{"title":"PE-DeepNet: A deep neural network model for pulmonary embolism detection","authors":"Damian Lynch , Suriya M","doi":"10.1016/j.ijin.2022.10.001","DOIUrl":"10.1016/j.ijin.2022.10.001","url":null,"abstract":"<div><p>Machine learning in medical image processing has shown to be a useful way for discovering patterns in both poorly labelled and unlabeled datasets. Venous thromboembolism, which includes deep vein thrombosis and pulmonary embolism, is a major cause of death in patients and requires quick detection by specialists. Using an artificial neural network, the suggested study was carried out to aid doctors in identifying and forecasting the risk level of pulmonary embolism in patients. This research presents a hybrid deep learning convolutional neural network model called PE-DeepNet (Pulmonary Embolism detection using Deep neural Network) to perform quick and accurate pulmonary embolism detection. The experiment uses a case study from the standard RSNA STR Pulmonary Embolism Chest CT scan image dataset. The proposed work results in an accuracy of 94.2%, an improvement over existing CNN models with minor trainable parameters.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"3 ","pages":"Pages 176-180"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666603022000185/pdfft?md5=fe8baf48f3fa5865d5ca0cb0c3b749a2&pid=1-s2.0-S2666603022000185-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87178258","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":"Enhancing investigations in data migration and security using sequence cover cat and cover particle swarm optimization in the fog paradigm","authors":"T. Saravanan , S. Saravanakumar","doi":"10.1016/j.ijin.2022.11.002","DOIUrl":"10.1016/j.ijin.2022.11.002","url":null,"abstract":"<div><p>In recent years, fog and mobile edge computing have grown rapidly due to the large amount of data generated by the Internet of Thing (IoT) devices. It provides a variety of services within the end user IoT environment, but suffers from inefficient scheduling, which results in more significant delays than cloud computing. In this research we propose a data migration procedure that beats the metrics of delay, response time, and load balancing rate in the fog computing paradigm. It is possible to reduce the amount of replicated and integrated data by using Sequence Cover Cat Swarm Optimization (SCCSO) and Sequence Cover Particle Swarm Optimization (SCPSO) by using appropriate Virtual machines (VMs) which lock highly used machines and give service to low used machines in cloud communication storage.; this allows us to obtain resources efficiently in the fog environment. After being tested in the iFogsim climate, The protocols performed better in the iFogsim climate in terms of response time, scheduling time load balancing rate and delay than the other scheduling algorithms.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"3 ","pages":"Pages 204-212"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666603022000227/pdfft?md5=8aba7309e338c223536254e7fb1f2c20&pid=1-s2.0-S2666603022000227-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76561016","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}
Mohd Javaid , Abid Haleem , Ravi Pratap Singh , Shanay Rab , Mir Irfan Ul Haq , Ankush Raina
{"title":"Internet of Things in the global healthcare sector: Significance, applications, and barriers","authors":"Mohd Javaid , Abid Haleem , Ravi Pratap Singh , Shanay Rab , Mir Irfan Ul Haq , Ankush Raina","doi":"10.1016/j.ijin.2022.10.002","DOIUrl":"10.1016/j.ijin.2022.10.002","url":null,"abstract":"<div><p>Internet of Things (IoT) is a modern paradigm with broad applications in various industries, including healthcare and its associated fields. The full implementation of this technology in the healthcare field is a shared goal, as it enables medical services to operate more efficiently and patients to receive quality care. There are various IoT technology-based healthcare system applications for improving the efficacy and quality of diagnosis & treatments. Globally, the healthcare sector is in a peculiar state. The global population is ageing, and the number of lifestyle and chronic diseases is increasing, whereas individual aspirations are increasing, whereas healthcare is getting expensive. Technological interventions can help to solve this problem. One aspect of problem-solving can be bringing health checkups from the hospital to the patients. This paper aims to study the IoT and its implementation in healthcare. Smart Features, Supportive Enablers, and Operative Work-Process Flow of IoT in the Healthcare Domain are discussed diagrammatically. In this paper, we identified and studied the significant applications of IoT for Healthcare. Various barriers and future challenges in adopting IoT in Healthcare services are also discussed. IoT in healthcare is beneficial at various stages of the patient healthcare-system relationship. Thus, Healthcare providers can obtain necessary health data via real-time monitoring of a patient's condition through intelligent medical devices linked to a mobile application. A physician can assess the patient's condition to develop a better treatment process. In healthcare, this technology can result in significant advancements in patient care management.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"3 ","pages":"Pages 165-175"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666603022000197/pdfft?md5=1b1ac58f01a3ad7de1cbd4179dd96387&pid=1-s2.0-S2666603022000197-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87234135","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}
Abid Haleem , Mohd Javaid , Mohd Asim Qadri , Ravi Pratap Singh , Rajiv Suman
{"title":"Artificial intelligence (AI) applications for marketing: A literature-based study","authors":"Abid Haleem , Mohd Javaid , Mohd Asim Qadri , Ravi Pratap Singh , Rajiv Suman","doi":"10.1016/j.ijin.2022.08.005","DOIUrl":"10.1016/j.ijin.2022.08.005","url":null,"abstract":"<div><p>Artificial Intelligence (AI) has vast potential in marketing. It aids in proliferating information and data sources, improving software's data management capabilities, and designing intricate and advanced algorithms. AI is changing the way brands and users interact with one another. The application of this technology is highly dependent on the nature of the website and the type of business. Marketers can now focus more on the customer and meet their needs in real time. By using AI, they can quickly determine what content to target customers and which channel to employ at what moment, thanks to the data collected and generated by its algorithms. Users feel at ease and are more inclined to buy what is offered when AI is used to personalise their experiences. AI tools can also be used to analyse the performance of a competitor's campaigns and reveal their customers' expectations. Machine Learning (ML) is a subset of AI that allows computers to analyse and interpret data without being explicitly programmed. Furthermore, ML assists humans in solving problems efficiently. The algorithm learns and improves performance and accuracy as more data is fed into the algorithm. For this research, relevant articles on AI in marketing are identified from Scopus, Google scholar, researchGate and other platforms. Then these articles were read, and the theme of the paper was developed. This paper attempts to review the role of AI in marketing. The specific applications of AI in various marketing segments and their transformations for marketing sectors are examined. Finally, critical applications of AI for marketing are recognised and analysed.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"3 ","pages":"Pages 119-132"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666603022000136/pdfft?md5=8b54967bcc5b749f2f1bf4f9c2dfbab9&pid=1-s2.0-S2666603022000136-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88368944","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}
S. Shanthi , S. Saradha , J.A. Smitha , N. Prasath , H. Anandakumar
{"title":"An efficient automatic brain tumor classification using optimized hybrid deep neural network","authors":"S. Shanthi , S. Saradha , J.A. Smitha , N. Prasath , H. Anandakumar","doi":"10.1016/j.ijin.2022.11.003","DOIUrl":"10.1016/j.ijin.2022.11.003","url":null,"abstract":"<div><p>A significant topic of investigation in the area of medical imaging is brain tumor classification. Since precision is significant for classification, computer vision researchers have developed several approaches, but they still struggle with poor accuracy. In this paper, an automatic optimized hybrid deep neural network (OHDNN) is suggested for brain tumors. The proposed approach consists of two phases such as pre-processing and brain tumor classification. At first, the images are composed of the data, and then the collected imageries are pre-processed by using the following steps such as image enhancement and noise removal. Then the pre-processed images are fed to the classification stage. For the classification process, in this paper, OHDNN is used. The HDNN is a combination of a convolution neural network and long short-term memory (CNN-LSTM). Here, the CNN classifier is used for feature map generation and the classification process LSTM classifier is used. Besides, to improve the performance of the CNN-LSTM classifier, the parameter extant in the classifiers is randomly selected utilizing the adaptive rider optimization (ARO) algorithm. For the experimental process, an MRI image dataset is utilized. The experimental results show proposed approach attained the maximum accuracy of 97.5.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"3 ","pages":"Pages 188-196"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666603022000239/pdfft?md5=4f4b0efe7d943431b7e6ab7b8342a453&pid=1-s2.0-S2666603022000239-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80694039","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":"Machine learning and quantum computing for 5G/6G communication networks - A survey","authors":"Suriya M","doi":"10.1016/j.ijin.2022.11.004","DOIUrl":"https://doi.org/10.1016/j.ijin.2022.11.004","url":null,"abstract":"<div><p>Recently fifth generation (5G) and beyond applications are evolving, which demands more computational and complex data processing. Quantum computing and quantum learning algorithms are incorporated to enhance processing capabilities and data computation compared to conventional machine learning approaches. This study presents the significance of quantum computing and quantum machine learning models and their research challenges concerning 5G and beyond applications. The researchers focus on global coverage, enhanced spectrum support, increased energy and cost efficiency, high security, and dynamic intelligence, along with big data processing that demands complex data structures and algorithms.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"3 ","pages":"Pages 197-203"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666603022000240/pdfft?md5=db0140218702517bb55e207933ca8c9e&pid=1-s2.0-S2666603022000240-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"137227980","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":"Remora optimization algorithm-based optimized node clustering technique for reliable data delivery in VANETs","authors":"Swathi Konduru , M. Sathya","doi":"10.1016/j.ijin.2022.07.002","DOIUrl":"10.1016/j.ijin.2022.07.002","url":null,"abstract":"<div><p>Vehicular ad hoc Network (VANET) is one of the recently growing trends which motivate the provision of several service providers in the urban areas. In VANETs, the vehicles represent the nodes in the network topology that needs to guarantee better cooperation when there is a higher node density. Moreover, the problem of determining an optimal route and achieving network scalability is a herculean task. In this context, the incorporation of a potential clustering algorithm has the possibility of improving the road safety and facilitating a reliable option of promoting message routing. The clustering protocols are determined to be the ideal candidate for solving the problems of network scalability to guarantee reliable data dissemination. In this paper, Remora optimization algorithm-based Optimized Node Clustering (ROAONC) Technique is proposed for node clustering in VANETs to achieved optimal CH selection process. This ROAONC scheme was proposed for minimizing network overhead in the scenarios of unpredictable node density. The simulation results of this ROAONC scheme confirmed better performance in terms of transmission range, node density, network area and number of clusters compared to the competitive ant colony, grey wolf, grasshopper, and dragonfly optimization algorithm-based clustering protocols.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"3 ","pages":"Pages 74-79"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666603022000082/pdfft?md5=1c34e7af1d5a3879e53b71b071d8e46a&pid=1-s2.0-S2666603022000082-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77721851","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":"Development and performance evaluation of Correntropy Kalman Filter for improved accuracy of GPS position estimation","authors":"Sirish Kumar Pagoti , Srilatha Indira Dutt Vemuri","doi":"10.1016/j.ijin.2022.01.002","DOIUrl":"10.1016/j.ijin.2022.01.002","url":null,"abstract":"<div><p>It is well known that a Global Positioning System (GPS) receiver needs to ‘see’ at least four satellites to provide a three-dimensional fix solution. However, if any GPS receiver is operated in urban canyons, the visibility further reduces. To improve the position estimation accuracy, a novel kinematic positioning algorithm designated as Correntropy Kalman Filter (CKF) is proposed in this study. Instead of minimum mean square error (MMSE), the correntropy criterion (CC) is used as the optimality criterion of CKF. Like the traditional Kalman Filter (KF), the prior estimate of the state and covariance matrix are computed in CKF, and a novel fixed-point algorithm is then used to update the posterior estimates. The data of a dual-frequency GPS receiver located at the Indian Institute of Science (IISc), Bangalore (13.021°N/77.5°E) is collected from Scripps Orbit and Permanent Array Centre (SOPAC) to implement the proposed algorithm. The results of the proposed CKF algorithm are promising and exhibit significant improvement in position estimation compared to the conventional methods.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"3 ","pages":"Pages 1-8"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666603022000021/pdfft?md5=51aea651ebdade2d4c3fd01491e80616&pid=1-s2.0-S2666603022000021-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75487717","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":"Radix Trie improved Nahrain chaotic map-based image encryption model for effective image encryption process","authors":"Fazly Salleh Abas , R Arulmurugan","doi":"10.1016/j.ijin.2022.08.002","DOIUrl":"10.1016/j.ijin.2022.08.002","url":null,"abstract":"<div><p>As the intrinsic features of images include huge size and additional correlation prevailing among pixels, it is tedious to accomplish by using outdated models. The cryptographic features of Chaotic Maps (CM), including early criteria and random nature, aid in designing novel Image Encryption (IE) methods. In this paper, Nahrain Map with Radix Trie-based Image Encryption (NMRTIE) model is proposed to guarantee image encryption that resists known attacks that could be launched during its transmission in the cloud environment. The propounded NMRTIE model includes three essential phases: NCM-based Image Encryption (IE), Radix Trie (RT) based scrambling, and incessant diffusion. Initially, the NCM model uses more than one chaotic function to produce a sequence of keys. The RT model eases scrambling, where the rows and columns' pixels are swapped substantially. Lastly, the propounded diffusion scheme cooperates with NCM to produce key streams for remarkably hastening diffusion and dispersing effect. The propounded NMRTIE model is evaluated, and the results are confirmed based on numerous characteristics. The investigational consequence confirms that the propounded NMRTIE scheme is more appropriate than the associated approaches.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"3 ","pages":"Pages 102-108"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666603022000100/pdfft?md5=a6ab2c96f5980eb523a11448d7bb76b4&pid=1-s2.0-S2666603022000100-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75100302","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}
M. Premkumar , S.R. Ashokkumar , G. Mohanbabu , V. Jeevanantham , S. Jayakumar
{"title":"Security behavior analysis in web of things smart environments using deep belief networks","authors":"M. Premkumar , S.R. Ashokkumar , G. Mohanbabu , V. Jeevanantham , S. Jayakumar","doi":"10.1016/j.ijin.2022.10.003","DOIUrl":"10.1016/j.ijin.2022.10.003","url":null,"abstract":"<div><p>The advancements in modern wireless communications enhances the Internet of Things (IoT) which in turns the extensive variety of applications which covers smart home, healthcare, smart energy, and Industrial 4.0. The idea of the Web of Things (WoT) was established to expand the potential of these smart devices. It enables the devices that are connected through a common network. It has played a significant part in connecting all smart devices over the internet, allowing them to share services and resources globally. However, as devices become more connected, they become more exposed to various forms of malicious activities. The DDoS and DoS attacks are the major one that can disrupt the regular operation of network and expose the malicious information. So detecting and preventing the attacks in the WoT is a significant research area. The deep belief networks based intrusion detection system is proposed in this paper to detect the malicious activities like Normal, Botnet, Brute Force, Dos/DDos, Infiltration, PortScan and Web based attacks in WoTs. We examined the proposed method with the CICIDS2017 dataset for training and testing purposes and also achieved the average of 97.8% of accuracy and 97.6% of detection rate.</p></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"3 ","pages":"Pages 181-187"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666603022000203/pdfft?md5=729ad5f88bc4ff6261dceb331c08e6a0&pid=1-s2.0-S2666603022000203-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79314895","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}