Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 2627

World Academy of Science, Engineering and Technology

[Computer and Information Engineering]

Online ISSN : 1307-6892

2627 A Novel Framework toward CO2 Reduction Using Smart Parking System

Authors: Muhammad Sajjad, Rahman Ali, Farkhund Iqbal, Mohammed Hussain, Zulfiqar Ahmad Khan

Abstract:

Nowadays, CO2 (Carbon Dioxide) emission is increasing every day in urban areas all over the world due to many reasons like burning coal, oil, gas etc. The main factors involving its higher rate of emission are vehicles in urban. Each driver wants closer car parking at many institutions such as hospitals, store, and offices etc. These travelers’ vehicles consume fuel and produce CO2, while searching for the nearest location of parking car to empty slot or sometimes even driving around a parking lot for a while until they find a vacant parking slot. For that reason, it can be cover long distance, wasting time and fuel. In this paper, we developed an automatic smart parking system which is helping to reduce, fuel consumption, searching time and CO2 emission. The proposed smart parking system is based on resource contain device Raspberry Pi which take advantage of IoT and integrated with cloud server. The proposed system using GPS system of the vehicle to get the position and wireless communication system to communicate with cloud server. A smart phone application is developed to remotely find the nearest parking, slot status and booking of slot where searching of empty slot is based on merge sort algorithm. The experimental results show that the proposed smart parking framework provide user friendly interface and efficiently reduce CO2 emission.

Keywords:

Procedia PDF Downloads 1
2626 Predicting Shortage of Hospital Beds during COVID-19 Pandemic in United States

Authors: Saeed Ahmadian, Saba Ebrahimi, Hedie Ashrafi

Abstract:

World-wide spread of coronavirus grows the concern about planning for the excess demand of hospital services in response to COVID-19 pandemic. The surge in the hospital services demand beyond the current capacity leads to shortage of ICU beds and ventilators in some parts of US. In this study, we forecast the required number of hospital beds and possible shortage of beds in US during COVID-19 pandemic to be used in the planning and hospitalization of new cases. In this paper, we used a data on COVID-19 deaths and patients’ hospitalization besides the data on hospital capacities and utilization in US from publicly available sources and national government websites. we used a novel ensemble modelling of deep learning networks, based on stacking different linear and non-linear layers to predict the shortage in hospital beds. The results showed that our proposed approach can predict the excess hospital beds demand very well and this can be helpful in developing strategies and plans to mitigate this gap.

Keywords: Deep learning, COVID-19, ensembled models, hospital capacity planning

Procedia PDF Downloads 1
2625 An Ensemble Deep Learning Architecture for Imbalanced Classification of Thoracic Surgery Patients

Authors: Saba Ebrahimi, Saeed Ahmadian, Hedie Ashrafi

Abstract:

Selecting appropriate patients for surgery is one of the main issues in thoracic surgery (TS). Both short-term and long-term risks and benefits of surgery must be considered in the patient selection criteria. There are some limitations in the existing datasets of TS patients because of missing values of attributes and imbalanced distribution of survival classes. In this study, a novel ensemble architecture of deep learning networks is proposed based on stacking different linear and non-linear layers to deal with imbalance datasets. The categorical and numerical features are split using different layers with ability to shrink the unnecessary features. Then, after extracting the insight from the raw features, a novel biased-kernel layer is applied to reinforce the gradient of the minority class and cause the network to be trained better comparing the current methods. Finally, the performance and advantages of our proposed model over the existing models are examined for predicting patient survival after thoracic surgery using a real-life clinical data for lung cancer patients.

Keywords: Lung cancer, Deep learning, imbalanced classification, ensemble models, TS patient selection

Procedia PDF Downloads 1
2624 Visual Template Detection and Compositional Automatic Regular Expression Generation for Business Invoice Extraction

Authors: Anthony Proschka, Deepak Mishra, Merlyn Ramanan, Zurab Baratashvili

Abstract:

Small and medium-sized businesses receive over 160 billion invoices every year. Since these documents exhibit many subtle differences in layout and text, extracting structured fields such as sender name, amount and VAT rate from them automatically is an open research question. In this paper, existing work in template-based document extraction is extended and a system is devised that is able to reliably extract all required fields for up to 70% of all documents in the data set, more than any other previously reported method. Novel approaches are described for 1) detecting through visual features which template a given document belongs to, 2) automatically generating extraction rules for a given new template by composing regular expressions from multiple components and 3) computing confidence scores that indicate the accuracy of the automatic extractions. The system can generate templates with as little as one training sample, and only requires the ground truth field values instead of detailed annotations such as bounding boxes that are hard to obtain. The system is deployed and used inside a commercial accounting software.

Keywords:

Procedia PDF Downloads 1
2623 Prediction of Covid-19 Cases and Current Situation of Italy and Its Different Regions Using Machine Learning Algorithm

Authors: Shafait Hussain Ali

Abstract:

Since its outbreak in China, the Covid_19 19 disease has been caused by the corona virus SARS N coyote 2. Italy was the first Western country to be severely affected, and the first country to take drastic measures to control the disease. In start of December 2019, the sudden outbreaks of the Coronary Virus Disease was caused by a new Corona 2 virus (SARS-CO2) of acute respiratory syndrome in china city Wuhan. The World Health Organization declared the epidemic a public health emergency of international concern on January 30, 2020,. On February 14, 2020, 49,053 laboratory-confirmed deaths and 1481 deaths have been reported worldwide. The threat of the disease has forced most of the governments to implement various control measures. Therefore it becomes necessary to analyze the Italian data very carefully, in particular to investigates and to find out the present condition and the number of infected persons in the form of positive cases, death, hospitalized or some other features of infected persons will clear in simple form. So used such a model that will clearly shows the real facts and figures and also understandable to every readable person which can get some real benefit after reading it. The model used must includes(total positive cases, current positive cases, hospitalized patients, death, recovered peoples frequency rates ) all features that explains and clear the wide range facts in very simple form and helpful to administration of that country.

Keywords:

Procedia PDF Downloads 1
2622 Seeing Living Atoms with Electrons, One at a Time: 2D Image Processing in Real Space with Poisson Statistics

Authors: Geoffrey Woollard

Abstract:

We can see living atoms with electrons. Electron microscopes use hundreds of thousands of volts to speed up single electrons to three quarters the speed of light. At such high speeds electrons have picometer wavelengths and can resolve the distances between atoms in biomolecules. Electron cryomicroscopy (cryoEM) won the 2017 Nobel prize in Chemistry, and pharmaceutical companies have invested in this technology for applications like structure based drug design. After biochemical sample preparation of a purified biomolecule, two dimensional images are collected on electron microscopes. Images of single biomolecules are very noisy and computer algorithms average tens of thousands to millions of 2D images to reconstruct a 3D discrete scalar map that represents the Coulomb density (what the electron feels). Historically cryoEM computational workflows have drawn from digital signal and image processing theory that assume a Gaussian statistics in the noise model. This has certain benefits for pedagogical and numerical purposes. However, the recent advances underlying the resolution revolution in cryoEM leveraged the single electron detection capabilities of modern direct electron detectors. Individual frames of an exposure are captured over an exposure time of seconds, and can be aligned afterwards. In practice, even the movie frames are averages. Although the underlying statistics are better modeled with the Poisson distribution, at high enough total doses, this is well approximated by the Gaussian distribution. However at low doses, this approximation breaks down. In order to work with extremely low doses (ie movie frames, or the detection events that are averaged into these movie frames) Poisson statistics could be used for problems like motion correction and 2D classification. Here a forward model of cryoEM image formation is presented that assumes a Poisson distribution. The observed image is assumed to be the sum of an underlying signal, with a pixel specific parameter (ie the lambda/mean/variance), and another Poisson noise parameter that is shared between all the pixels, and all the observed images. Using this image formation model, synthetic data is generated and an expectation maximization algorithm for 2D image classification is developed, which has an intuitive Bayesian interpretation. Situations of numerical overflow and underflow are considered, as well as the suitable data types. Analytical equations are used to refactor for analytical equations for numerical stability. It is hoped that this work will encourage others in the field to develop new algorithms that deal directly with the individual low dose movie frames and underlying direct electron counts.

Keywords: Digital Signal Processing, Structural biology, Bayesian Inference, Protein Biochemistry, expectation-maximization algorithm, computational image analysis, Poisson statistics, single particle electron cryomicroscopy

Procedia PDF Downloads 1
2621 Facial Emotion Recognition (FER) with Convolutional Neural Network Based Architecture

Authors: Koray U. Erbas

Abstract:

Neural Networks are appealing for many applications since they are able learn complex non-linear relationships between input and output data. As the number of neuros and layers in a neural network increase, it is possible to represent more complex relationships with automatically extracted features. Nowadays Deep Neural Networks (DNNs) are widely used in Computer Vision problems such as; classification, object detection, segmentation image editing etc. In this work, Facial Emotion Recognition task is performed is by proposed Convolutional Neural Network (CNN) based DNN architecture using FER2013 Dataset. Moreover, the effects of different hyper-parameters (activation function, kernel size, initializer, batch size and network size) are investigated and ablation study results for Pooling Layer, Dropout and Batch Normalization is presented.

Keywords: Deep learning, convolutional neural network, deep learning based FER, facial emotion recognition

Procedia PDF Downloads 1
2620 Transportation Mode Classification Using GPS Coordinates and Recurrent Neural Networks

Authors: Taylor Kolody, Farkhund Iqbal, Rabia Batool, Benjamin Fung, Mohammed Hussaeni, Saiqa Aleem

Abstract:

The rising threat of climate change has led to an increase in public awareness and care about our collective and individual environmental impact. A key component of this impact is our use of cars and other polluting forms of transportation, but it is often difficult for an individual to know how severe this impact is. While there are applications that offer this feedback, they require manual entry of what transportation mode was used for a given trip, which can be burdensome. In order to alleviate this shortcoming, a data from the 2016 TRIPlab datasets has been used to train a variety of machine learning models to automatically recognize the mode of transportation. The accuracy of 89.6% is achieved using single deep neural network model with Gated Recurrent Unit (GRU) architecture applied directly to trip data points over 4 primary classes, namely walking, public transit, car, and bike. These results are comparable in accuracy to results achieved by others using ensemble methods and require far less computation when classifying new trips. The lack of trip context data, e.g., bus routes, bike paths, etc., and the need for only a single set of weights make this an appropriate methodology for applications hoping to reach a broad demographic and have responsive feedback.

Keywords:

Procedia PDF Downloads 1
2619 Fuzzy-Machine Learning Models for the Prediction of Fire Outbreak: A Comparative Analysis

Authors: Uduak Umoh, Imo Eyoh, Emmauel Nyoho

Abstract:

This paper compares fuzzy-machine learning algorithms such as Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) for the predicting cases of fire outbreak. The paper uses the fire outbreak dataset with three features (Temperature, Smoke, and Flame). The data is pre-processed using Interval Type-2 Fuzzy Logic (IT2FL) algorithm. Min-Max Normalization and Principal Component Analysis (PCA) are used to predict feature labels in the dataset, normalize the dataset, and select relevant features respectively. The output of the pre-processing is a dataset with two principal components (PC1 and PC2). The pre-processed dataset is then used in the training of the aforementioned machine learning models. K-fold (with K=10) cross-validation method is used to evaluate the performance of the models using the matrices – ROC (Receiver Operating Curve), Specificity, and Sensitivity. The model is also tested with 20% of the dataset. The validation result shows KNN is the better model for fire outbreak detection with an ROC value of 0.99878, followed by SVM with an ROC value of 0.99753.

Keywords: Principal Component Analysis, Machine Learning Algorithms, support vector machine, Interval Type-2 Fuzzy Logic, Fire Outbreak, K-Nearest Neighbour

Procedia PDF Downloads 1
2618 A Survey of the Applications of Sentiment Analysis

Authors: Pingping Lin, Xudong Luo

Abstract:

Natural language often conveys emotions of speakers. Therefore, sentiment analysis on what people say is prevalent in the field of natural language process and has great application value in many practical problems. Thus, to help people understand its application value, in this paper, we survey various applications of sentiment analysis, including the ones in online business and offline business as well as other types of its applications. In particular, we give some application examples in intelligent customer service systems in China. Besides, we compare the applications of sentiment analysis on Twitter, Weibo, Taobao and Facebook, and discusses some challenges. Finally, we point out the challenges faced in the applications of sentiment analysis and the work that is worth being studied in the future.

Keywords: natural language processing, Application, sentiment analysis, online comments

Procedia PDF Downloads 1
2617 Development of Fake News Model Using Machine Learning through Natural Language Processing

Authors: Sajjad Ahmed, Knut Hinkelmann, Flavio Corradini

Abstract:

Fake news detection research is still in the early stage as this is a relatively new phenomenon in the interest raised by society. Machine learning helps to solve the complex problems and to build AI systems nowadays and especially in those cases where we have tacit knowledge or the knowledge that is not known. We used machine learning algorithms and for identification of fake news we applied three classifiers like Passive Aggressive, Naïve Bayes and Support Vector Machine. Simple classification is not completely correct in fake news detection because classification methods are not specialized for fake news. With the integration of machine learning and text-based processing, we can detect fake news and build classifiers that can classify the news data. Text classification mainly focuses on extracting various features of text and after that incorporating those features into classification. The big challenge in this area is the lack of an efficient way to differentiate between fake or non fake due to unavailability of corpora. We applied three different machine learning classifiers on two publicly available datasets. Experimental analysis based on the existing dataset that indicates very encouraging and improved performance.

Keywords: Machine Learning, natural language processing, classification techniques, fake news detection

Procedia PDF Downloads 1
2616 A Generative Adversarial Framework for Bounding Confounded Causal Effects

Authors: Lu Zhang, Yaowei Hu, Yongkai Wu, Xintao Wu

Abstract:

Causal inference from observational data is receiving wide applications in many fields. However, unidentifiable situations, where causal effects cannot be uniquely computed from observational data, pose critical barriers to applying causal inference to complicated real applications. In this paper, we develop a bounding method for estimating the average causal effect (ACE) under unidentifiable situations due to hidden confounders. We propose to parameterize the unknown exogenous random variables and structural equations of a causal model using neural networks and implicit generative models. Then, with an adversarial learning framework, we search the parameter space to explicitly traverse causal models that agree with the given observational distribution and find those that minimize or maximize the ACE to obtain its lower and upper bounds. The proposed method does not make any assumption about the data generating process and the type of the variables. Experiments using both synthetic and real-world datasets show the effectiveness of the method.

Keywords: average causal effect, hidden confounding, bound estimation, generative adversarial learning

Procedia PDF Downloads 1
2615 Physical Objects Authentication with Dot-Based 2D Code

Authors: Michal Glet, Kamil Kaczynski

Abstract:

Counterfeit goods and documents are a global problem, which needs more and more sophisticated methods of resolving it. Existing techniques using watermarking or embedding symbols on object are not suitable for all use cases. To address those special needs, we created complete system allowing authentication of paper documents and physical objects with flat surface. Objects are marked using orientation independent and resistant to camera noise 2D graphic codes, named DotAuth. Based on the identifier stored in 2D code, system is able to perform basic authentication and allows to conduct more sophisticated analysis methods, e.g., relying on augmented reality and physical properties of object. In this paper, we present the complete architecture, algorithms, and applications of our system. Results of the features, comparison of the proposed solution, and other products are presented as well, pointing to the existence of many advantages that increase usability and efficiency in the means of protecting physical objects.

Keywords: Security, Authentication, anti-forgery, paper documents

Procedia PDF Downloads 1
2614 Convolutional Neural Networks for Feature Extraction and Automated Target Recognition in Synthetic Aperture Radar Images

Authors: Ying Zhao, John Geldmacher, Christopher Yerkes

Abstract:

Advances in the development of deep neural networks and other machine learning algorithms combined with ever more powerful hardware and the huge amount of data available on the internet has led to a revolution in ML research and applications. These advances present massive potential and opportunity for the military applications such as the analysis of Synthetic Aperture Radar (SAR) imagery. Synthetic Aperture Radar imagery is a useful tool capable of capturing high resolution images regardless of cloud coverage and at night. However, there is a limited amount of publicly available SAR data to train a machine learning model. This paper shows how to successfully dissect, modify, and re-architect cross-domain object recognition models such as the VGG-16 model, transfer learning models from the ImageNet, and the k-nearest neighbor (kNN) classifier. The paper demonstrates that the combinations of these factors can significantly and effectively improve the automated object recognition (ATR) of SAR clean and noisy images. The paper shows a potentially inexpensive, accurate, transfer and unsurpervised learning SAR ATR system when data labels are scarce and data are noisy, simplifying the whole recognition for the tactical operation requirements in the area of SAR ATR.

Keywords: Deep learning, Transfer Learning, kNN, SAR images, k-nearest neighbor, synthetic aperture radar images, VGG-16

Procedia PDF Downloads 1
2613 Face Recognition Using Body-Worn Camera: Dataset and Baseline Algorithms

Authors: Ali Almadan, Anoop Krishnan, Ajita Rattani

Abstract:

Facial recognition is a widely adopted technology in surveillance, border control, healthcare, banking services, and lately, in mobile user authentication with Apple introducing “Face ID” moniker with iPhone X. A lot of research has been conducted in the area of face recognition on datasets captured by surveillance cameras, DSLR, and mobile devices. Recently, face recognition technology has also been deployed on body-worn cameras to keep officers safe, enabling situational awareness and providing evidence for trial. However, limited academic research has been conducted on this topic so far, without the availability of any publicly available datasets with a sufficient sample size. This paper aims to advance research in the area of face recognition using body-worn cameras. To this aim, the contribution of this work is two-fold: (1) collection of a dataset consisting of a total of 136,939 facial images of 102 subjects captured using body-worn cameras in in-door and daylight conditions and (2) evaluation of various deep-learning architectures for face identification on the collected dataset. Experimental results suggest a maximum True Positive Rate(TPR) of 99.86% at False Positive Rate(FPR) of 0.000 obtained by SphereFace based deep learning architecture in daylight condition. The collected dataset and the baseline algorithms will promote further research and development. A downloadable link of the dataset and the algorithms is available by contacting the authors.

Keywords: Face Recognition, Deep learning, Person Identification, body-worn cameras

Procedia PDF Downloads 1
2612 The Vertex Degree Distance of One Vertex Union of the Cycle and the Star

Authors: Ying Wang, Haiyan Xie, Aoming Zhang

Abstract:

The degree distance of a graph is a graph invariant that is more sensitive than the Wiener index. In this paper, we calculate the vertex degree distances of one vertex union of the cycle and the star, and the degree distance of one vertex union of the cycle and the star. These results lay a foundation for further study on the extreme value of the vertex degree distances, and the distribution of the vertices with the extreme value in one vertex union of the cycle and the star.

Keywords: graph, degree distance, vertex-degree-distance, one vertex union of a cycle and a star

Procedia PDF Downloads 1
2611 Emotion Classification Using Recurrent Neural Network and Scalable Pattern Mining

Authors: Jaishree Ranganathan, Muthupriya Shanmugakani Velsamy, Shamika Kulkarni, Angelina Tzacheva

Abstract:

Emotions play an important role in everyday life. Analyzing these emotions or feelings from social media platforms like Twitter, Facebook, Blogs, and Forums based on user comments and reviews plays an important role in various factors. Some of them include brand monitoring, marketing strategies, reputation, and competitor analysis. The opinions or sentiments mined from such data helps to understand the current state of the user. It does not directly provide intuitive insights on what actions to be taken to benefit the end user or business. Actionable Pattern Mining method provides suggestions or actionable recommendations on what changes or actions need to be taken in order to benefit the end user. In this paper, we propose automatic classification of emotions in twitter data using Recurrent Neural Network - Gated Recurrent Unit. We achieve training accuracy of 87.58% and validation accuracy of 86.16%. Also, we extract action rules with respect to the user emotion, that help provide actionable suggestion.

Keywords:

Procedia PDF Downloads 1
2610 An Improved Multiple Scattering Reflectance Model Based on Specular V-Cavity

Authors: Hongbin Yang, Mingxue Liao, Changwen Zheng, Mengyao Kong, Chaohui Liu

Abstract:

Microfacet-based reflection models are widely used to model light reflections for rough surfaces. Microfacet models have become the standard surface material building block for describing specular components with varying roughness; and yet, while they possess many desirable properties as well as produce convincing results, their design ignores important sources of scattering, which can cause a significant loss of energy. Specifically, they only simulate the single scattering on the microfacets and ignore the subsequent interactions. As the roughness increases, the interaction will become more and more important. So a multiple-scattering microfacet model based on specular V-cavity is presented for this important open problem. However, it spends much unnecessary rendering time because of setting the same number of scatterings for different roughness surfaces. In this paper, we design a geometric attenuation term G to compute the BRDF (Bidirectional reflection distribution function) of multiple scattering of rough surfaces. Moreover, we consider determining the number of scattering by deterministic heuristics for different roughness surfaces. As a result, our model produces a similar appearance of the objects with the state of the art model with significantly improved rendering efficiency. Finally, we derive a multiple scattering BRDF based on the original microfacet framework.

Keywords: multiple scattering, bidirectional reflection distribution function, BRDF, geometric attenuation term, V-cavity model

Procedia PDF Downloads 1
2609 Intrusion Detection Based on Graph Oriented Big Data Analytics

Authors: Ahlem Abid, Farah Jemili

Abstract:

Intrusion detection has been the subject of numerous studies in industry and academia, but cyber security analysts always want greater precision and global threat analysis to secure their systems in cyberspace. To improve intrusion detection system, the visualisation of the security events in form of graphs and diagrams is important to improve the accuracy of alerts. In this paper, we propose an approach of an IDS based on cloud computing, big data technique and using a machine learning graph algorithm which can detect in real time different attacks as early as possible. We use the MAWILab intrusion detection dataset . We choose Microsoft Azure as a unified cloud environment to load our dataset on. We implement the k2 algorithm which is a graphical machine learning algorithm to classify attacks. Our system showed a good performance due to the graphical machine learning algorithm and spark structured streaming engine.

Keywords: Machine Learning, Intrusion Detection, graph, Apache Spark Streaming, k2 algorithm, MAWILab, Microsoft Azure Cloud

Procedia PDF Downloads 1
2608 Green Thumb Engineering - Explainable Artificial Intelligence for Managing IoT Enabled Houseplants

Authors: Antti Nurminen, Avleen Malhi

Abstract:

Significant progress in intelligent systems in combination with exceedingly wide application domains having machine learning as the core technology are usually opaque, non-intuitive, and commonly complex for human users. We use innovative IoT technology which monitors and analyzes moisture, humidity, luminosity and temperature levels to assist end users for optimization of environmental conditions for their houseplants. For plant health monitoring, we construct a system yielding the Normalized Difference Vegetation Index (NDVI), supported by visual validation by users. We run the system for a selected plant, basil, in varying environmental conditions to cater for typical home conditions, and bootstrap our AI with the acquired data. For end users, we implement a web based user interface which provides both instructions and explanations.

Keywords: Intelligent Agent, IoT, NDVI, explainable artificial intelligence

Procedia PDF Downloads 1
2607 Scalable Action Mining for Recommendations to Reduce Hospital Readmission

Authors: Angelina Tzacheva, Arunkumar Bagavathi, Apurwa Apurwa

Abstract:

Hospital re-admission problem is one of the longtime issues of healthcares in USA. Unplanned re-admissions to hospitals not only increase cost for patients, but also for hospitals and taxpayers. Action mining is one of the data mining approaches to recommend actions to undertake for an organization or individual to achieve required condition or status. Undertaking such actionable recommendations incur some form of cost to users. The actionable recommendation system fails when the recommended actions are cost wise unendurable or non-profitable and uninteresting to the end user. Finding low cost actionable patterns in larger datasets is a time consuming and requires a scalable approach. In this work, we propose a scalable action mining method to recommend hospitals and taxpayers on what actions would potentially reduce patient readmission to hospitals at lowest costs. Most importantly we incorporated graph search methods to extract low cost actionable patterns. We use the Healthcare Cost and Utilization Project(HCUP) databases to evaluate our approach. All our proposed scalable approaches are cloud based and use Apache Spark to handle data processing and to make recommendations.

Keywords: Data Mining, Scalable, action mining, hospital readmission

Procedia PDF Downloads 1
2606 Impact of Network Workload between Virtualization Solutions on a Testbed Environment for Cybersecurity Learning

Authors: Kevin Fernagut, Olivier Flauzac, Erick Mauricio Gallegos Robledo, Florent Nolot

Abstract:

The adoption of modern lightweight virtualization often comes with new threats and network vulnerabilities. This paper seeks to assess this with a different approach studying the behavior of a testbed built with tools such as Kernel-Based Virtual Machine (KVM), Linux Containers (LXC) and Docker, by performing stress tests within a platform where students experiment simultaneously with cyber-attacks, and thus observe the impact on the campus network and also find the best solution for cyber-security learning. Interesting outcomes can be found in the literature comparing these technologies. It is, however, difficult to find results of the effects on the global network where experiments are carried out. Our work shows that other physical hosts and the faculty network were impacted while performing these trials. The problems found are discussed, as well as security solutions and the adoption of new network policies.

Keywords: cybersecurity, Performance, Virtualization, Isolation, Cyberattacks, Virtual Machines, containerization, containers

Procedia PDF Downloads 1
2605 Churn Prediction for Telecommunication Industry Using Artificial Neural Networks

Authors: Ulas Vural, M. Ergun Okay, E. Mesut Yildiz

Abstract:

Telecommunication service providers demand accurate and precise prediction of customer churn probabilities to increase the effectiveness of their customer relation services. The large amount of customer data owned by the service providers is suitable for analysis by machine learning methods. In this study, expenditure data of customers are analyzed by using an artificial neural network (ANN). The ANN model is applied to the data of customers with different billing duration. The proposed model successfully predicts the churn probabilities at 83\% accuracy for only three months expenditure data and the prediction accuracy increases up to 89\% when the nine month data is used. The experiments also show that the accuracy of ANN model increases on an extended feature set with information of the changes on the bill amounts.

Keywords: Artificial Neural Networks, Deep learning, Customer Relationship Management, telecom industry, churn prediction

Procedia PDF Downloads 1
2604 A Review of Polymorphic Malware Detection Techniques

Authors: Joma Alrzini, Diane Pennington

Abstract:

Despite the continuous updating of anti-detection systems for malicious programs (malware), malware has moved to an abnormal threat level; it is being generated and spread faster than before. One of the most serious challenges faced by anti-detection malware programs is an automatic mutation in the code; this is called polymorphic malware via the polymorphic engine. In this case, it is difficult to block the impact of signature-based detection. Hence new techniques have to be used to analyse modern malware. One of these techniques is machine learning algorithms in a virtual machine (VM) that can run the packed malicious file and analyse it dynamically through automated testing of the code. Moreover, recent research used image processing techniques with deep learning framework as a hybrid method with two analysis types and extracting a feature engineering approach in the analysis process to detect polymorphic malware efficiently. This paper presents a brief review of the latest applied techniques against this type of malware with more focus on the machine learning method for analysing and detecting polymorphic malware. It will discuss briefly the merits and demerits of it.

Keywords: anti-detection, polymorphic automated testing, abnormal threats, packed malicious file

Procedia PDF Downloads 1
2603 Efficient Positioning of Data Aggregation Point for Wireless Sensor Network

Authors: Sifat Rahman Ahona, Rifat Tasnim, Naima Hassan

Abstract:

Data aggregation is a helpful technique for reducing the data communication overhead in wireless sensor network. One of the important tasks of data aggregation is positioning of the aggregator points. There are a lot of works done on data aggregation. But, efficient positioning of the aggregators points is not focused so much. In this paper, authors are focusing on the positioning or the placement of the aggregation points in wireless sensor network. Authors proposed an algorithm to select the aggregators positions for a scenario where aggregator nodes are more powerful than sensor nodes.

Keywords: Data Communication, Wireless Sensor Network, data aggregation, aggregation point

Procedia PDF Downloads 1
2602 Artificial Neural Network for Forecasting of Daily Reservoir Inflow: Case Study of the Kotmale Reservoir in Sri Lanka

Authors: E. U. Dampage, Ovindi D. Bandara, Vinushi S. Waraketiya, Samitha S. R. De Silva, Yasiru S. Gunarathne

Abstract:

The knowledge of water inflow figures is paramount in decision making on the allocation for consumption for numerous purposes; irrigation, hydropower, domestic and industrial usage, and flood control. The understanding of how reservoir inflows are affected by different climatic and hydrological conditions is crucial to enable effective water management and downstream flood control. In this research, we propose a method using a Long Short Term Memory (LSTM) Artificial Neural Network (ANN) to assist the aforesaid decision-making process. The Kotmale reservoir, which is the uppermost reservoir in the Mahaweli reservoir complex in Sri Lanka, was used as the test bed for this research. The ANN uses the runoff in the Kotmale reservoir catchment area and the effect of Sea Surface Temperatures (SST) to make a forecast for seven days ahead. Three types of ANN are tested; Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), and LSTM. The extensive field trials and validation endeavors found that the LSTM ANN provides superior performance in the aspects of accuracy and latency.

Keywords: Neural Network, multi-layer perceptron, MLP, convolutional neural network, long short-term memory, LSTM, CNN, inflow

Procedia PDF Downloads 1
2601 Machine Learning Strategies for Data Extraction from Unstructured Documents in Financial Services

Authors: Delphine Vendryes, Dushyanth Sekhar, Baojia Tong, Matthew Theisen, Chester Curme

Abstract:

Much of the data that inform the decisions of governments, corporations and individuals are harvested from unstructured documents. Data extraction is defined here as a process that turns non-machine-readable information into a machine-readable format that can be stored, for instance, in a database. In financial services, introducing more automation in data extraction pipelines is a major challenge. Information sought by financial data consumers is often buried within vast bodies of unstructured documents, which have historically required thorough manual extraction. Automated solutions provide faster access to non-machine-readable datasets, in a context where untimely information quickly becomes irrelevant. Data quality standards cannot be compromised, so automation requires high data integrity. This multifaceted task is broken down into smaller steps: ingestion, table parsing (detection and structure recognition), text analysis (entity detection and disambiguation), schema-based record extraction, user feedback incorporation. Selected intermediary steps are phrased as machine learning problems. Solutions leveraging cutting-edge approaches from the fields of computer vision (e.g. table detection) and natural language processing (e.g. entity detection and disambiguation) are proposed.

Keywords: Computer Vision, Finance, Machine Learning, Information Retrieval, natural language processing, Entity Recognition

Procedia PDF Downloads 1
2600 Variational Explanation Generator: Generating Explanation for Natural Language Inference using Variational Auto-Encoder

Authors: Zhen Cheng, Xinyu Dai, Shujian Huang, Jiajun Chen

Abstract:

Recently, explanatory natural language inference has attracted much attention for the interpretability of logic relationship prediction, which also known as explanation generation for Natural Language Inference (NLI). Existing explanation generators based on discriminative Encoder-Decoder architecture have achieved noticeable results. However, we find that these discriminative generators usually generate explanations with correct evidence but incorrect logic semantic. It is due to that logic information is implicitly encoded in the premise-hypothesis pairs and difficult to model. Actually, logic information identically exists between premise-hypothesis pair and explanation. And it is easy to extract logic information that is explicitly contained in the target explanation. Hence we assume that there exists a latent space of logic information while generating explanations. Specifically, we propose a generative model called Variational Explanation Generator (VariationalEG) with a latent variable to model this space. Training with the guide of explicit logic information in target explanations, latent variables in VariationalEG could capture the implicit logic information in premise-hypothesis pairs effectively. Additionally, to tackle the problem of posterior collapse while training VariaztionalEG, we propose a simple yet effective approach called Logic Supervision on the latent variable to force it to encode logic information. Experiments on explanation generation benchmark—explanation-Stanford Natural Language Inference (e-SNLI) demonstrate that the proposed VariationalEG achieves significant improvement compared to previous studies and yields a state-of-the-art result. Furthermore, we perform the analysis of generated explanations to demonstrate the effect of the latent variable.

Keywords: natural language inference, Generative Model, explanation generation, variational auto-encoder

Procedia PDF Downloads 1
2599 Image Inpainting Model with Small-Sample Size Based on Generative Adversary Network and Genetic Algorithm

Authors: Jiawen Wang, Qijun Chen

Abstract:

The performance of most machine-learning methods for image inpainting depends on the quantity and quality of the training samples. However, it is very expensive or even impossible to obtain a great number of training samples in many scenarios. In this paper, an image inpainting model based on a generative adversary network (GAN) is constructed for the cases when the number of training samples is small. Firstly, a feature extraction network (F-net) is incorporated into the GAN network to utilize the available information of the inpainting image. The weighted sum of the extracted feature and the random noise acts as the input to the generative network (G-net). The proposed network can be trained well even when the sample size is very small. Secondly, in the phase of the completion for each damaged image, a genetic algorithm is designed to search an optimized noise input for G-net; based on this optimized input, the parameters of the G-net and F-net are further learned (Once the completion for a certain damaged image ends, the parameters restore to its original values obtained in the training phase) to generate an image patch that not only can fill the missing part of the damaged image smoothly but also has visual semantics.

Keywords: Genetic Algorithm, image inpainting, generative adversary nets, small-sample size

Procedia PDF Downloads 1
2598 Use of Interpretable Evolved Search Query Classifiers for Sinhala Documents

Authors: Prasanna Haddela

Abstract:

Document analysis is a well matured yet still active research field, partly as a result of the intricate nature of building computational tools but also due to the inherent problems arising from the variety and complexity of human languages. Breaking down language barriers is vital in enabling access to a number of recent technologies. This paper investigates the application of document classification methods to new Sinhalese datasets. This language is geographically isolated and rich with many of its own unique features. We will examine the interpretability of the classification models with a particular focus on the use of evolved Lucene search queries generated using a Genetic Algorithm (GA) as a method of document classification. We will compare the accuracy and interpretability of these search queries with other popular classifiers. The results are promising and are roughly in line with previous work on English language datasets.

Keywords: Genetic Algorithm, evolved search queries, Sinhala document classification, Lucene Sinhala analyzer, interpretable text classification

Procedia PDF Downloads 1