Pub Date : 2021-04-06DOI: 10.1109/CAIDA51941.2021.9425200
S. Qaisar, M. Krichen, A. Mihoub
The technological advancement is evolving the human–computer interaction (HCI). The goal is to ameliorate the HCI to a level where computers can be interacted in a natural way. It is a demanding aim and keeps the contemporary HCI systems complex and challenging. This paper aims to develop an effective hand gesture identification piloted HCI. It is realizable by three stages of preprocessing, features extraction and classification. The system functionality is studied by using a colored images database. Each incoming instance presents a hand gesture. Firstly it is subtracted from the background template to focus on the intended hand gesture. Afterward the subtracted image is enhanced and then converted into the grayscale one which is then thresholded by converting it in a binary image. This segmented version is further enhanced by using the morphological filters. The features are extracted by using the grayscale pixel values and shape context analysis (SC). Gestures are automatically recognized by using the k-Nearest Neighbor (k-NN) classification algorithm. The system achieves 83.3% of gesture recognition precision. The classification decisions are conveyed to the front-end embedded controller for systematic actuations and actions.
{"title":"Hand Gesture Recognition Based on Shape Context Analysis","authors":"S. Qaisar, M. Krichen, A. Mihoub","doi":"10.1109/CAIDA51941.2021.9425200","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425200","url":null,"abstract":"The technological advancement is evolving the human–computer interaction (HCI). The goal is to ameliorate the HCI to a level where computers can be interacted in a natural way. It is a demanding aim and keeps the contemporary HCI systems complex and challenging. This paper aims to develop an effective hand gesture identification piloted HCI. It is realizable by three stages of preprocessing, features extraction and classification. The system functionality is studied by using a colored images database. Each incoming instance presents a hand gesture. Firstly it is subtracted from the background template to focus on the intended hand gesture. Afterward the subtracted image is enhanced and then converted into the grayscale one which is then thresholded by converting it in a binary image. This segmented version is further enhanced by using the morphological filters. The features are extracted by using the grayscale pixel values and shape context analysis (SC). Gestures are automatically recognized by using the k-Nearest Neighbor (k-NN) classification algorithm. The system achieves 83.3% of gesture recognition precision. The classification decisions are conveyed to the front-end embedded controller for systematic actuations and actions.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132930178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-06DOI: 10.1109/CAIDA51941.2021.9425343
Hilalah F. Al-Turkistani, Samar Aldobaian, R. Latif
Recent technological advancement demands organizations to have measures in place to manage their Information Technology (IT) systems. Enterprise Architecture Frameworks (EAF) offer companies an efficient technique to manage their IT systems aligning their business requirements with effective solutions. As a result, experts have developed multiple EAF’s such as TOGAF, Zachman, MoDAF, DoDAF, SABSA to help organizations to achieve their objectives by reducing the costs and complexity. These frameworks however, concentrate mostly on business needs lacking holistic enterprise-wide security practices, which may cause enterprises to be exposed for significant security risks resulting financial loss. This study focuses on evaluating business capabilities in TOGAF, NIST, COBIT, MoDAF, DoDAF, SABSA, and Zachman, and identify essential security requirements in TOGAF, SABSA and COBIT19 frameworks by comparing their resiliency processes, which helps organization to easily select applicable framework. The study shows that; besides business requirements, EAF need to include precise cybersecurity guidelines aligning EA business strategies. Enterprises now need to focus more on building resilient approach, which is beyond of protection, detection and prevention. Now enterprises should be ready to withstand against the cyber-attacks applying relevant cyber resiliency approach improving the way of dealing with impacts of cybersecurity risks.
{"title":"Enterprise Architecture Frameworks Assessment: Capabilities, Cyber Security and Resiliency Review","authors":"Hilalah F. Al-Turkistani, Samar Aldobaian, R. Latif","doi":"10.1109/CAIDA51941.2021.9425343","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425343","url":null,"abstract":"Recent technological advancement demands organizations to have measures in place to manage their Information Technology (IT) systems. Enterprise Architecture Frameworks (EAF) offer companies an efficient technique to manage their IT systems aligning their business requirements with effective solutions. As a result, experts have developed multiple EAF’s such as TOGAF, Zachman, MoDAF, DoDAF, SABSA to help organizations to achieve their objectives by reducing the costs and complexity. These frameworks however, concentrate mostly on business needs lacking holistic enterprise-wide security practices, which may cause enterprises to be exposed for significant security risks resulting financial loss. This study focuses on evaluating business capabilities in TOGAF, NIST, COBIT, MoDAF, DoDAF, SABSA, and Zachman, and identify essential security requirements in TOGAF, SABSA and COBIT19 frameworks by comparing their resiliency processes, which helps organization to easily select applicable framework. The study shows that; besides business requirements, EAF need to include precise cybersecurity guidelines aligning EA business strategies. Enterprises now need to focus more on building resilient approach, which is beyond of protection, detection and prevention. Now enterprises should be ready to withstand against the cyber-attacks applying relevant cyber resiliency approach improving the way of dealing with impacts of cybersecurity risks.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133209664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-06DOI: 10.1109/CAIDA51941.2021.9425223
A.A. Al-Ameer, F. Al-Sunni
This paper discusses securities and cryptocurrency trading using artificial intelligence (AI) in the sense that it focuses on performing Exploratory Data Analysis (EDA) on selected technical indicators before proceeding to modelling, and then to develop more practical models by introducing new reward loss function that maximizes the returns during training phase. The results of EDA reveal that the complex patterns within the data can be better captured by discriminative classification models and this was endorsed by performing back-testing on two securities using Artificial Neural Network (ANN) and Random Forests (RF) as discriminative models against their counterpart Naïve Bayes as a generative model. To enhance the learning process, the new reward loss function is utilized to retrain the ANN with testing on AAPL, IBM, BRENT CRUDE and BTC using auto-trading strategy that serves as the intelligent unit, and the results indicate this loss superiorly outperforms the conventional cross-entropy used in predictive models. The overall results of this work suggest that there should be larger focus on EDA and more practical losses in the research of machine learning modelling for stock market prediction applications.
{"title":"A Methodology for Securities and Cryptocurrency Trading Using Exploratory Data Analysis and Artificial Intelligence","authors":"A.A. Al-Ameer, F. Al-Sunni","doi":"10.1109/CAIDA51941.2021.9425223","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425223","url":null,"abstract":"This paper discusses securities and cryptocurrency trading using artificial intelligence (AI) in the sense that it focuses on performing Exploratory Data Analysis (EDA) on selected technical indicators before proceeding to modelling, and then to develop more practical models by introducing new reward loss function that maximizes the returns during training phase. The results of EDA reveal that the complex patterns within the data can be better captured by discriminative classification models and this was endorsed by performing back-testing on two securities using Artificial Neural Network (ANN) and Random Forests (RF) as discriminative models against their counterpart Naïve Bayes as a generative model. To enhance the learning process, the new reward loss function is utilized to retrain the ANN with testing on AAPL, IBM, BRENT CRUDE and BTC using auto-trading strategy that serves as the intelligent unit, and the results indicate this loss superiorly outperforms the conventional cross-entropy used in predictive models. The overall results of this work suggest that there should be larger focus on EDA and more practical losses in the research of machine learning modelling for stock market prediction applications.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132381529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-06DOI: 10.1109/CAIDA51941.2021.9425264
M. O. Aftab, Mazhar Javed Awan, Shahid Khalid, R. Javed, Hassan Shabir
Acute Leukemia disease is the bone marrow problem common both in children and adults. Medical image analytics is applied in the field of Digital Image Processing (DIP) and Deep Learning (DL). The role of deep learning in medical research with big data has been a huge benefit, opening new doors and possibilities for disease diagnostics procedures. Now the medical specialists like pathologists, hematologists, mammalogists and researchers are working in deep learning area. The proposed methodology is Leukemia detection by implementing apache spark BigDL library from the microscopic images of human blood cells using Convolutional Neural Network (CNN) architecture GoogleNet deep transfer learning. The proposed system is an efficient enough to detect 4 types of leukemia Acute Myeloid Leukemia (AML), Actuate Lymphocytic Leukemia (ALL), Chronic Myeloid Leukemia (CML) and Chronic Lymphocytic Leukemia (CLL) and normal from the microscopic images of human blood sample. The proposed methodology after using Spark BigDL framework with Google Net architecture, we achieved 97.33% accuracy in case of training and 94.78% of validation respectively. Moreover we are also compared our model without BigDL GoogleNet. The accuracy of training and validation accuracy are 96.42% and 92.69% respectively. The BigDL model outperformed the Keras model with more efficient and accurate results.
{"title":"Executing Spark BigDL for Leukemia Detection from Microscopic Images using Transfer Learning","authors":"M. O. Aftab, Mazhar Javed Awan, Shahid Khalid, R. Javed, Hassan Shabir","doi":"10.1109/CAIDA51941.2021.9425264","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425264","url":null,"abstract":"Acute Leukemia disease is the bone marrow problem common both in children and adults. Medical image analytics is applied in the field of Digital Image Processing (DIP) and Deep Learning (DL). The role of deep learning in medical research with big data has been a huge benefit, opening new doors and possibilities for disease diagnostics procedures. Now the medical specialists like pathologists, hematologists, mammalogists and researchers are working in deep learning area. The proposed methodology is Leukemia detection by implementing apache spark BigDL library from the microscopic images of human blood cells using Convolutional Neural Network (CNN) architecture GoogleNet deep transfer learning. The proposed system is an efficient enough to detect 4 types of leukemia Acute Myeloid Leukemia (AML), Actuate Lymphocytic Leukemia (ALL), Chronic Myeloid Leukemia (CML) and Chronic Lymphocytic Leukemia (CLL) and normal from the microscopic images of human blood sample. The proposed methodology after using Spark BigDL framework with Google Net architecture, we achieved 97.33% accuracy in case of training and 94.78% of validation respectively. Moreover we are also compared our model without BigDL GoogleNet. The accuracy of training and validation accuracy are 96.42% and 92.69% respectively. The BigDL model outperformed the Keras model with more efficient and accurate results.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126990217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-06DOI: 10.1109/CAIDA51941.2021.9425114
Aisha Batool, M. W. Nisar, Jamal Hussain Shah, A. Rehman, Tariq Sadad
Traffic Sign Recognition (TSR) is a crucial step for automated vehicles and driver assistance systems. Automated TSD in an extreme environment has always been challenging due to foggy, rainy, blurry, and cropping images. A real-time TSD model named improved Extreme Learning Machine Network (iELMNet) is proposed to tackle these challenges. Primary modules of iELMNet include: a) Custom DensNet; b) Accurate Anchor Prediction Model (A2PM); c) Scale Transformation (ST), and d) Extreme Learning Machine (ELM) classifier. Convolutional Neural Network (CNN) model improvises edges of traffic-signs using mapped images extracted from handcrafted features. A2PM removes the redundant features to improve efficiency. ST is utilized to allow the proposed technique for detecting these signs of variant sizes. ELM classifier tries to classify traffic signs robustly by minimizing the feature dimensions. The proposed model is evaluated over three publicly available datasets, i.e., CURE-TSR, TT100k, and GTSRB, and acquired 98.63%, 95.22%, and 99.45% precision, respectively. The output of proposed model demonstrates its competence and ability to implement it in a practical environment.
{"title":"iELMNet: An Application for Traffic Sign Recognition using CNN and ELM","authors":"Aisha Batool, M. W. Nisar, Jamal Hussain Shah, A. Rehman, Tariq Sadad","doi":"10.1109/CAIDA51941.2021.9425114","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425114","url":null,"abstract":"Traffic Sign Recognition (TSR) is a crucial step for automated vehicles and driver assistance systems. Automated TSD in an extreme environment has always been challenging due to foggy, rainy, blurry, and cropping images. A real-time TSD model named improved Extreme Learning Machine Network (iELMNet) is proposed to tackle these challenges. Primary modules of iELMNet include: a) Custom DensNet; b) Accurate Anchor Prediction Model (A2PM); c) Scale Transformation (ST), and d) Extreme Learning Machine (ELM) classifier. Convolutional Neural Network (CNN) model improvises edges of traffic-signs using mapped images extracted from handcrafted features. A2PM removes the redundant features to improve efficiency. ST is utilized to allow the proposed technique for detecting these signs of variant sizes. ELM classifier tries to classify traffic signs robustly by minimizing the feature dimensions. The proposed model is evaluated over three publicly available datasets, i.e., CURE-TSR, TT100k, and GTSRB, and acquired 98.63%, 95.22%, and 99.45% precision, respectively. The output of proposed model demonstrates its competence and ability to implement it in a practical environment.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123097001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-06DOI: 10.1109/CAIDA51941.2021.9425158
Walter Gamarra, Elvia Martínez, Kevin Cikel, Maira Santacruz, M. Arzamendia, D. Gregor, Marcos Villagra, José Colbes
This work proposes the use of deep neural networks for the prediction of traffic variables for measuring traffic congestion. Deep neural networks are used in this work in order to determine how much time each vehicle spends in traffic, considering a certain amount of vehicles in the traffic network and traffic light configurations. A genetic algorithm is also implemented that finds an optimal traffic light configuration. With the implementation of a deep neural network for the simulation of traffic instead of using a simulation software, the computation time of the fitness function in the genetic algorithm improved considerably, with a decrease of precision of less than 10%. Genetic algorithms are used in order to show how useful deep neural networks models can be when dealing with vehicular flow slowdown.
{"title":"Deep Learning for Traffic Prediction with an Application to Traffic Lights Optimization","authors":"Walter Gamarra, Elvia Martínez, Kevin Cikel, Maira Santacruz, M. Arzamendia, D. Gregor, Marcos Villagra, José Colbes","doi":"10.1109/CAIDA51941.2021.9425158","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425158","url":null,"abstract":"This work proposes the use of deep neural networks for the prediction of traffic variables for measuring traffic congestion. Deep neural networks are used in this work in order to determine how much time each vehicle spends in traffic, considering a certain amount of vehicles in the traffic network and traffic light configurations. A genetic algorithm is also implemented that finds an optimal traffic light configuration. With the implementation of a deep neural network for the simulation of traffic instead of using a simulation software, the computation time of the fitness function in the genetic algorithm improved considerably, with a decrease of precision of less than 10%. Genetic algorithms are used in order to show how useful deep neural networks models can be when dealing with vehicular flow slowdown.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132622574","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-06DOI: 10.1109/CAIDA51941.2021.9425212
Md Shahin Ali, Md. Khairul Islam, Jahurul Haque, A. Das, D. Duranta, Md Ariful Islam
Alzheimer’s disease is basically a neurodegenerative disease that is impossible to fully be cured. It is one kind of dementia that occurs along with aging. It not only damages human memory but also affects behavior, movement, and responses to external stimulations. Moreover, AD breaks the connections of the neurons and spoils the brain cells. The worst sequel of AD is death. Though it can not be properly cured, pre-detection can make an early treatment that might reduce the symptoms. AD can also be detected by analyzing brain images captured from several imaging techniques like Electroencephalogram, Magnetic Resonance Imaging, etc with the aid of machine learning algorithms. Machine learning algorithms are highly successful techniques in the case of processing and classifying the images to determine the stages of AD. In this paper, we propose an upgraded machine learning algorithm named Modified Random Forest (m-RF) to individualize between normal people and people with the risk of having Alzheimer’s disease. We have achieved an accuracy of 96.43% that is far better than other algorithms like Support Vector Machine, Adaptive Boosting, K-Nearest Neighbors, etc.
阿尔茨海默病基本上是一种神经退行性疾病，不可能完全治愈。这是一种随着年龄增长而发生的痴呆症。它不仅会损害人的记忆，还会影响人的行为、运动和对外界刺激的反应。此外，阿尔茨海默病还会破坏神经元之间的联系，破坏脑细胞。《AD》最糟糕的结局就是死亡。虽然不能完全治愈，但预先发现可以及早治疗，减轻症状。AD也可以通过分析从脑电图、磁共振成像等多种成像技术捕获的大脑图像来检测，并借助机器学习算法。机器学习算法在处理和分类图像以确定AD阶段的情况下是非常成功的技术。在本文中，我们提出了一种名为Modified Random Forest (m-RF)的升级机器学习算法，用于在正常人和有阿尔茨海默病风险的人之间进行个性化。我们实现了96.43%的准确率，远远优于其他算法，如支持向量机，自适应增强，k近邻等。
{"title":"Alzheimer’s Disease Detection Using m-Random Forest Algorithm with Optimum Features Extraction","authors":"Md Shahin Ali, Md. Khairul Islam, Jahurul Haque, A. Das, D. Duranta, Md Ariful Islam","doi":"10.1109/CAIDA51941.2021.9425212","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425212","url":null,"abstract":"Alzheimer’s disease is basically a neurodegenerative disease that is impossible to fully be cured. It is one kind of dementia that occurs along with aging. It not only damages human memory but also affects behavior, movement, and responses to external stimulations. Moreover, AD breaks the connections of the neurons and spoils the brain cells. The worst sequel of AD is death. Though it can not be properly cured, pre-detection can make an early treatment that might reduce the symptoms. AD can also be detected by analyzing brain images captured from several imaging techniques like Electroencephalogram, Magnetic Resonance Imaging, etc with the aid of machine learning algorithms. Machine learning algorithms are highly successful techniques in the case of processing and classifying the images to determine the stages of AD. In this paper, we propose an upgraded machine learning algorithm named Modified Random Forest (m-RF) to individualize between normal people and people with the risk of having Alzheimer’s disease. We have achieved an accuracy of 96.43% that is far better than other algorithms like Support Vector Machine, Adaptive Boosting, K-Nearest Neighbors, etc.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"2012 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130899868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-06DOI: 10.1109/CAIDA51941.2021.9425106
Abdullah-Al Tariq, Muhammad Zeeshan Khan, M. U. Ghani Khan
Being the most dominant part of the vehicle, colour anticipate vital role in vehicle identification. Thus, colour also plays significant part in Intelligent Transportation System (ITS) and can be very effective in various applications of ITS. In past, most of the work had done on colour recognition of vehicle are not able to achieve the high accuracy because they rely on hand-crafted feature i.e. Speeded Up Robust Features (SURF), Scale Invariant Feature Transform (SIFT) and Histogram of Oriented Gradient (HOG). In this work, we proposed a solution by utilizing one of the latest deep learning algorithm for the detection of vehicle and the classification of detected vehicles colour. Proposed methodology is based on the tuned features of Faster R-CNN and achieved the good results as compared to current state of the art techniques. In addition to that, this work is also contributes towards the dataset collection of related vehicles being used in Pakistan. Proposed method outperformed the previous works by achieving 95.31% accuracy on testing data. The robust results in terms of accuracy and the generation of dataset depicts the novelty of proposed technique in the literature.
{"title":"Real Time Vehicle Detection and Colour Recognition using tuned Features of Faster-RCNN","authors":"Abdullah-Al Tariq, Muhammad Zeeshan Khan, M. U. Ghani Khan","doi":"10.1109/CAIDA51941.2021.9425106","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425106","url":null,"abstract":"Being the most dominant part of the vehicle, colour anticipate vital role in vehicle identification. Thus, colour also plays significant part in Intelligent Transportation System (ITS) and can be very effective in various applications of ITS. In past, most of the work had done on colour recognition of vehicle are not able to achieve the high accuracy because they rely on hand-crafted feature i.e. Speeded Up Robust Features (SURF), Scale Invariant Feature Transform (SIFT) and Histogram of Oriented Gradient (HOG). In this work, we proposed a solution by utilizing one of the latest deep learning algorithm for the detection of vehicle and the classification of detected vehicles colour. Proposed methodology is based on the tuned features of Faster R-CNN and achieved the good results as compared to current state of the art techniques. In addition to that, this work is also contributes towards the dataset collection of related vehicles being used in Pakistan. Proposed method outperformed the previous works by achieving 95.31% accuracy on testing data. The robust results in terms of accuracy and the generation of dataset depicts the novelty of proposed technique in the literature.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131394606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Skin cancer is basically the unnatural growth of skin tissues and it can be fatal. Lately, it has evolved into one of the most perilous types of other cancers in the human body. Premature detection can help to endure the patient. Detection of skin cancer is quite difficult. At present in medical image diagnosis, the performance of computer vision is quite conducive. Together with the progress in technology and impetuous increment in computer provision, different types of machine learning techniques and deep learning models have arisen for the analysis of medical images particularly skin lesion images. In this study, we propose a deep learning model with some image pre-processing steps that help to categorize skin lesions with a better classification rate than other existing models. Normalization, data reduction, and data augmentation are used in pre-processing steps to classify benign and malignant cancer lesions from the HAM10000 dataset. From the experimental result, the proposed model gained an accuracy of 96.10% in training and 90.93% during testing. This model reduces the execution time and performs well-handled.
{"title":"Melanoma Skin Lesions Classification using Deep Convolutional Neural Network with Transfer Learning","authors":"Md. Khairul Islam, Md Shahin Ali, Md Mosahak Ali, Mst. Farija Haque, Abhilash Arjan Das, M. Hossain, D. Duranta, Md Afifur Rahman","doi":"10.1109/CAIDA51941.2021.9425117","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425117","url":null,"abstract":"Skin cancer is basically the unnatural growth of skin tissues and it can be fatal. Lately, it has evolved into one of the most perilous types of other cancers in the human body. Premature detection can help to endure the patient. Detection of skin cancer is quite difficult. At present in medical image diagnosis, the performance of computer vision is quite conducive. Together with the progress in technology and impetuous increment in computer provision, different types of machine learning techniques and deep learning models have arisen for the analysis of medical images particularly skin lesion images. In this study, we propose a deep learning model with some image pre-processing steps that help to categorize skin lesions with a better classification rate than other existing models. Normalization, data reduction, and data augmentation are used in pre-processing steps to classify benign and malignant cancer lesions from the HAM10000 dataset. From the experimental result, the proposed model gained an accuracy of 96.10% in training and 90.93% during testing. This model reduces the execution time and performs well-handled.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114066126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-06DOI: 10.1109/CAIDA51941.2021.9425079
M. Tanveer, N. Khan, Abdul-Rahim Ahmad
Artificial Intelligence (AI) fundamentally works on the antecedents of business management’s exploration, systematical incorporation of businesses details, and focus on business extension. The main purpose of this study is to know the morals of services related to AI in order to develop the marketing and businesses. This study shows the opinions of marketers to know the value of Artificial Intelligence. We propose the research model so that study can be seen in one frame. Study indicates the observations of marketers regarding AI which is composed of 12 services of marketing, the 4Ps (Product, Price, Place, Promotion), the 4Cs (Consumer, Cost, Convenience, Communication), and the 4Es (Experience, Exchange, Everyplace, Evangelism). Using Cronbach’s alpha to analyze the data collected from 508 samples. We showed the reliability and validity of the data so that it can be used for further analysis. We proposed the hypothesis which showed the relationship of each marketing service with AI for developing the business. Consequently, results indicates that all the services, except Evangelism, have positive relationship with AI. Additionally, study also showed that AI highly works on the business development. And marketing also shows significant effect on Business development. Study also offers some important implications for business development that further research should be done on different services, area and audience.
{"title":"AI Support Marketing: Understanding the Customer Journey towards the Business Development","authors":"M. Tanveer, N. Khan, Abdul-Rahim Ahmad","doi":"10.1109/CAIDA51941.2021.9425079","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425079","url":null,"abstract":"Artificial Intelligence (AI) fundamentally works on the antecedents of business management’s exploration, systematical incorporation of businesses details, and focus on business extension. The main purpose of this study is to know the morals of services related to AI in order to develop the marketing and businesses. This study shows the opinions of marketers to know the value of Artificial Intelligence. We propose the research model so that study can be seen in one frame. Study indicates the observations of marketers regarding AI which is composed of 12 services of marketing, the 4Ps (Product, Price, Place, Promotion), the 4Cs (Consumer, Cost, Convenience, Communication), and the 4Es (Experience, Exchange, Everyplace, Evangelism). Using Cronbach’s alpha to analyze the data collected from 508 samples. We showed the reliability and validity of the data so that it can be used for further analysis. We proposed the hypothesis which showed the relationship of each marketing service with AI for developing the business. Consequently, results indicates that all the services, except Evangelism, have positive relationship with AI. Additionally, study also showed that AI highly works on the business development. And marketing also shows significant effect on Business development. Study also offers some important implications for business development that further research should be done on different services, area and audience.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116024859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：