http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Real-Time Validation Scheme using Blockchain Technology for Industrial IoT
Cosmas Ifeanyi Nwakanma,Williams-Paul Nwadiugwu,Jae-Min Lee,Dong-Seong Kim 한국통신학회 2019 한국통신학회 학술대회논문집 Vol.2019 No.6
This paper proposes a prototype real time validation scheme using ’solidity’ and ’node.js’ for the building of blockchain used as decentralized database of an Industrial Internet of thing (IIoT) model. A major challenge or demand of Industry 4.0 is the need for real-time systems and associated capabilities. Several works have emerged in the past one decade since the inception of block-chain technology but no contribution towards its expansion is considered trivial as the technology is continuously evolving and the ranges of applications keep expanding. The result of the design shows that the proposed system has the capacity to validate industrial IoT activities in real time and boost confidence which is critical to the growth of industries beyond the 21st century.
Delay-Aware and Scalable Ethernet Network for Indoor Environment
Cosmas Ifeanyi Nwakanma,Md. Sajjad Hossain,Min-Hui Jang,Jae-Min Lee,Dong Seong Kim 한국통신학회 2020 한국통신학회 학술대회논문집 Vol.2020 No.2
Scalability of a network is the aspect which proves the competence of a network or a system to handle enlarged amount of demand without disturbing the existing users of the network. This paper simulated and evaluated the delay-awareness of networks scaled by incremental workloads. Five scenarios were created and analysed to identify the level of delay tolerance of the networks. The simulation and analysis were done using OPNET Modeler 14.5 to capture delay and traffic elements of the scenarios. Results showed that for the scalable network, using Ethernet 16 hub outperforms the use of Ethernet 16 bridge and Ethernet switch respectively for Indoor office network. Ethernet delay element results was 0.00015 seconds which is lower than 0.00025 seconds of other scenarios.
Heterogeneous IoT Sensor Data Classification for Emergency Detection using Machine Learning
Cosmas Ifeanyi Nwakanma,Ade Pitra Hermawan,Jae-Min Lee,Dong Seong Kim 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.2
Inertial Measurement Unit (IMU) and Ultra Wide Band (UWB) sensors were integrated to collect heterogeneous data in a smart factory scenario. In this paper, various machine learning algorithms were used to classify the data with a view to detect normal and anomaly situations based on threshold values of the sensor data. System was simulated using keras with GPU 1xTesla K80, 2496 CUDA cores and 12GB GDDR5 VRAM on top of Google colaboratory. Training and testing data were split into 75% and 25% respectively. Classification of the vibration data from the IMU gave Logistic regression (75.9% ), KNN1 (73.37%) and KNN2 (78.4%). In the case of the UWB sensor, KNN1 (100% for movement and respiration), KNN2 (98.60% for movement and 100% for respiration) and Logistic regression gave 100% accuracy both for movement and respiration data. Therefore, it is recommended that based on trade-off, KNN-2 outperformed other machine learning algorithms.
Reliability Analysis of Modified Random Forest Model for Activity Detection using F-Test
Cosmas Ifeanyi Nwakanma,Ahmad Zainudin,Love Allen Chijioke Ahakonye,Goodness Oluchi Anyanwu,Jae Min Lee,Dong-Seong Kim 한국통신학회 2022 한국통신학회 학술대회논문집 Vol.2022 No.2
Activity detection and classification schemes in Smart spaces involve using artificial intelligence models. However, most researchers employ the traditional performance metrics such as accuracy, loss, and recall. In this work, reliability is determined using F-test statistics. The modified random forest proposed shows to be reliable with the F-test value 0.3471 which is below 2.5 benchmark value.
Thermal Sensor-Based Activity Detection in Smart Spaces using GentleBoost Optimized Classifier
Cosmas Ifeanyi Nwakanma,Goodness Oluchi Anyanwu,Adinda Riztia Putri,Jae Min Lee,Dong-Seong Kim 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.6
On the smart factory shop floor, the safety of persons can be enhanced with an effective human activity detection system. This system should have the ability to monitor issues like fall detection which is a common work-related accident. In this work, we have used a public dataset that is based on a thermal array (ambient) sensor for the detection and classification of falls on the smart factory shop floor. The performance of the proposed optimized ensemble learning in MATLAB R2019b shows an accuracy of 100%, and a loss value of 0.00015642 using the minimum classification error plot.
Broadband Penetration Beyond 5G: Challenges and Open Issues
Cosmas Ifeanyi Nwakanma,Jae-Min Lee,Dong-Seong Kim,Stanley Adiele Okolie,Andrew Omame 한국통신학회 2020 한국통신학회 학술대회논문집 Vol.2020 No.8
This paper presents a review and analysis of the trend of broadband penetration in a developing country case study. The presentation is compared with the trend of broadband penetration in South Korea that has launched its’ 5G in 2019. The year 2020 promises to be the implementation and commercialization of 5G globally. However, there are challenges facing developing nations with respect to the eventual launch. As the world moves to begin research work in beyond 5G and likely deployment in 2030, will developing countries be captured and what will be the drivers to give a critical attention? The findings of this paper is based on a 18 year data (2001-2018) of Nigeria as case study. It is recommended that Information and Communication Technology researches should be targeted at less developed and developing countries with the hope of expanding the reach of 5G and beyond 5G. To predict the expected broadband penetration in the nearest future, we used MATLAB R2019b linear regression trainer to train data and predict based on response plot. Result shows that there is a positive linear relationship between year under review and rise in number of broadband penetration. The regression model has an R-Squared value of 0.96 or 96% which is a good fit. Furthermore, we also implemented an Artificial Neural Network (ANN) model to predict broadband subscription. The model which was implemented using R-Programming gave an accuracy 93% with a projection of over 200million broadband subscription in 2021.
Edge AI Prospect using the NeuroEdge Computing System: Introducing a Novel Neuromorphic Technology
Cosmas Ifeanyi Nwakanma,Jae-Woo Kim,Jae-Min Lee,Dong-Seong Kim 한국통신학회 2021 ICT Express Vol.7 No.2
This paper presents a test bed demonstration of NeuroEdge computing for face recognition using a novel neuromorphic chip- NM500. First, a general description and important specifications of the NM500 are presented. Second, a face recognition test-bed case study is used to demonstrate the efficacy and efficiency of the chip. Neuromorphic technology offers scalability and consistent recognition time, which is required by real-time networked systems, and presents a considerable advantage for real-time computations, making them virtually independent of the dataset size. In this study, intelligent edge computing technology was introduced using NeuroEdge. The performance was verified using a face recognition test. The results demonstrated that using neuromorphic technology, such as the NM500 chip, saves the time needed for training systems and does not impose the burden of requiring many datasets for effective training.
Smart Building HVAC Monitoring using Thermal Sensor for Occupancy Estimation
Cosmas Ifeanyi Nwakanma,Dong-Seong Kim,Jae-Min Lee 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.11
In view of the goal for environmental sustainability, power conservation, and energy cost management, it is imperative to monitor the heating, ventilation, and air conditioning (HVAC) in smart buildings. This work reviewed a system of thermal array sensors rightly deployed to detect and track human occupation in a smart building. In addition, traditional machine learning algorithms were reviewed to determine the best performance in terms of estimating the occupancy status of smart buildings. Estimating the occupancy of smart buildings will help in establishing their HVAC requirements.