Pub Date : 2023-05-01DOI: 10.53106/160792642023052403003
Junwei Xin Junwei Xin, Xiaoyong Chen Junwei Xin, Zixin Liu Xiaoyong Chen, Yan Luo Zixin Liu, Zhenxing Liu Yan Luo
This paper presents a valid shadow detection method subjected to WorldView-II remote images combining band standardization with principal component transformation algorithm. Eight bands among The WorldView-II image, each band indicates a specified range of values. Firstly, each band is standardized to the same scale, then utilizing three optimal bands forms a new single band. According to the characteristics of principal component, if the gray value of dark material is positive, just take it for granted, which will be used in next operation. Once the gray value is negative, it will be inverted comparing with the former. In this study, selecting the above adaption builds up an advanced shadow index. Experimental results show that the shadow index can distinguish the shadow from other objects effectively, such as water in high brightness, vegetation, roads, buildings. Meanwhile, there is no significant difference between the water in low brightness and high when using the shadow index. To cope with this problem, we propose an advanced water index based on the normalized differential water index, which is constructed to eliminate the interference of water in low brightness. Results indicate that the indexes can accurately distinguish shadow regions in the WorldView-II image data.
{"title":"Study on Shadow Detection of World View-II Remote Sensing Image Based on Band Standardization","authors":"Junwei Xin Junwei Xin, Xiaoyong Chen Junwei Xin, Zixin Liu Xiaoyong Chen, Yan Luo Zixin Liu, Zhenxing Liu Yan Luo","doi":"10.53106/160792642023052403003","DOIUrl":"https://doi.org/10.53106/160792642023052403003","url":null,"abstract":"\u0000 This paper presents a valid shadow detection method subjected to WorldView-II remote images combining band standardization with principal component transformation algorithm. Eight bands among The WorldView-II image, each band indicates a specified range of values. Firstly, each band is standardized to the same scale, then utilizing three optimal bands forms a new single band. According to the characteristics of principal component, if the gray value of dark material is positive, just take it for granted, which will be used in next operation. Once the gray value is negative, it will be inverted comparing with the former. In this study, selecting the above adaption builds up an advanced shadow index. Experimental results show that the shadow index can distinguish the shadow from other objects effectively, such as water in high brightness, vegetation, roads, buildings. Meanwhile, there is no significant difference between the water in low brightness and high when using the shadow index. To cope with this problem, we propose an advanced water index based on the normalized differential water index, which is constructed to eliminate the interference of water in low brightness. Results indicate that the indexes can accurately distinguish shadow regions in the WorldView-II image data.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124975366","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 : 2023-05-01DOI: 10.53106/160792642023052403017
Xian Guo Xian Guo, Keyu Chen Xian Guo, An Yang Keyu Chen, Zhanhui Gang An Yang
With the rapid development of "Internet +" and the construction of a new generation of information infrastructure, the intrusion behaviors against the Industrial Internet of Things are increasingly common. How to ensure the security of the industrial Internet of Things is one of the current research hotspots. The modern technology trend has the hottest technologies of the Internet of Things (IoT). The application of IoT on the other hand improves work efficiency and brings convenience to people’s life; on the other hand, it makes the network face increasingly serious security threat problems and attacks the network by unscrupulous elements occur from time to time. Machine learning-based intrusion detection techniques involve a large number of mathematical formula operations, while with the development of neural networks, the excellent autonomous feature learning capability of deep learning is recognized. An intrusion detection system plays an important role in preventing security threats and protecting them from attacks. The current research on industrial IoT security technology focuses on authentication technology, encryption technology, access control technology, and intrusion detection technology. In this paper, we analyze deep learning and industrial IoT intrusion detection and use the powerful data processing capability and feature learning capability of deep learning to conduct an in-depth study on industrial IoT intrusion detection methods based on deep learning. This paper achieves a 96.32% detection rate on industrial control dataset, which can better adapt to the needs of industrial IoT intrusion detection.
{"title":"Research on Industrial IoT Security Based on Deep Learning","authors":"Xian Guo Xian Guo, Keyu Chen Xian Guo, An Yang Keyu Chen, Zhanhui Gang An Yang","doi":"10.53106/160792642023052403017","DOIUrl":"https://doi.org/10.53106/160792642023052403017","url":null,"abstract":"\u0000 With the rapid development of \"Internet +\" and the construction of a new generation of information infrastructure, the intrusion behaviors against the Industrial Internet of Things are increasingly common. How to ensure the security of the industrial Internet of Things is one of the current research hotspots. The modern technology trend has the hottest technologies of the Internet of Things (IoT). The application of IoT on the other hand improves work efficiency and brings convenience to people’s life; on the other hand, it makes the network face increasingly serious security threat problems and attacks the network by unscrupulous elements occur from time to time. Machine learning-based intrusion detection techniques involve a large number of mathematical formula operations, while with the development of neural networks, the excellent autonomous feature learning capability of deep learning is recognized. An intrusion detection system plays an important role in preventing security threats and protecting them from attacks. The current research on industrial IoT security technology focuses on authentication technology, encryption technology, access control technology, and intrusion detection technology. In this paper, we analyze deep learning and industrial IoT intrusion detection and use the powerful data processing capability and feature learning capability of deep learning to conduct an in-depth study on industrial IoT intrusion detection methods based on deep learning. This paper achieves a 96.32% detection rate on industrial control dataset, which can better adapt to the needs of industrial IoT intrusion detection.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128281869","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 : 2023-05-01DOI: 10.53106/160792642023052403015
Renyang Wang Renyang Wang, Badamasi Sani Mohammed Renyang Wang, R. P. Badamasi Sani Mohammed
The economy was slump mainly due to the credit market disruptions and losses generated by systemic credit institutions. The trust in the banking system to satisfy payment commitments collapsed, and financial, economic, and political risks were increased, and during that era, their significant volatility. Such dangers have skewed economic development and laid the foundations for creating an economy of dread. The financial risks occur due to investments made to firms that fail to meet their financial responsibilities. The trouble is due to the probability of financial expense. Therefore, a culture of risk consciousness must be created to increase risk sensitivity in a company. Risk awareness and agility in responding to incidents are essential, and then reaction times might be impeded, mainly when an organization has grown too fast. Creating that culture, awareness of risk management benefits, safety improvements, lower claims, and lower risk costs, and better financial outcomes improved and shown. This article examines the influence on the economic growth of financial development using time series data. This research has been conducted using three popular financial development indicators: wide cash, deposit/GDP, and private sector domestic credit. The risk awareness model (RAM) estimate has a favourable and substantial influence on economic development for all financial development indices. Therefore, this article demonstrates that all financial product economic growth indexes utilize a binding test in a profitable and long-term way. Consequently, it is suggested to push ahead with financial reforms to enhance financial sector development, increasing its contribution to economic expansion. The proposed method allows achieving better throughput by performance ratios, accuracy ratios, low error rate, precision ratio, poverty rates, and risk management levels, financial volatility rate.
{"title":"Analysis on Risk Awareness Model and Economic Growth of Finance Industry","authors":"Renyang Wang Renyang Wang, Badamasi Sani Mohammed Renyang Wang, R. P. Badamasi Sani Mohammed","doi":"10.53106/160792642023052403015","DOIUrl":"https://doi.org/10.53106/160792642023052403015","url":null,"abstract":"\u0000 The economy was slump mainly due to the credit market disruptions and losses generated by systemic credit institutions. The trust in the banking system to satisfy payment commitments collapsed, and financial, economic, and political risks were increased, and during that era, their significant volatility. Such dangers have skewed economic development and laid the foundations for creating an economy of dread. The financial risks occur due to investments made to firms that fail to meet their financial responsibilities. The trouble is due to the probability of financial expense. Therefore, a culture of risk consciousness must be created to increase risk sensitivity in a company. Risk awareness and agility in responding to incidents are essential, and then reaction times might be impeded, mainly when an organization has grown too fast. Creating that culture, awareness of risk management benefits, safety improvements, lower claims, and lower risk costs, and better financial outcomes improved and shown. This article examines the influence on the economic growth of financial development using time series data. This research has been conducted using three popular financial development indicators: wide cash, deposit/GDP, and private sector domestic credit. The risk awareness model (RAM) estimate has a favourable and substantial influence on economic development for all financial development indices. Therefore, this article demonstrates that all financial product economic growth indexes utilize a binding test in a profitable and long-term way. Consequently, it is suggested to push ahead with financial reforms to enhance financial sector development, increasing its contribution to economic expansion. The proposed method allows achieving better throughput by performance ratios, accuracy ratios, low error rate, precision ratio, poverty rates, and risk management levels, financial volatility rate.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122471339","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 : 2023-05-01DOI: 10.53106/160792642023052403001
Ya-Yu Huang Ya-Yu Huang, Zi-Wen Li Ya-Yu Huang, Chun-Hao Yang Zi-Wen Li, Yueh-Min Huang Chun-Hao Yang
The reduction of the agricultural workforce due to the rapid development of technology has resulted in labor shortages. Agricultural mechanization, such as drone use for pesticide spraying, can solve this problem. However, the terrain, culture, and operational limitations in mountainous orchards in Taiwan make pesticide spraying challenging. By combining reinforcement learning with deep neural networks, we propose to train drones to avoid obstacles and find optimal paths for pesticide spraying that reduce operational difficulties, pesticide costs, and battery consumption. We experimented with different reward mechanisms, neural network depths, flight direction granularities, and environments to devise a plan suitable for sloping orchards. Reinforcement learning is more effective than traditional algorithms for solving path planning in complex environments.
{"title":"Automatic Path Planning for Spraying Drones Based on Deep Q-Learning","authors":"Ya-Yu Huang Ya-Yu Huang, Zi-Wen Li Ya-Yu Huang, Chun-Hao Yang Zi-Wen Li, Yueh-Min Huang Chun-Hao Yang","doi":"10.53106/160792642023052403001","DOIUrl":"https://doi.org/10.53106/160792642023052403001","url":null,"abstract":"\u0000 The reduction of the agricultural workforce due to the rapid development of technology has resulted in labor shortages. Agricultural mechanization, such as drone use for pesticide spraying, can solve this problem. However, the terrain, culture, and operational limitations in mountainous orchards in Taiwan make pesticide spraying challenging. By combining reinforcement learning with deep neural networks, we propose to train drones to avoid obstacles and find optimal paths for pesticide spraying that reduce operational difficulties, pesticide costs, and battery consumption. We experimented with different reward mechanisms, neural network depths, flight direction granularities, and environments to devise a plan suitable for sloping orchards. Reinforcement learning is more effective than traditional algorithms for solving path planning in complex environments.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"259 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122928383","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 : 2023-05-01DOI: 10.53106/160792642023052403024
Ke Zhang Ke Zhang, Decai Zou Ke Zhang, Pei Wang Decai Zou, Wenfang Jing Pei Wang
The netted wireless sensor nodes or coherent accumulation processing in multistatic radar imaging requires high accuracy time synchronization. Although GNSS timing can also be used as a time synchronization method to serve the applications above, its timing accuracy will be limited. In this context, we present the hardware implementation for Two-Way Time-Frequency Real-Time Synchronization (TWTFRTS) with an automatic adaptive jitter elimination algorithm based on Kalman and PID, which is implemented in a real-time, low-cost, portable Xilinx ZYNQ device. A short (2 km) baseline TWTFRTS experiment was done with a pair of devices composed of a master device and a slave device. The result shows a high precision of time synchronization performance with the standard deviation (1 σ) better than 1 ns.
{"title":"A New Device for Two-Way Time-Frequency Real-Time Synchronization","authors":"Ke Zhang Ke Zhang, Decai Zou Ke Zhang, Pei Wang Decai Zou, Wenfang Jing Pei Wang","doi":"10.53106/160792642023052403024","DOIUrl":"https://doi.org/10.53106/160792642023052403024","url":null,"abstract":"\u0000 The netted wireless sensor nodes or coherent accumulation processing in multistatic radar imaging requires high accuracy time synchronization. Although GNSS timing can also be used as a time synchronization method to serve the applications above, its timing accuracy will be limited. In this context, we present the hardware implementation for Two-Way Time-Frequency Real-Time Synchronization (TWTFRTS) with an automatic adaptive jitter elimination algorithm based on Kalman and PID, which is implemented in a real-time, low-cost, portable Xilinx ZYNQ device. A short (2 km) baseline TWTFRTS experiment was done with a pair of devices composed of a master device and a slave device. The result shows a high precision of time synchronization performance with the standard deviation (1 σ) better than 1 ns.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133593434","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}
MQTT (Message Queue Telemetry Transport) is one of the most popular Internet of Things (IoT) communication protocols, owing to its lightweight and easiness to use. The previous MQTT standards (including version 3.1 and its precedents) do not provide proper security functions; instead, they assume the adoption of SSL/TLS in the underlying layer. However, it not only incurs larger overhead but also hinders the development of suitable authentication/confidentiality protection to suit various MQTT deployment scenarios. The newest MQTT standard called MQTT 5.0 responds to these challenges by supporting the Enhanced Authentication framework in which designers can design and implement any secure authentication mechanisms within the framework. This paper designs and implements two efficient authentication protocols, using the MQTT 5.0 Enhanced Authentication framework. One is simple challenge-response authentication scheme, and the other is an anonymous challenge-response authentication scheme. We extend HiveMQ platform to implement the schemes and evaluate the performance. The results show that the proposed schemes demand only hundred few more milliseconds to achieve much robust authentication, compared to the simple identity-password authentication.
{"title":"Design and Implementation of Efficient IoT Authentication Schemes for MQTT 5.0","authors":"Hung-Yu Chien Hung-Yu Chien, Pin-Ping Ciou Hung-Yu Chien","doi":"10.53106/160792642023052403012","DOIUrl":"https://doi.org/10.53106/160792642023052403012","url":null,"abstract":"\u0000 MQTT (Message Queue Telemetry Transport) is one of the most popular Internet of Things (IoT) communication protocols, owing to its lightweight and easiness to use. The previous MQTT standards (including version 3.1 and its precedents) do not provide proper security functions; instead, they assume the adoption of SSL/TLS in the underlying layer. However, it not only incurs larger overhead but also hinders the development of suitable authentication/confidentiality protection to suit various MQTT deployment scenarios. The newest MQTT standard called MQTT 5.0 responds to these challenges by supporting the Enhanced Authentication framework in which designers can design and implement any secure authentication mechanisms within the framework. This paper designs and implements two efficient authentication protocols, using the MQTT 5.0 Enhanced Authentication framework. One is simple challenge-response authentication scheme, and the other is an anonymous challenge-response authentication scheme. We extend HiveMQ platform to implement the schemes and evaluate the performance. The results show that the proposed schemes demand only hundred few more milliseconds to achieve much robust authentication, compared to the simple identity-password authentication.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129975082","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 : 2023-05-01DOI: 10.53106/160792642023052403006
Yangming Zhang Yangming Zhang, Ping He Yangming Zhang, Huaying Qi Ping He, Shiyi Wang Huaying Qi
Homogeneous and heterogeneous data retrieval problem refers that these requested data items are retrieved on the basis of data items broadcast at some channels such that the access latency of all requested data items is minimized. The problem has an important study significance in MIMO (Multiple Input and Multiple Output) wireless communication. Almost researches are focused on proposing some schemes for solving signal antenna or multiple antennae data retrieval based on homogeneous data items, but these schemes are not suitable for heterogeneous data retrieval problem. So in this paper, we describe a SPR (Shortest Paths Retrieval) algorithm that is suitable for solving homogeneous and heterogeneous data retrieval problem at the same time. Moreover, for avoiding the retrieval time too long, when the each requested data item is set a constrained condition-deadline, we propose another DKPR (Deadline-based Key Path Retrieval) algorithm that finds the critical path with the largest number of requested data items in a broadcast cycle, so as to complete the retrieval operation of data items within the deadline of requesting data items as much as possible. Through experiments, the proposed scheme has good efficiency.
{"title":"A Retrieval Algorithm for Time-constrained Heterogeneous Data Items in Wireless Networks","authors":"Yangming Zhang Yangming Zhang, Ping He Yangming Zhang, Huaying Qi Ping He, Shiyi Wang Huaying Qi","doi":"10.53106/160792642023052403006","DOIUrl":"https://doi.org/10.53106/160792642023052403006","url":null,"abstract":"\u0000 Homogeneous and heterogeneous data retrieval problem refers that these requested data items are retrieved on the basis of data items broadcast at some channels such that the access latency of all requested data items is minimized. The problem has an important study significance in MIMO (Multiple Input and Multiple Output) wireless communication. Almost researches are focused on proposing some schemes for solving signal antenna or multiple antennae data retrieval based on homogeneous data items, but these schemes are not suitable for heterogeneous data retrieval problem. So in this paper, we describe a SPR (Shortest Paths Retrieval) algorithm that is suitable for solving homogeneous and heterogeneous data retrieval problem at the same time. Moreover, for avoiding the retrieval time too long, when the each requested data item is set a constrained condition-deadline, we propose another DKPR (Deadline-based Key Path Retrieval) algorithm that finds the critical path with the largest number of requested data items in a broadcast cycle, so as to complete the retrieval operation of data items within the deadline of requesting data items as much as possible. Through experiments, the proposed scheme has good efficiency. \u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"250 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121483125","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}
Deep learning is an influencer in hardware security applications, which grows up to be an essential tool in hardware security, threats the confidentiality, integrity, and availability of remote sensing equipment. Comparing to traditional physical attack, not only it can greatly reduce the workload of manual selection of POIs (Points of Interests) in security attack and Trojan backdoor, but also replenishes the toolbox for attacking. On account of minute changes between network structure model and hyperparameters constantly affecting the training and attacking effect, literally, deep learning serves as a tool but not key role in hardware security attack, which means it cannot completely replace template attack and other traditional energy attack methods. In this study, we present a method using Bi-LSTM Attention mechanism to focus on the POIs related to Hamming Weight at the last round s-box output. Firstly, it can increase attacking effect and decrease guessing entropy, where attacking FPGA data demonstrates the efficiency of attacking. Secondly, it is different from the traditional template attack and deep learning attack without preprocessing subjecting to raw traces but provides attentional POIs which is the same with artificial selection. Finally, it provides a solution for attacking encrypting equipment running in parallel.
深度学习是硬件安全应用的重要影响因素，它逐渐成为硬件安全的重要工具，威胁着遥感设备的机密性、完整性和可用性。与传统的物理攻击相比，它不仅可以大大减少安全攻击和木马后门中手动选择poi (point of Interests)的工作量，而且还补充了攻击工具箱。由于网络结构模型和超参数之间的微小变化不断影响训练和攻击效果，从字面上看，深度学习在硬件安全攻击中只是工具而非关键，不能完全取代模板攻击等传统能量攻击方法。在本研究中，我们提出了一种使用Bi-LSTM注意力机制来关注最后一轮s盒输出中与汉明权重相关的poi的方法。首先，它可以提高攻击效果，降低猜测熵，其中攻击FPGA数据证明了攻击的效率。其次，它不同于传统的模板攻击和深度学习攻击不受原始痕迹的预处理，而是提供了与人工选择相同的注意点。最后，提出了一种针对并行运行的加密设备进行攻击的解决方案。
{"title":"Security Attack on Remote Sensing Equipment: PoIs Recognition Based on HW with Bi-LSTM Attention","authors":"Wei Jiang Wei Jiang, Xianhua Zhang Wei Jiang, Yanpeng Li Xianhua Zhang, Chuansheng Chen Yanpeng Li, Jianfeng Zhu Chuansheng Chen","doi":"10.53106/160792642023052403005","DOIUrl":"https://doi.org/10.53106/160792642023052403005","url":null,"abstract":"\u0000 Deep learning is an influencer in hardware security applications, which grows up to be an essential tool in hardware security, threats the confidentiality, integrity, and availability of remote sensing equipment. Comparing to traditional physical attack, not only it can greatly reduce the workload of manual selection of POIs (Points of Interests) in security attack and Trojan backdoor, but also replenishes the toolbox for attacking. On account of minute changes between network structure model and hyperparameters constantly affecting the training and attacking effect, literally, deep learning serves as a tool but not key role in hardware security attack, which means it cannot completely replace template attack and other traditional energy attack methods. In this study, we present a method using Bi-LSTM Attention mechanism to focus on the POIs related to Hamming Weight at the last round s-box output. Firstly, it can increase attacking effect and decrease guessing entropy, where attacking FPGA data demonstrates the efficiency of attacking. Secondly, it is different from the traditional template attack and deep learning attack without preprocessing subjecting to raw traces but provides attentional POIs which is the same with artificial selection. Finally, it provides a solution for attacking encrypting equipment running in parallel.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131637299","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 : 2023-05-01DOI: 10.53106/160792642023052403021
Rong Li Rong Li, Zhi-e Lou Rong Li
Single Nucleotide Polymorphism (SNP) is the variant on a single nucleotide in the genome. Functional SNP, as one of the most important molecular markers in disease research, has been widely used in various research fields, such as tumor pathogenesis, disease diagnosis and treatment, prognostic evaluation, drug development, etc. The number of functional SNPs in noncoding genome regions is much more than that in coding regions, and their detection is more difficult. In this work, a multi-feature mining based computational method is proposed to predict the functional SNPs in human noncoding genomes. We first analyzed the sequence properties, evolutionary conservation properties and epigenetic modification signal properties of the sample SNPs. Statistical methods together with multiple annotation data from genomes and epigenetics were used to mine high-dimensional discriminative features subsequently. In particular, the allele-specific features were designed to distinguish the function of SNPs with close locations. The random forest method was used to conduct feature dimension reduction and classification. The 10-fold cross-validation result showed the Area Under the Receiver Operating Characteristic Curve (AUC) of our method improved by 16.9% and 43.4% over existing methods GWAVA and CADD, respectively, illustrating that the allele-specific based features can help to distinguish functional and netural SNPs with near locations.
{"title":"A Computational Method for Identification of Functional SNPs in Human Noncoding Genome Regions based on Multi-feature Mining","authors":"Rong Li Rong Li, Zhi-e Lou Rong Li","doi":"10.53106/160792642023052403021","DOIUrl":"https://doi.org/10.53106/160792642023052403021","url":null,"abstract":"\u0000 Single Nucleotide Polymorphism (SNP) is the variant on a single nucleotide in the genome. Functional SNP, as one of the most important molecular markers in disease research, has been widely used in various research fields, such as tumor pathogenesis, disease diagnosis and treatment, prognostic evaluation, drug development, etc. The number of functional SNPs in noncoding genome regions is much more than that in coding regions, and their detection is more difficult. In this work, a multi-feature mining based computational method is proposed to predict the functional SNPs in human noncoding genomes. We first analyzed the sequence properties, evolutionary conservation properties and epigenetic modification signal properties of the sample SNPs. Statistical methods together with multiple annotation data from genomes and epigenetics were used to mine high-dimensional discriminative features subsequently. In particular, the allele-specific features were designed to distinguish the function of SNPs with close locations. The random forest method was used to conduct feature dimension reduction and classification. The 10-fold cross-validation result showed the Area Under the Receiver Operating Characteristic Curve (AUC) of our method improved by 16.9% and 43.4% over existing methods GWAVA and CADD, respectively, illustrating that the allele-specific based features can help to distinguish functional and netural SNPs with near locations.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125212883","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 : 2023-05-01DOI: 10.53106/160792642023052403019
Chao Ma Chao Ma, Faren Huo Chao Ma, Aiqin Shi Faren Huo
As the fifth subversive and innovative technology for computing paradigm after the mainframe computer, personal computer, internet and mobile/social network, blockchain technology has entered into a new phase of development. Nevertheless, more intrinsic issues remain to be explored. With the usage of cryptography and a distributed database, once a block is recorded, it can no longer be changed. To defeat these issues, more existing techniques have emerged. The blockchain system mainly features decentralization, but as the existing architectures of the blockchain system are mixed up, it is hard to determine whether they are centralized or decentralized. Such hybrid feature is derived from the impact of uncertainty of human demands. In this study, we intend to explore the scientific perception of the blockchain technology after its integration with human activities by adopting the method of interaction design. Furthermore, we plan to establish a set of mechanisms on the method of blockchain system-based interaction design, so as to identify the impact of human uncertainty factors on the design of the blockchain system. In addition, we aim to provide theoretical guidance for establishing the decentralized blockchain systems in both standardized and mixed categories and the centralized blockchain system with decentralization as central node. Through the methods of the observational results, the article is summarized and assessed the methods of the interaction design based on blockchain system. Moreover, the evaluation process consists of the analysis of expert evaluation, practical evaluation and participatory evaluation ferments an efficient outcome.
{"title":"Framework of Interaction Design Method Based on Blockchain System","authors":"Chao Ma Chao Ma, Faren Huo Chao Ma, Aiqin Shi Faren Huo","doi":"10.53106/160792642023052403019","DOIUrl":"https://doi.org/10.53106/160792642023052403019","url":null,"abstract":"\u0000 As the fifth subversive and innovative technology for computing paradigm after the mainframe computer, personal computer, internet and mobile/social network, blockchain technology has entered into a new phase of development. Nevertheless, more intrinsic issues remain to be explored. With the usage of cryptography and a distributed database, once a block is recorded, it can no longer be changed. To defeat these issues, more existing techniques have emerged. The blockchain system mainly features decentralization, but as the existing architectures of the blockchain system are mixed up, it is hard to determine whether they are centralized or decentralized. Such hybrid feature is derived from the impact of uncertainty of human demands. In this study, we intend to explore the scientific perception of the blockchain technology after its integration with human activities by adopting the method of interaction design. Furthermore, we plan to establish a set of mechanisms on the method of blockchain system-based interaction design, so as to identify the impact of human uncertainty factors on the design of the blockchain system. In addition, we aim to provide theoretical guidance for establishing the decentralized blockchain systems in both standardized and mixed categories and the centralized blockchain system with decentralization as central node. Through the methods of the observational results, the article is summarized and assessed the methods of the interaction design based on blockchain system. Moreover, the evaluation process consists of the analysis of expert evaluation, practical evaluation and participatory evaluation ferments an efficient outcome.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130343286","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：