A Response-Aware Traffic Offloading Scheme Using Regression Machine Learning for User-Centric Large-Scale Internet of Things

Manogaran, Gunasekaran; Srivastava, Gautam; Muthu, BalaAnand; Baskar, S.; Shakeel, P. Mohamed; Hsu, Ching‐Hsien; Kumar, Priyan Malarvizhi

doi:10.1109/jiot.2020.3022322

Cited by 36 publications

(12 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, 70% of the sample data is used to perform training, 15% for the validation set, while the remaining 15% for the testing set. For the training, validation, and testing process, 9.8×10 4 , 2.1×10 4 , and 2.1×10 4 information packets were respectively processed, thus making a total of 1.4×10 5 . The LSTM architecture is configured with 1 hidden layer (100 Neurons), 'Initial Learn Rate' equal to 0.0001, RMSE loss function, maximum 50 epochs [62], [63], and using the Adam optimizer [64].…”

Section: B Simulation Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

Energy-Efficient Wake-Up Signalling for Machine-Type Devices Based on Traffic-Aware Long Short-Term Memory Prediction

Ruíz-Guirola

Rodríguez-López

Montejo‐Sánchez³

et al. 2022

IEEE Internet Things J.

View full text Add to dashboard Cite

educing energy consumption is a pressing issueeducing energy consumption is a pressing issueR in low-power machine-type communication (MTC) networks. In this regard, the Wake-up Signal (WuS) technology, which aims to minimize the energy consumed by the radio interface of the machine-type devices (MTDs), stands as a promising solution. However, stateof-the-art WuS mechanisms use static operational parameters, so they cannot efficiently adapt to the system dynamics. To overcome this, we design a simple but efficient neural network to predict MTC traffic patterns and configure WuS accordingly. Our proposed forecasting WuS (FWuS) leverages an accurate long-short term memory (LSTM)-based traffic prediction that allows extending the sleep time of MTDs by avoiding frequent page monitoring occasions in idle state. Simulation results show the effectiveness of our approach. The traffic prediction errors are shown to be below 4%, being false alarm and miss-detection probabilities respectively below 8.8% and 1.3%. In terms of energy consumption reduction, FWuS can outperform the best benchmark mechanism in up to 32%. Finally, we certify the ability of FWuS to dynamically adapt to traffic density changes, promoting low-power MTC scalability.

show abstract

Section: B Simulation Frameworkmentioning

confidence: 99%

“…318927) and Tekniikan Edistämissäätiön. fleet management, smart grid, industrial automation, realtime monitoring/control, and remote medical systems [5]- [10]. Consequently, the number of MTDs is explosively growing, and billions of MTDs, such as sensors, actuators, and meters, are predicted to be operational in the coming years.…”

Section: Introductionmentioning

confidence: 99%

Energy-Efficient Wake-Up Signalling for Machine-Type Devices Based on Traffic-Aware Long Short-Term Memory Prediction

Ruíz-Guirola

Rodríguez-López

Montejo‐Sánchez³

et al. 2022

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…Precision agriculture can help eliminate the excessive use of fertilizer, reduce the overall impact of agriculture on the environment, and improve the yield of crops. It can reduce the consumption of water, pesticides, and chemical fertilizers, reduce food production costs, reduce runoff, and minimize the impact on natural ecosystems (Gebremichael et al, 2020;Manogaran et al, 2020). Moreover, IoT devices provide farmers with a great opportunity to remotely monitor the condition of their livestock and obtain data about livestock and their health, which means that farm managers can make better decisions faster and bring higher profits.…”

Section: Application Of Iot System In Intelligent Agriculturementioning

confidence: 99%

Practical Application of Internet of Things in the Creation of Intelligent Services and Environments

2022

Front. Internet Things

View full text Add to dashboard Cite

The information era is coming. As a popular technology in the information age, Internet of Things (IoT) can collect various types of information in real time, realize the ubiquitous connection between things and people, and process the intelligent perception, identification, and management of things, processes, and information, and environment protection through various network access methods. Applying IoT to various fields is like wrapping the Earth with a layer of "digital skin" (Gubbi et al., 2013;Bauwens et al., 2020;Li and Da Xu, 2020). Moreover, under the trend of global warming, the emergence of the theme of Energy Saving and Emission Reduction (ESER) undoubtedly poses new challenges to the development of IoT.When IoT is widely used in various life scenarios, its main purpose is to provide intelligent services and environments. IoT applications can connect any sensing device to the Internet for data transmission, so as to realize intelligent identification, tracking, positioning, and monitoring of sensing devices. In addition, IoT contains many types of Wireless Sensor Networks (WSN), which, as a part of IoT sensing layer, can meet the actual needs of people to obtain reliable data in special environments (Sadowski and Spachos, 2020). WSN is a multi-hop network which is self-organized by many sensor nodes. It has the characteristics of flexibility, fault tolerance, high awareness, low cost, strong survivability, and fast layout. Therefore, IoT has a wide range of applications, such as environmental monitoring, agriculture, military, and medical care, and can collect, process, and disseminate collected data deployed in various environments (Aman et al., 2020;Fortino et al., 2020). However, for some special scenes, many sensor nodes are often placed in areas that cannot be accessed by human beings. While enjoying the convenience brought by WSN, people are also faced with the problems that illegal personnel obtain illegitimate interests by intercepting the monitoring data transmitted in the public channel. Therefore, the attention to security issues in IoT cannot be ignored.With the increasing commercial scope of 5th Generation Mobile Communication Technology (5G) communication technology in cities, the application of IoT in power, construction, industry, intelligent transportation, agriculture, logistics, intelligence, high efficiency, and ESER is being promoted (Verma et al., 2020). Of course, applying IoT is also inseparable from the combination of 5G communication, Cloud Computing (CC), Edge Computing (EC), blockchain, AI, and other technologies. IoT can collect many data from the environment, effectively monitor, analyze, and manage energy consumption, and reasonably improve IoT by identifying and analyzing opportunities of energy efficiency improvement (Khan et al., 2020;Liao et al., 2020;Saračević et al., 2020).In summary, in today's high-speed 5G communication technology, IoT is widely applied, and guaranteeing its performance is of high significance. Therefore, taking the practical application of IoT...

show abstract

“…Artificial intelligence influences English Education with learning awareness and technologies in educational institutions (Manogaran et al, 2020). Basic knowledge in a text can be easily read by individual students (Hsu et al, 2021).…”

Section: Significant Of Machine Learning Based English Teaching For S...mentioning

confidence: 99%

An English teaching quality evaluation model based on Gaussian process machine learning

et al. 2021

View full text Add to dashboard Cite

Background The efficiency of conventional English teaching quality evaluation is comparatively small, and evaluation statistics are challenging. To investigate the use of artificial intelligence (AI) technology in teacher teaching assessment, a machine learning algorithm is proposed to create a teaching evaluation model suitable for the current educational model to assist colleges and universities in overcoming existing teaching challenges. Objectives The proposed Machine learning‐based Gaussian process model (MLGPM) improves the student's language skills. The proposed model uses Gaussian mixed model to express the circulation features of samples and enhances the support vector machine. Therefore, this paper suggests an active learning algorithm that, in association with Gaussian mixed model and sparse Bayesian learning, strategically chooses and labels samples to construct a classifier that syndicates the distribution characteristics of the samples. As a result, the accuracy of a considered quality index for English classrooms is verified, and the quality and control of English as a foreign language can be enhanced. Results The experiment results show that the model presented in this study is effective and beneficial when assessing the efficiency of teaching in universities and analyzing big data sets. Conclusion The simulation analysis with student performance improvement in English teaching quality using machine learning high fluency rate of 95.3, high accuracy ratio of 98.1%, improve vocabulary prediction ratio of 94.6%, improve passage prediction ratio of 92.7%, enhance learning rate of 95.2%, reduce the error rate of 24.1%, F1‐score of 91.5% and assessment score of 92.1% when compared with other methods.

show abstract

A Response-Aware Traffic Offloading Scheme Using Regression Machine Learning for User-Centric Large-Scale Internet of Things

Cited by 36 publications

References 30 publications

Energy-Efficient Wake-Up Signalling for Machine-Type Devices Based on Traffic-Aware Long Short-Term Memory Prediction

Energy-Efficient Wake-Up Signalling for Machine-Type Devices Based on Traffic-Aware Long Short-Term Memory Prediction

Practical Application of Internet of Things in the Creation of Intelligent Services and Environments

An English teaching quality evaluation model based on Gaussian process machine learning

Contact Info

Product

Resources

About