5G networks are essential in all locations owing to the multitude of advantages they provide. As a result, the number of users has increased dramatically. Nevertheless, these users require a variety of resources in order to function efficiently. Deep learning techniques have been created to improve the precision and dependability of resource allocation in the context of 5G networks. This research utilizes an efficient recurrent neural network (ERNN) to handle resource allocation for 5G multiuser (MU)‐massive multiple input multiple output (MIMO). In order to optimize the objective functions, the first application of the multi‐objective differential evaluation algorithm (MODEA) is used. The neural network is provided with these updated goal functions in order to allocate resources. ERNN evaluates the level of need for each individual user. By partitioning the resource at this level, it maintains a high throughput while distributing it to each user. In addition, the fairness index of the resource distribution system based on neural networks is established. The suggested method achieves a data transfer rate of 290 bits per second (bps) and a fairness index of 0.97% when used by 50 users. The findings of the proposed method exhibit superior performance compared to other existing methods in the field of 5G massive MIMO.
{"title":"Innovative resource allocation mechanism for optimizing 5G multi user‐massive multiple input multiple output system","authors":"P. Leela Rani, N. Devi, A. Guru Gokul","doi":"10.1002/itl2.569","DOIUrl":"https://doi.org/10.1002/itl2.569","url":null,"abstract":"5G networks are essential in all locations owing to the multitude of advantages they provide. As a result, the number of users has increased dramatically. Nevertheless, these users require a variety of resources in order to function efficiently. Deep learning techniques have been created to improve the precision and dependability of resource allocation in the context of 5G networks. This research utilizes an efficient recurrent neural network (ERNN) to handle resource allocation for 5G multiuser (MU)‐massive multiple input multiple output (MIMO). In order to optimize the objective functions, the first application of the multi‐objective differential evaluation algorithm (MODEA) is used. The neural network is provided with these updated goal functions in order to allocate resources. ERNN evaluates the level of need for each individual user. By partitioning the resource at this level, it maintains a high throughput while distributing it to each user. In addition, the fairness index of the resource distribution system based on neural networks is established. The suggested method achieves a data transfer rate of 290 bits per second (bps) and a fairness index of 0.97% when used by 50 users. The findings of the proposed method exhibit superior performance compared to other existing methods in the field of 5G massive MIMO.","PeriodicalId":509592,"journal":{"name":"Internet Technology Letters","volume":"2 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141920895","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}
Finding an accessible parking spot using 5G technology can be considered as time and fuel expenses. In this manner, it might make drivers disappointed in the parking zone. This will prompt awful traffic around the parking spot and may likewise prompt a mishap. That is the reason this task proposes a Smart Parking framework that utilizes cameras which will be associated with a Raspberry Pi and it will likewise have an Android application as an interface to help book or view accessible spaces. E Parking framework for security empowerment in 5G can be characterized as the utilization of trend setting innovations for the effective activity, checking, and the board of parking inside an urban versatility technique. This task will help tackle issues referenced by permitting clients to see and select accessible space in the parking, which will keep clients from driving around. You Only Look Once (YOLO) algorithm, Adaptive Background Learning and also pre‐trained Mask‐RCNN are used for finding the nearest free parking slot. Currently, Raspberry Pi will be utilized as the connection between the Cameras and the Server, by moving information gathered from the Raspberry Pi to an online server in order to process the information and empower the Android application to get outcome. In an end, this venture will help in decreasing the measure of time a driver needs to spend around the parking just to locate an accessible spot, lessening the measure of traffic, diminishing contamination, expanding the security using 5G technologies and furthermore better monetizing the parking spot. The proposed system detects vehicles in indoor as well as outdoor parking fields accurately.
{"title":"An Internet of Things security‐based E parking framework for smart city application using Lora","authors":"S. K. Tripathy, G. Palai","doi":"10.1002/itl2.566","DOIUrl":"https://doi.org/10.1002/itl2.566","url":null,"abstract":"Finding an accessible parking spot using 5G technology can be considered as time and fuel expenses. In this manner, it might make drivers disappointed in the parking zone. This will prompt awful traffic around the parking spot and may likewise prompt a mishap. That is the reason this task proposes a Smart Parking framework that utilizes cameras which will be associated with a Raspberry Pi and it will likewise have an Android application as an interface to help book or view accessible spaces. E Parking framework for security empowerment in 5G can be characterized as the utilization of trend setting innovations for the effective activity, checking, and the board of parking inside an urban versatility technique. This task will help tackle issues referenced by permitting clients to see and select accessible space in the parking, which will keep clients from driving around. You Only Look Once (YOLO) algorithm, Adaptive Background Learning and also pre‐trained Mask‐RCNN are used for finding the nearest free parking slot. Currently, Raspberry Pi will be utilized as the connection between the Cameras and the Server, by moving information gathered from the Raspberry Pi to an online server in order to process the information and empower the Android application to get outcome. In an end, this venture will help in decreasing the measure of time a driver needs to spend around the parking just to locate an accessible spot, lessening the measure of traffic, diminishing contamination, expanding the security using 5G technologies and furthermore better monetizing the parking spot. The proposed system detects vehicles in indoor as well as outdoor parking fields accurately.","PeriodicalId":509592,"journal":{"name":"Internet Technology Letters","volume":"6 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141928795","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}
Several other optical antenna topologies have been developed and implemented throughout the years. These topologies include a variety of optical components, including the axicon optical element, dual‐secondary mirror, cone reflecting mirror, prism beam slier, and beam‐splitter/beam combiner. In contrast, the secondary reflecting mirror causes an obscuration loss that must be compensated for by reducing the transmission power in an optical antenna design. In order to address this issue in space optical communication, the present research helps to develop an enhanced two diffractive optical elements (DOEs) technology however the data presented therein only shows that DOEs may boost transmission power efficiency, which is insufficient for system designers. Though On‐Off Keying (OOK) is widely used in optical communication systems at the moment, the proposed research include DOEs into an OOK space uplink optical. The proposed research uses numerical simulation to explore how much a space uplink OOK system's bit error rate (BER) may be improved by using DOEs and adjusting fundamental parameters. The proposed BER model takes environmental factors like wind and detector noise into account. Using this theoretical model, the present work helps to investigate the effect of DOEs on the BER versus fundamental parameter characteristic curves in space uplink optical communication. Based on the findings, the DOEs structure has the potential to significantly enhance the BER performance of space uplink optical communication systems, especially at high obscuration ratios. When the obscuration ratio is 0.25, 0.167, or 0.125 and the transmission power is 1 W, for instance, the DOEs may improve the BER by a factor of two or one order of magnitude or less when the parameters are changed to the typical parameter values as specified. Results increase by a factor of six, three, and two orders of magnitude, respectively, when transmitting at 5 W. The results show that DOEs can significantly enhance the BER performance, especially at high obscuration ratios. The findings suggest that integrating DOEs into the optical subsystem is a straightforward approach to improving the performance of space uplink optical communication systems.
多年来，还开发并实施了其他几种光学天线拓扑结构。这些拓扑结构包括各种光学元件，包括轴光学元件、双二次反射镜、锥反射镜、棱镜分束器和分束器/合束器。相比之下，二次反射镜会造成遮蔽损失，必须通过降低光学天线设计中的传输功率来补偿。为了解决空间光通信中的这一问题，目前的研究有助于开发一种增强型双衍射光学元件（DOEs）技术，但其中提供的数据仅表明 DOEs 可以提高传输功率效率，这对于系统设计人员来说是不够的。虽然开-关键控（OOK）目前已广泛应用于光通信系统，但本研究建议将 DOEs 纳入 OOK 空间上行链路光学系统。拟议的研究通过数值模拟来探索使用 DOE 和调整基本参数能在多大程度上提高空间上行链路 OOK 系统的误码率（BER）。拟议的误码率模型考虑了风和探测器噪声等环境因素。利用这一理论模型，本研究有助于探讨 DOE 对空间上行链路光通信误码率与基本参数特性曲线的影响。根据研究结果，DOEs 结构有可能显著提高空间上行链路光通信系统的误码率性能，尤其是在高遮蔽率的情况下。例如，当遮蔽率为 0.25、0.167 或 0.125，传输功率为 1 W 时，当参数改变为规定的典型参数值时，DOEs 可将误码率提高 2 倍或 1 个数量级或更低。当传输功率为 5 W 时，结果分别提高了 6 倍、3 倍和 2 个数量级。结果表明，DOE 能显著提高误码率性能，尤其是在高遮蔽率的情况下。研究结果表明，将 DOE 集成到光学子系统中是提高空间上行链路光通信系统性能的直接方法。
{"title":"Performance evaluation and investigation of diffraction optical elements effect on bit error rate of free space optics and performance investigation of space uplink wireless optical communication under varying atmospheric turbulence conditions","authors":"Gaurav Soni, Manish Sharma","doi":"10.1002/itl2.538","DOIUrl":"https://doi.org/10.1002/itl2.538","url":null,"abstract":"Several other optical antenna topologies have been developed and implemented throughout the years. These topologies include a variety of optical components, including the axicon optical element, dual‐secondary mirror, cone reflecting mirror, prism beam slier, and beam‐splitter/beam combiner. In contrast, the secondary reflecting mirror causes an obscuration loss that must be compensated for by reducing the transmission power in an optical antenna design. In order to address this issue in space optical communication, the present research helps to develop an enhanced two diffractive optical elements (DOEs) technology however the data presented therein only shows that DOEs may boost transmission power efficiency, which is insufficient for system designers. Though On‐Off Keying (OOK) is widely used in optical communication systems at the moment, the proposed research include DOEs into an OOK space uplink optical. The proposed research uses numerical simulation to explore how much a space uplink OOK system's bit error rate (BER) may be improved by using DOEs and adjusting fundamental parameters. The proposed BER model takes environmental factors like wind and detector noise into account. Using this theoretical model, the present work helps to investigate the effect of DOEs on the BER versus fundamental parameter characteristic curves in space uplink optical communication. Based on the findings, the DOEs structure has the potential to significantly enhance the BER performance of space uplink optical communication systems, especially at high obscuration ratios. When the obscuration ratio is 0.25, 0.167, or 0.125 and the transmission power is 1 W, for instance, the DOEs may improve the BER by a factor of two or one order of magnitude or less when the parameters are changed to the typical parameter values as specified. Results increase by a factor of six, three, and two orders of magnitude, respectively, when transmitting at 5 W. The results show that DOEs can significantly enhance the BER performance, especially at high obscuration ratios. The findings suggest that integrating DOEs into the optical subsystem is a straightforward approach to improving the performance of space uplink optical communication systems.","PeriodicalId":509592,"journal":{"name":"Internet Technology Letters","volume":"30 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141124008","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}
R. Krishna Priya, N. Sakhare, Ajay Paithane, R. Shekhar, M. Sabarimuthu
A Stochastic Low‐Density Parity‐Check (LDPC) decoder is a type of 5G New Radio standard LDPC decoder that uses stochastic techniques to perform decoding. Stochastic LDPC decoding with 5G NR standard typically uses an iterative process, where messages exchanged among variable nodes (VN), check nodes multiple times. Stochastic LDPC decoders are often used in scenarios where the received signal is subject to varying levels of noise. They will provide improved error correction performance compared to traditional LDPC decoders, especially when dealing with channels with varying signal‐to‐noise ratios in 5G networks. Using the adaptive sparse quantization kernel least mean square algorithm (SLDPC‐ASQ‐KLMSA), this paper proposes an area‐efficient architecture design for a stochastic LDPC decoder. The LDPC code (2048, 1723) is taken from the LOGBASE‐T standard and used in this study. We examine the ASQ‐KLMSA connection effects. Starting with the VN. It makes checking node functioning easier and reduces inter‐connect complexity by capping extrinsic message length at 2 bits. Because of the simplified check node operation in ASQ‐KLMSA, the decoder nodes must exchange messages with a greater degree of accuracy. The 3–3 input grouping sub‐node of the degree‐6 VN was changed with an adder‐based 5–1 input grouping sub‐node for the (2048, 1723) code in order to get more accurate results when the check‐to‐variable messages aren't strong enough. A suggested decoder architecture was determined using a stochastic LDPC decoder developed for TSMC 65 nm process (2048, 1723). Bite error rate, throughput, mean square error, latency, power, and area usage are some of the metrics used to evaluate the effectiveness of the SLDPC‐ASQ‐KLMSA algorithm that has been suggested and implemented in Python. Thus, the proposed approach has attained 34.44%, and 38.39% low mean square error while compared with the existing methods such as higher‐performance stochastic LDPC decoder architecture designed through correlation analysis (HP‐SLDPC‐CA), Higher Throughput and Hardware Efficient Hybrid LDPC Decoder Utilizing Bit‐Serial Stochastic Updating(HLDPC‐BSSU), Flexible FPGA‐Based Stochastic Decoder for 5G LDPC codes (FPGA‐SD‐5G‐LDPC), respectively.
{"title":"Design and analysis of stochastic 5G new radio LDPC decoder using adaptive sparse quantization kernel least mean square algorithm for optical satellite communications","authors":"R. Krishna Priya, N. Sakhare, Ajay Paithane, R. Shekhar, M. Sabarimuthu","doi":"10.1002/itl2.539","DOIUrl":"https://doi.org/10.1002/itl2.539","url":null,"abstract":"A Stochastic Low‐Density Parity‐Check (LDPC) decoder is a type of 5G New Radio standard LDPC decoder that uses stochastic techniques to perform decoding. Stochastic LDPC decoding with 5G NR standard typically uses an iterative process, where messages exchanged among variable nodes (VN), check nodes multiple times. Stochastic LDPC decoders are often used in scenarios where the received signal is subject to varying levels of noise. They will provide improved error correction performance compared to traditional LDPC decoders, especially when dealing with channels with varying signal‐to‐noise ratios in 5G networks. Using the adaptive sparse quantization kernel least mean square algorithm (SLDPC‐ASQ‐KLMSA), this paper proposes an area‐efficient architecture design for a stochastic LDPC decoder. The LDPC code (2048, 1723) is taken from the LOGBASE‐T standard and used in this study. We examine the ASQ‐KLMSA connection effects. Starting with the VN. It makes checking node functioning easier and reduces inter‐connect complexity by capping extrinsic message length at 2 bits. Because of the simplified check node operation in ASQ‐KLMSA, the decoder nodes must exchange messages with a greater degree of accuracy. The 3–3 input grouping sub‐node of the degree‐6 VN was changed with an adder‐based 5–1 input grouping sub‐node for the (2048, 1723) code in order to get more accurate results when the check‐to‐variable messages aren't strong enough. A suggested decoder architecture was determined using a stochastic LDPC decoder developed for TSMC 65 nm process (2048, 1723). Bite error rate, throughput, mean square error, latency, power, and area usage are some of the metrics used to evaluate the effectiveness of the SLDPC‐ASQ‐KLMSA algorithm that has been suggested and implemented in Python. Thus, the proposed approach has attained 34.44%, and 38.39% low mean square error while compared with the existing methods such as higher‐performance stochastic LDPC decoder architecture designed through correlation analysis (HP‐SLDPC‐CA), Higher Throughput and Hardware Efficient Hybrid LDPC Decoder Utilizing Bit‐Serial Stochastic Updating(HLDPC‐BSSU), Flexible FPGA‐Based Stochastic Decoder for 5G LDPC codes (FPGA‐SD‐5G‐LDPC), respectively.","PeriodicalId":509592,"journal":{"name":"Internet Technology Letters","volume":"115 48","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141124565","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}
Facial expression recognition has been studied for many years, especially with the development of deep learning. However, the existing researches still have the following two issues. Firstly, the intensity of facial expression is neglected. Secondly, the deep learning based approaches cannot be directly deployed in the devices with limited resources. In order to tackle these two issues, this paper proposes a lightweight facial expression estimation method using a shallow ordinal regression algorithm, which is deployed in a portable smart device for mobile computing in IoTs. Compared with classification based facial expression recognition methods, ordinal regression considers the intensity of facial expression to achieve better mean absolute error (MAE), which is validated by experiments on several public facial expression datasets. The simulation in portable device also demonstrates its effectiveness for mobile computing.
{"title":"Lightweight facial expression estimation for mobile computing in portable device","authors":"Jinming Liu","doi":"10.1002/itl2.533","DOIUrl":"https://doi.org/10.1002/itl2.533","url":null,"abstract":"Facial expression recognition has been studied for many years, especially with the development of deep learning. However, the existing researches still have the following two issues. Firstly, the intensity of facial expression is neglected. Secondly, the deep learning based approaches cannot be directly deployed in the devices with limited resources. In order to tackle these two issues, this paper proposes a lightweight facial expression estimation method using a shallow ordinal regression algorithm, which is deployed in a portable smart device for mobile computing in IoTs. Compared with classification based facial expression recognition methods, ordinal regression considers the intensity of facial expression to achieve better mean absolute error (MAE), which is validated by experiments on several public facial expression datasets. The simulation in portable device also demonstrates its effectiveness for mobile computing.","PeriodicalId":509592,"journal":{"name":"Internet Technology Letters","volume":"67 44","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140663796","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}
Speech‐emotion analysis plays an important role in English teaching. The existing convolutional neural networks (CNNs) can fully explore the spatial features of speech information, and cannot effectively utilize the temporal dependence of speech signals. In addition, it is difficult to build a more efficient and robust sentiment analysis system by solely utilizing speech information. With the development of the Internet of Things (IoTs), online multimodal information, including speech, video, and text, has become more convenient. To this end, this paper proposes a novel multimodal fusion emotion analysis system. Firstly, by combining convolutional networks with Transformer encoders, the spatiotemporal dependencies of speech information are effectively utilized. To improve multimodal information fusion, we introduce the exchange‐based fusion mechanism. The experimental results on the public dataset indicate that the proposed multimodal fusion model achieves the best performance. In online English teaching, teachers can effectively improve the quality of teaching by leveraging the feedback information of students' emotional states through our proposed deep model.
{"title":"Research on the application of English short essay reading emotional analysis in online English teaching under IoT scenario","authors":"Xiaoli Zhan","doi":"10.1002/itl2.535","DOIUrl":"https://doi.org/10.1002/itl2.535","url":null,"abstract":"Speech‐emotion analysis plays an important role in English teaching. The existing convolutional neural networks (CNNs) can fully explore the spatial features of speech information, and cannot effectively utilize the temporal dependence of speech signals. In addition, it is difficult to build a more efficient and robust sentiment analysis system by solely utilizing speech information. With the development of the Internet of Things (IoTs), online multimodal information, including speech, video, and text, has become more convenient. To this end, this paper proposes a novel multimodal fusion emotion analysis system. Firstly, by combining convolutional networks with Transformer encoders, the spatiotemporal dependencies of speech information are effectively utilized. To improve multimodal information fusion, we introduce the exchange‐based fusion mechanism. The experimental results on the public dataset indicate that the proposed multimodal fusion model achieves the best performance. In online English teaching, teachers can effectively improve the quality of teaching by leveraging the feedback information of students' emotional states through our proposed deep model.","PeriodicalId":509592,"journal":{"name":"Internet Technology Letters","volume":"49 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140661003","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}
Malware presents a significant threat to computer systems security, especially in ARM and MIPS architectures, driven by the rise of the internet of things (IoT). This paper introduces Heimdall, a hybrid approach that integrates YARA signatures and machine learning in programmable switches for efficient malware detection in SDN‐enabled IoT environments. The machine learning classifier achieved an accuracy of 99.33% against the IoT‐23 dataset. When evaluated in an emulated environment with real malware samples, Heimdall exhibits a 98.44% detection rate and an average processing time of 0.0217 s.
在物联网（IoT）兴起的推动下，恶意软件对计算机系统安全构成了重大威胁，尤其是在 ARM 和 MIPS 架构中。本文介绍了一种混合方法 Heimdall，它将 YARA 签名和机器学习集成到可编程交换机中，用于在支持 SDN 的物联网环境中高效检测恶意软件。机器学习分类器对 IoT-23 数据集的准确率达到 99.33%。在使用真实恶意软件样本的模拟环境中进行评估时，Heimdall 的检测率为 98.44%，平均处理时间为 0.0217 秒。
{"title":"A hybrid approach for malware detection in SDN‐enabled IoT scenarios","authors":"Cristian H. M. Souza, Carlos H. Arima","doi":"10.1002/itl2.534","DOIUrl":"https://doi.org/10.1002/itl2.534","url":null,"abstract":"Malware presents a significant threat to computer systems security, especially in ARM and MIPS architectures, driven by the rise of the internet of things (IoT). This paper introduces Heimdall, a hybrid approach that integrates YARA signatures and machine learning in programmable switches for efficient malware detection in SDN‐enabled IoT environments. The machine learning classifier achieved an accuracy of 99.33% against the IoT‐23 dataset. When evaluated in an emulated environment with real malware samples, Heimdall exhibits a 98.44% detection rate and an average processing time of 0.0217 s.","PeriodicalId":509592,"journal":{"name":"Internet Technology Letters","volume":"104 20","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140669824","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}
This study explores low‐resource language data translation models in the realms of multimedia teaching and cyber security. A rapid learning‐based neural machine translation (NMT) method is developed based on meta‐learning theory. Subsequently, the back translation method is employed to further improve the NMT model for low‐resource language data. Results indicate that the proposed low‐resource language NMT method based on meta‐learning achieves increased Bilingual Evaluation Understudy (BLEU) scores for three target tasks in a supervised environment. This study emphasizes the auxiliary role of meta‐learning theory in low‐resource language data translation, aiming to enhance the efficiency of translation models in utilizing information from low‐resource languages.
{"title":"Optimization of data analysis models for low‐resource Eurasian languages using machine translation","authors":"HongYan Chen, Kim Kyung Yee","doi":"10.1002/itl2.528","DOIUrl":"https://doi.org/10.1002/itl2.528","url":null,"abstract":"This study explores low‐resource language data translation models in the realms of multimedia teaching and cyber security. A rapid learning‐based neural machine translation (NMT) method is developed based on meta‐learning theory. Subsequently, the back translation method is employed to further improve the NMT model for low‐resource language data. Results indicate that the proposed low‐resource language NMT method based on meta‐learning achieves increased Bilingual Evaluation Understudy (BLEU) scores for three target tasks in a supervised environment. This study emphasizes the auxiliary role of meta‐learning theory in low‐resource language data translation, aiming to enhance the efficiency of translation models in utilizing information from low‐resource languages.","PeriodicalId":509592,"journal":{"name":"Internet Technology Letters","volume":" 30","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140687143","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}
Network intrusion detection refers to detect the threaten behaviors in the network to guarantee the network security. Compared with computer network, Internet of Things (IoT) consists of various devices, including computer, smart phone, smart watch, various sensors etc. The data in IoT may be captured from heterogeneous scenes using various devices. The data may follow from different distributions. Most previous works may fail when they are used in heterogeneous scenes of IoT. In order to overcome this issue, this paper designs a heterogeneous network intrusion detection scheme using attention sharing mechanism to implement domain adaptation for the intrusion detection of the data with heterogeneous distributions. The data from heterogeneous IoT devices is projected into the same sharing space via attention sharing to alleviate the bias between the distributions of data from these devices. Thus, the intrusion detection model learnt from the data from a scene can be migrated to another scene. The experiments and simulation demonstrate that the proposed intrusion detection scheme can adapt the changes of IoT scene.
{"title":"Heterogeneous network intrusion detection via domain adaptation in IoT environment","authors":"Jun Zhang, Yao Li, Litian Zhang","doi":"10.1002/itl2.531","DOIUrl":"https://doi.org/10.1002/itl2.531","url":null,"abstract":"Network intrusion detection refers to detect the threaten behaviors in the network to guarantee the network security. Compared with computer network, Internet of Things (IoT) consists of various devices, including computer, smart phone, smart watch, various sensors etc. The data in IoT may be captured from heterogeneous scenes using various devices. The data may follow from different distributions. Most previous works may fail when they are used in heterogeneous scenes of IoT. In order to overcome this issue, this paper designs a heterogeneous network intrusion detection scheme using attention sharing mechanism to implement domain adaptation for the intrusion detection of the data with heterogeneous distributions. The data from heterogeneous IoT devices is projected into the same sharing space via attention sharing to alleviate the bias between the distributions of data from these devices. Thus, the intrusion detection model learnt from the data from a scene can be migrated to another scene. The experiments and simulation demonstrate that the proposed intrusion detection scheme can adapt the changes of IoT scene.","PeriodicalId":509592,"journal":{"name":"Internet Technology Letters","volume":"333 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140698077","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}
Vehicular Ad‐hoc Network (VANET) is an emerging field of wireless networks that enables a variety of vehicle safety and convenience applications. It employs Intrusion Detection System (IDS) frameworks in its different tiers to ensure reliable and secure communication among nodes. However, IDS requires a significant amount of data to process for monitoring intrusive activities in the network. As a result, the volume of traffic increases, resulting in the network congestion. Motivated by this fact, this study provides an overview of the optimization techniques for VANET traffic congestion control. It discusses a state‐of‐the‐art analysis along with the requirements for IDS‐generated traffic congestion control. It highlights the congestion control approaches for the traffic generated by an IDS and identifies the challenges in this domain. This study also proposes a novel IDS framework for reducing IDS‐generated network traffic by combining the Local Outlier Factor and Random Forest classifier. The proposed study achieved a high precision while yielding low false positive and false negative rates. The study outperformed the existing studies with an increase in accuracy of 1.16% and a reduction in attack detection time of 1.1869 seconds. Additionally, it discusses the possible future research directions that can be applied to address the issues of IDS‐generated traffic congestion. Overall, this study serves as a comprehensive guide to the current status of IDS‐generated traffic congestion control and diverse approaches to lessen it that can be employed by academicians and researchers.
{"title":"Optimization techniques for IDS‐Generated traffic congestion control in VANET","authors":"Yogendra Kumar, Vijay Kumar, Basant Subba","doi":"10.1002/itl2.518","DOIUrl":"https://doi.org/10.1002/itl2.518","url":null,"abstract":"Vehicular Ad‐hoc Network (VANET) is an emerging field of wireless networks that enables a variety of vehicle safety and convenience applications. It employs Intrusion Detection System (IDS) frameworks in its different tiers to ensure reliable and secure communication among nodes. However, IDS requires a significant amount of data to process for monitoring intrusive activities in the network. As a result, the volume of traffic increases, resulting in the network congestion. Motivated by this fact, this study provides an overview of the optimization techniques for VANET traffic congestion control. It discusses a state‐of‐the‐art analysis along with the requirements for IDS‐generated traffic congestion control. It highlights the congestion control approaches for the traffic generated by an IDS and identifies the challenges in this domain. This study also proposes a novel IDS framework for reducing IDS‐generated network traffic by combining the Local Outlier Factor and Random Forest classifier. The proposed study achieved a high precision while yielding low false positive and false negative rates. The study outperformed the existing studies with an increase in accuracy of 1.16% and a reduction in attack detection time of 1.1869 seconds. Additionally, it discusses the possible future research directions that can be applied to address the issues of IDS‐generated traffic congestion. Overall, this study serves as a comprehensive guide to the current status of IDS‐generated traffic congestion control and diverse approaches to lessen it that can be employed by academicians and researchers.","PeriodicalId":509592,"journal":{"name":"Internet Technology Letters","volume":"25 50","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140711558","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：