Pub Date : 2021-04-06DOI: 10.1109/CAIDA51941.2021.9425059
Iman M. Almomani, Aala Alkhayer, Mohanned Ahmed
Android ransomware is a threatening malware that is targeting individuals and enterprises. Many existing approaches suggested different ransomware detection solutions to protect users’ devices and data. These solutions used mainly static-based or dynamic-based analysis systems. However, the current solutions have considered only the old versions of Android platforms. In this paper, an efficient machine learning-based ransomware detection approach is proposed. This approach has studied deeply the latest version of Android (Version 11, API Level 30) to include the updated list of features including permissions and API packages calls that might be utilized by ransomware attacks. A new dataset was created after parsing 1000 apps to extract these features. Afterwards, different machine learning techniques were executed to generate different predictive models for Andoird ransomware. Some predictive models reached 98.3% of detection accuracy even after reducing around 26% of the overall features set.
{"title":"An Efficient Machine Learning-based Approach for Android v.11 Ransomware Detection","authors":"Iman M. Almomani, Aala Alkhayer, Mohanned Ahmed","doi":"10.1109/CAIDA51941.2021.9425059","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425059","url":null,"abstract":"Android ransomware is a threatening malware that is targeting individuals and enterprises. Many existing approaches suggested different ransomware detection solutions to protect users’ devices and data. These solutions used mainly static-based or dynamic-based analysis systems. However, the current solutions have considered only the old versions of Android platforms. In this paper, an efficient machine learning-based ransomware detection approach is proposed. This approach has studied deeply the latest version of Android (Version 11, API Level 30) to include the updated list of features including permissions and API packages calls that might be utilized by ransomware attacks. A new dataset was created after parsing 1000 apps to extract these features. Afterwards, different machine learning techniques were executed to generate different predictive models for Andoird ransomware. Some predictive models reached 98.3% of detection accuracy even after reducing around 26% of the overall features set.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"854 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":"116777698","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/CAIDA51941.2021.9425342
Elias Nemer
Time-Frequency transformation and spectral representations of audio signals are commonly used in various machine learning applications. Training a network on features such as the Mel-Spectrogram or Cochleogram has been proven more effective than training on time samples. In practical realizations, these are generated on a separate processor or pre-computed and stored on disk, requiring additional efforts and making it difficult to experiment with different variants. In this paper, we provide a PyTorch framework for generating the Cochleogram as well as the time-domain complex filter-banks for analysis and re-synthesis using the built-in trainable conv1d() layer. This allows computing this spectral feature on the fly as part of a larger network and enables experimenting with varying parameters. The analysis / synthesis banks enable building a trainable network that operates on complex subbands, where resynthesizing the time samples is desirable. The convolutional kernels may be trained from random values, or may be initialized and frozen or initialized and continuously trained with the rest of any network they are part of.
{"title":"Audio Cochleogram with Analysis and Synthesis Banks Using 1D Convolutional Networks","authors":"Elias Nemer","doi":"10.1109/CAIDA51941.2021.9425342","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425342","url":null,"abstract":"Time-Frequency transformation and spectral representations of audio signals are commonly used in various machine learning applications. Training a network on features such as the Mel-Spectrogram or Cochleogram has been proven more effective than training on time samples. In practical realizations, these are generated on a separate processor or pre-computed and stored on disk, requiring additional efforts and making it difficult to experiment with different variants. In this paper, we provide a PyTorch framework for generating the Cochleogram as well as the time-domain complex filter-banks for analysis and re-synthesis using the built-in trainable conv1d() layer. This allows computing this spectral feature on the fly as part of a larger network and enables experimenting with varying parameters. The analysis / synthesis banks enable building a trainable network that operates on complex subbands, where resynthesizing the time samples is desirable. The convolutional kernels may be trained from random values, or may be initialized and frozen or initialized and continuously trained with the rest of any network they are part of.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"166 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":"116058685","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/CAIDA51941.2021.9425115
Ibrahim Alotaibi
The main aim of this research paper is to understand whether firms in the UAE should take advantage of the augmented reality technology, and implement it within their marketing strategies. The paper will first explore what augmented reality marketing, the benefits of augmented reality marketing, and delve into why firms should focus more on using augmented reality in their marketing. Primary research carried out locally in the UAE to have an in depth understanding of the consumer preferences and attitudes towards augmented reality in marketing. Results showed that consumers do indeed have a positive preference towards augmented reality marketing. Recommendations were given along with further research directions.
{"title":"An Exploratory Study of Augmented Reality Marketing in UAE","authors":"Ibrahim Alotaibi","doi":"10.1109/CAIDA51941.2021.9425115","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425115","url":null,"abstract":"The main aim of this research paper is to understand whether firms in the UAE should take advantage of the augmented reality technology, and implement it within their marketing strategies. The paper will first explore what augmented reality marketing, the benefits of augmented reality marketing, and delve into why firms should focus more on using augmented reality in their marketing. Primary research carried out locally in the UAE to have an in depth understanding of the consumer preferences and attitudes towards augmented reality in marketing. Results showed that consumers do indeed have a positive preference towards augmented reality marketing. Recommendations were given along with further research directions.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"205 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":"116392747","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/CAIDA51941.2021.9425149
The Artificial Intelligence and Data Analytics (AIDA) Lab, the first interdisciplinary lab established at Prince Sultan University (PSU) in Sep 2019. Prof. Tanzila Saba is the leader of the AIDA lab. AIDA research lab focuses on the study and development of advanced theories, novel algorithms and techniques in the domain of artificial intelligence, data science and information security. The objective is to foster the lab activities to be aligned with national priorities in particular the 2020 National Transformation Plan and Saudi Vision 2030. The goal of the AIDA Lab is to conduct research and attract funds related to AI, Data Science, IoT and real time data applications. The AIDA lab provides consulting services, publishes novel research finding for real time solutions, provides technical training, workshops, seminars services for the community, academia, and business sectors.
{"title":"About the Artificial Intelligence and Data Analytics (AIDA) Lab","authors":"","doi":"10.1109/CAIDA51941.2021.9425149","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425149","url":null,"abstract":"The Artificial Intelligence and Data Analytics (AIDA) Lab, the first interdisciplinary lab established at Prince Sultan University (PSU) in Sep 2019. Prof. Tanzila Saba is the leader of the AIDA lab. AIDA research lab focuses on the study and development of advanced theories, novel algorithms and techniques in the domain of artificial intelligence, data science and information security. The objective is to foster the lab activities to be aligned with national priorities in particular the 2020 National Transformation Plan and Saudi Vision 2030. The goal of the AIDA Lab is to conduct research and attract funds related to AI, Data Science, IoT and real time data applications. The AIDA lab provides consulting services, publishes novel research finding for real time solutions, provides technical training, workshops, seminars services for the community, academia, and business sectors.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"50 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":"123896669","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/CAIDA51941.2021.9425054
S. Kamal, Bilal Muhammad Khan
Wireless sensor networks have become so popular in many applications such as vehicle tracking and monitoring, environmental measurements and radiation analysis. These applications can be ready to go for further processing by connecting it to remote servers through protocols that outside world used such as internet. This brings IPv6 over low power wireless sensor network (6LowPAN) into very important role to develop a bridge between internet and WSN network. Though a reliable communication demands many parameters such as data rate, effective data transmission, data security as well as packet size etc. A gateway between 6lowPAN network and IPV6 is needed where frame size compression is required in order to increase payload of data frame on hardware platform.
{"title":"Hardware Implementation of IP-Enabled Wireless Sensor Network Using 6LoWPAN","authors":"S. Kamal, Bilal Muhammad Khan","doi":"10.1109/CAIDA51941.2021.9425054","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425054","url":null,"abstract":"Wireless sensor networks have become so popular in many applications such as vehicle tracking and monitoring, environmental measurements and radiation analysis. These applications can be ready to go for further processing by connecting it to remote servers through protocols that outside world used such as internet. This brings IPv6 over low power wireless sensor network (6LowPAN) into very important role to develop a bridge between internet and WSN network. Though a reliable communication demands many parameters such as data rate, effective data transmission, data security as well as packet size etc. A gateway between 6lowPAN network and IPV6 is needed where frame size compression is required in order to increase payload of data frame on hardware platform.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"14 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":"128058442","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/CAIDA51941.2021.9425127
A. Alanezi, Bassem Abd-El-Atty, H. Kolivand, A. A. Abd El-Latif
Data security and privacy act vital tasks in our daily lives. Traditional cryptosystems may be hacked amidst the growth of quantum resources. Consequently, we need new cryptosystems its construction is based on quantum concepts. In this work, we proposed a novel image cryptosystem using quantum walks. We employ a diversity of tools for experimental assessment of the presented cryptosystem including correlation analysis, histogram analysis, Shannon entropy analysis, UACI and NPCR analyses, Key sensitivity analysis, and occlusion analysis. These metrics show the advantages of our cryptosystem over some robust state-of-art cryptosystems.
{"title":"Quantum based encryption approach for secure images","authors":"A. Alanezi, Bassem Abd-El-Atty, H. Kolivand, A. A. Abd El-Latif","doi":"10.1109/CAIDA51941.2021.9425127","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425127","url":null,"abstract":"Data security and privacy act vital tasks in our daily lives. Traditional cryptosystems may be hacked amidst the growth of quantum resources. Consequently, we need new cryptosystems its construction is based on quantum concepts. In this work, we proposed a novel image cryptosystem using quantum walks. We employ a diversity of tools for experimental assessment of the presented cryptosystem including correlation analysis, histogram analysis, Shannon entropy analysis, UACI and NPCR analyses, Key sensitivity analysis, and occlusion analysis. These metrics show the advantages of our cryptosystem over some robust state-of-art cryptosystems.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"10 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":"116819777","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/CAIDA51941.2021.9425062
R. Javed, T. Saba, Salman Humdullah, Nor Shahida MOHD JAMAIL, Mazhar Javed Awan
The diagnosis of interactions between two drugs is an essential procedure in drug development. Many medical tool’s offer inclusive records related to DDI. However, this tool’s results are not very satisfactory. The main aim is to propose an efficient approach based on pattern matching that identifies the interaction between two drugs. In this study, the goal is to collect the data from the DrugBank, which is a publicly available source. The drug-related data includes drug ID, drug names, and various kinds of sentences of drug-drug interaction. Drug names will be identified by drug names dictionary defined in the corpus, and sentences will be determined according to given patterns. These sentences will treat as input data, and preprocessing steps will perform in these sentences. Various types of features are selected for machine learning classification. Then all the attributes will be classified into desired classes. The proposed method gains 95.4% accuracy from the random forest classifier.
{"title":"An Efficient Pattern Recognition Based Method for Drug-Drug Interaction Diagnosis","authors":"R. Javed, T. Saba, Salman Humdullah, Nor Shahida MOHD JAMAIL, Mazhar Javed Awan","doi":"10.1109/CAIDA51941.2021.9425062","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425062","url":null,"abstract":"The diagnosis of interactions between two drugs is an essential procedure in drug development. Many medical tool’s offer inclusive records related to DDI. However, this tool’s results are not very satisfactory. The main aim is to propose an efficient approach based on pattern matching that identifies the interaction between two drugs. In this study, the goal is to collect the data from the DrugBank, which is a publicly available source. The drug-related data includes drug ID, drug names, and various kinds of sentences of drug-drug interaction. Drug names will be identified by drug names dictionary defined in the corpus, and sentences will be determined according to given patterns. These sentences will treat as input data, and preprocessing steps will perform in these sentences. Various types of features are selected for machine learning classification. Then all the attributes will be classified into desired classes. The proposed method gains 95.4% accuracy from the random forest classifier.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"9 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":"124507242","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/CAIDA51941.2021.9425252
Hamza Mukhtar, Muhammad Zeeshan Khan, M. Usman Ghani Khan, T. Saba, R. Latif
Plant counting in major grain crops like wheat through aerial images still poses a challenge due to the very high infield density of plants and occlusion. Annotation of aerial images for counting through perfect detection or segmentation is extremely difficult due to a large number of extremely small plant instances. In this paper, we present a semi-supervised method based on cross-consistency for the semantic segmentation of field images and an inception-based regression network for plant counting. Through loosely semantic segmentation, tiny plant clusters are extracted from the RGB image and fed to a regression network to get the count. Cross-consistency under the cluster assumption is a powerful semi-supervised training technique to leverage the unlabeled images. In this work, it is observed that regions with lower density are more detectable within hidden representations as compared to inputs. Supervised training of an encoder in a shared fashion and the main decoder is carried out on the RGB images and the corresponding mask. Consistency between the prediction of main and auxiliary decoders is imposed to leverage the unlabeled images. Induction of inception in the regression network benefits in extracting the multi-scale features which are very important because of quite tiny plant instances as compared to the whole image. The proposed plant counting framework achieves very high performance having a standard deviation of 0.94 and a mean of 0.87 of absolute difference in the count given the semi-supervised nature. Our network has performed reasonably well as compared to supervised detection and segmentation-based counting framework. Moreover, labeling for detection or segmentation is a quite tedious task, so our network has the leverage to train the model with few labeled and large numbers of unlabeled images which also provides the advantage to train the system for other crops like rice and maize with few labeled images.
{"title":"Wheat Plant Counting Using UAV Images Based on Semi-supervised Semantic Segmentation","authors":"Hamza Mukhtar, Muhammad Zeeshan Khan, M. Usman Ghani Khan, T. Saba, R. Latif","doi":"10.1109/CAIDA51941.2021.9425252","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425252","url":null,"abstract":"Plant counting in major grain crops like wheat through aerial images still poses a challenge due to the very high infield density of plants and occlusion. Annotation of aerial images for counting through perfect detection or segmentation is extremely difficult due to a large number of extremely small plant instances. In this paper, we present a semi-supervised method based on cross-consistency for the semantic segmentation of field images and an inception-based regression network for plant counting. Through loosely semantic segmentation, tiny plant clusters are extracted from the RGB image and fed to a regression network to get the count. Cross-consistency under the cluster assumption is a powerful semi-supervised training technique to leverage the unlabeled images. In this work, it is observed that regions with lower density are more detectable within hidden representations as compared to inputs. Supervised training of an encoder in a shared fashion and the main decoder is carried out on the RGB images and the corresponding mask. Consistency between the prediction of main and auxiliary decoders is imposed to leverage the unlabeled images. Induction of inception in the regression network benefits in extracting the multi-scale features which are very important because of quite tiny plant instances as compared to the whole image. The proposed plant counting framework achieves very high performance having a standard deviation of 0.94 and a mean of 0.87 of absolute difference in the count given the semi-supervised nature. Our network has performed reasonably well as compared to supervised detection and segmentation-based counting framework. Moreover, labeling for detection or segmentation is a quite tedious task, so our network has the leverage to train the model with few labeled and large numbers of unlabeled images which also provides the advantage to train the system for other crops like rice and maize with few labeled images.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"49 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":"126422949","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/caida51941.2021.9425060
Sahar Alwadei, Moataz A. Ahmed
Time series classification (TCS) is an essential task in many applications. There have been different models proposed for TSC where deep learning models proved to be an excellent option. However, deep learning models' performance is generally known to be highly affected by the settings of their architectural design decisions and values of corresponding hyperparameters. In this research, we study the impact of such decisions and values on Residual Neural Networks (ResNets), a leading deep learning model for TSC. The study considered four factors to be investigated those are the model’s depth and width besides learning and dropout rates. The interplay between the characteristics of time series data and these factors has been looked at as well. A set of designed variants of the model was analyzed statistically, which led to recommend specific settings while building the model. Experimental results show that learning and dropout rates influence the model’s performance the most, while deeper and wider networks did not enhance the performance despite the extended cost of training.
{"title":"On the Sensitivity of Residual Networks for Time Series Classification","authors":"Sahar Alwadei, Moataz A. Ahmed","doi":"10.1109/caida51941.2021.9425060","DOIUrl":"https://doi.org/10.1109/caida51941.2021.9425060","url":null,"abstract":"Time series classification (TCS) is an essential task in many applications. There have been different models proposed for TSC where deep learning models proved to be an excellent option. However, deep learning models' performance is generally known to be highly affected by the settings of their architectural design decisions and values of corresponding hyperparameters. In this research, we study the impact of such decisions and values on Residual Neural Networks (ResNets), a leading deep learning model for TSC. The study considered four factors to be investigated those are the model’s depth and width besides learning and dropout rates. The interplay between the characteristics of time series data and these factors has been looked at as well. A set of designed variants of the model was analyzed statistically, which led to recommend specific settings while building the model. Experimental results show that learning and dropout rates influence the model’s performance the most, while deeper and wider networks did not enhance the performance despite the extended cost of training.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"67 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":"131289378","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/CAIDA51941.2021.9425162
W. Adoni, Nahhal Tarik, M. Krichen, Abdeltif El byed
Graph are ubiquitous because the fields of application are varied. Well-known examples are social networks, biological networks and path-finding in road networks. Real-world graphs processing is very challenging because of 4V characteristics related to big data. They are huge to process them on single-node and the time complexity is exponential. Unfortunately, due to the lack of research, only a few systems are able to ensure the storage and quick processing of large-scale graphs. In this paper, we propose HGraph, a parallel and distributed tool which handles large-scale graphs. HGraph is build on top of Hadoop and Spark frameworks. The proposed tool provides high scalability and is adapted to easily implement algorithms for various graph problems. Experimental tests performed on real-world graphs showed that HGraph is reliable and achieves significant gain time over the state of the art of graph processing systems.
{"title":"HGraph: Parallel and Distributed Tool for Large-Scale Graph Processing","authors":"W. Adoni, Nahhal Tarik, M. Krichen, Abdeltif El byed","doi":"10.1109/CAIDA51941.2021.9425162","DOIUrl":"https://doi.org/10.1109/CAIDA51941.2021.9425162","url":null,"abstract":"Graph are ubiquitous because the fields of application are varied. Well-known examples are social networks, biological networks and path-finding in road networks. Real-world graphs processing is very challenging because of 4V characteristics related to big data. They are huge to process them on single-node and the time complexity is exponential. Unfortunately, due to the lack of research, only a few systems are able to ensure the storage and quick processing of large-scale graphs. In this paper, we propose HGraph, a parallel and distributed tool which handles large-scale graphs. HGraph is build on top of Hadoop and Spark frameworks. The proposed tool provides high scalability and is adapted to easily implement algorithms for various graph problems. Experimental tests performed on real-world graphs showed that HGraph is reliable and achieves significant gain time over the state of the art of graph processing systems.","PeriodicalId":272573,"journal":{"name":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)","volume":"248 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":"123283663","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：