BrainyEdge: An AI-enabled framework for IoT edge computing

Kim-Hung Le,Khanh-Hoi Le-Minh,Huy-Tan Thai 한국통신학회 2023 ICT Express Vol.9 No.2

Along with the proliferation of the Internet of Things (IoT) and the surge in the use of artificial intelligence (AI), Edge Computing has proved considerable success in reducing latency, network traffic consumption, and security risks. The convergence of AI and Edge Computing, emerging a brand-new paradigm called edge intelligence, has been expected to unleash the full potential of intelligent IoT services. Unfortunately, integrating AI and Edge Computing into IoT is highly challenging due to the concerns over IoT device performance, energy efficiency, and privacy. In this paper, we present brainyEdge, an AI-enabled framework for edge devices able to jointly satisfy the Quality of Experience (QoE) criteria of IoT applications. We enhanced the intelligence of AI models operating at edges by designing a learning procedure consisting of transfer learning and incremental learning to dynamically retrain the models with personalized and incremental data locally stored. These data are classified into private data permanently stored in edges and public data shared in the cloud. This increases the edge-cloud collaboration level while preserving data privacy. To minimize the network cost of deploying the models to edge devices, we developed a lightweight deployment paradigm supporting cloud-compression and edge-decompression based on a user-desired compression ratio. Our prototype-based evaluation results indicate the superiority of brainyEdge over a typical edge-cloud paradigm.

Fiscal Decentralization, Corruption, and Income Inequality: Evidence from Vietnam

Hung Thanh NGUYEN,Thuy Hoang Ngoc VO,Duc Doan Minh LE,Vu Thanh NGUYEN 한국유통과학회 2020 The Journal of Asian Finance, Economics and Busine Vol.7 No.11

The objective of this research paper is to study the simultaneous relationship between fiscal decentralization, corruption, and income inequality among Vietnamese provinces. We use a balanced panel data set of 63 provinces/cities in Vietnam in the period from 2011 to 2018. The study used 3SLS-GMM (Three Stage Least Squares - Generalized Method of Moments estimator) and GMM-HAC (Generalized Method of Moments - Heteroskedastic and Autocorrelation Consistent estimator). Empirical evidence shows a strong simultaneous relationship: increased corruption will increase regional income disparities, income inequality, and increase fiscal decentralization. In addition, the results also suggest that an increase in per-capita income will reduce the level of corruption, or better control corruption of each province. The degree of increase in income inequality, which reduces fiscal decentralization, is the same for trade liberalization. All demonstrate that there is a simultaneous relationship between fiscal decentralization, corruption, and income inequality. In a region of high public governance quality, fiscal decentralization positively effects its economic growth. This issue will indirectly increase income inequality between provinces within a country. Our findings imply that a country’s fiscal decentralization strategy should be linked to improving corruption control and local governance effectiveness, indirectly improving income inequality between localities or regions.

An Advanced Closed-Loop Control to Improve the Performance of Hybrid Stepper Motors

Le, Kien Minh,Van Hoang, Hung,Jeon, Jae Wook Institute of Electrical and Electronics Engineers 2017 IEEE transactions on power electronics Vol. No.

<P>This paper presents an effective closed-loop control approach for a stepper motor. The proposed approach consists of motor parameter identification, closed-loop current control, closed-loop position control, and damping control. The presented implementation achieves accurate position, high torque, and smooth speed. By using an improved proportional-integral current control algorithm, this approach not only guarantees the current tracking performance but also increases the bandwidth during the speed response. The advanced position controller achieves both high torque and the synchronous condition of the motor after a loss of synchronism occurs. In addition, this method applies an effective speed damping method to remove resonance at low speed and reduce vibration at high speed. All the proposed algorithms were implemented on an industrial test-bench. The experimental results demonstrate the validity of the proposed approach for practical applications.</P>

Landscape Function and Tourism Industry: A Case Study of Moc Chau Plateau, Vietnam

LE, Hoa Thi Thu,TONG, Binh Thanh,VU, Ngoc Thi Minh,HO, Luu Si,PHAM, Thang Viet,TRINH, Hang Thi Thu Korea Distribution Science Association 2020 The Journal of Asian Finance, Economics and Busine Vol.7 No.12

Tourism is not only a cultural service but also a resource consuming industry. Landscape function framework is a powerful tool to show the relationship between nature and people. This study collects 50 documents around the world to analyze the relationship between the 4 functional groups of the landscape (regulatory functions, production and supply functions, resident functions, information and entertainment functions) and the tourism industry. On that basis, we created an establishment for practical contact analysis of the goods and services of the landscape for tourism development in Moc Chau plateau, Vietnam. Research results show that tourism is an economic sector that benefits from the landscape and has a clear resource orientation. Moc Chau plateau has rich tourism resources and has the conditions to develop various types of tourism, especially cultural tourism based on community and resort tourism. The two cultural functions and the providing functions are the two most important functional groups for the tourism development of Moc Chau district, bringing the two most important tourism icons for Moc Chau, a green steppe, cool milk benevolent and also a district rich in national culture. From these conclusions, the authors give recommendations and notable points about landscapes in the tourism industry, especially in places with topography like Moc Chau.

Appropriation of Protocol for Laparoscopic Pancreaticoduodenectomy in Treatment of Periampullary Cancer

( Minh Hai Pham ),( Quan Anh Tuan Le ),( Hoang Bac Nguyen ),( Quang Hung Vu ),( Thai Ngoc Huy Tran ),( Hang Dang Khoa N Guyen ),( Thi Ngoc Sang Duong ),( Van Toan Tran ) 대한간학회 2020 춘·추계 학술대회 (KASL) Vol.2020 No.1

Aims: Laparoscopic pancreaticoduodenectomy (LPD) is considered as a safe and effective procedure in well - selected patients and appropriate surgical technique. Our aim is to evaluate suitability of using protocol for LPD in treatment of periampullary cancer at a single team. Methods: case series Results: Indication for LPD included 37 cases with resectable tumors which were classified basing on NCCN. All witness evaluation risk of complications with PREPARE score, ASA and evaluation risk of postoperative pancreatic fistula (POPF) with FRS classification. There were 2 open conversions because of vein resections, accounting for 5.4%. Standard lymphadenectomy was performed in all of 37 cases. In term of PREPARE score, major complications (Clavien - Dindo >= III) were 17.8%, 0% and 0% (5/28, 0/5 and 0/2 cases) in low risk, intermediate risk and high risk group, respectively. All of cases had ASA I or II. POPF happened 11.1% (1/9), 4.1% (1/24) and 50% (1/2) in low risk, intermediate risk and high risk group, respectively. Frozen section was needed for R0 margin. Retrieved lymph nodes was 8 - 18 with 12 lymph nodes in average. Conclusions: Indication for LPD with resectable tumors is acceptable. ASA I or II is a safe measure to select patient for LPD. FRS classification shows appropriation to evaluate risk of POPF.

Adaptive Reduced Power Subframe in LTE Heterogeneous Networks

Le Hung Nguyen,Minh Thang Nguyen,Sungoh Kwon 한국통신학회 2018 한국통신학회 학술대회논문집 Vol.2018 No.11

Aerodynamic drag of axisymmetric models with different boattail angles under subsonic and supersonic flow conditions

The Hung Tran,Cong Truong Dao,Dinh Anh Le,Van Khiem Pham,Van Minh Do,Trang Minh Nguyen 대한기계학회 2023 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.37 No.12

This study examines the drag trend and flow behavior of axisymmetric models with conical boattails under subsonic and supersonic conditions by using a numerical approach. Mach numbers ranging from 0.1 to 3.0 and boattail angles varying from 0° to 24° are investigated. The numerical results are validated by experimental data under identical flow conditions. The flow behavior around the boattail body, the total drag, and the pressure distribution are analyzed in detail. The drag components acting on the boattail surface are examined to determine the reason for the change in drag due to different boattail angles and Mach number conditions. Results show that the minimum drag is around 14° for subsonic flow, but this value suddenly decreases to around 7° for supersonic flow. Formalization of the expansion and oblique shocks on the boattail is the main cause of changes in the pressure distribution on the surfaces, which in turn affect the drag trend. Moreover, the relationships among boattail angle, flow conditions, and four flow types on the boattail surface are presented in detail.

Heat Dissipation for the Intel Core i5 Processor Using Multiwalled Carbon-nanotube-based Ethylene Glycol

Bui Hung Thang,Pham Van Trinh,Le Dinh Quang,Nguyen Thi Huong,Phan Hong Khoi,Phan Ngoc Minh 한국물리학회 2014 THE JOURNAL OF THE KOREAN PHYSICAL SOCIETY Vol.65 No.3

Carbon nanotubes (CNTs) are some of the most valuable materials with high thermal conductivity. The thermal conductivity of individual multiwalled carbon nanotubes (MWCNTs) grown byusing chemical vapor deposition is 600 ± 100 Wm−1K−1 compared with the thermal conductivity419 Wm−1K−1 of Ag. Carbon-nanotube-based liquids – a new class of nanomaterials, have shownmany interesting properties and distinctive features offering potential in heat dissipation applicationsfor electronic devices, such as computer microprocessor, high power LED, etc. In this work,a multiwalled carbon-nanotube-based liquid was made of well-dispersed hydroxyl-functional multiwalledcarbon nanotubes (MWCNT-OH) in ethylene glycol (EG)/distilled water (DW) solutionsby using Tween-80 surfactant and an ultrasonication method. The concentration of MWCNT-OHin EG/DW solutions ranged from 0.1 to 1.2 gram/liter. The dispersion of the MWCNT-OH-basedEG/DW solutions was evaluated by using a Zeta-Sizer analyzer. The MWCNT-OH-based EG/DWsolutions were used as coolants in the liquid cooling system for the Intel Core i5 processor. Thethermal dissipation efficiency and the thermal response of the system were evaluated by directlymeasuring the temperature of the micro-processor using the Core Temp software and the temperaturesensors built inside the micro-processor. The results confirmed the advantages of CNTs inthermal dissipation systems for computer processors and other high-power electronic devices.

A Statistical Data-Filtering Method Proposed for Short-Term Load Forecasting Models

Duong Minh Bui,Phuc Duy Le,Tien Minh Cao,Hung Nguyen,Trang Thi Pham,Duy Anh Pham 대한전기학회 2020 Journal of Electrical Engineering & Technology Vol.15 No.5

Reliability assessment of the SCADA-system based load data is necessary for improving accuracy of short-term load forecasting (STLF) methods in a distribution network (DN). Specifi cally, the reliability evaluation of the load data is to properly eliminate noise/outliers caused by random power consumption behaviors or the sudden change in load demand from industrial and residential customers in the DN. Thus, this paper proposes a novel statistical data-fi ltering method, working at an input data pre-processing stage, which will evaluate the reliability of input load data by analyzing all possible data confi dence levels in order to fi lter-out the noise/outliers for accuracy improvement of diff erent short-term load forecasting models. The proposed statistical data-fi ltering method is also compared to other existing data-fi ltering methods (such as Kalman Filter, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Discrete Wavelet Transform (DWT) and Singular Spectrum Analysis (SSA)). Moreover, several case studies of short-term load forecasting for a typical 22 kV distribution network in Vietnam are conducted with an Artifi cial Neural Network (ANN) model, a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) model, a combined model of Long Short-Term Memory Network and Convolutional Neural Network (LSTM-CNN), and a conventional Autoregressive Integrated Moving Average (ARIMA) model to validate the statistical data-fi ltering method proposed. The achieved results demonstrate which the STLF using ANN, LSTM-RNN, LSTMCNN, and ARIMA models with the statistical data-fi ltering method can all outperform those with the existing data-fi ltering methods. Additionally, the numerical results also indicate that in case the SCADA-based load data is normally distributed, time-series forecasting models should be more preferred than neural network models; otherwise, when the SCADA-based load data contains multiple normally distributed sub-datasets, neural network-based prediction models are highly recommended.

Adaptive hierarchical sliding mode control using an artificial neural network for a ballbot system with uncertainties

Hai Le Xuan,Quoc-Dong Hoang,Soon Geul Lee,Dat Pham Xuan,Hoang Tran Viet,Minh Pham Van,Hung Pham Van,Hung Pham Viet,PHAM DUC TUAN,Duc Anh Nguyen 대한기계학회 2022 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.36 No.2

Ballbots, which have been studied for over ten years, are under-actuated mobile robots that operate using the inverted pendulum paradigm. Controlling a ballbot poses a number of challenges, including maintaining the stable upright posture from the ground in all directions and making sure it follows the desired trajectory. External factors such as a minor change in contact surface properties or fabrication errors can affect the system's stabilization and transfer capabilities. In this study, an adaptive hierarchical sliding mode control algorithm based on an artificial neural network is developed to make the ballbot robust to external factors. The use of the proposed controller ensures system stability despite uncertainties including friction, accidental centrifugal forces and gravity that occur when the ballbot follows the reference trajectory. The system stability is guaranteed on the basis of Lyapunov theory. Control efficiency and robot stability under system uncertainties are demonstrated by numerical simulation.