The continuous improvements in the Internet of Things (IoTs) and machine learning (ML) make them the key enabling technologies for intelligent traffic management (ITM).The ability to accurately predict network traffic has been demonstrated as crucial for effective network management and strategic planning. Proactive management of future congestion incidents requires access to reliable long-term forecasting models. Conventional prediction methods often fail to completely capture the spatiotemporal features of the traffic flows because of the complexity of the interdependence between the flows. To this end, we proposed to improve the management of traffic with a novel framework for the predictive modeling of traffic flows. The proposed formwork introduces an improved graph network to capture the positional information in traffic follows. It is also capable of precisely capturing temporal dynamics using an improved bidirectional learning module. An attention mechanism is presented to capture the interactions among spatial and temporal patterns to further empower the predictive power of the model. Proof-of-concept experimentations are conducted on the PeMSD7 dataset, and the results (MAE: 0.197, MSE: 0.13, RMSE: 0.36, ) demonstrate the efficiency of our model over the state-of-the-art.
Read MoreDoi: https://doi.org/10.54216/JISIoT.080201
Vol. 8 Issue. 2 PP. 08-19, (2023)
The COVID-19 epidemic has in fact placed the whole community in a dire predicament that has led to numerous tragedies, including an economic downturn, political unrest, and job losses. Forecasting and identifying COVID-19 infection cases is crucial for the government at all levels because the pandemic grows exponentially and results in fatalities. Hence, by giving information about the spread of the epidemic, the government can move quickly at multiple levels to establish new policies and modalities in order to minimize the trajectory of the COVID-19 pandemic's effects on both public health and the economic sectors. Forecasting models for COVID-19 infection cases in the Ural region in Russia were developed using two deep Long Short-Term Memory (LSTM) learning-based approaches namely Encoder–Decoder LSTM and Attention LSTM algorithms. The models were evaluated based on five standard performance evaluation metrics which include Mean Square Error (MSE), Mean Absolute Error (MAE), Root MSE (RMSE), Relative RMSE (RRMSE), and coefficient of determination (R2). However, the Encoder–Decoder LSTM deep learning-based forecasting model achieved the best performance results (MSE=32794.09, MAE=168.56, RMSE=181.09, RRMSE=13.46, and R2=0.87) compared to the model developed with Attention LSTM models.
Read MoreDoi: https://doi.org/10.54216/JISIoT.080202
Vol. 8 Issue. 2 PP. 20-33, (2023)
Our ability to align with the trend of innovations in science and technology will not only emancipate ignorance but also unfold our ability to evaluate, understand and predict possibilities in our society, environment, and the world at large. Radar system technology gives us the privilege to achieve the above-mentioned fact. The word Radar is an acronym for Radio Detection and Ranging. It is a mean of getting information about a distant target, by sending electromagnetic waves to them and analyzing the echoes from the target to generate relevant reports about the target. In this paper, we will focus on some metrics and the effect of changes in them on the performance of the radar system using the MATLAB Radar Designer.
Read MoreDoi: https://doi.org/10.54216/JISIoT.080203
Vol. 8 Issue. 2 PP. 34-44, (2023)
Smart Sensor Networks (SSNs) are an indispensable part of the Industrial Internet of Things (IIoT), which seeks to improve efficiency, productivity, and safety in different industrial applications. SSNs consist of a large number of sensors, regularly deployed in a wireless ad-hoc network, which communicates with each other and with other devices, such as gateways and servers. Nevertheless, the building of SSNs in IIoT environments encounters many challenges, such as trust management, data reliability, privacy, and security. These challenges necessitate proposing novel solutions and protocols, to provide a reliable, secure, and efficient SSN. To this end, this study presents a novel DL system that can effectively discriminate between normal traffics and malicious traffic in SSNs. A convolutional feature extractor is developed to learn important discriminative features necessary for the early detection of security threats in SSNs. Then, an improved LSTM (ILSTM) is presented to model the temporal dynamics of the SSNs flows, which helps model long interdependency between traffic samples. A focal loss function is applied to deal with the imbalance between class samples. Experimental analysis is performed on an open-source SSN security dataset, named WSN-DS, the findings demonstrated the competitive advantages of our system over the prevailing solutions.
Read MoreDoi: https://doi.org/10.54216/JISIoT.080204
Vol. 8 Issue. 2 PP. 45-53, (2023)
As AI-based smart homes become increasingly popular, there is a need to better understand the benefits and challenges of this emerging technology. A survey on AI-based smart homes can provide valuable insights into user needs, adoption rates, user satisfaction, barriers to adoption, and opportunities for innovation. This research overviews the cutting-edge literature on smart home development with an emphasis on the utilization of artificial intelligence (AI) approaches in this application area. We begin with a review of AI technologies and the smart home necessities needed to implement AI. Then, we introduce several applications of AI for smart homes and describe the most popular approaches already present in literary works. The open Issues (e.g., security and privacy, data collection and sharing, data analytics, and latency) meeting the development of smart homes are also discussed in this work. Finally, the paper suggests some directions for future study that could be fruitful.
Read MoreDoi: https://doi.org/10.54216/JISIoT.080205
Vol. 8 Issue. 2 PP. 54-62, (2023)