Search results for: encrypted traffic classification

Authors: Pahirangan Sivapatham, Barbara Esser, Andreas Grimmel

Abstract:

In times of limited public funds and, in particular, an increased social, environmental awareness, as well as the limited availability of construction materials, sustainable and resource-saving pavement management system, is becoming more and more important. Therefore, the knowledge about the condition of the structural substances, particularly bearing capacity and its consideration while planning the maintenance measures of the subordinate network, i.e., state and municipal roads unavoidable. According to the experience, the recommended ride speed of the Traffic Speed Deflectometer (TSD) shall be higher than 40 km/h. Holding of this speed on the intra-urban roads is nearly not possible because of intersections and traffic lights as well as the speed limit. A sufficient background of experience for the evaluation of bearing capacity measurements with TSD in the range of lower speeds is not available yet. The aim of this study is to determine the possible lowest ride speed of the TSD while the bearing capacity measurement on the intra-urban roads. The manufacturer of the TSD used in this study states that the measurements can be conducted at a ride speed of higher than 5 km/h. It is well known that with decreasing ride speed, the viscous fractions in the response of the asphalt pavement increase. This must be taken into account when evaluating the bearing capacity data. In the scope of this study, several measurements were carried out at different speeds between 10 km/h and 60 km/h on the selected intra-urban roads with Pavement-Scanner of the University of Wuppertal, which is equipped with TSD. Pavement-Scanner is able to continuously determine the deflections of asphalt roads in flowing traffic at speeds of up to 80 km/h. The raw data is then aggregated to 10 m mean values so that, as a rule, a bearing capacity characteristic value can be determined for each 10 m road section. By means of analysing of obtained test results, the quality and validity of the determined data rate subject to the riding speed of TSD have been determined. Moreover, the data and pictures of the additional measuring systems of Pavement-Scanners such as High-Speed Road Monitor, Ground Penetration Radar and front cameras can be used to determine and eliminate irregularities in the pavement, which could influence the bearing capacity.

Keywords: bearing capacity measurement, traffic speed deflectometer, inter-urban roads, Pavement-Scanner, structural substance

Procedia PDF Downloads 229

Authors: Abdullah Bal

Abstract:

This paper presents a one-class classification (OCC) technique based on Fukunaga-Koontz Transform (FKT) for binary classification problems. The FKT is originally a powerful tool to feature selection and ordering for two-class problems. To utilize the standard FKT for data domain description problem (i.e., one-class classification), in this paper, a set of non-class samples which exist outside of positive class (target class) describing boundary formed with limited training data has been constructed synthetically. The tunnel-like decision boundary around upper and lower border of target class samples has been designed using statistical properties of feature vectors belonging to the training data. To capture higher order of statistics of data and increase discrimination ability, the proposed method, termed one-class FKT (OC-FKT), has been extended to its nonlinear version via kernel machines and referred as OC-KFKT for short. Multiple kernel learning (MKL) is a favorable family of machine learning such that tries to find an optimal combination of a set of sub-kernels to achieve a better result. However, the discriminative ability of some of the base kernels may be low and the OC-KFKT designed by this type of kernels leads to unsatisfactory classification performance. To address this problem, the quality of sub-kernels should be evaluated, and the weak kernels must be discarded before the final decision making process. MKL/OC-FKT and selective MKL/OC-FKT frameworks have been designed stimulated by ensemble learning (EL) to weight and then select the sub-classifiers using the discriminability and diversities measured by eigenvalue ratios. The eigenvalue ratios have been assessed based on their regions on the FKT subspaces. The comparative experiments, performed on various low and high dimensional data, against state-of-the-art algorithms confirm the effectiveness of our techniques, especially in case of small sample size (SSS) conditions.

Keywords: ensemble methods, fukunaga-koontz transform, kernel-based methods, multiple kernel learning, one-class classification

Procedia PDF Downloads 7

Authors: Steffy Maria Joseph, Abdu Rahiman V, Abdul Hameed K. M.

Abstract:

Online handwritten character recognition is a challenging field in Artificial Intelligence. The classification success rate of current techniques decreases when the dataset involves similarity and complexity in stroke styles, number of strokes and stroke characteristics variations. Malayalam is a complex south indian language spoken by about 35 million people especially in Kerala and Lakshadweep islands. In this paper, we consider the significant feature extraction for the similar stroke styles of Malayalam. This extracted feature set are suitable for the recognition of other handwritten south indian languages like Tamil, Telugu and Kannada. A classification scheme based on support vector machines (SVM) is proposed to improve the accuracy in classification and recognition of online malayalam handwritten characters. SVM Classifiers are the best for real world applications. The contribution of various features towards the accuracy in recognition is analysed. Performance for different kernels of SVM are also studied. A graphical user interface has developed for reading and displaying the character. Different writing styles are taken for each of the 44 alphabets. Various features are extracted and used for classification after the preprocessing of input data samples. Highest recognition accuracy of 97% is obtained experimentally at the best feature combination with polynomial kernel in SVM.

Keywords: SVM, matlab, malayalam, South Indian scripts, onlinehandwritten character recognition

Procedia PDF Downloads 567

Authors: Shelby Simpson, William Stanley, Namir Naba, Xiaodi Wang

Abstract:

Both t-SNE and UMAP are brand new state of art tools to predominantly preserve the local structure that is to group neighboring data points together, which indeed provides a very informative visualization of heterogeneity in our data. In this research, we develop a t-SNE and UMAP base neural network image classification algorithm to embed the original dataset to a corresponding low dimensional dataset as a preprocessing step, then use this embedded database as input to our specially designed neural network classifier for image classification. We use the fashion MNIST data set, which is a labeled data set of images of clothing objects in our experiments. t-SNE and UMAP are used for dimensionality reduction of the data set and thus produce low dimensional embeddings. Furthermore, we use the embeddings from t-SNE and UMAP to feed into two neural networks. The accuracy of the models from the two neural networks is then compared to a dense neural network that does not use embedding as an input to show which model can classify the images of clothing objects more accurately.

Keywords: t-SNE, UMAP, fashion MNIST, neural networks

Procedia PDF Downloads 192

Authors: George Kyriakopoulos, Photini Pazartzis, Anthi Koskina, Crystalie Bourcha

Abstract:

The need for securing safe access to and return from outer space, as well as ensuring the viability of outer space operations, maintains vivid the debate over the promotion of organization of space traffic through a Space Traffic Management System (STM). The proliferation of outer space activities in recent years as well as the dynamic emergence of the private sector has gradually resulted in a diverse universe of actors operating in outer space. The said developments created an increased adverse impact on outer space sustainability as the case of the growing number of space debris clearly demonstrates. The above landscape sustains considerable threats to outer space environment and its operators that need to be addressed by a combination of scientific-technological measures and regulatory interventions. In this context, recourse to recent technological advancements and, in particular, to Artificial Intelligence (AI) and machine learning systems, could achieve exponential results in promoting space traffic management with respect to collision avoidance as well as launch and re-entry procedures/phases. New technologies can support the prospects of a successful space traffic management system at an international scale by enabling, inter alia, timely, accurate and analytical processing of large data sets and rapid decision-making, more precise space debris identification and tracking and overall minimization of collision risks and reduction of operational costs. What is more, a significant part of space activities (i.e. launch and/or re-entry phase) takes place in airspace rather than in outer space, hence the overall discussion also involves the highly developed, both technically and legally, international (and national) Air Traffic Management System (ATM). Nonetheless, from a regulatory perspective, the use of AI for the purposes of space traffic management puts forward implications that merit particular attention. Key issues in this regard include the delimitation of AI-based activities as space activities, the designation of the applicable legal regime (international space or air law, national law), the assessment of the nature and extent of international legal obligations regarding space traffic coordination, as well as the appropriate liability regime applicable to AI-based technologies when operating for space traffic coordination, taking into particular consideration the dense regulatory developments at EU level. In addition, the prospects of institutionalizing international cooperation and promoting an international governance system, together with the challenges of establishment of a comprehensive international STM regime are revisited in the light of intervention of AI technologies. This paper aims at examining regulatory implications advanced by the use of AI technology in the context of space traffic management operations and its key correlating concepts (SSA, space debris mitigation) drawing in particular on international and regional considerations in the field of STM (e.g. UNCOPUOS, International Academy of Astronautics, European Space Agency, among other actors), the promising advancements of the EU approach to AI regulation and, last but not least, national approaches regarding the use of AI in the context of space traffic management, in toto. Acknowledgment: The present work was co-funded by the European Union and Greek national funds through the Operational Program "Human Resources Development, Education and Lifelong Learning " (NSRF 2014-2020), under the call "Supporting Researchers with an Emphasis on Young Researchers – Cycle B" (MIS: 5048145).

Keywords: artificial intelligence, space traffic management, space situational awareness, space debris

Procedia PDF Downloads 247

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 56

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 346

Authors: M. O. Adda

Abstract:

In this paper, we propose a topology called Zoned fat tree (Z-Fat tree) which is a further extension to the classical fat trees. The extension relates to the provision of extra degree of connectivity to maximize the number of deployed ports per routing nodes, and hence increases the bisection bandwidth especially for slimmed fat trees. The extra links, when classical routing is used, tend, in deterministic environment, to be under-utilized for some traffic patterns, hence achieving poor performance. We suggest two versions of a dynamic round robin scheme that outperforms the classical D-mod-k and S-mod-K routing and show by simulation that our proposal utilize all the extra added links to the classical fat tree, and achieve better performance for general applications.

Keywords: deterministic routing, fat tree, interconnection, traffic pattern

Procedia PDF Downloads 478

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 125

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 434

Authors: Siham G. Farag

Abstract:

The main objective of this paper is to provide a new methodology for road safety assessment in Oman through the development of suitable accident prediction models. GLM technique with Poisson or NBR using SAS package was carried out to develop these models. The paper utilized the accidents data of 31 un-signalized T-intersections during three years. Five goodness-of-fit measures were used to assess the overall quality of the developed models. Two types of models were developed separately; the flow-based models including only traffic exposure functions, and the full models containing both exposure functions and other significant geometry and traffic variables. The results show that, traffic exposure functions produced much better fit to the accident data. The most effective geometric variables were major-road mean speed, minor-road 85th percentile speed, major-road lane width, distance to the nearest junction, and right-turn curb radius. The developed models can be used for intersection treatment or upgrading and specify the appropriate design parameters of T- intersections. Finally, the models presented in this thesis reflect the intersection conditions in Oman and could represent the typical conditions in several countries in the middle east area, especially gulf countries.

Keywords: accidents prediction models (APMs), generalized linear model (GLM), T-intersections, Oman

Procedia PDF Downloads 266

Authors: Oliver Ohneiser, Francesca De Crescenzio, Gianluca Di Flumeri, Jan Kraemer, Bruno Berberian, Sara Bagassi, Nicolina Sciaraffa, Pietro Aricò, Gianluca Borghini, Fabio Babiloni

Abstract:

An increasing degree of automation in air traffic will also change the role of the air traffic controller (ATCO). ATCOs will fulfill significantly more monitoring tasks compared to today. However, this rather passive role may lead to Out-Of-The-Loop (OOTL) effects comprising vigilance decrement and less situation awareness. The project MINIMA (Mitigating Negative Impacts of Monitoring high levels of Automation) has conceived a system to control and mitigate such OOTL phenomena. In order to demonstrate the MINIMA concept, an experimental simulation set-up has been designed. This set-up consists of two parts: 1) a Task Environment (TE) comprising a Terminal Maneuvering Area (TMA) simulator as well as 2) a Vigilance and Attention Controller (VAC) based on neurophysiological data recording such as electroencephalography (EEG) and eye-tracking devices. The current vigilance level and the attention focus of the controller are measured during the ATCO’s active work in front of the human machine interface (HMI). The derived vigilance level and attention trigger adaptive automation functionalities in the TE to avoid OOTL effects. This paper describes the full-scale experimental set-up and the component development work towards it. Hence, it encompasses a pre-test whose results influenced the development of the VAC as well as the functionalities of the final TE and the two VAC’s sub-components.

Keywords: automation, human factors, air traffic controller, MINIMA, OOTL (Out-Of-The-Loop), EEG (Electroencephalography), HMI (Human Machine Interface)

Procedia PDF Downloads 377

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 125

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 505

Authors: Tesfaye Dagne, Dagmawit Solomon, Firmaye Bogale, Yosef Gebreyohannes, Samson Mideksa, Mamuye Hadis, Desalegn Ararso, Ermias Woldie, Tsegaye Getachew, Sabit Ababor, Zelalem Kebede

Abstract:

Globally, road traffic accident (RTA) is causing millions of deaths and injuries every year. It is one of the leading causes of death among people of all age groups and the problem is worse among young reproductive age group. Moreover the problem is increasing with an increasing number of vehicles. The majority of the problem happen in low and middle income countries (LMIC), even if the number of vehicles in these countries is low compared to their population. So, the objective of this paper is to summarize the best available evidence on interventions that can reduce road traffic accidents in low and middle income countries (LMIC). Method: A rapid evidence synthesis approach adapted from the SURE Rapid Response Service was applied to search, appraise and summarize the best available evidence on effective intervention in reducing road traffic injury. To answer the question under review, we searched for relevant studies from databases including PubMed, the Cochrane Library, TRANSPORT, Health system evidence, Epistemonikos, and SUPPORT summary. The following key terms were used for searching: Road traffic accident, RTA, Injury, Reduc*, Prevent*, Minimiz*, “Low and middle-income country”, LMIC. We found 18 articles through a search of different databases mentioned above. After screening for the titles and abstracts of the articles, four of them which satisfy the inclusion criteria were included in the final review. Then we appraised and graded the methodological quality of systematic reviews that are deemed to be highly relevant using AMSTAR. Finding: The identified interventions to reduce road traffic accidents were legislation and enforcement, public awareness/education, speed control/ rumble strips, road improvement, mandatory motorcycle helmet, graduated driver license, street lighting. Legislation and Enforcement: Legislation focusing on mandatory motorcycle helmet usage, banning cellular phone usage when driving, seat belt laws, decreasing the legal blood alcohol content (BAC) level from 0.06 g/L to 0.02 g/L bring the best result where enforcement is there. Public Awareness/Education: focusing on seat belt use, child restraint use, educational training in health centers and schools/universities, and public awareness with media through the distribution of videos, posters/souvenirs, and pamphlets are effective in the short run. Speed Control: through traffic calming bumps, or speed bumps, rumbled strips are effective in reducing accidents and fatality. Mandatory Motorcycle Helmet: is associated with reduction in mortality. Graduated driver’s license (GDL): reduce road traffic injury by 19%. Street lighting: is a low-cost intervention which may reduce road traffic accidents.

Keywords: evidence synthesis, injury, rapid review, reducing, road traffic accident

Procedia PDF Downloads 159

Authors: Yuxiao Jiang, Dong Ma, Mengyu Zhan, Yingxia Yun

Abstract:

China now is entering the phase of old aging and the aging speed is on acceleration. The proportion of the aged citizens in the urban areas is getting larger. Traveling on foot is one of the main travel methods for the old, but the bad walking environment and unsystematic pedestrian system cause inconvenience to the old who travel on foot. The paper analyzes the behavioral characteristics and the spatial preferences of the elderly group as well as the new traffic demands of them, finding out that some problems exist in the current pedestrian system. Thus, the paper proposes strategies in the areas of planning and design, and engineering technology so as to promote the traffic environment and perfect the pedestrian system for the old people.

Keywords: old aging, pedestrian system, perfection strategies, travel characteristics, future demand

Procedia PDF Downloads 385

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 160

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 119

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 361

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 42

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 235

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 172

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 352

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 312

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 252

Authors: Prabhat Kashyap, Krishan Kumar

Abstract:

Delhi, the capital of India, is one of the most populated and polluted city among the world. In terms of air quality, Delhi’s air is degrading day by day & becomes worst of any major city in the world. The role of biogenic volatile organic compounds (BVOCs) is not much studied in cities like Delhi as a culprit for degraded air quality. They not only play a critical role in rural areas but also determine the atmospheric chemistry of urban areas as well. Particularly, Isoprene (2-methyl 1,3-butadiene, C5H8) is the single largest emitted compound among other BVOCs globally, that influence the tropospheric ozone chemistry in urban environment as the ozone forming potential of isoprene is very high. It is mainly emitted by vegetation & a small but significant portion is also released by vehicular exhaust of petrol operated vehicles. This study investigates the spatial and temporal variations of quantitative measurements of isoprene emissions along with different traffic tracers in 2 different seasons (post-monsoon & winter) at four different locations of Delhi. For the quantification of anthropogenic and biogenic isoprene, two sites from traffic intersections (Punjabi Bagh & CRRI) and two sites from vegetative locations (JNU & Yamuna Biodiversity Park) were selected in the vicinity of isoprene emitting tree species like Ficus religiosa, Dalbergia sissoo, Eucalyptus species etc. The concentrations of traffic tracers like benzene, toluene were also determined & their robust ratios with isoprene were used to differentiate anthropogenic isoprene with biogenic portion at each site. The ozone forming potential (OFP) of all selected species along with isoprene was also estimated. For collection of intra-day samples (3 times a day) in each season, a pre-conditioned fenceline monitoring (FLM) carbopack X thermal desorption tubes were used and further analysis was done with Gas chromatography attached with mass spectrometry (GC-MS). The results of the study proposed that the ambient air isoprene is always higher in post-monsoon season as compared to winter season at all the sites because of high temperature & intense sunlight. The maximum isoprene emission flux was always observed during afternoon hours in both seasons at all sites. The maximum isoprene concentration was found to be 13.95 ppbv at Biodiversity Park during afternoon time in post monsoon season while the lower concentration was observed as low as 0.07 ppbv at the same location during morning hours in winter season. OFP of isoprene at vegetation sites is very high during post-monsoon because of high concentrations. However, OFP for other traffic tracers were high during winter seasons & at traffic locations. Furthermore, high correlation between isoprene emissions with traffic volume at traffic sites revealed that a noteworthy share of its emission also originates from road traffic.

Keywords: biogenic VOCs, isoprene emission, anthropogenic isoprene, urban vegetation

Procedia PDF Downloads 114

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 245

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 204

Authors: P. S. Jagadeesh Kumar, Yang Yung, Wenli Hu

Abstract:

Speech emotion classification is a dominant research field in finding a sturdy and profligate classifier appropriate for different real-life applications. This effort accentuates on classifying different emotions from speech signal quarried from the features related to pitch, formants, energy contours, jitter, shimmer, spectral, perceptual and temporal features. Tensor deep stacking neural networks were supported to examine the factors that influence the classification success rate. Facial electromyography signals were composed of several forms of focuses in a controlled atmosphere by means of audio-visual stimuli. Proficient facial electromyography signals were pre-processed using moving average filter, and a set of arithmetical features were excavated. Extracted features were mapped into consistent emotions using bilinear mapping. With facial electromyography signals, a database comprising diverse emotions will be exposed with a suitable fine-tuning of features and training data. A success rate of 92% can be attained deprived of increasing the system connivance and the computation time for sorting diverse emotional states.

Keywords: speech emotion classification, tensor deep stacking neural networks, facial electromyography, bilinear mapping, audio-visual stimuli

Procedia PDF Downloads 249

Authors: Jae-Hyun Ro, Yong-Jun Kim, Eui-Hak Lee, Hyoung-Kyu Song

Abstract:

Mobile communication has been developing very rapidly since it appeared. However, although mobile communication market has been rapidly developing, many mobile users are not offered good quality of service (QoS) due to increment of the amount of data traffic. Recently, femtocell is very hot issue in mobile communication because femtocell can solve the problems of data traffic and offer better QoS to mobile users. However, the deployment of femtocell in existing macrocell coverage area is not so simple due to the influence of inter-cell-interference (ICI) with existing macrocell. Thus, this paper proposes femtocell scheme which is able to reduce the influence of ICI to deploy femtocell easily.

Keywords: CDD, femtocell, interference, macrocell, OFDM

Procedia PDF Downloads 499