Pub Date : 2024-05-20DOI: 10.37256/ccds.5220244503
Hashida Haidros Rahima Manzil, Manohar Naik S
The increasing prevalence of Android malware poses significant risks to mobile devices and user privacy. The traditional detection methods have limitations in keeping up with the evolving landscape of malware attacks, necessitating the development of more effective solutions. In this paper, we present DeepMetaDroid, a real-time detection approach for Android malware that leverages metadata features. By analyzing crucial metadata, including APK size, download size, permissions, certificates, and DEX files, the proposed method enables effective identification of malware and enhances mobile security. Using deep learning techniques, a lightweight Android real-time monitoring system is equipped with the trained model. These methods include long short-term memory (LSTM), gated recurrent units (GRU), convolutional neural networks (CNN), deep neural networks (DNN), and other ensemble models. Utilizing the rectified linear unit (ReLU) as the activation function, the DNN model is constructed with 32 neurons in the input layer. A one-dimensional convolutional layer with 32 neurons and a filter size of three is used as the input layer in the CNN model. The LSTM model is designed with an input layer consisting of 16 neurons. The GRU model with 32 neurons is employed in the input layer. Additionally, ensemble models that combined several architectures were developed. The proposed method offers a faster and more scalable solution for malware detection by consuming fewer resources like memory and CPU. This work ensures device security by providing real-time monitoring on Android devices to prevent users from installing malicious applications and, thus, enhance user privacy and security.
{"title":"DeepMetaDroid: Real-Time Android Malware Detection Using Deep Learning and Metadata Features","authors":"Hashida Haidros Rahima Manzil, Manohar Naik S","doi":"10.37256/ccds.5220244503","DOIUrl":"https://doi.org/10.37256/ccds.5220244503","url":null,"abstract":"The increasing prevalence of Android malware poses significant risks to mobile devices and user privacy. The traditional detection methods have limitations in keeping up with the evolving landscape of malware attacks, necessitating the development of more effective solutions. In this paper, we present DeepMetaDroid, a real-time detection approach for Android malware that leverages metadata features. By analyzing crucial metadata, including APK size, download size, permissions, certificates, and DEX files, the proposed method enables effective identification of malware and enhances mobile security. Using deep learning techniques, a lightweight Android real-time monitoring system is equipped with the trained model. These methods include long short-term memory (LSTM), gated recurrent units (GRU), convolutional neural networks (CNN), deep neural networks (DNN), and other ensemble models. Utilizing the rectified linear unit (ReLU) as the activation function, the DNN model is constructed with 32 neurons in the input layer. A one-dimensional convolutional layer with 32 neurons and a filter size of three is used as the input layer in the CNN model. The LSTM model is designed with an input layer consisting of 16 neurons. The GRU model with 32 neurons is employed in the input layer. Additionally, ensemble models that combined several architectures were developed. The proposed method offers a faster and more scalable solution for malware detection by consuming fewer resources like memory and CPU. This work ensures device security by providing real-time monitoring on Android devices to prevent users from installing malicious applications and, thus, enhance user privacy and security.","PeriodicalId":158315,"journal":{"name":"Cloud Computing and Data Science","volume":"66 26","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141121606","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 : 2024-05-15DOI: 10.37256/ccds.5220244470
Ishtiaq Ahammad, William Ankan Sarkar, Famme Akter Meem, Jannatul Ferdus, Md. Kawsar Ahmed, Md. R. Rahman, Rabeya Sultana, Md. Shihabul Islam
Predicting stock market prices accurately is a major task for investors and traders seeking to optimize their decision-making processes. This research focuses on the comparative analysis of advanced machine learning (ML) techniques, particularly, the Long Short-Term Memory (LSTM) model and Autoregressive Integrated Moving Average (ARIMA) model for predicting stock market prices. The study enforces thorough data collection and preprocessing to ensure the quality and reliability of the historical stock price data, forming a robust foundation for the predictive models. The core contribution of this paper lies in its systematic and comparative analysis of these two models. A range of performance metrics, including Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), are employed to assess and contrast the predictive accuracy and efficiency of the LSTM and ARIMA models. The research findings indicate that the ARIMA model, contrary to expectations, outperforms the LSTM model in this study, achieving lower RMSE and MAE values. Specifically, the ARIMA model demonstrates a Test RMSE of 4.336 and a Test MAE of 3.45926, indicating its superior predictive accuracy compared to the LSTM model. Furthermore, the study sets its findings against the backdrop of existing literature by comparing the performance of its models with those reported in previous research. This comparison shows better results achieved by our stock market prediction models. By addressing limitations observed in prior studies and demonstrating practical applicability, this research contributes to advancing stock market prediction methodologies, offering valuable insights for investors and traders.
{"title":"Advancing Stock Market Predictions with Time Series Analysis including LSTM and ARIMA","authors":"Ishtiaq Ahammad, William Ankan Sarkar, Famme Akter Meem, Jannatul Ferdus, Md. Kawsar Ahmed, Md. R. Rahman, Rabeya Sultana, Md. Shihabul Islam","doi":"10.37256/ccds.5220244470","DOIUrl":"https://doi.org/10.37256/ccds.5220244470","url":null,"abstract":"Predicting stock market prices accurately is a major task for investors and traders seeking to optimize their decision-making processes. This research focuses on the comparative analysis of advanced machine learning (ML) techniques, particularly, the Long Short-Term Memory (LSTM) model and Autoregressive Integrated Moving Average (ARIMA) model for predicting stock market prices. The study enforces thorough data collection and preprocessing to ensure the quality and reliability of the historical stock price data, forming a robust foundation for the predictive models. The core contribution of this paper lies in its systematic and comparative analysis of these two models. A range of performance metrics, including Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), are employed to assess and contrast the predictive accuracy and efficiency of the LSTM and ARIMA models. The research findings indicate that the ARIMA model, contrary to expectations, outperforms the LSTM model in this study, achieving lower RMSE and MAE values. Specifically, the ARIMA model demonstrates a Test RMSE of 4.336 and a Test MAE of 3.45926, indicating its superior predictive accuracy compared to the LSTM model. Furthermore, the study sets its findings against the backdrop of existing literature by comparing the performance of its models with those reported in previous research. This comparison shows better results achieved by our stock market prediction models. By addressing limitations observed in prior studies and demonstrating practical applicability, this research contributes to advancing stock market prediction methodologies, offering valuable insights for investors and traders.","PeriodicalId":158315,"journal":{"name":"Cloud Computing and Data Science","volume":" 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128158","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 : 2023-09-06DOI: 10.37256/ccds.5120233470
D. Egirani, Miebi M. Alaowei
This study investigated the geochemical and geospatial distribution of organic contaminants in the floodplain water and sediments of Ekpetiama in the Niger Delta Region of Nigeria. This study is necessary because there are limited data on the level of organic contamination in this section of the Niger Delta Region of Nigeria. The extinction of planktons in Ekpetiama became a source of concern to the residents. This concern is because this section of the coastal plain provides fisher folks with livelihood. So, there was a need to track the source of contamination in this part of the Niger Delta region. Previous studies have suggested a high level of Total Petroleum Hydrocarbon and Total Hydrocarbon Content as possible sources of reduced dissolved oxygen in similar deltaic terrain. A total of 10 water and 10 sediment samples were collected and analyzed in triplicate at an interval of 100 m in the flood plain. A particle size analyzer was used to perform particle size analyses of air-dried sediments. The American Public Health Association method (APHA) was used to do the chemical analysis of the water samples. Here, a liquid-liquid extraction procedure was performed on sediment samples using 30 mL of Dichloromethane (DCM) as the extracting agent. The results were subjected to statistical validation. The mean grain size ranged from 2.37-4.83, kurtosis (1.94-0.49), and skewness (-0.8-0.71). The contaminant indicators (pH, biochemical oxygen demand, chemical oxygen demand, dissolved oxygen and Total Organic Carbon) point to the presence of organic contamination of the flood plain. The results indicated a total petroleum hydrocarbon range of 0.47-0.87 ppm in water and 0.69-0.96 ppm in sediments and a total hydrocarbon content range of 1.10-2.80 ppm in water and 2.56-3.90 ppm in sediment# samples. The results were above the permitted limits of the World Health Organisation. The source of ecological damage is the abnormal concentrations of organic contaminants in the flood plain. These results significantly caused ecosystem damage and human health effects in the food chain. This study provides information to the National Oil Spill Detection and Response Agency for a cleanup process.
{"title":"Geochemical and Geospatial Distribution of Organic Contaminants in the Flood Plain of Ekpetiama, Niger Delta Region of Nigeria","authors":"D. Egirani, Miebi M. Alaowei","doi":"10.37256/ccds.5120233470","DOIUrl":"https://doi.org/10.37256/ccds.5120233470","url":null,"abstract":"This study investigated the geochemical and geospatial distribution of organic contaminants in the floodplain water and sediments of Ekpetiama in the Niger Delta Region of Nigeria. This study is necessary because there are limited data on the level of organic contamination in this section of the Niger Delta Region of Nigeria. The extinction of planktons in Ekpetiama became a source of concern to the residents. This concern is because this section of the coastal plain provides fisher folks with livelihood. So, there was a need to track the source of contamination in this part of the Niger Delta region. Previous studies have suggested a high level of Total Petroleum Hydrocarbon and Total Hydrocarbon Content as possible sources of reduced dissolved oxygen in similar deltaic terrain. A total of 10 water and 10 sediment samples were collected and analyzed in triplicate at an interval of 100 m in the flood plain. A particle size analyzer was used to perform particle size analyses of air-dried sediments. The American Public Health Association method (APHA) was used to do the chemical analysis of the water samples. Here, a liquid-liquid extraction procedure was performed on sediment samples using 30 mL of Dichloromethane (DCM) as the extracting agent. The results were subjected to statistical validation. The mean grain size ranged from 2.37-4.83, kurtosis (1.94-0.49), and skewness (-0.8-0.71). The contaminant indicators (pH, biochemical oxygen demand, chemical oxygen demand, dissolved oxygen and Total Organic Carbon) point to the presence of organic contamination of the flood plain. The results indicated a total petroleum hydrocarbon range of 0.47-0.87 ppm in water and 0.69-0.96 ppm in sediments and a total hydrocarbon content range of 1.10-2.80 ppm in water and 2.56-3.90 ppm in sediment# samples. The results were above the permitted limits of the World Health Organisation. The source of ecological damage is the abnormal concentrations of organic contaminants in the flood plain. These results significantly caused ecosystem damage and human health effects in the food chain. This study provides information to the National Oil Spill Detection and Response Agency for a cleanup process.","PeriodicalId":158315,"journal":{"name":"Cloud Computing and Data Science","volume":"2008 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125580173","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 : 2023-09-01DOI: 10.37256/ccds.5120233271
Fadele Ayotunde Alaba, Hakeem Adewale Sulaimon, Madu Ifeyinwa, Owamoyo Najeem
There has been a rise in the demand for blockchain-based smart contract development platforms and language implementations. On the other hand, smart contracts and blockchain applications are generated using non-standard software life cycles, which means that, for example, distributed applications are rarely updated, or bugs are fully addressed by releasing a newer version, leading to security flaws and challenges for users to adopt the technology. Smart contracts have gained significant attention due to their potential to automate and secure various transactions in diverse domains. However, the increasing adoption of smart contracts has also raised concerns about security vulnerabilities and potential risks. In this paper, an overview of smart contracts was discussed in detail. It further distinguished and compared smart contracts security with conventional security regarding security, privacy, communication channel, etc. Different platforms for smart contracts, such as Bitcoin, Ethereum, Counterparty, Stellar, Monax, and Lisk, are also discussed in this paper. Some proposed techniques are used in different areas for handling security threats in smart contracts. In addition, a taxonomy of the smart contracts security application was proposed, which attempts to solve some of the flaws and inadequacies in smart contracts. The study also provides a comprehensive smart contracts security scenario with different techniques. Lastly, the possible attacks posed by threats and vulnerabilities of the smart contracts are provided. The security threats and vulnerabilities addressed in this study are unique to smart contracts.
{"title":"Smart Contracts Security Application and Challenges: A Review","authors":"Fadele Ayotunde Alaba, Hakeem Adewale Sulaimon, Madu Ifeyinwa, Owamoyo Najeem","doi":"10.37256/ccds.5120233271","DOIUrl":"https://doi.org/10.37256/ccds.5120233271","url":null,"abstract":"There has been a rise in the demand for blockchain-based smart contract development platforms and language implementations. On the other hand, smart contracts and blockchain applications are generated using non-standard software life cycles, which means that, for example, distributed applications are rarely updated, or bugs are fully addressed by releasing a newer version, leading to security flaws and challenges for users to adopt the technology. Smart contracts have gained significant attention due to their potential to automate and secure various transactions in diverse domains. However, the increasing adoption of smart contracts has also raised concerns about security vulnerabilities and potential risks. In this paper, an overview of smart contracts was discussed in detail. It further distinguished and compared smart contracts security with conventional security regarding security, privacy, communication channel, etc. Different platforms for smart contracts, such as Bitcoin, Ethereum, Counterparty, Stellar, Monax, and Lisk, are also discussed in this paper. Some proposed techniques are used in different areas for handling security threats in smart contracts. In addition, a taxonomy of the smart contracts security application was proposed, which attempts to solve some of the flaws and inadequacies in smart contracts. The study also provides a comprehensive smart contracts security scenario with different techniques. Lastly, the possible attacks posed by threats and vulnerabilities of the smart contracts are provided. The security threats and vulnerabilities addressed in this study are unique to smart contracts.","PeriodicalId":158315,"journal":{"name":"Cloud Computing and Data Science","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126215756","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 : 2023-07-25DOI: 10.37256/ccds.4220233292
R. Robinson
The technology known as cloud computing makes it possible to provide computing services over the Internet. Because it allows users to access and manage information and applications through a network of remote servers, this service model has been quickly adopted due to its numerous benefits, including cost savings, scalability, and accessibility. The global market for cloud computing is expected to reach $732 billion by 2023, according to a report from International Data Corporation (IDC). A first-hand survey of approximately sixty (60) cloud companies will be used to provide an overview of cloud computing technology, its architecture, and security, privacy, and trust (SPT) concerns. Privacy concerns for users, data theft, unauthenticated access, and hacker attacks are just a few of the cloud computing problems. These perplexing security issues of validation protection, information assurance and information check are the primary impediment to cloud transformation for future turns of events, which is getting addressed to recognize the sufficiency and adequacy of cloud security through subjective review relaxed near techniques.
{"title":"Insights on Cloud Security Management","authors":"R. Robinson","doi":"10.37256/ccds.4220233292","DOIUrl":"https://doi.org/10.37256/ccds.4220233292","url":null,"abstract":"The technology known as cloud computing makes it possible to provide computing services over the Internet. Because it allows users to access and manage information and applications through a network of remote servers, this service model has been quickly adopted due to its numerous benefits, including cost savings, scalability, and accessibility. The global market for cloud computing is expected to reach $732 billion by 2023, according to a report from International Data Corporation (IDC). A first-hand survey of approximately sixty (60) cloud companies will be used to provide an overview of cloud computing technology, its architecture, and security, privacy, and trust (SPT) concerns. Privacy concerns for users, data theft, unauthenticated access, and hacker attacks are just a few of the cloud computing problems. These perplexing security issues of validation protection, information assurance and information check are the primary impediment to cloud transformation for future turns of events, which is getting addressed to recognize the sufficiency and adequacy of cloud security through subjective review relaxed near techniques.","PeriodicalId":158315,"journal":{"name":"Cloud Computing and Data Science","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127713423","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 : 2023-07-25DOI: 10.37256/ccds.4220233257
Isuru Udayangani Hewapathirana
Standard research on social media and its applications has been widely disseminated in developed nations. But in Sri Lanka, research in this area has been released far less frequently. However, social media usage in the country is evolving regardless of age, sex, education level, or other limitations. This study aims to fill the gap by conducting a comprehensive review of social media-based research conducted in Sri Lanka between 2012 and 2022. A systematic search of reputable databases, including IEEE Xplore, ScienceDirect, Emerald Insight, Google Scholar, and Springer Link, identified 57 relevant papers for analysis. The review highlights the diversity of application areas where social media research has been employed in Sri Lanka, including disaster management, public health, marketing, education, and more. Additionally, the analysis highlights the methodological approaches employed in social media analytics and the specific social media platforms utilized by researchers in Sri Lanka. The results of the current study serve as a timely resource, enabling policymakers and decision-makers to identify the potential avenues of social media research in Sri Lanka. By understanding the existing trends and implications, stakeholders can harness the power of social media data to make informed policy decisions, develop effective marketing strategies, enhance public health initiatives, and revolutionize educational practices.
{"title":"A Review on Current Trends and Applications of Social Media Research in Sri Lanka","authors":"Isuru Udayangani Hewapathirana","doi":"10.37256/ccds.4220233257","DOIUrl":"https://doi.org/10.37256/ccds.4220233257","url":null,"abstract":"Standard research on social media and its applications has been widely disseminated in developed nations. But in Sri Lanka, research in this area has been released far less frequently. However, social media usage in the country is evolving regardless of age, sex, education level, or other limitations. This study aims to fill the gap by conducting a comprehensive review of social media-based research conducted in Sri Lanka between 2012 and 2022. A systematic search of reputable databases, including IEEE Xplore, ScienceDirect, Emerald Insight, Google Scholar, and Springer Link, identified 57 relevant papers for analysis. The review highlights the diversity of application areas where social media research has been employed in Sri Lanka, including disaster management, public health, marketing, education, and more. Additionally, the analysis highlights the methodological approaches employed in social media analytics and the specific social media platforms utilized by researchers in Sri Lanka. The results of the current study serve as a timely resource, enabling policymakers and decision-makers to identify the potential avenues of social media research in Sri Lanka. By understanding the existing trends and implications, stakeholders can harness the power of social media data to make informed policy decisions, develop effective marketing strategies, enhance public health initiatives, and revolutionize educational practices.","PeriodicalId":158315,"journal":{"name":"Cloud Computing and Data Science","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114330715","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 : 2023-07-17DOI: 10.37256/ccds.4220233051
Taskeen Taj, Manash Sarkar
This paper proposes an innovative approach called "Embedding Iris Biometric Watermarking" for user authentication. By utilizing the unique characteristics of the iris, a secure watermark is generated and embedded into the biometric data. This technique enhances the security and robustness of authentication systems, offering advantages such as high security, resistance to attacks, and non-intrusiveness. The proposed method has potential applications in access control, secure transactions, and digital rights management, providing a reliable solution for ensuring the integrity and confidentiality of digital systems and services.
{"title":"A Survey on Embedding Iris Biometric Watermarking for User Authentication","authors":"Taskeen Taj, Manash Sarkar","doi":"10.37256/ccds.4220233051","DOIUrl":"https://doi.org/10.37256/ccds.4220233051","url":null,"abstract":"This paper proposes an innovative approach called \"Embedding Iris Biometric Watermarking\" for user authentication. By utilizing the unique characteristics of the iris, a secure watermark is generated and embedded into the biometric data. This technique enhances the security and robustness of authentication systems, offering advantages such as high security, resistance to attacks, and non-intrusiveness. The proposed method has potential applications in access control, secure transactions, and digital rights management, providing a reliable solution for ensuring the integrity and confidentiality of digital systems and services.","PeriodicalId":158315,"journal":{"name":"Cloud Computing and Data Science","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130408388","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 : 2023-06-09DOI: 10.37256/ccds.4220232722
O. Elharrouss, Kawther Hassine, Ayman A. Zayyan, Zakariyae Chatri, Noor Almaadeed, S. Al-Máadeed, K. Abualsaud
Three-dimensional (3D) point cloud analysis has become one of the attractive subjects in realistic imaging and machine visions due to its simplicity, flexibility and powerful capacity of visualization. Actually, the representation of scenes and buildings using 3D shapes and formats leveraged many applications among which automatic driving, scenes and objects reconstruction, etc. Nevertheless, working with this emerging type of data has been a challenging task for objects representation, scenes recognition, segmentation, and reconstruction. In this regard, a significant effort has recently been devoted to developing novel strategies, using different techniques such as deep learning models. To that end, we present in this paper a comprehensive review of existing tasks on 3D point cloud: a well-defined taxonomy of existing techniques is performed based on the nature of the adopted algorithms, application scenarios, and main objectives. Various tasks performed on 3D point could data are investigated, including objects and scenes detection, recognition, segmentation, and reconstruction. In addition, we introduce a list of used datasets, discuss respective evaluation metrics, and compare the performance of existing solutions to better inform the state-of-the-art and identify their limitations and strengths. Lastly, we elaborate on current challenges facing the subject of technology and future trends attracting considerable interest, which could be a starting point for upcoming research studies.
{"title":"3D Point Cloud for Objects and Scenes Classification, Recognition, Segmentation, and Reconstruction: A Review","authors":"O. Elharrouss, Kawther Hassine, Ayman A. Zayyan, Zakariyae Chatri, Noor Almaadeed, S. Al-Máadeed, K. Abualsaud","doi":"10.37256/ccds.4220232722","DOIUrl":"https://doi.org/10.37256/ccds.4220232722","url":null,"abstract":"Three-dimensional (3D) point cloud analysis has become one of the attractive subjects in realistic imaging and machine visions due to its simplicity, flexibility and powerful capacity of visualization. Actually, the representation of scenes and buildings using 3D shapes and formats leveraged many applications among which automatic driving, scenes and objects reconstruction, etc. Nevertheless, working with this emerging type of data has been a challenging task for objects representation, scenes recognition, segmentation, and reconstruction. In this regard, a significant effort has recently been devoted to developing novel strategies, using different techniques such as deep learning models. To that end, we present in this paper a comprehensive review of existing tasks on 3D point cloud: a well-defined taxonomy of existing techniques is performed based on the nature of the adopted algorithms, application scenarios, and main objectives. Various tasks performed on 3D point could data are investigated, including objects and scenes detection, recognition, segmentation, and reconstruction. In addition, we introduce a list of used datasets, discuss respective evaluation metrics, and compare the performance of existing solutions to better inform the state-of-the-art and identify their limitations and strengths. Lastly, we elaborate on current challenges facing the subject of technology and future trends attracting considerable interest, which could be a starting point for upcoming research studies.","PeriodicalId":158315,"journal":{"name":"Cloud Computing and Data Science","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130012685","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 : 2023-05-11DOI: 10.37256/ccds.4220232740
Song Jiang, Yuan Gu, Ela Kumar
With the emergence of new technologies, vast amounts of data have become pervasive in various aspects of social life, including public transportation, community services, and scientific research. As the population ages, healthcare has become increasingly crucial, and reducing the public burdens, especially in hospitals, has become an urgent issue. For instance, manually managing vast electronic medical files, such as MRI images, based on their types is practically impossible. However, accurate classification is fundamental and critical for subsequent tasks, such as diagnosis. In this article, we utilized machine learning techniques to classify MRI brain tumor images. We employed a range of machine learning models, including k-Nearest Neighbors (k-NN), decision tree, Support Vector Machine (SVM), logistic regression, and Stochastic Gradient Descent (SGD). The performance of each model type was measured by True Skill Statistics (TSS), based on the results obtained from the confusion matrix. The results showed that k-NN works most efficiently among all those classification models. However, due to the constraints of limited running time and computational power, further investigation of the models and parameter optimization are necessary for future work.
{"title":"Magnetic Resonance Imaging (MRI) Brain Tumor Image Classification Based on Five Machine Learning Algorithms","authors":"Song Jiang, Yuan Gu, Ela Kumar","doi":"10.37256/ccds.4220232740","DOIUrl":"https://doi.org/10.37256/ccds.4220232740","url":null,"abstract":"With the emergence of new technologies, vast amounts of data have become pervasive in various aspects of social life, including public transportation, community services, and scientific research. As the population ages, healthcare has become increasingly crucial, and reducing the public burdens, especially in hospitals, has become an urgent issue. For instance, manually managing vast electronic medical files, such as MRI images, based on their types is practically impossible. However, accurate classification is fundamental and critical for subsequent tasks, such as diagnosis. In this article, we utilized machine learning techniques to classify MRI brain tumor images. We employed a range of machine learning models, including k-Nearest Neighbors (k-NN), decision tree, Support Vector Machine (SVM), logistic regression, and Stochastic Gradient Descent (SGD). The performance of each model type was measured by True Skill Statistics (TSS), based on the results obtained from the confusion matrix. The results showed that k-NN works most efficiently among all those classification models. However, due to the constraints of limited running time and computational power, further investigation of the models and parameter optimization are necessary for future work.","PeriodicalId":158315,"journal":{"name":"Cloud Computing and Data Science","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123688306","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 : 2023-04-14DOI: 10.37256/ccds.4220232697
Yuan-Ko Huang
With the rapid advancements in mobile devices and wireless network technologies, the Internet of Things (IoT) has become more powerful and popular than ever. The aim of IoT is to efficiently control various types of objects through wireless communications. This paper aims to design an IoT-based smart lighting system that reduces development costs and saves power consumption. Unlike public open spaces, the focus of this paper is on ship cabin spaces. As ship cabins have unique properties, such as requiring gas-based power generation and preferring a wireless environment, designing a smart cabin lighting system is crucial and has significant commercial value. The smart cabin lighting system is designed with four features. Firstly, it can automatically control the lighting devices around people using position-sensitive devices. Secondly, it enables setting on/off and adjusting the luminance for lighting devices through Touch Keypads. Thirdly, the system can be controlled using an app to turn on/off and adjust the luminance of lighting devices. Lastly, the lighting devices equipped with sensors collect specific data on cloud servers for analysis. The underlying communication protocol used to interconnect the smart lighting devices, sensors, and Touch Keypads is Zigbee. The smart cabin lighting system can be applied to marine lighting, thus improving the commercial value of enterprises related to marine lighting.
{"title":"Design of a Smart Cabin Lighting System Based on Internet of Things","authors":"Yuan-Ko Huang","doi":"10.37256/ccds.4220232697","DOIUrl":"https://doi.org/10.37256/ccds.4220232697","url":null,"abstract":"With the rapid advancements in mobile devices and wireless network technologies, the Internet of Things (IoT) has become more powerful and popular than ever. The aim of IoT is to efficiently control various types of objects through wireless communications. This paper aims to design an IoT-based smart lighting system that reduces development costs and saves power consumption. Unlike public open spaces, the focus of this paper is on ship cabin spaces. As ship cabins have unique properties, such as requiring gas-based power generation and preferring a wireless environment, designing a smart cabin lighting system is crucial and has significant commercial value. The smart cabin lighting system is designed with four features. Firstly, it can automatically control the lighting devices around people using position-sensitive devices. Secondly, it enables setting on/off and adjusting the luminance for lighting devices through Touch Keypads. Thirdly, the system can be controlled using an app to turn on/off and adjust the luminance of lighting devices. Lastly, the lighting devices equipped with sensors collect specific data on cloud servers for analysis. The underlying communication protocol used to interconnect the smart lighting devices, sensors, and Touch Keypads is Zigbee. The smart cabin lighting system can be applied to marine lighting, thus improving the commercial value of enterprises related to marine lighting.","PeriodicalId":158315,"journal":{"name":"Cloud Computing and Data Science","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127468958","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：