2690-6791ISSN (Online)
2769-786XISSN (Print)
The spread of Internet sources has increased the volume of big data that is difficult to handle in traditional ways. So, most users need modern search systems to facilitate the search and retrieval of information in the presence of big data. However, the main challenge in the first and second conventional generations of search engines are linking different web data based on the syntax of keywords not on the semantic meaning and without a knowledge base. This manuscript proposes a framework based on modern technologies such as ETI processes, ontology graphs, and indexing RDF using wide column NoSQL technique. The main contribution of our work is introducing a mathematical model that is used to calculate the similarity score between a query and stored RDF documents based on semantic relations. Various operations were carried out to measure the proposed model's efficiency using data sources such as DBpedia, YAGO dataset. According to experimental results, the proposed model is achieving high precision compared to other related systems.
Read MoreDoi: https://doi.org/10.54216/JISIoT.030201
Vol. 3 Issue. 2 PP. 43-56, (2021)
Many conferences all over the world about environmental protection are situated. Air pollution resulted is an urgent issue for all people on the earth. Crowded cars in the intersections in traffic light intersections are one of the causes of air pollution. Also, rapid accelerations and deacceleration in the intersection cause air pollution. They also lead to packet transmission delay. This paper treats these issues using an intelligent warning message which reduces crowded cars, rapid accelerations, and deacceleration. Using vehicular ad hoc networks (VANETs), intelligent warning messages are used. Results show that our system outperforms previous studies such as traffic light control and pre-timed method in transmission delay, CO2 emission which causes air pollution.
Read MoreDoi: https://doi.org/10.54216/JISIoT.030202
Vol. 3 Issue. 2 PP. 57-67, (2021)
Botnet attacks involving Internet-of-Things (IoT) devices have skyrocketed in recent years due to the proliferation of internet IoT devices that can be readily infiltrated. The botnet is a common threat, exploiting the absence of basic IoT security technologies and can perform several DDoS attacks. Existing IoT botnet detection methods still have issues, such as relying on labeled data, not being validated with newer botnets, and using very complex machine learning algorithms, making the development of new methods to detect compromised IoT devices urgent to reduce the negative implications of these IoT botnets. Due to the vast amount of normal data accessible, anomaly detection algorithms seem to promise for identifying botnet attacks on the Internet of Things (IoT). For anomaly detection, the One-Class Support vector machine is a strong method (ONE-SVM). Many aspects influence the classification outcomes of the ONE-SVM technique, like that of the subset of features utilized for training the ONE-SVM model, hyperparameters of the kernel. An evolutionary IoT botnet detection algorithm is described in this paper. Particle Swarm Optimization technique (PSO) is used to tune the hyperparameters of the ONE-SVM to detect IoT botnet assaults launched from hacked IoT devices. A new version of a real benchmark dataset is used to evaluate the proposed method's performance using traditional anomaly detection evaluation measures. This technique exceeds all existing algorithms in terms of false positive, true positive and rates, and G-mean for all IoT device categories, according to testing results. It also achieves the shortest detection time despite lowering the number of picked features by a significant amount.
Read MoreDoi: https://doi.org/10.54216/JISIoT.030203
Vol. 3 Issue. 2 PP. 68-84, (2021)
Energy management in smart homes involves the use of technology to optimize energy consumption, reduce waste, and lower energy costs. Smart homes are equipped with various devices, sensors, and systems that are designed to monitor and control energy usage. We proposed a novel Energy Management System (EMS) that integrates Machine Learning (ML) techniques and IoT paradigms to optimize energy consumption and reduce energy costs for sustainable smart homes. In addition to the AI-based EMS, we propose integrating fog computing, a decentralized computing infrastructure, to improve the speed, accuracy, privacy, and security of the EMS. The fog nodes can collect data from the various sensors and devices in the smart home and process the data in real time, reducing latency and allowing for quicker decision-making. By processing data at the edge of the network, fog computing also reduces the amount of data that needs to be sent to the cloud, improving privacy and security. Experimental proof-of-concept simulations demonstrated the efficiency and effectiveness of our system in improving sustainability in smart homes.
Read MoreDoi: https://doi.org/10.54216/JISIoT.030204
Vol. 3 Issue. 2 PP. 85-94, (2021)