International Journal of Intelligent Networks最新文献

{"title":"Intelligent prediction method for power generation based on deep learning and cloud computing in big data networks","authors":"Zhaolong Zhou","doi":"10.1016/j.ijin.2023.08.004","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.08.004","url":null,"abstract":"<div><p>This paper aims to elevate the precision and efficiency of prevailing photovoltaic prediction algorithms by integrating deep learning and cloud computing techniques. The emphasis lies in leveraging measured solar power generation data to simulate the model's predictive capabilities and determine optimal parameters. The study employs a hybrid approach, combining a multilayer perceptron-deep belief network (MLP-DBN) algorithm, and contrasts it with other methods like support vector machine (SVM), long short-term memory (LSTM), multilayer perception (MLP), and deep belief networks (DBN). Assessment of model performance encompasses root-mean-square deviation, mean absolute error and the decision coefficient metrics. Empirical results highlight the superiority of the MLP-DBN technique, showcasing reductions in root mean square error by 2.20%, 1.64%, 2.09%, and 4.83%, and mean absolute error by 0.67%, 0.11%, 1.12%, and 1.30%, respectively. The coefficient of determination (R2) exhibits notable increments of 2.96%, 2.05%, 2.77%, and 8.64%. These strides underscore substantial advancements in prediction accuracy and error mitigation. The findings underscore the efficacy of the proposed hybrid model in ameliorating existing photovoltaic forecast algorithms, effectively addressing their limitations, including inadequate accuracy and performance.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 224-230"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194619","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":"Prediction of floods using improved PCA with one-dimensional convolutional neural network","authors":"Tegil J. John,&nbsp;R. Nagaraj","doi":"10.1016/j.ijin.2023.05.004","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.05.004","url":null,"abstract":"<div><p>Forecasting floods have always been a difficult task due to the complexity of the available data. Machine learning techniques have been widely used to predict floods based on precipitation, humidity, temperature, water velocity, and level variables. However, most prior studies have examined the monthly rainfall intensity to determine the likelihood of flooding. As a result, a state's daily and monthly rainfall intensity has been used to train deep-learning models to predict floods. In addition, feature reduction approaches are critical for dealing with data of a large dimensionality and improving classification accuracy. This article utilizes improved Principal Component Analysis (i-PCA), a linear unsupervised statistical transformation, as a feature reduction procedure. A 1D-Convolutional Neural Network (CNN) model forecasts the flood based on the reduced features. The experiments are based on a dataset of daily and monthly rainfall data collected from 1901 to 2021 for Kerala state. Qualitative analysis is performed using precision, accuracy, recall and F1-score parameters. The experiment analysis proves that the proposed algorithm attained 94.24% accuracy, and existing techniques achieved 86% of accuracy performance. The reason is that the proposed model uses the improved PCA for the feature reduction technique.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 122-129"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194626","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":"Solar irradiance forecasting models using machine learning techniques and digital twin: A case study with comparison","authors":"Neha Sehrawat ,&nbsp;Sahil Vashisht ,&nbsp;Amritpal Singh","doi":"10.1016/j.ijin.2023.04.001","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.04.001","url":null,"abstract":"<div><p>The ever-increasing demand for energy and power consumption due to population growth, economic expansion, and evolving consumer choices has led to the need for renewable energy sources. Traditional energy sources such as coal, oil, and gas have contributed to global pollution and have adverse effects on human health. As a result, the use of renewable energy for power generation has increased tremendously. One such area of research is solar irradiation prediction, which utilizes Artificial Intelligence and Machine Learning techniques. With the use of real-time predicted data, the digital twins are intended to add value to the organization by identifying and preventing problems, predicting performance, and improving operations. This paper provides an overview of various learning methods used for predicting irradiance and presents a new ensemble solar irradiance forecasting model that combines eight machine learning models to ensure model diversity. The model's most critical factors for predicting irradiance include temperature, cloudiness index, relative humidity, and day of the week. To conduct a comprehensive analysis, the proposed 8-Stacking Regression Cross Validation (8 STR-CV) model was tested using data from three different climatic zones in India. The model's high accuracy scores of 98.8% for Visakhapatnam, 98% for Nagpur, and 97.8% for the mountainous region make it a valuable tool for future prediction in various sectors, including power generation and utilization planning.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 90-102"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194631","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":"Intelligent personalized content recommendations based on neural networks","authors":"HeQiang Zhou","doi":"10.1016/j.ijin.2023.09.001","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.09.001","url":null,"abstract":"<div><p>To effectively assist users in discovering content tailored to their specific interests, this research aims to create an intelligent content recommendation system. The inadequacy of conventional recommendation models, which depend uniquely on historical reading data, becomes evident in their limited capacity to meet contemporary users' diverse and ever-changing preferences within the information. The proposed architecture makes the most of the advancements in deep learning technology. It integrates the self-attention mechanism, allowing for precise calibration of the significance attributed to each feature within the news data. The proposed multilevel data classification network enables a more refined and personalized knowledge of users' preferences and the array of content information attributes while incorporating the users' unique characteristics. The proposed model achieved an accuracy rate of 85.2%, a recall rate of 83.7%, an F1 score of 84.3%, and an Area Under the Curve (AUC) of 84.5%. By developing a multilevel, intelligent, personalized content recommendation network, the research attempts to introduce a solution that effectively provides users' preferences, thereby enriching their experience in discovering relevant information within the modern digital system.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 231-239"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194718","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":"Covertvasion: Depicting threats through covert channels based novel evasive attacks in android","authors":"Sunil Gautam ,&nbsp;Ketaki Pattani ,&nbsp;Mohd Zuhair ,&nbsp;Mamoon Rashid ,&nbsp;Nazir Ahmad","doi":"10.1016/j.ijin.2023.11.006","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.11.006","url":null,"abstract":"<div><p>Privacy and security issues concerning mobile devices have substantial consequences for individuals, groups, governments, and businesses. The Android operating system bolsters smartphone data protection by imposing restrictions on app behavior. Nevertheless, attackers conduct systematic resource analyses and divert privacy-sensitive information from plain view. They employ evasive mechanisms to evade system monitoring and create an illusion of benign and non-sensitive communication. Furthermore, covert channels amplify the impact of these malicious activities by facilitating information transfer through non-standard methods. The purpose of this research is to shed light on these novel threats targeting Android systems. The study delves into security and privacy attacks that compromise sensitive user information. The methodology leverages evasion concepts and employs sound-specific covert channel communication, particularly ultrasonic channels. This research work introduces novel evasive attacks, namely Prime-Composite Evasive Information Invasion (PCEII) and File-lock-based Evasive Information Invasion (FEII), both relying on covert channel communication. These unique variants of attacks successfully evade user data within a few milliseconds for both noisy as well as non-noisy environments and do not show any signs of detection by antivirus mechanisms like Anti-Virus Guard (AVG), 360 security, etc. and state-of-the-art tools such as TaintDroid, MockDroid and others. The paper not only assesses their impact on the privacy and security of information but also introduces avenues for their detection and mitigation.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 337-348"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666603023000349/pdfft?md5=4613738e91ae35e1a7c1f702498bd0ca&pid=1-s2.0-S2666603023000349-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138558902","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":"Proposed artificial intelligence algorithm and deep learning techniques for development of higher education","authors":"Amin Al Ka'bi","doi":"10.1016/j.ijin.2023.03.002","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.03.002","url":null,"abstract":"<div><p>Artificial intelligence (AI) has been increasingly impacting various aspects of our daily lives, including education. With the rise of digital technologies, higher education has also been experiencing a transformation, and AI has been playing a crucial role in this transformation. The application of AI in higher education has been rapidly increasing, with a focus on improving student engagement, increasing efficiency, and enhancing the learning experience. The use of AI in higher education is not without its challenges and ethical considerations. One of the biggest challenges is ensuring the accuracy and fairness of AI algorithms, as well as avoiding potential biases. In addition, there are concerns about the privacy of student data, as well as the potential for AI to replace human instructors and support staff. Another challenge is ensuring that AI is used in a way that supports the overall goals of higher education, such as promoting critical thinking and creativity, rather than just being used as a tool for automating tasks and increasing efficiency. In this article, we will discuss the various ways in which AI is being applied in higher education where a proposed model for improving the cognitive capability of students is proposed and compared to other existing algorithms. It will be shown that the proposed model shows better performance compared to other models.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 68-73"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194632","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":"An optimized framework for VANET routing: A multi-objective hybrid model for data synchronization with digital twin","authors":"Madhuri Husan Badole,&nbsp;Anuradha D. Thakare","doi":"10.1016/j.ijin.2023.10.001","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.10.001","url":null,"abstract":"<div><p>The utilization of Digital Twin technology allows for the simulation of network behavior, anticipating traffic surges, and implementing efficient traffic routing strategies to prevent congestion. This enhances network efficiency and improves overall speed. However, VANETs (Vehicular Ad-Hoc Networks) pose unique challenges due to their dynamic nature and frequent network disconnects. Developing and implementing effective VANET routing protocols becomes complex considering these factors. To address these challenges, a novel hybrid optimization model is proposed in this research. The model comprises optimal Cluster Head (CH) selection for data transmission. The clustering of mobile nodes is initially performed, but ensuring consistency in fast-paced environments remains a significant challenge. Therefore, the selection of the most suitable node as the CH is crucial. This research introduces a novel route selection mechanism that focuses on optimal CH selection. Multiple objectives such as mean routing load, packet delivery ratio, throughput, End-to-End Delay, and Control packet overhead are considered in the CH selection process. To determine the ideal CH from a pool of potential candidates, a new hybrid optimization model called Hunger's Foraging Behavior Customized Honey Badger Optimization (HFCHBO) is introduced. The HFCHBO combines the standard Honey Badger Algorithm (HBA) with Hunger Games Search (HGS). This hybrid model effectively formulates successful routing paths for data transmission between vehicles and the CH to the Base Station (BS). By combining these two approaches, the HFCHBO model aims to overcome the limitations of traditional clustering algorithms in ensuring consistent performance in dynamic environments. The proposed route selection mechanism incorporates multiple objectives to evaluate the performance of potential CHs, including mean routing load, packet delivery ratio, throughput, End-to-End Delay, and Control packet overhead. To facilitate data transmission between vehicles and the CH to the Base Station (BS), the HFCHBO model formulates successful routing paths. By utilizing the simulation capabilities of the Digital Twin technology, the model analyzes the network behavior, predicts traffic patterns, and makes informed decisions on routing strategies.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 272-282"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194721","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":"Conversational chat system using attention mechanism for COVID-19 inquiries","authors":"Wang Xin Hui ,&nbsp;Nagender Aneja ,&nbsp;Sandhya Aneja ,&nbsp;Abdul Ghani Naim","doi":"10.1016/j.ijin.2023.05.003","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.05.003","url":null,"abstract":"<div><p>Conversational artificial intelligence (AI) is a type of artificial intelligence that uses machine learning techniques to understand and respond to user inputs. This paper presents a conversational chat system that uses an attention mechanism to respond to COVID-19 inquiries. The model is based on the Luong Attention Mechanism’s three scoring methodologies the Dot Attention Mechanism, the General Attention Mechanism, and the Concat Attention Mechanism. The results show that the accuracy of the dot attention mechanism is highest and is 87% when the test questions were obtained directly from the database, as determined by an examination of the results, compared to 38% when the attention mechanism is not used. Furthermore, when the questions are asked with natural variations, human verification accuracy is 63% compared to 16% when the attention mechanism is not used. The research suggests that chatbots can be used everywhere due to their accuracy and accessibility around the clock.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 140-144"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194728","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":"Roadside sensor network deployment based on vehicle-infrastructure cooperative intelligent driving","authors":"Xin An ,&nbsp;Baigen Cai","doi":"10.1016/j.ijin.2023.11.002","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.11.002","url":null,"abstract":"<div><p>The sensor network for intelligent roadways, comprised of devices like cameras, laser radars, millimeter-wave radars, and weather stations, is an integral part of the roadside digital infrastructure. One of the main challenges in building intelligent highway sensor networks is to create a controllable, manageable, and useable sensor network with multi-modal sensors deployed on highways. This network should not only facilitate global and scene sensing but also enable collaborative sensing and control functions. Therefore, this study aims to define the concept, main features, and technical connotation of Vehicle-Infrastructure Cooperative Intelligent Driving (VICID). It also outlines the development of a cloud-native cloud control platform for intelligent roadways and refines the technology requirements and indices. This platform is designed to support open services for innovative applications, such as addressing bottlenecks, managing roadworks zones, and implementing dynamic lane assignments for automated driving. Lastly, we introduce Beijing's highway pilot projects, which can serve as a guide and reference for designing and constructing sensor network equipment for intelligent roadways in China, as well as for key technology research and development.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 283-300"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666603023000301/pdfft?md5=098fe9a05d083ab3002d5f2e7e6fabbb&pid=1-s2.0-S2666603023000301-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138423189","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":"Priority based k-coverage hole restoration and m-connectivity using whale optimization scheme for underwater wireless sensor networks","authors":"Sangeeta Kumari ,&nbsp;Pavan Kumar Mishra ,&nbsp;Arun Kumar Sangaiah ,&nbsp;Veena Anand","doi":"10.1016/j.ijin.2023.08.005","DOIUrl":"https://doi.org/10.1016/j.ijin.2023.08.005","url":null,"abstract":"<div><p>Coverage hole restoration and connectivity is a typical problem for underwater wireless sensor networks. In underwater applications like underwater oilfield reservoirs, undersea minerals and monitoring etc., where nodes face many hurdles and are unable to cover the required region during a natural disaster such as tsunami, flood, earthquakes, and environmental interference. It creates a coverage hole and consumes high energy with bad network quality. This problem considered as an <em>N</em>P-complete problem where a set of sensor nodes is required to identify the k-coverage hole and m-connectivity. In the literature, researchers have not focused on <em>k</em>-coverage hole restoration and <em>m</em>-connectivity issues during natural disasters and environmental interference. To mitigate this problem, we proposed priority-based coverage hole restoration and -connection using a whale optimization scheme to restore coverage holes and extract relevant information for the construction of undersea oilfield reservoirs, minerals, and mines. In this scheme, we identified the list of k-coverage holes and addressed autonomous underwater vehicles (AUVs) to place the additional mobile nodes in an appropriate coverage hole. A novel multi-objective function is formulated to obtain the optimal path for AUVs. Furthermore, while restoring coverage holes, we checked the connectivity of nodes. In the network, each node coordinated sleep scheduling with neighbor nodes to maintain energy efficiency. Performance evaluation of the proposed scheme shows better results than the existing schemes under different network scenarios which provide maximum coverage and connectivity, less energy consumption with a high convergence rate.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"4 ","pages":"Pages 240-252"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50194717","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}