforced polymer composite materials are observed. It was found that strain concentrations observed in the specimens can be used to identify full-field damage onset and to monitor damage progression during loading. Moreover, there is an interaction between laminate pattern, laminate thickness, fastener size and type, surface strain concentrations, and out-of-plane displacement. Conclusions include a failure analysis associated with bolt angle inclinations and supported by microscopic visualizations of the composite specimen. The DIC results can be used to develop and accurately validate numerical models.

Keywords: Carbone, woven, damage, digital image, bolted joint, the inclination of angle

Procedia PDF Downloads 67

Authors: Anukriti Kumar, Tanmay Singh, Dinesh Kumar Vishwakarma

Abstract:

Traffic control has been one of the most common and irritating problems since the time automobiles have hit the roads. Problems like traffic congestion have led to a significant time burden around the world and one significant solution to these problems can be the proper implementation of the Intelligent Transport System (ITS). It involves the integration of various tools like smart sensors, artificial intelligence, position technologies and mobile data services to manage traffic flow, reduce congestion and enhance driver's ability to avoid accidents during adverse weather. Road and traffic signs’ recognition is an emerging field of research in ITS. Classification problem of traffic signs needs to be solved as it is a major step in our journey towards building semi-autonomous/autonomous driving systems. The purpose of this work focuses on implementing an approach to solve the problem of traffic sign classification by developing a Convolutional Neural Network (CNN) classifier using the GTSRB (German Traffic Sign Recognition Benchmark) dataset. Rather than using hand-crafted features, our model addresses the concern of exploding huge parameters and data method augmentations. Our model achieved an accuracy of around 97.6% which is comparable to various state-of-the-art architectures.

Keywords: multiclass classification, convolution neural network, OpenCV

Procedia PDF Downloads 165

Authors: Ebtehal Aljedaani, Maha Aljohani

Abstract:

Privacy and security patterns are both important for developing software that protects users' data and privacy. Privacy patterns are designed to address common privacy problems, such as unauthorized data collection and disclosure. Security patterns are designed to protect software from attack and ensure reliability and trustworthiness. Using privacy and security patterns, software engineers can implement security and privacy by design principles, which means that security and privacy are considered throughout the software development process. These patterns are available to translate "security & privacy-by-design" into practical advice for software engineering. Previous research on privacy and security patterns has typically focused on one category of patterns at a time. This paper aims to bridge this gap by merging the two categories and identifying their similarities and differences. To do this, the authors conducted a systematic literature review of 25 research papers on privacy and security patterns. The papers were analysed based on the category of the pattern, the classification of the pattern, and the security requirements that the pattern addresses. This paper presents the results of a comprehensive review of privacy and security design patterns. The review is intended to help future IT designers understand the relationship between the two types of patterns and how to use them to design secure and privacy-preserving software. The paper provides a clear classification of privacy and security design patterns, along with examples of each type. The authors found that there is only one widely accepted classification of privacy design patterns, while there are several competing classifications of security design patterns. Three types of security design patterns were found to be the most commonly used.

Keywords: design patterns, security, privacy, classification of patterns, security patterns, privacy patterns

Procedia PDF Downloads 114

Authors: R. R. Ramsheeja, R. Sreeraj

Abstract:

For view the internal structures of the human body such as liver, brain, kidney etc have a wide range of different modalities for medical images are provided nowadays. Computer Tomography is one of the most significant medical image modalities. In this paper use CT liver images for study the use of automatic computer aided techniques to calculate the volume of the liver tumor. Segmentation method is used for the detection of tumor from the CT scan is proposed. Gaussian filter is used for denoising the liver image and Adaptive Thresholding algorithm is used for segmentation. Multiple Region Of Interest(ROI) based method that may help to characteristic the feature different. It provides a significant impact on classification performance. Due to the characteristic of liver tumor lesion, inherent difficulties appear selective. For a better performance, a novel proposed system is introduced. Multiple ROI based feature selection and classification are performed. In order to obtain of relevant features for Support Vector Machine(SVM) classifier is important for better generalization performance. The proposed system helps to improve the better classification performance, reason in which we can see a significant reduction of features is used. The diagnosis of liver cancer from the computer tomography images is very difficult in nature. Early detection of liver tumor is very helpful to save the human life.

Keywords: computed tomography (CT), multiple region of interest(ROI), feature values, segmentation, SVM classification

Procedia PDF Downloads 503

Authors: Yu Chen

Abstract:

This paper investigates the influence of flaw on failure process of rock-like material under uniaxial compression. In laboratory, the uniaxial compression tests of intact specimens and a series of specimens within single flaw were conducted. The inclination angle of flaws includes 0°, 15°, 30°, 45°, 60°, 75° and 90°. Based on the laboratory tests, the corresponding models of numerical simulation were built and loaded in PFC2D. After analysing the crack initiation and failure modes, deformation field, and energy mechanism for both laboratory tests and numerical simulation, it can be concluded that the influence of flaws on the failure process is determined by its inclination. The characteristic stresses increase as flaw angle rising basically. The tensile cracks develop from gentle flaws (α ≤ 30°) and the shear cracks develop from other flaws. The propagation of cracks changes during failure process and the failure mode of a specimen corresponds to the orientation of the flaw. A flaw has significant influence on the transverse deformation field at the middle of the specimen, except the 75° and 90° flaw sample. The input energy, strain energy and dissipation energy of specimens show approximate increase trends with flaw angle rising and it presents large difference on the energy distribution.

Keywords: failure pattern, particle deformation field, energy mechanism, PFC

Procedia PDF Downloads 202

Authors: Mayank Gupta, Siba Prasad Samal, Vasu Kakkirala

Abstract:

The internet world and its priorities have changed considerably in the last decade. Browsing on smart phones has increased manifold and is set to explode much more. Users spent considerable time browsing different websites, that gives a great deal of insight into user’s preferences. Instead of plain information classifying different aspects of browsing like Bookmarks, History, and Download Manager into useful categories would improve and enhance the user’s experience. Most of the classification solutions are server side that involves maintaining server and other heavy resources. It has security constraints and maybe misses on contextual data during classification. On device, classification solves many such problems, but the challenge is to achieve accuracy on classification with resource constraints. This on device classification can be much more useful in personalization, reducing dependency on cloud connectivity and better privacy/security. This approach provides more relevant results as compared to current standalone solutions because it uses content rendered by browser which is customized by the content provider based on user’s profile. This paper proposes a Naive Bayes based lightweight classification engine targeted for a resource constraint devices. Our solution integrates with Web Browser that in turn triggers classification algorithm. Whenever a user browses a webpage, this solution extracts DOM Tree data from the browser’s rendering engine. This DOM data is a dynamic, contextual and secure data that can’t be replicated. This proposal extracts different features of the webpage that runs on an algorithm to classify into multiple categories. Naive Bayes based engine is chosen in this solution for its inherent advantages in using limited resources compared to other classification algorithms like Support Vector Machine, Neural Networks, etc. Naive Bayes classification requires small memory footprint and less computation suitable for smartphone environment. This solution has a feature to partition the model into multiple chunks that in turn will facilitate less usage of memory instead of loading a complete model. Classification of the webpages done through integrated engine is faster, more relevant and energy efficient than other standalone on device solution. This classification engine has been tested on Samsung Z3 Tizen hardware. The Engine is integrated into Tizen Browser that uses Chromium Rendering Engine. For this solution, extensive dataset is sourced from dmoztools.net and cleaned. This cleaned dataset has 227.5K webpages which are divided into 8 generic categories ('education', 'games', 'health', 'entertainment', 'news', 'shopping', 'sports', 'travel'). Our browser integrated solution has resulted in 15% less memory usage (due to partition method) and 24% less power consumption in comparison with standalone solution. This solution considered 70% of the dataset for training the data model and the rest 30% dataset for testing. An average accuracy of ~96.3% is achieved across the above mentioned 8 categories. This engine can be further extended for suggesting Dynamic tags and using the classification for differential uses cases to enhance browsing experience.

Keywords: chromium, lightweight engine, mobile computing, Naive Bayes, Tizen, web browser, webpage classification

Procedia PDF Downloads 154

Authors: Doyin Afolabi, Phillip Adewole, Oladipupo Sennaike

Abstract:

Most well-known classifiers, including the decision tree algorithm, can make predictions on balanced datasets efficiently. However, the decision tree algorithm tends to be biased towards imbalanced datasets because of the skewness of the distribution of such datasets. To overcome this problem, this study proposes a weighted decision tree algorithm that aims to remove the bias toward the majority class and prevents the reduction of majority observations in imbalance datasets classification. The proposed weighted decision tree algorithm was tested on three imbalanced datasets- cancer dataset, german credit dataset, and banknote dataset. The specificity, sensitivity, and accuracy metrics were used to evaluate the performance of the proposed decision tree algorithm on the datasets. The evaluation results show that for some of the weights of our proposed decision tree, the specificity, sensitivity, and accuracy metrics gave better results compared to that of the ID3 decision tree and decision tree induced with minority entropy for all three datasets.

Keywords: data mining, decision tree, classification, imbalance dataset

Procedia PDF Downloads 115

Authors: Eiman Kattan

Abstract:

This study aims to evaluate the impact of classifying labelled remote sensing images conventional neural network (CNN) architecture, i.e., AlexNet on different land cover scenarios based on two remotely sensed datasets from different point of views such as the computational time and performance. Thus, a set of experiments were conducted to specify the effectiveness of the selected convolutional neural network using two implementing approaches, named fully trained and fine-tuned. For validation purposes, two remote sensing datasets, AID, and RSSCN7 which are publicly available and have different land covers features were used in the experiments. These datasets have a wide diversity of input data, number of classes, amount of labelled data, and texture patterns. A specifically designed interactive deep learning GPU training platform for image classification (Nvidia Digit) was employed in the experiments. It has shown efficiency in training, validation, and testing. As a result, the fully trained approach has achieved a trivial result for both of the two data sets, AID and RSSCN7 by 73.346% and 71.857% within 24 min, 1 sec and 8 min, 3 sec respectively. However, dramatic improvement of the classification performance using the fine-tuning approach has been recorded by 92.5% and 91% respectively within 24min, 44 secs and 8 min 41 sec respectively. The represented conclusion opens the opportunities for a better classification performance in various applications such as agriculture and crops remote sensing.

Keywords: conventional neural network, remote sensing, land cover, land use

Procedia PDF Downloads 356

Authors: Arian Hosseini, Mahmudul Hasan

Abstract:

To address the increasing need for efficient and accurate content moderation, we propose an efficient and lightweight deep classification ensemble structure. Our approach is based on a combination of simple visual features, designed for high-accuracy classification of violent content with low false positives. Our ensemble architecture utilizes a set of lightweight models with narrowed-down color features, and we apply it to both images and videos. We evaluated our approach using a large dataset of explosion and blast contents and compared its performance to popular deep learning models such as ResNet-50. Our evaluation results demonstrate significant improvements in prediction accuracy, while benefiting from 7.64x faster inference and lower computation cost. While our approach is tailored to explosion detection, it can be applied to other similar content moderation and violence detection use cases as well. Based on our experiments, we propose a "think small, think many" philosophy in classification scenarios. We argue that transforming a single, large, monolithic deep model into a verification-based step model ensemble of multiple small, simple, and lightweight models with narrowed-down visual features can possibly lead to predictions with higher accuracy.

Keywords: deep classification, content moderation, ensemble learning, explosion detection, video processing

Procedia PDF Downloads 37

Authors: Mohammad Tarek Al Muallim, Ozhan Duzenli, Ceyhun Ilguy

Abstract:

Harbor protection systems are so important. The need for automatic protection systems has increased over the last years. Diver detection active sonar has great significance. It used to detect underwater threats such as divers and autonomous underwater vehicle. To automatically detect such threats the sonar image is processed by algorithms. These algorithms used to detect, track and classify of underwater objects. In this work, divers tracking and classification algorithm is improved be proposing a robust wake detection method. To detect objects the sonar images is normalized then segmented based on fixed threshold. Next, the centroids of the segments are found and clustered based on distance metric. Then to track the objects linear Kalman filter is applied. To reduce effect of noise and creation of false tracks, the Kalman tracker is fine tuned. The tuning is done based on our active sonar specifications. After the tracks are initialed and updated they are subjected to a filtering stage to eliminate the noisy and unstable tracks. Also to eliminate object with a speed out of the diver speed range such as buoys and fast boats. Afterwards the result tracks are subjected to a classification stage to deiced the type of the object been tracked. Here the classification stage is to deice wither if the tracked object is an open circuit diver or a close circuit diver. At the classification stage, a small area around the object is extracted and a novel wake detection method is applied. The morphological features of the object with his wake is extracted. We used support vector machine to find the best classifier. The sonar training images and the test images are collected by ARMELSAN Defense Technologies Company using the portable diver detection sonar ARAS-2023. After applying the algorithm to the test sonar data, we get fine and stable tracks of the divers. The total classification accuracy achieved with the diver type is 97%.

Keywords: harbor protection, diver detection, active sonar, wake detection, diver classification

Procedia PDF Downloads 229

Authors: Salima Smiti, Ines Gasmi, Makram Soui

Abstract:

Credit risk is the most important issue for financial institutions. Its assessment becomes an important task used to predict defaulter customers and classify customers as good or bad payers. To this objective, numerous techniques have been applied for credit risk assessment. However, to our knowledge, several evaluation techniques are black-box models such as neural networks, SVM, etc. They generate applicants’ classes without any explanation. In this paper, we propose to assess credit risk using rules classification method. Our output is a set of rules which describe and explain the decision. To this end, we will compare seven classification algorithms (JRip, Decision Table, OneR, ZeroR, Fuzzy Rule, PART and Genetic programming (GP)) where the goal is to find the best rules satisfying many criteria: accuracy, sensitivity, and specificity. The obtained results confirm the efficiency of the GP algorithm for German and Australian datasets compared to other rule-based techniques to predict the credit risk.

Keywords: credit risk assessment, classification algorithms, data mining, rule extraction

Procedia PDF Downloads 168

Authors: Yulong Wang, Yuan Yan Tang, Cuiming Zou, Lina Yang

Abstract:

This paper presents a novel sparse representation method for robust pattern classification. Generalized orthogonal matching pursuit (GOMP) is a recently proposed efficient sparse representation technique. However, GOMP adopts the mean square error (MSE) criterion and assign the same weights to all measurements, including both severely and slightly corrupted ones. To reduce the limitation, we propose an information-theoretic GOMP (ITGOMP) method by exploiting the correntropy induced metric. The results show that ITGOMP can adaptively assign small weights on severely contaminated measurements and large weights on clean ones, respectively. An ITGOMP based classifier is further developed for robust pattern classification. The experiments on public real datasets demonstrate the efficacy of the proposed approach.

Keywords: correntropy induced metric, matching pursuit, pattern classification, sparse representation

Procedia PDF Downloads 349

Authors: Qi Xiu, Hiromu Hota, Yohsuke Ishii, Takuya Oda

Abstract:

Recently, collectable manufacturing data are rapidly increasing. On the other hand, mega recall is getting serious as a social problem. Under such circumstances, there are increasing needs for preventing mega recalls by defect analysis such as root cause analysis and abnormal detection utilizing manufacturing data. However, the time to classify strings in manufacturing data by traditional method is too long to meet requirement of quick defect analysis. Therefore, we present String Length Distribution Classification method (SLDC) to correctly classify strings in a short time. This method learns character features, especially string length distribution from Product ID, Machine ID in BOM and asset list. By applying the proposal to strings in actual manufacturing data, we verified that the classification time of strings can be reduced by 80%. As a result, it can be estimated that the requirement of quick defect analysis can be fulfilled.

Keywords: string classification, data quality, feature selection, probability distribution, string length

Procedia PDF Downloads 311

Authors: Samiah Alammari, Nassim Ammour

Abstract:

When providing a massive number of tasks successively to a deep learning process, a good performance of the model requires preserving the previous tasks data to retrain the model for each upcoming classification. Otherwise, the model performs poorly due to the catastrophic forgetting phenomenon. To overcome this shortcoming, we developed a successful continual learning deep model for remote sensing hyperspectral image regions classification. The proposed neural network architecture encapsulates two trainable subnetworks. The first module adapts its weights by minimizing the discrimination error between the land-cover classes during the new task learning, and the second module tries to learn how to replicate the data of the previous tasks by discovering the latent data structure of the new task dataset. We conduct experiments on HSI dataset Indian Pines. The results confirm the capability of the proposed method.

Keywords: continual learning, data reconstruction, remote sensing, hyperspectral image segmentation

Procedia PDF Downloads 246

Authors: Brahim Mahfoud, Ali Bendjaghlouli

Abstract:

Natural convection is simulated in a truncated cone filled with nanofluid. Inclined and top walls have constant temperature where the heat source is located on the bottom wall of the conical container which is thermally insulated. A finite volume approach is used to solve the governing equations using the SIMPLE algorithm for different parameters such as Rayleigh number, inclination angle of inclined walls of the enclosure and heat source length. The results showed an enhancement in cooling system by using a nanofluid, when conduction regime is assisted. The inclination angle of inclined sidewall and heat source length affect the heat transfer rate and the maximum temperature.

Keywords: heat source, truncated cone, nanofluid, natural convection

Procedia PDF Downloads 360

Authors: Jularat Chumnaul

Abstract:

In forensic science, corpses from various homicides are different; there are both complete and incomplete, depending on causes of death or forms of homicide. For example, some corpses are cut into pieces, some are camouflaged by dumping into the river, some are buried, some are burned to destroy the evidence, and others. If the corpses are incomplete, it can lead to the difficulty of personally identifying because some tissues and bones are destroyed. To specify gender of the corpses from skeletal remains, the most precise method is DNA identification. However, this method is costly and takes longer so that other identification techniques are used instead. The first technique that is widely used is considering the features of bones. In general, an evidence from the corpses such as some pieces of bones, especially the skull and pelvis can be used to identify their gender. To use this technique, forensic scientists are required observation skills in order to classify the difference between male and female bones. Although this technique is uncomplicated, saving time and cost, and the forensic scientists can fairly accurately determine gender by using this technique (apparently an accuracy rate of 90% or more), the crucial disadvantage is there are only some positions of skeleton that can be used to specify gender such as supraorbital ridge, nuchal crest, temporal lobe, mandible, and chin. Therefore, the skeletal remains that will be used have to be complete. The other technique that is widely used for gender specifying in forensic science and archeology is skeletal measurements. The advantage of this method is it can be used in several positions in one piece of bones, and it can be used even if the bones are not complete. In this study, the classification and cluster analysis are applied to this technique, including the Kth Nearest Neighbor Classification, Classification Tree, Ward Linkage Cluster, K-mean Cluster, and Two Step Cluster. The data contains 507 particular individuals and 9 skeletal measurements (diameter measurements), and the performance of five methods are investigated by considering the apparent error rate (APER). The results from this study indicate that the Two Step Cluster and Kth Nearest Neighbor method seem to be suitable to specify gender from human skeletal remains because both yield small apparent error rate of 0.20% and 4.14%, respectively. On the other hand, the Classification Tree, Ward Linkage Cluster, and K-mean Cluster method are not appropriate since they yield large apparent error rate of 10.65%, 10.65%, and 16.37%, respectively. However, there are other ways to evaluate the performance of classification such as an estimate of the error rate using the holdout procedure or misclassification costs, and the difference methods can make the different conclusions.

Keywords: skeletal measurements, classification, cluster, apparent error rate

Procedia PDF Downloads 241

Authors: Evan Lowhorn, Rocio Alba-Flores

Abstract:

The purpose of this work is to develop a method for classifying hand signals and using the output in a drone control algorithm. To achieve this, methods based on Convolutional Neural Networks (CNN) were applied. CNN's are a subset of deep learning, which allows grid-like inputs to be processed and passed through a neural network to be trained for classification. This type of neural network allows for classification via imaging, which is less intrusive than previous methods using biosensors, such as EMG sensors. Classification CNN's operate purely from the pixel values in an image; therefore they can be used without additional exteroceptive sensors. A development bench was constructed using a desktop computer connected to a high-definition webcam mounted on a scissor arm. This allowed the camera to be pointed downwards at the desk to provide a constant solid background for the dataset and a clear detection area for the user. A MATLAB script was created to automate dataset image capture at the development bench and save the images to the desktop. This allowed the user to create their own dataset of 12,000 images within three hours. These images were evenly distributed among seven classes. The defined classes include forward, backward, left, right, idle, and land. The drone has a popular flip function which was also included as an additional class. To simplify control, the corresponding hand signals chosen were the numerical hand signs for one through five for movements, a fist for land, and the universal “ok” sign for the flip command. Transfer learning with PyTorch (Python) was performed using a pre-trained 18-layer residual learning network (ResNet-18) to retrain the network for custom classification. An algorithm was created to interpret the classification and send encoded messages to a Ryze Tello drone over its 2.4 GHz Wi-Fi connection. The drone’s movements were performed in half-meter distance increments at a constant speed. When combined with the drone control algorithm, the classification performed as desired with negligible latency when compared to the delay in the drone’s movement commands.

Keywords: classification, computer vision, convolutional neural networks, drone control

Procedia PDF Downloads 197

Authors: Konstanca Nikolajevic, Nicolas Belanger, David Duvivier, Rabie Ben Atitallah, Abdelhakim Artiba

Abstract:

Finding the optimal 3D path of an aerial vehicle under flight mechanics constraints is a major challenge, especially when the algorithm has to produce real-time results in flight. Kinematics models and Pythagorian Hodograph curves have been widely used in mobile robotics to solve this problematic. The level of difficulty is mainly driven by the number of constraints to be saturated at the same time while minimizing the total length of the path. In this paper, we suggest a pragmatic algorithm capable of saturating at the same time most of dimensioning helicopter 3D trajectories’ constraints like: curvature, curvature derivative, torsion, torsion derivative, climb angle, climb angle derivative, positions. The trajectories generation algorithm is able to generate versatile complex 3D motion primitives feasible by a helicopter with parameterization of the curvature and the climb angle. An upper ”motion primitives’ concatenation” algorithm is presented based. In this article we introduce a new way of designing three-dimensional trajectories based on what we call the ”Dubins gliding symmetry conjecture”. This extremely performing algorithm will be soon integrated to a real-time decisional system dealing with inflight safety issues.

Keywords: robotics, aerial robots, motion primitives, helicopter

Procedia PDF Downloads 607

Authors: Enemeri George Uweiyohowo

Abstract:

Improved achievement with respect to output control of photovoltaic (PV) systems is one of the major focus of PV in recent times. This is evident to its low carbon emission and efficiency. Power failure or outage from commercial providers, in general, does not promote development to public and private sector, these basically limit the development of industries. The need for a well-structured PV system is of importance for an efficient and cost-effective monitoring system. The purpose of this paper is to validate the maximum power point of an off-grid PV system taking into consideration the most effective tilt and orientation angles for PV's in the southern hemisphere. This paper is based on analyzing the system using a solar charger with MPPT from a pulse width modulation (PWM) perspective. The power conditioning device chosen is a solar charger with MPPT. The practical setup consists of a PV panel that is set to an orientation angle of 0∘N, with a corresponding tilt angle of 36∘, 26∘ and 16∘. Preliminary results include regression analysis (normal probability plot) showing the maximum power point in the system as well the best tilt angle for maximum power point tracking.

Keywords: poly-crystalline PV panels, information technology (IT), maximum power point tracking (MPPT), pulse width modulation (PWM)

Procedia PDF Downloads 204