International Journal of Intelligent Networks最新文献

{"title":"Hierarchical energy efficient secure routing protocol for optimal route selection in wireless body area networks","authors":"A. Roshini,&nbsp;K.V.D. Kiran","doi":"10.1016/j.ijin.2022.11.006","DOIUrl":"https://doi.org/10.1016/j.ijin.2022.11.006","url":null,"abstract":"<div><p>Growth in technology has witnessed the comfort of an individual in domestic and professional life. Although, such existence was not able to meet the medical emergencies during the pandemic COVID-19 and during other health monitoring scenarios. This demand is due to the untouched Quality of Service network parameters like throughput, reliability, security etc. Hence, remote health monitoring systems for the patients who have undergone a medical surgery, bed ridden patients, autism affected subjects etc is in need that considers postural change and then forward to the caretaker in hospitals through wireless body area networks (WBAN). Security in these data are very important as it deals with the life of a subject. In this work, a Hierarchical Energy Efficient Secure Routing protocol (HEESR) is proposed that categorizes the deployed body nodes in to direct node and relay node based on the threshold vale. Unlike other conventional protocols the cluster head selection is based on the energy levels and the traffic priority data like critical and non-critical data, followed by an optimal route to forward the acquired data is identified and the data is compressed using Huffman encoding technique and encrypted using asymmetric cryptographic algorithm for secure data transmission. This protocol mainly appends security and routing efficiency in a hierarchical pattern through data prioritization and out performs the other conventional routing protocols by yielding a better energy consumption of 6%, throughput 92% and security of 93%, which has balanced the packet drop rate considerably and deliver the data within the stipulated time period.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 19-28"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194733","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}

{"title":"Research on the impact of artificial intelligence-based e-commerce personalization on traditional accounting methods","authors":"Pan Cao","doi":"10.1016/j.ijin.2023.07.004","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.07.004","url":null,"abstract":"<div><p>With the development of artificial intelligence technology in various fields, the traditional accounting method is no longer applicable to the personalized development of e-commerce industry; Therefore, it is essential to improve the accounting method and construct a personalized recommendation model for e-commerce. Based on this background, this study firstly reconstructs the steps of accounting element recognition in the traditional accounting system and constructs an automated accounting recognition mechanism using BP neural network algorithm, aiming to improve the accuracy and efficiency of accounting element recognition; Secondly, a personalized e-commerce recommendation model based on multiple intelligence is built, which uses intelligent Q-learning algorithm to optimize the recommendation module, aiming to improve the accuracy of personalized recommendation. By comparing the performance of different accounting models under different personalized e-commerce systems, the accounting model proposed in this paper can predict the accounting entries well under the three-layer BP neural network, and the error between the maximum predicted value and the actual value is 0.23%. The recommendation model proposed in the study outperforms the traditional recommendation model and the recommendation model under collaborative filtering algorithm in predicting customers' personal preferences, whose predicted value is closer to the real situation. In summary, both the accounting method and the personalized recommendation model for e-commerce proposed in this study can achieve better application results, thus providing a new idea for the development of the e-commerce industry.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 193-201"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194735","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}

{"title":"Secure short-packet communications using a full-duplex receiver","authors":"Dechuan Chen ,&nbsp;Jin Li ,&nbsp;Jianwei Hu ,&nbsp;Xingang Zhang ,&nbsp;Shuai Zhang","doi":"10.1016/j.ijin.2023.11.004","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.11.004","url":null,"abstract":"<div><p>In this work, we consider the physical layer security in short-packet communications, where a full-duplex (FD) receiver receives information signals from a source while generating artificial noise (AN) to confuse an eavesdropper. Taking into account the finite blocklength coding and the self-interference (SI) in FD mode, we derive new approximation closed-form expression for the secrecy throughput. Moreover, we analyze the asymptotic secrecy throughput in two distinct scenarios, i.e., high signal-to-noise ratio (SNR) regime and infinite blocklength coding, to gain more insights. Our examination illustrates the correctness of our expressions and shows how the critical system variables affect the secrecy throughput.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 349-354"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666603023000325/pdfft?md5=32f343bd6b882324238bf3c98be45c75&pid=1-s2.0-S2666603023000325-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138564396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quadratic ensemble weighted emphasis boosting based energy and bandwidth efficient routing in Underwater Sensor Network","authors":"O. Vidhya,&nbsp;S. Ranjitha Kumari","doi":"10.1016/j.ijin.2023.05.001","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.05.001","url":null,"abstract":"<div><p>Underwater Sensor Network (UWSN) is a network that comprises a large number of independent underwater sensor nodes to perform monitoring tasks over a given area. UWSN minimized propagation delay, bandwidth, and packet loss. However, the implementation of efficient communication is a significant problem at UWSN. Therefore, Energy and Bandwidth-aware Quadratic Ensemble Weighted Emphasis Boosting Classification (EB-QEWEBC) method for performing energy-efficient routing in UWSN is proposed. Initially, different numbers of underwater sensor nodes are considered as input. Next, the bandwidth and energy consumption of every underwater sensor node is measured. After that, classification between underwater sensor nodes is made by considering energy and bandwidth as factors using Regularized Quadratic Classifier (i.e., weak classifier) for performing routing with minimum delay. Followed by, Weighted Emphasis Boosting is utilized to ensemble weak learners to form strong learners for improving data routing performance results with the biconvex combination. Finally, after classifying the node, data packets are sent to higher energy and bandwidth-efficient underwater sensor nodes. The classification process is carried out at every underwater sensor node for transmitting data packets to the sink node with minimum delay. This method determines the energy-efficient data communication through classification and boosting to reduce the misclassification rate. Experimental results EB-QEWEBC shows a minimization of 14%, 21%, 26%, and 54% in terms of bandwidth, energy consumption, end-to-end delay, and misclassification rate as compared to state-of-art-methods respectively.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 130-139"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194625","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}

{"title":"PARouting: Prediction-supported adaptive routing protocol for FANETs with deep reinforcement learning","authors":"Cunzhuang Liu ,&nbsp;Yixuan Wang ,&nbsp;Qi Wang","doi":"10.1016/j.ijin.2023.05.002","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.05.002","url":null,"abstract":"<div><p>Flying Ad-hoc Networks (FANETs) are becoming increasingly popular for various applications. Effective routing protocols for FANETs are essential yet challenging due to the high dynamic nature of Unmanned Aerial Vehicles (UAVs). Most existing routing protocols require the periodic broadcast of Hello packets to maintain neighbor tables that store the locations of neighbors, mobility patterns, etc. However, the frequent exchange of Hello packets leads to a large routing overhead in FANETs. This paper proposes PARouting, a prediction-supported adaptive routing protocol with Deep Reinforcement Learning, which introduces a novel UAV mobility prediction algorithm using Deep Learning (DL-UMP) to estimate the locations of UAVs. Based on DL-UMP, we design an adaptive Hello packet mechanism to realize on-demand broadcasting of Hello packets, which reduces routing overhead. The routing process is formulated as a Partially Observable Markov Decision Process, and a new Q-network structure is proposed to select the optimal next hop. Simulation results confirm the accuracy of the DL-UMP and show that PARouting outperforms benchmark routing protocols in terms of packet delivery rate, end-to-end delay, and routing overhead.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 113-121"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194627","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}

{"title":"HNTSumm: Hybrid text summarization of transliterated news articles","authors":"Padhma Muniraj ,&nbsp;K.R. Sabarmathi ,&nbsp;R. Leelavathi ,&nbsp;Saravana Balaji B","doi":"10.1016/j.ijin.2023.03.001","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.03.001","url":null,"abstract":"<div><p>Data generated from social networking sites, blogs, digital magazines, and news websites is the largest human-generated data. Summarization is the process of extracting the crux of a document which when done manually can be tedious and deluging. Automatic text summarization is an approach that encapsulates long documents into a few sentences or words by enwrapping the gist and the principal information of the document. With the growth of social networking sites, eBooks, and e-Papers, the prevalence of transliterated words in text corpora is also on the rise. In this paper, we propose a word embeddings-based algorithm called HNTSumm by combining the advantages of unsupervised and supervised learning methods. The proposed algorithm HNTSumm algorithm is an imminent method for automatic text summarization of huge volumes of data that can learn word embeddings for words transliterated from other languages to English by utilizing weighted word embeddings from a Neural Embedding Model. Further, the amalgamation of extractive and abstractive approaches yields a concise and unambiguous summary of the text documents as the extractive approach eliminates redundant information. We employ a hybrid version of the Sequence-to-sequence models to generate an abstractive summary for the transliterated words. The feasibility of this algorithm was evaluated using two different news summary datasets and the accuracy scores were computed with the ROUGE evaluation metric. Experimental results corroborate the higher performance of the proposed algorithm and show HNTSumm outperforms relevant state-of-the-art algorithms for datasets with transliterated words.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 53-61"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194629","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}

{"title":"A systematic review on early prediction of Mild cognitive impairment to alzheimers using machine learning algorithms","authors":"K.P. Muhammed Niyas ,&nbsp;P. Thiyagarajan","doi":"10.1016/j.ijin.2023.03.004","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.03.004","url":null,"abstract":"<div><h3>Background</h3><p>A person consults a doctor when he or she is suspicious of their cognitive abilities. Finding patients who can be converted into Alzheimer's in the future is a difficult task for doctors. A person's dementia can be converted into several types of dementia conditions. Among all dementia, Alzheimer's is considered to be the most dangerous as its rapid progression can even lead to the death of an individual. Consequently, early detection of Alzheimer's would help in better planning for the treatment of the disease. Thereby, it is possible to reduce the progression of the disease. The application of Machine Learning algorithms is useful in accurately identifying Alzheimer's patients. Advanced Machine Learning algorithms are capable of increasing the performance classification of future AD patients. Hence, this study is made on a number of previous works from 2016 onwards on Alzheimer's detection. The aspects such as the country of the participants, modalities of data used and the features involved, feature extraction methods used, how many follow-up data were used, the period of Mild Cognitive Impairment to Alzheimer's Disease converters predicted, and the various machine learning models used in the previous studies of Alzheimer's detection are reviewed in this study. This review helps a new researcher to know the features and Machine Learning models used in the previous studies for the early detection of Alzheimer's. Thus, this study also helps a researcher to critically evaluate the literature on Alzheimer's disease detection very easily as the paper is organized according to the various steps of the Machine Learning process for Alzheimer's detection in a simplified manner.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 74-88"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194727","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}

{"title":"Fairness-driven link scheduling approach for heterogeneous gateways for digital twin enabled industry 4.0","authors":"Suvarna Patil ,&nbsp;Mandeep Kaur ,&nbsp;Katarina Rogulj","doi":"10.1016/j.ijin.2023.06.001","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.06.001","url":null,"abstract":"<div><p>The advent of Industry 4.0 has brought with it the integration of digital twin technology, which has enabled businesses to develop a virtual replica of their physical assets. This technology allows businesses to optimize their operations and improve their overall efficiency. However, the successful implementation of digital twin technology in Industry 4.0 heavily relies on the effective utilization of gateways. A significant challenge in gateway utilization is the fair allocation of resources, particularly in heterogeneous environments where gateways have different capabilities<strong>.</strong> Digital Twin is helping Industry 4.0 vision by connecting the authorized people to the exact data and processes to protect the data/assets from unauthorized access. It is accomplished by connecting sensing devices using a unique addressing system and transmitting their combined data to the Internet of Things (IoT) cloud. Massive volumes of heterogeneous data have resulted from the rapid growth of IoT applications and services. As a result, evaluation of data which affects the Digital Twin enabled industry is studied in this article which focuses on data traffic generated from different Industry 4.0 applications and protection of data along with the industry assets is looked by Digital Twin technology. IoT gateways are currently used to connect the devices from various technologies to the Digital Twins. In such networks, sudden increase in demand of IoT gateways will increase with the increase in IoT devices and the operational cost will also be increased. In the proposed system, low-cost specific gateways are proposed to minimize cost and maximize network performance for protecting assets of smart city through Digital Twin technology. In order to accomplish effective resource allocation in a Digital Twin based infrastructure, data transmission fairness at every gateway is accomplished in an IIoT network by considering link scheduling issues. To address these issues and provide fairness in heterogeneous networks with enhanced data transfer, two steps solution is implemented. The Long Short-Term Memory (LSTM) technique is used in the initial step of traffic prediction to assess the minimal time of prior traffic conditions before being applied to estimate dynamic traffic. In the second step, effective link scheduling and selection are made for each wireless technology, taking into account predicted load, gateway distance, link capacity, and estimated time. More data is transmitted at maximum capacity as a result of improved data transfer fairness for all gateways and then the data is protected by Digital Twin technology. Simulated results show that our suggested strategy performs better than other approaches by obtaining maximum network throughput in Industry 4.0 to provide protective solutions using Digital Twin technology.</p><p>Index Terms – Internet of Things (IoT), Link Scheduling, Traffic Prediction, Machine Learning (ML), Industry 4.0.</p></di","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 162-170"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194212","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}

{"title":"Genetic algorithm with self adaptive immigrants for effective virtual machine placement in cloud environment","authors":"P. Karthikeyan","doi":"10.1016/j.ijin.2023.07.001","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.07.001","url":null,"abstract":"<div><p>In cloud environments, optimization of resource utilizations is one among the predominant challenges. The two sub-research topics are cloud resource prediction and allocation. A few contributions to virtual machine (VM) placement techniques have been identified in the literature. In order to efficiently put up the virtual machine (VM) on the physical machine (PM), a Self Adaptive Immigrants with Genetic Algorithm (SAI-GA) is presented in this study. Based on CPU and memory usage, the proposed technique would forecast the best PM for each VM. The algorithm will adjust itself with the appropriate immigrant based on the history of past VM placement to find the best VM placement. In this paper, the VM live dataset from the CSAP lab at SNU in Korea has been used. For the purpose of demonstrating the significance of the findings, a number of non-parametric tests were used to evaluate how well the proposed SAI-GA performed. The outcomes demonstrate that the suggested approach makes a considerable contribution to the placement of VMs in cloud environments.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 155-161"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194623","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}

{"title":"Customer churning analysis using machine learning algorithms","authors":"B. Prabadevi,&nbsp;R. Shalini,&nbsp;B.R. Kavitha","doi":"10.1016/j.ijin.2023.05.005","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.05.005","url":null,"abstract":"<div><p>Businesses must compete fiercely to win over new consumers from suppliers. Since it directly affects a company's revenue, client retention is a hot topic for analysis, and early detection of client churn enables businesses to take proactive measures to keep customers. As a result, all firms could practice a variety of approaches to identify their clients early on through client retention initiatives. Consequently, this study aims to advise on the optimum machine-learning strategy for early client churn prediction. The data included in this investigation includes all customer data going back about nine months before the churn. The goal is to predict existing customers' responses to keep them. The study has tested algorithms like stochastic gradient booster, random forest, logistics regression, and k-nearest neighbors methods. The accuracy of the aforementioned algorithms are 83.9%, 82.6%, 82.9% and 78.1% respectively. We have acquired the most effective results by examining these algorithms and discussing the best among the four from different perspectives.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 145-154"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194624","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}