Pub Date : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583184
Youssef Mansour, Hamdan Hammad, O. A. Waraga, M. A. Talib
Smartphones are a crucial necessity in people’s lives nowadays. Many smartphone hardware components (i.e., CPU, Wi-Fi, etc…) are in rapid development, improving their performance. However, battery technology has not been able to keep up with this pace of development where battery life becomes shorter and shorter with every new update. Therefore, smartphone energy management has become very important and has been studied by many researchers. In this research paper, we conducted a Systematic Literature Review (SLR) to review the research contribution made in the field of smartphone Energy Management Systems (EMS). We analyzed 72 relevant papers and grouped them into two categories: 1) energy management techniques that reduce or limit energy consumption, and 2) smartphone energy assessments that focus on analyzing energy consumption by smartphone components. Then, we found that mobile application was the most studied smartphone module followed by network and operating system. Around 29 studies built their solution on Android which shows the importance of open source. Finally, the study highlights the research gap in power management for closed source systems and drivers as well as specific hardware modules.
{"title":"Energy Management Systems and Smart Phones: A Systematic Literature Survey","authors":"Youssef Mansour, Hamdan Hammad, O. A. Waraga, M. A. Talib","doi":"10.1109/CCCI52664.2021.9583184","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583184","url":null,"abstract":"Smartphones are a crucial necessity in people’s lives nowadays. Many smartphone hardware components (i.e., CPU, Wi-Fi, etc…) are in rapid development, improving their performance. However, battery technology has not been able to keep up with this pace of development where battery life becomes shorter and shorter with every new update. Therefore, smartphone energy management has become very important and has been studied by many researchers. In this research paper, we conducted a Systematic Literature Review (SLR) to review the research contribution made in the field of smartphone Energy Management Systems (EMS). We analyzed 72 relevant papers and grouped them into two categories: 1) energy management techniques that reduce or limit energy consumption, and 2) smartphone energy assessments that focus on analyzing energy consumption by smartphone components. Then, we found that mobile application was the most studied smartphone module followed by network and operating system. Around 29 studies built their solution on Android which shows the importance of open source. Finally, the study highlights the research gap in power management for closed source systems and drivers as well as specific hardware modules.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115455825","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}
With the number of in-vehicle infotainment applications exponentially increasing, offloading several subtasks divided from computation-intensive application to different fog nodes is convinced as a promising paradigm to satisfy the offloading requirements. However, failure transmission of subtask in any fog node will increase execution latency and energy consumption in Vehicular Fog Networks (VeFNs). In this paper, we leverage the code technology to produce extra subtasks and exchange the redundancy of computing resources for reliability, which improve the robustness of vehicle to vehicle (V2V) communication and decrease the overhead of computation offloading. Furthermore, we adopt a code-based computation offloading algorithm based on simulated annealing (CBSA) that finds the optimal coding scheme and resources allocation strategy. The numerical results are illustrated to demonstrate effectiveness of proposed algorithm.
{"title":"Code-based Computation Offloading in Vehicular Fog Networks","authors":"Fangzhe Chen, Zhibin Gao, Zhang Liu, Lianfeng Huang, Yuliang Tang","doi":"10.1109/CCCI52664.2021.9583208","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583208","url":null,"abstract":"With the number of in-vehicle infotainment applications exponentially increasing, offloading several subtasks divided from computation-intensive application to different fog nodes is convinced as a promising paradigm to satisfy the offloading requirements. However, failure transmission of subtask in any fog node will increase execution latency and energy consumption in Vehicular Fog Networks (VeFNs). In this paper, we leverage the code technology to produce extra subtasks and exchange the redundancy of computing resources for reliability, which improve the robustness of vehicle to vehicle (V2V) communication and decrease the overhead of computation offloading. Furthermore, we adopt a code-based computation offloading algorithm based on simulated annealing (CBSA) that finds the optimal coding scheme and resources allocation strategy. The numerical results are illustrated to demonstrate effectiveness of proposed algorithm.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126033371","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583196
Shanyin Peng, Ning Wang
Pneumonia is one of the most common infectious diseases in clinic. X-ray chest is an important basis for early diagnosis of pneumonia. With the development of computer vision technology, using convolutional neural network to train pneumonia image classification model has been gradually applied to the process of medical clinical diagnosis. However, there are many problems in the process of using convolutional neural network to train pneumonia image classification model, such as too long model training time, over fitting and low accuracy due to too small training dataset. To solve these problems, this paper proposes an optimization method of pneumonia image classification model based on transfer learning and feature fusion, which is called Transfer Fusion. The Transfer Fusion optimization method will transplant the trained source model parameters to the target model, and add a specific feature fusion classification layer, so as to significantly shorten the training time of the new model, improve the accuracy and prevent over fitting. In this paper, Transfer Fusion optimization method is applied to three common convolutional neural network models: Google InceptionNetV3, MobileNetV2 and ResNet50. Through a large number of experiments, the performance of the three models has been significantly improved and improved.
{"title":"Optimization Method of Pneumonia Image Classification Model Based on Deep Transfer Learning","authors":"Shanyin Peng, Ning Wang","doi":"10.1109/CCCI52664.2021.9583196","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583196","url":null,"abstract":"Pneumonia is one of the most common infectious diseases in clinic. X-ray chest is an important basis for early diagnosis of pneumonia. With the development of computer vision technology, using convolutional neural network to train pneumonia image classification model has been gradually applied to the process of medical clinical diagnosis. However, there are many problems in the process of using convolutional neural network to train pneumonia image classification model, such as too long model training time, over fitting and low accuracy due to too small training dataset. To solve these problems, this paper proposes an optimization method of pneumonia image classification model based on transfer learning and feature fusion, which is called Transfer Fusion. The Transfer Fusion optimization method will transplant the trained source model parameters to the target model, and add a specific feature fusion classification layer, so as to significantly shorten the training time of the new model, improve the accuracy and prevent over fitting. In this paper, Transfer Fusion optimization method is applied to three common convolutional neural network models: Google InceptionNetV3, MobileNetV2 and ResNet50. Through a large number of experiments, the performance of the three models has been significantly improved and improved.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"177 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114380547","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583217
C. Meshram, M. Obaidat, K. Hsiao, A. Imoize, A. Meshram
Along with the proliferation of cyberspace and the beginning of electronic trade, many electronic cash protocols were suggested. Electronic cash allows digital coins to be exchanged with value guaranteed by the signature of the financial institution and the hidden identity of the client. A client can withdraw money from the financial institution in an electronic cash protocol and then anonymously and unlinkably spend each coin. The present article suggests a practical, fair offline electronic cash protocol using extended chaotic maps capable of coin locating and seller locating. Under certain conditions, the protocol’s anonymity perchance was revoked from an offline trusted third party. The trustworthy third party verifies the financial institution’s e-coin signature in our protocol and then logs the location of data that isn’t part of the normal electronic cash protocol.
{"title":"An Effective Fair Off-Line Electronic Cash Protocol using Extended Chaotic Maps with Anonymity Revoking Trustee","authors":"C. Meshram, M. Obaidat, K. Hsiao, A. Imoize, A. Meshram","doi":"10.1109/CCCI52664.2021.9583217","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583217","url":null,"abstract":"Along with the proliferation of cyberspace and the beginning of electronic trade, many electronic cash protocols were suggested. Electronic cash allows digital coins to be exchanged with value guaranteed by the signature of the financial institution and the hidden identity of the client. A client can withdraw money from the financial institution in an electronic cash protocol and then anonymously and unlinkably spend each coin. The present article suggests a practical, fair offline electronic cash protocol using extended chaotic maps capable of coin locating and seller locating. Under certain conditions, the protocol’s anonymity perchance was revoked from an offline trusted third party. The trustworthy third party verifies the financial institution’s e-coin signature in our protocol and then logs the location of data that isn’t part of the normal electronic cash protocol.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128370036","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583197
Lianfeng Huang, Tao Chen, Zhibin Gao, Manman Luo, Zhang Liu
Ultra-Reliable Low-Latency Communication (URLLC) as one of the three fifth-generation (5G) typical application scenarios in the future, which requires extreme reliability and low latency. The 3rd Generation Partnership Project (3GPP) expects the transmission of 32-byte packets with the user plane latency of less than 1 ms and 99.999% reliability. With the aim to evaluate the performance of 5G URLLC network, performing system level simulations is a crucial and effective method. In this paper, we modify and expand the Vienna 5G System Level Simulator to support the 5G URLLC scenario, and finally study the impact of three different scheduling algorithms on throughput, Signal to Interference plus Noise Ratio (SINR), latency and reliability of URLLC network.
{"title":"System Level simulation for 5G Ultra-Reliable Low-Latency Communication","authors":"Lianfeng Huang, Tao Chen, Zhibin Gao, Manman Luo, Zhang Liu","doi":"10.1109/CCCI52664.2021.9583197","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583197","url":null,"abstract":"Ultra-Reliable Low-Latency Communication (URLLC) as one of the three fifth-generation (5G) typical application scenarios in the future, which requires extreme reliability and low latency. The 3rd Generation Partnership Project (3GPP) expects the transmission of 32-byte packets with the user plane latency of less than 1 ms and 99.999% reliability. With the aim to evaluate the performance of 5G URLLC network, performing system level simulations is a crucial and effective method. In this paper, we modify and expand the Vienna 5G System Level Simulator to support the 5G URLLC scenario, and finally study the impact of three different scheduling algorithms on throughput, Signal to Interference plus Noise Ratio (SINR), latency and reliability of URLLC network.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116182302","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583202
Xiaoqing Yang, Yuelong Zhu, Jun Feng, Jiamin Lu
The development of information technology has resulted in an exponential increase of archive information. Using cross-modal retrieval can achieve mutual retrieval of data like image and text. Aside from the former progresses, it is still challenging to mine both inter-modal connection and the intrinsic semantic associations of cross-modal data. In this paper, we propose a method to achieve an accurate and effective cross-modal retrieval. It uniformly represents heterogeneous data through the principal affinity representation algorithm based on a hybrid kernel function. To improve the accuracy of retrieval, we first employ an adaptive nearest neighbor search method to dynamically decide the retrieval radius. The search method is then combined with the existing tree structure-based retrieval algorithm to find the nearest neighbor points efficiently. The experimental results show our algorithms have a certain improvement in efficiency and accuracy of cross-modal retrieval.
{"title":"Cross-modal Retrieval of Archives based on Principal Affinity Representation","authors":"Xiaoqing Yang, Yuelong Zhu, Jun Feng, Jiamin Lu","doi":"10.1109/CCCI52664.2021.9583202","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583202","url":null,"abstract":"The development of information technology has resulted in an exponential increase of archive information. Using cross-modal retrieval can achieve mutual retrieval of data like image and text. Aside from the former progresses, it is still challenging to mine both inter-modal connection and the intrinsic semantic associations of cross-modal data. In this paper, we propose a method to achieve an accurate and effective cross-modal retrieval. It uniformly represents heterogeneous data through the principal affinity representation algorithm based on a hybrid kernel function. To improve the accuracy of retrieval, we first employ an adaptive nearest neighbor search method to dynamically decide the retrieval radius. The search method is then combined with the existing tree structure-based retrieval algorithm to find the nearest neighbor points efficiently. The experimental results show our algorithms have a certain improvement in efficiency and accuracy of cross-modal retrieval.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115851079","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583189
Yabin Xu, Shengjie Sun, Zhuang Wu
In order to speed up the development of new iron-base alloy materials and reduce the consumption of time and resources caused by a large number of experiments, a prediction method for Gibbs free energy of iron-base alloy materials was proposed based on the theory of material genetic engineering. Firstly, the collected data were preprocessed by splicing, filling, normalization and one-hot coding to adapt to the training of the model. Then, based on the DeepFM model, a fusion model based on Factorization Machine (FM), bitwise self-attention mechanism and Bi-directional Long Short-term Memory Network (Bi-LSTM) was proposed to predict the Gibbs free energy of iron-base alloy materials. It can not only extract the low-order and high-order features of the data effectively, but also the weight coefficients of each data feature can be reasonably optimized and the correlation between the data can be fully considered. The comparative experimental results show that the Gibbs free energy prediction method based on deep learning has a good prediction effect. It provides a new method to predict the Gibbs free energy of iron-base alloys.
{"title":"Gibbs Free-energy Prediction Method for Iron-base Alloy Materials Based on Deep Learning*","authors":"Yabin Xu, Shengjie Sun, Zhuang Wu","doi":"10.1109/CCCI52664.2021.9583189","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583189","url":null,"abstract":"In order to speed up the development of new iron-base alloy materials and reduce the consumption of time and resources caused by a large number of experiments, a prediction method for Gibbs free energy of iron-base alloy materials was proposed based on the theory of material genetic engineering. Firstly, the collected data were preprocessed by splicing, filling, normalization and one-hot coding to adapt to the training of the model. Then, based on the DeepFM model, a fusion model based on Factorization Machine (FM), bitwise self-attention mechanism and Bi-directional Long Short-term Memory Network (Bi-LSTM) was proposed to predict the Gibbs free energy of iron-base alloy materials. It can not only extract the low-order and high-order features of the data effectively, but also the weight coefficients of each data feature can be reasonably optimized and the correlation between the data can be fully considered. The comparative experimental results show that the Gibbs free energy prediction method based on deep learning has a good prediction effect. It provides a new method to predict the Gibbs free energy of iron-base alloys.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"313 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132340931","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583204
Yue Chen, Yu Guo, Yuanyan Xie, Zhenqiang Mi
With the advent of big data, the number of web pages and information are increasing exponentially. Much of the information we retrieve is mixed and redundant, which affects the effectiveness of retrieval. Therefore, information retrieval has become an indispensable technology. Compared with ordinary retrieval, the retrieval of laws and regulations needs higher relevance and accuracy. Aiming at the poor retrieval effect and unreasonable results in terms of legal retrieval, this paper proposes a legal and regulation retrieval system, our work is establishing a high-quality database, removing the stop word, and increasing hierarchical retrieval. Experimental results show that the proposed method in terms of legal retrieval is more effective than general legal search systems and wide-area search systems. In the end, we complete the design and visual display of the whole retrieval system to ensure the accuracy of retrieval results and the conciseness of retrieval contents.
{"title":"Legal and Regulation Retrieval System Based on Hierarchical Retrieval","authors":"Yue Chen, Yu Guo, Yuanyan Xie, Zhenqiang Mi","doi":"10.1109/CCCI52664.2021.9583204","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583204","url":null,"abstract":"With the advent of big data, the number of web pages and information are increasing exponentially. Much of the information we retrieve is mixed and redundant, which affects the effectiveness of retrieval. Therefore, information retrieval has become an indispensable technology. Compared with ordinary retrieval, the retrieval of laws and regulations needs higher relevance and accuracy. Aiming at the poor retrieval effect and unreasonable results in terms of legal retrieval, this paper proposes a legal and regulation retrieval system, our work is establishing a high-quality database, removing the stop word, and increasing hierarchical retrieval. Experimental results show that the proposed method in terms of legal retrieval is more effective than general legal search systems and wide-area search systems. In the end, we complete the design and visual display of the whole retrieval system to ensure the accuracy of retrieval results and the conciseness of retrieval contents.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130131422","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583214
Xinyi Hu, Chunxiang Gu, Yihang Chen, Fushan Wei
The Internet is about to enter the era of full encryption. Traditional traffic classification methods only work well in non-encrypted environments. How to identify the specific types of network encrypted traffic in an encrypted environment without decryption is one of the foundations for maintaining cyberspace security. Traffic classification based on machine learning relies heavily on the prior knowledge of experts to construct feature sets. Although traffic classification based on deep learning can reduce human intervention, it requires a large amount of labeled data for parameter determination. This paper proposes a tCLD-Net model that combines transfer learning and deep learning. It can be trained on a small amount of labeled data to distinguish network encrypted traffic with a high accuracy. It pre-trains a CLD-Net model in the source domain data set, and fixes the parameters of the convolutional neural network module in it, and trains and tests it in the target domain data set. In order to verify the effectiveness of the tCLD-Net model, we use the ISCX public data set to conduct experiments. The results show that our proposed model can complete 100 epoches training in 208 seconds when the training set only occupies 20% of the target domain. And achieve a classification accuracy rate about 86%. This is 4% higher than the model without pre-training, and the training time is only one third of the model without pre-training.
{"title":"tCLD-Net: A Transfer Learning Internet Encrypted Traffic Classification Scheme Based on Convolution Neural Network and Long Short-Term Memory Network","authors":"Xinyi Hu, Chunxiang Gu, Yihang Chen, Fushan Wei","doi":"10.1109/CCCI52664.2021.9583214","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583214","url":null,"abstract":"The Internet is about to enter the era of full encryption. Traditional traffic classification methods only work well in non-encrypted environments. How to identify the specific types of network encrypted traffic in an encrypted environment without decryption is one of the foundations for maintaining cyberspace security. Traffic classification based on machine learning relies heavily on the prior knowledge of experts to construct feature sets. Although traffic classification based on deep learning can reduce human intervention, it requires a large amount of labeled data for parameter determination. This paper proposes a tCLD-Net model that combines transfer learning and deep learning. It can be trained on a small amount of labeled data to distinguish network encrypted traffic with a high accuracy. It pre-trains a CLD-Net model in the source domain data set, and fixes the parameters of the convolutional neural network module in it, and trains and tests it in the target domain data set. In order to verify the effectiveness of the tCLD-Net model, we use the ISCX public data set to conduct experiments. The results show that our proposed model can complete 100 epoches training in 208 seconds when the training set only occupies 20% of the target domain. And achieve a classification accuracy rate about 86%. This is 4% higher than the model without pre-training, and the training time is only one third of the model without pre-training.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132395791","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583195
Jinghu Li, Lili Wang, Q. Xing
Video surveillance is an important method to obtain the dynamic changes of green macroalgae along the coast. The paper proposes a coastal green macroalgae extraction method based on the SLIC superpixel segmentation, CNN and SVM to realize the automated recognition of green macroalgae from lots of high-resolution RGB video data collected by unmanned aerial vehicle (UAV) and handheld devices. Firstly, SLIC algorithm is used to generate the multi-scale patches on the original high-resolution image. Then, three classification CNN is used to divide the multi-scale patches into three types: green macroalgae, background and mixing. Finally, SVM algorithm is used to extract the green macroalgae to improve the accuracy at the pixel level in the mixed patches. In order to evaluate the performance of the proposed method, experiments are conducted on our coastal green macroalgae image dataset. Compared with the method of RGB vegetation indices (such as ExR, RGBVI, NGBDI), the overall accuracy (OA), F1 score, and Kappa of the green macroalgae extraction with the method proposed in this paper are up to 95.23%, 0.9612, 0.9436, respectively. The results show that our method is significantly better than that of RGB vegetation indices since it effectively reduces the influence of sea waves and light on the recognition results. The automated extraction method for coastal green macroalgae proposed in this paper can provide a reference for the automatic monitoring of coastal green macroalgae with high precision.
{"title":"Detection of Coastal Green Macroalgae based on SLIC, CNN and SVM","authors":"Jinghu Li, Lili Wang, Q. Xing","doi":"10.1109/CCCI52664.2021.9583195","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583195","url":null,"abstract":"Video surveillance is an important method to obtain the dynamic changes of green macroalgae along the coast. The paper proposes a coastal green macroalgae extraction method based on the SLIC superpixel segmentation, CNN and SVM to realize the automated recognition of green macroalgae from lots of high-resolution RGB video data collected by unmanned aerial vehicle (UAV) and handheld devices. Firstly, SLIC algorithm is used to generate the multi-scale patches on the original high-resolution image. Then, three classification CNN is used to divide the multi-scale patches into three types: green macroalgae, background and mixing. Finally, SVM algorithm is used to extract the green macroalgae to improve the accuracy at the pixel level in the mixed patches. In order to evaluate the performance of the proposed method, experiments are conducted on our coastal green macroalgae image dataset. Compared with the method of RGB vegetation indices (such as ExR, RGBVI, NGBDI), the overall accuracy (OA), F1 score, and Kappa of the green macroalgae extraction with the method proposed in this paper are up to 95.23%, 0.9612, 0.9436, respectively. The results show that our method is significantly better than that of RGB vegetation indices since it effectively reduces the influence of sea waves and light on the recognition results. The automated extraction method for coastal green macroalgae proposed in this paper can provide a reference for the automatic monitoring of coastal green macroalgae with high precision.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126208547","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：