In the cloud computing and the internet of things (IoT), various devices are connected. Therefore, to enhance the security of IoT applications, lightweight ciphers, which can be implemented in small area, have attracted attention. SPECK is a typical lightweight cipher, which is proposed by the National Security Agency (NSA), is optimized for the software implementation of microcontrollers. Regarding hardware security, the risk of fault analysis, which can easily reveal the secret key of a cryptographic circuit, is pointed out. To improve the IoT security, the study of fault analysis for SPECK is very important. This study proposes a round addition differential fault analysis method for a lightweight cipher SPECK. The proposed method uses an only one pair of ciphertext, and can reveal two round keys of SPECK. The simulation result verifies the validity of the proposed method and indicates the vulnerability of SPECK.
{"title":"Security Evaluation of a Lightweight Cipher SPECK against Round Addition DFA","authors":"Y. Nozaki, M. Yoshikawa","doi":"10.1145/3299819.3299837","DOIUrl":"https://doi.org/10.1145/3299819.3299837","url":null,"abstract":"In the cloud computing and the internet of things (IoT), various devices are connected. Therefore, to enhance the security of IoT applications, lightweight ciphers, which can be implemented in small area, have attracted attention. SPECK is a typical lightweight cipher, which is proposed by the National Security Agency (NSA), is optimized for the software implementation of microcontrollers. Regarding hardware security, the risk of fault analysis, which can easily reveal the secret key of a cryptographic circuit, is pointed out. To improve the IoT security, the study of fault analysis for SPECK is very important. This study proposes a round addition differential fault analysis method for a lightweight cipher SPECK. The proposed method uses an only one pair of ciphertext, and can reveal two round keys of SPECK. The simulation result verifies the validity of the proposed method and indicates the vulnerability of SPECK.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121756068","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}
In this paper, a data lake architecture is proposed for a class of monitoring and diagnostic systems applied to power grid. The differences between data lake and data warehouse is studied to make an informed decision on how to manage a huge amount of data. To adapt to the characteristics and performances of historical data and real-time data of power grid equipment, a monitoring and diagnosis system based on data lake storage architecture is designed. The application of the framework indicates the applicability and effectiveness of data lake architecture.
{"title":"A Data Lake Architecture for Monitoring and Diagnosis System of Power Grid","authors":"Ying Li, Aimin Zhang, Xinman Zhang, Zhihui Wu","doi":"10.1145/3299819.3299850","DOIUrl":"https://doi.org/10.1145/3299819.3299850","url":null,"abstract":"In this paper, a data lake architecture is proposed for a class of monitoring and diagnostic systems applied to power grid. The differences between data lake and data warehouse is studied to make an informed decision on how to manage a huge amount of data. To adapt to the characteristics and performances of historical data and real-time data of power grid equipment, a monitoring and diagnosis system based on data lake storage architecture is designed. The application of the framework indicates the applicability and effectiveness of data lake architecture.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132983526","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}
Alex Ferrin, J. Larrea, Miguel Realpe, Daniel Ochoa
In recent years 3D urban maps have become more common, thus providing complex point clouds that include diverse urban furniture such as pole-like objects. Utility poles detection in urban environment is of particular interest for electric utility companies in order to maintain an updated inventory for better planning and management. The present study develops an automatic method for the detection of utility poles from noisy point cloud data of Guayaquil - Ecuador, where many poles are located very close to buildings, which increases the difficulty of discriminating poles, walls, columns, fences and building corners. The proposed method applies a segmentation stage based on clustering with vertical voxels and a classification stage based on neural networks.
{"title":"Detection of utility poles from noisy Point Cloud Data in Urban environments","authors":"Alex Ferrin, J. Larrea, Miguel Realpe, Daniel Ochoa","doi":"10.1145/3299819.3299829","DOIUrl":"https://doi.org/10.1145/3299819.3299829","url":null,"abstract":"In recent years 3D urban maps have become more common, thus providing complex point clouds that include diverse urban furniture such as pole-like objects. Utility poles detection in urban environment is of particular interest for electric utility companies in order to maintain an updated inventory for better planning and management. The present study develops an automatic method for the detection of utility poles from noisy point cloud data of Guayaquil - Ecuador, where many poles are located very close to buildings, which increases the difficulty of discriminating poles, walls, columns, fences and building corners. The proposed method applies a segmentation stage based on clustering with vertical voxels and a classification stage based on neural networks.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"700 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122986387","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}
Autism community is now receiving broad attention from Chinese society. Though data-mining on textual data have been widely used, its application on Chinese language environment on autism is rare. The previous research on textual mining of online posts did not target a specific symptom exhibited on children with autism; meanwhile, the written language is limited to English. In this paper, we conduct a comparison on text analysis of parents, reporters and experts' online posts and published work, particularly targeting nonverbal autistic children. The text analysis contains the word frequency analysis and sentiment analysis. Our study revealed that parents tend to share emotional views, reporters are likely to provide introductory articles for the autism, and experts hold more critical comments for nonverbal autistic children.
{"title":"\"Voices of Autism\": Sentiment Analysis in Three Chinese Websites on Nonverbal Autistic Children","authors":"Aonan Guan, Jie Chen, T. Tang","doi":"10.1145/3299819.3299838","DOIUrl":"https://doi.org/10.1145/3299819.3299838","url":null,"abstract":"Autism community is now receiving broad attention from Chinese society. Though data-mining on textual data have been widely used, its application on Chinese language environment on autism is rare. The previous research on textual mining of online posts did not target a specific symptom exhibited on children with autism; meanwhile, the written language is limited to English. In this paper, we conduct a comparison on text analysis of parents, reporters and experts' online posts and published work, particularly targeting nonverbal autistic children. The text analysis contains the word frequency analysis and sentiment analysis. Our study revealed that parents tend to share emotional views, reporters are likely to provide introductory articles for the autism, and experts hold more critical comments for nonverbal autistic children.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116357026","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}
Differences in languages among various countries, regions, and nationalities have created huge obstacles in communication. Cross-language word similarity (CLWS) calculation is the most practical way to solve this problem. Selection of corpus is one of the factors that influence the calculate result. This paper compares the similarity in word embeddings of bilingual parallel and non-parallel corpus on traditional models. Firstly, this paper uses the fastText method to calculate the monolingual word embeddings of Chinese and English, and computes the semantic similarity between the two embeddings. Then it maps the word embeddings into an implicit shared space using Multilingual Unsupervised and Supervised Embedding (MUSE), and compares the effect of unsupervised and supervised machine learning methods in parallel and non-parallel corpus. Finally, the experimental results prove that MUSE model could be better align monolingual word embeddings space, non-parallel corpus have the same effect compares with parallel corpus in calculating the CLWS.
{"title":"English-Chinese Cross Language Word Embedding Similarity Calculation","authors":"Like Wang, Yuan Sun, Xiaobing Zhao","doi":"10.1145/3299819.3299831","DOIUrl":"https://doi.org/10.1145/3299819.3299831","url":null,"abstract":"Differences in languages among various countries, regions, and nationalities have created huge obstacles in communication. Cross-language word similarity (CLWS) calculation is the most practical way to solve this problem. Selection of corpus is one of the factors that influence the calculate result. This paper compares the similarity in word embeddings of bilingual parallel and non-parallel corpus on traditional models. Firstly, this paper uses the fastText method to calculate the monolingual word embeddings of Chinese and English, and computes the semantic similarity between the two embeddings. Then it maps the word embeddings into an implicit shared space using Multilingual Unsupervised and Supervised Embedding (MUSE), and compares the effect of unsupervised and supervised machine learning methods in parallel and non-parallel corpus. Finally, the experimental results prove that MUSE model could be better align monolingual word embeddings space, non-parallel corpus have the same effect compares with parallel corpus in calculating the CLWS.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126401665","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}
The main obstacles in the evolutionary design of sequential circuits are the state assignment and the large evolution time for a complete circuit. In this paper, in order to minimize evolution time, a genetic algorithm (GA) based on a cost evolution of the circuit evolution is proposed to evolve a state assignment, which can lead to complexity reduction. A cost evaluation of the circuit evolution is uniquely defined as the fitness function of state assignment candidates. Under the GA-evolved state assignment, a novel LUT-based circuit evolution (LCE) is proposed to improve the search for a complete circuit. An extrinsic EHW system namely GALCE, which combines GA and LCE, aims to the evolutionary optimization and design of sequential circuit. This system is tested extensively on eight sequential circuits. The simulation results demonstrate the proposed approach can perform better in terms of average evolution time reduction and success rate.
{"title":"An extrinsic EHW system for the evolutionary optimization and design of sequential circuit","authors":"Yanyun Tao, Yuzhen Zhang","doi":"10.1145/3299819.3299832","DOIUrl":"https://doi.org/10.1145/3299819.3299832","url":null,"abstract":"The main obstacles in the evolutionary design of sequential circuits are the state assignment and the large evolution time for a complete circuit. In this paper, in order to minimize evolution time, a genetic algorithm (GA) based on a cost evolution of the circuit evolution is proposed to evolve a state assignment, which can lead to complexity reduction. A cost evaluation of the circuit evolution is uniquely defined as the fitness function of state assignment candidates. Under the GA-evolved state assignment, a novel LUT-based circuit evolution (LCE) is proposed to improve the search for a complete circuit. An extrinsic EHW system namely GALCE, which combines GA and LCE, aims to the evolutionary optimization and design of sequential circuit. This system is tested extensively on eight sequential circuits. The simulation results demonstrate the proposed approach can perform better in terms of average evolution time reduction and success rate.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130393851","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}
In the legal domain it is important to differentiate between words in general, and afterwards to link the occurrences of the same entities. The topic to solve these challenges is called Named-Entity Linking (NEL). Current supervised neural networks designed for NEL use publicly available datasets for training and testing. However, this paper focuses especially on the aspect of applying transfer learning approach using networks trained for NEL to legal documents. Experiments show consistent improvement in the legal datasets that were created from the European Union law in the scope of this research. Using transfer learning approach, we reached F1-score of 98.90% and 98.01% on the legal small and large test dataset.
{"title":"Deep Learning for Named-Entity Linking with Transfer Learning for Legal Documents","authors":"Ahmed Elnaggar, Robin Otto, F. Matthes","doi":"10.1145/3299819.3299846","DOIUrl":"https://doi.org/10.1145/3299819.3299846","url":null,"abstract":"In the legal domain it is important to differentiate between words in general, and afterwards to link the occurrences of the same entities. The topic to solve these challenges is called Named-Entity Linking (NEL). Current supervised neural networks designed for NEL use publicly available datasets for training and testing. However, this paper focuses especially on the aspect of applying transfer learning approach using networks trained for NEL to legal documents. Experiments show consistent improvement in the legal datasets that were created from the European Union law in the scope of this research. Using transfer learning approach, we reached F1-score of 98.90% and 98.01% on the legal small and large test dataset.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"85 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123176218","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}
Many predictive tasks in recommender systems model from categorical variables. Different from continuous features extracted from images and videos, categorical data is discrete and of multi-field while their dependencies are little known, which brings the problem of heavy computation on a large-scale sparse feature space. Deep learning methods have strong feature extraction capabilities and now have been more and more widely applied to recommender systems, but they do not perform well on discrete data. To tackle these two problems, in this paper we propose Deep Feature Fusion Model(DFFM) over sparse multi-field categorical data. DFFM utilizes categorical features as inputs and applies the Stacked Denoising AutoEncoder to obtain a dense representation. We construct a full feature connection layer and adopt a multi-layer convolution neural network to further extract deeper features and convert rating prediction to a classification problem. The extensive experiments on real world datasets show that our proposed method outperforms other state-of-the-art approaches.
{"title":"Deep Feature Fusion over Multi-field Categorical Data for Rating Prediction","authors":"Yue Ding, Jie Liu, Dong Wang","doi":"10.1145/3299819.3299827","DOIUrl":"https://doi.org/10.1145/3299819.3299827","url":null,"abstract":"Many predictive tasks in recommender systems model from categorical variables. Different from continuous features extracted from images and videos, categorical data is discrete and of multi-field while their dependencies are little known, which brings the problem of heavy computation on a large-scale sparse feature space. Deep learning methods have strong feature extraction capabilities and now have been more and more widely applied to recommender systems, but they do not perform well on discrete data. To tackle these two problems, in this paper we propose Deep Feature Fusion Model(DFFM) over sparse multi-field categorical data. DFFM utilizes categorical features as inputs and applies the Stacked Denoising AutoEncoder to obtain a dense representation. We construct a full feature connection layer and adopt a multi-layer convolution neural network to further extract deeper features and convert rating prediction to a classification problem. The extensive experiments on real world datasets show that our proposed method outperforms other state-of-the-art approaches.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131864448","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}
Gomoku is an ancient board game. The traditional approach to solving the Gomoku is to apply tree search on a Gomoku game tree. Although the rules of Gomoku are straightforward, the game tree complexity is enormous. Unlike other board games such as chess and Shogun, the Gomoku board state is more intuitive. This feature is similar to another famous board game, the game of Go. The success of AlphaGo [5, 6] inspired us to apply a supervised learning method and deep neural network in solving the Gomoku game. We designed a deep convolutional neural network model to help the machine learn from the training data. In our experiment, we got 69% accuracy on the training data and 38% accuracy on the testing data. Finally, we combined the trained deep neural network model with a hard-coded convolution-based Gomoku evaluation function to form a hybrid Gomoku artificial intelligence (AI) which further improved performance.
{"title":"A Hybrid Gomoku Deep Learning Artificial Intelligence","authors":"Peizhi Yan, Yi Feng","doi":"10.1145/3299819.3299820","DOIUrl":"https://doi.org/10.1145/3299819.3299820","url":null,"abstract":"Gomoku is an ancient board game. The traditional approach to solving the Gomoku is to apply tree search on a Gomoku game tree. Although the rules of Gomoku are straightforward, the game tree complexity is enormous. Unlike other board games such as chess and Shogun, the Gomoku board state is more intuitive. This feature is similar to another famous board game, the game of Go. The success of AlphaGo [5, 6] inspired us to apply a supervised learning method and deep neural network in solving the Gomoku game. We designed a deep convolutional neural network model to help the machine learn from the training data. In our experiment, we got 69% accuracy on the training data and 38% accuracy on the testing data. Finally, we combined the trained deep neural network model with a hard-coded convolution-based Gomoku evaluation function to form a hybrid Gomoku artificial intelligence (AI) which further improved performance.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128665440","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}
Ahmed Elnaggar, Bernhard Waltl, Ingo Glaser, Jörg Landthaler, Elena Scepankova, F. Matthes
Deep learning methods are often difficult to apply in the legal domain due to the large amount of labeled data required by deep learning methods. A recent new trend in the deep learning community is the application of multi-task models that enable single deep neural networks to perform more than one task at the same time, for example classification and translation tasks. These powerful novel models are capable of transferring knowledge among different tasks or training sets and therefore could open up the legal domain for many deep learning applications. In this paper, we investigate the transfer learning capabilities of such a multi-task model on a classification task on the publicly available Kaggle toxic comment dataset for classifying illegal comments and we can report promising results.
{"title":"Stop Illegal Comments: A Multi-Task Deep Learning Approach","authors":"Ahmed Elnaggar, Bernhard Waltl, Ingo Glaser, Jörg Landthaler, Elena Scepankova, F. Matthes","doi":"10.1145/3299819.3299845","DOIUrl":"https://doi.org/10.1145/3299819.3299845","url":null,"abstract":"Deep learning methods are often difficult to apply in the legal domain due to the large amount of labeled data required by deep learning methods. A recent new trend in the deep learning community is the application of multi-task models that enable single deep neural networks to perform more than one task at the same time, for example classification and translation tasks. These powerful novel models are capable of transferring knowledge among different tasks or training sets and therefore could open up the legal domain for many deep learning applications. In this paper, we investigate the transfer learning capabilities of such a multi-task model on a classification task on the publicly available Kaggle toxic comment dataset for classifying illegal comments and we can report promising results.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116012348","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：