检索结果-内蒙古大学图书馆

Tourism forecasting using box-Jenkins SARIMA and artificial neural network (ANN) models: Case for outbound and inbound tourist in Malaysia

引用

AIP Conference Proceedings 2023年第1期2746卷

作者： Norizan Mohamed Maharani A. Bakar Siti Nurfarahanim Mohd Razali Nur Khalisa Mazlan Nurfarahin Idrus Nor Azlida Aleng Yusnita Yusof Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu 21030 Kuala Nerus Terengganu Malaysia Special Interest Group Modelling and Data Analytics Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu 21030 Kuala Nerus Terengganu Malaysia Faculty of Science and Technology Universiti Kebangsaan Malaysia 43600 UKM 43600 Bangi Selangor Malaysia Faculty of Business Economics and Social Development Universiti Malaysia Terengganu 21030 Kuala Nerus Terengganu Malaysia

Tourism industry has become an important sector for Malaysian economy through foreign exchange earnings and employment opportunities where generally increases the economic development of the country. Due to significant effect to Malaysia economy, it motivated us to come up with the best model for forecasting both outbound and inbound tourists in Malaysia. Hence, this paper aims to develop the best model for forecasting outbound and inbound tourists in Malaysia by using Box-Jenkins SARIMA model and multilayer feedforward neural network (MFNN) model. The dataset used was monthly basis, recorded from January 2010 to December 2019, and was split into in-sample data from January 2010 to December 2017 and out-sample data from January 2018 to December 2019. The accuracy of the models was measured by using MAPE. By applying SARIMA and MFNN to the dataset, results shown MFNN model is more accurate than the SARIMA model to forecast outbound and inbound tourists in Malaysia. The paper provides implications for policy makers and suggestions for future tourism forecasting models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Methods for Calibrated Photometric Stereo and Beyond

arXiv

引用

arXiv 2022年

作者： Ju, Yakun Lam, Kin-Man Xie, Wuyuan Zhou, Huiyu Dong, Junyu Shi, Boxin School of Electrical and Electronic Engineering Nanyang Technological University Singapore The Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Hong Kong The Research Institute for Future Media Computing Shenzhen University Shenzhen China The Department of Informatics University of Leicester Leicester United Kingdom The Faculty of Information Science and Engineering The Institute for Advanced Ocean Study Ocean University of China Qingdao China The National Key Laboratory for Multimedia Information Processing National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing China

Photometric stereo recovers the surface normals of an object from multiple images with varying shading cues, i.e., modeling the relationship between surface orientation and intensity at each pixel. Photometric stereo prevails in superior per-pixel resolution and fine reconstruction details. However, it is a complicated problem because of the non-linear relationship caused by non-Lambertian surface reflectance. Recently, various deep learning methods have shown a powerful ability in the context of photometric stereo against non-Lambertian surfaces. This paper provides a comprehensive review of existing deep learning-based calibrated photometric stereo methods utilizing orthographic cameras and directional light sources. We first analyze these methods from different perspectives, including input processing, supervision, and network architecture. We summarize the performance of deep learning photometric stereo models on the most widely-used benchmark data set. This demonstrates the advanced performance of deep learning-based photometric stereo methods. Finally, we give suggestions and propose future research trends based on the limitations of existing models. Copyright © 2022, The Authors. All rights reserved.

关键词： Light sources

来源：评论

学校读者我要写书评

暂无评论

Numerical Investigation on Motion Responses of Floating Structures by Application of Swarm Intelligence

引用

IOP Conference Series: Earth and Environmental Science 2022年第1期987卷

作者： S F Abdullah Program of Maritime Technology Faculty Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu 21030 Kuala Terengganu Terengganu Malaysia

In presence of complex-hydrodynamic interaction between water waves and floating structures, a reliable method that can analyse nonlinear structural properties is necessarily required. This paper presents a numerical investigation of the moored floating structures by application of swarm intelligence (SI). Here, a hybrid particle swarm optimization (PSO) algorithm with various swarm parameters are proposed to solve systems of sparse-nonlinear equations for the surge, heave, and pitch motion responses by considering distorted wave motion. In addition, a computational fluid dynamic (CFD) programme is developed using Reynolds Average Navier-Stokes (RANS) solver. Various wave parameters including a set of optimization criteria have been taken into account in a complete optimization simulation, where the optimum solutions are then selected at each numerical iteration. Meanwhile, the computed results of surge, heave, and pitch motions will be qualitatively validated, in which they are then visualized using CFD approach. The results show that the integrated SI-CFD model can simulate fairly well on hydrodynamics of floating structures with reasonable computational efficiency. Harnessing computational intelligence into a novel design concept of floating structures can serve as useful engineering decision-making tool.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive deep neural network using genetics algorithms for solving linear and non-linear ordinary differential equations

引用

AIP Conference Proceedings 2022年第1期2472卷

作者： Pratama A. Danang Maharani A. Bakar 1Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu 21300 Kuala Terengganu Malaysia

The numerical solution of a ordinary differential equation (ODE) basically describes any physical phenomenon of interest. Traditionally, the numerical solution of ODE is solved by a discretization process using the classical finite difference approximation. Recently, many studies have used deep neural networks (DNN) to approximate ODE solutions without discretization. However, without the optimization process, DNN cannot run independently. In this work, we proposed an alternative method that combines DNN with a genetic algorithm (GA) as an optimization method. GA initiates a population of DNN trainable parameters, making the DNN training process more streamlined on a single-generation GA. We focused on DNN-GA hybrid solution for linear and nonlinear ordinary differential equations (ODE‘s). Our method is achieved by solving several test problems and demonstrating a comparison with stochastic gradient descent (SGD) optimizers. In most ODE problems, using the same number of iterations and architecture, DNN-GA produces a better loss function than using DNN-SGD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A two-phase controlled drug release model in a one-compartmental system

引用

AIP Conference Proceedings 2023年第1期2484卷

作者： Amanina Setapa Shalela Mohd Mahali Fatimah Noor Harun 1Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Malaysia 2Management Science Research Group Universiti Malaysia Terengganu Malaysia

Small intestine is the main absorptive organ of orally consumed drugs in the body. Hydrogel is one of the materials that commonly used as a controlled drug release device that able to deliver drugs to be absorbed in the small intestine. This material swells to enable the drug release, leading to a dynamic diffusivity. In this paper, we aimed to simulate the controlled drug release from a swelling hydrogel considering the dynamic diffusion coefficient in a one-compartmental system of small intestine. The small intestine is considered as a single compartment where the controlled drug release process takes place simultaneously with the drug absorption and elimination process. We had formulated a two-phase controlled drug release model with two different constant diffusion coefficients using the advection-diffusion equation. The two-phase model was then adapted into the one-compartmental system and is solved using the forward finite difference method. The numerical simulation shows that the suggested mathematical model able to express the complex process of the controlled drug delivery in the small intestine.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling particulate pollution (PM2.5) in the Southern Region of Peninsular Malaysia

引用

AIP Conference Proceedings 2023年第1期2763卷

作者： Nurul Ain Ismail Nurul Atiqah Sopyan Samsuri Abdullah Amalina Abu Mansor Aimi Nursyahirah Ahmad Marzuki Ismail Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu 21030 Kuala Nerus Terengganu Malaysia Faculty of Science and Marine Environment Universiti Malaysia Terengganu 21030 Kuala Nerus Terengganu Malaysia

Haze pollution refers to the quality of the air during haze events that happened from local or transboundary haze affecting human health and the ecosystem. The Multiple Linear Regression (MLR) models is used in this study for identifying the PM2.5 concentrations for forecasting during haze events in the Southern Region of Peninsular Malaysia. The data from February to April 2019 were taken from three air monitoring stations which are Tangkak (Site 1), Batu Pahat (Site 2), and Kluang (Site 3) including PM2.5 concentrations, wind speed, temperature, and relative humidity. The result of this study shows Station 2 has the highest PM2.5 concentration (217.113 µg/m3), exceeding the standard limit (<35 µg/m3) due to peatland combustion at the District of Muar. There is a negative weak correlation between wind speed (r = -0.167, p < 0.01) and relative humidity (r = -0.029, p<0.01) but a positive weak correlation with temperature (r=0.161, p<0.01). For model development, PM2.5,t+1 had a higher coefficient of determination R2 values at 0.344. Meanwhile, for model validation maximum R2 for PM2.5,t+1 (0.9998). In conclusion, this study provides early information, especially to the local authority to improve the strategies for better air quality management during haze events.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Plasma-enhanced metamaterial for antenna application

引用

AIP Conference Proceedings 2022年第1期2454卷

作者： Ahmad Nazri Dagang Tan Swe Lan Iswan Lapagang 1Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu 21030 Kuala Nerus Terengganu Malaysia

Metamaterials is a lefthanded media that can be applied in antenna application to overcome the traditional design which is bigger in size and untunable. The wireless industry could overcome this problem since metamaterial antenna is designed with high permittivity dielectric substrate, using shorting well, shorting pins, and some deformation. Furthermore, antenna design not only reduces in size, but has high directivity, tunable frequency, and high performance to solve those aforementioned problems. Metamaterial antenna consists of hundred features which tunable to catch signals coming from any direction. This study proposed different structures of metamaterials using plasma to enhance its capability by using Computer Simulation technology (CST) simulation software. The aims are to analyze and compare antenna performance of the different structures in terms of return loss, gain, radiation pattern, as well as to investigate antenna performance of different plasma in terms of its plasma properties. This study used four different metamaterials structures namely split ring structure, Symmetrical structure, Omega structure, and S structure. There are 12-type of plasma conditions labeled with form Plasma A to L, with different plasma frequency and collision frequency. These materials were simulated using CST to calculate their return loss, gain, and radiation pattern, in order to identify the best antenna performance condition. The split ring structure has the highest return loss at -74.8 dB (Plasma D) while the S structure gives the best antenna gain at 7.9 dB (Plasma F). This is thought due to the electromagnetic properties in the split ring structure, and the high collision and plasma frequencies of plasma in the S structure. With 12 types of plasma parameters value, combined with 4 types of structures, it can be said that Plasma F, gave the best results in terms of the combination of antenna gain (average at 7.2 dB) and return loss value (average at -33.6 dB). In term

关键词：

来源：评论

学校读者我要写书评

暂无评论

Maritime law of tort collision regulations mobile apps (MLoTMA)

引用

AIP Conference Proceedings 2023年第1期2675卷

作者： Nurain Binti Mohd Razik Mohammad Aizat Bin Basir Mohd Sharifuddin Bin Ahmad Ahmad Faizal Bin Ahmad Fuad 1Faculty of Ocean Engineering Technology & Informatics Universiti Malaysia Terengganu Kuala Nerus Terengganu 21030 Malaysia 2Faculty of Ocean Engineering Technology & Informatics Universiti Malaysia Terengganu Kuala Nerus Terengganu 21030 Malaysia 3Faculty of Maritime Studies Universiti Malaysia Terengganu Kuala Nerus Terengganu 21030 Malaysia 4Faculty of Maritime Studies Universiti Malaysia Terengganu Kuala Nerus Terengganu 21030 Malaysia

A ship collision is one of the most hazardous incidents that may occur at sea. The circumstances that lead to these incidents vary widely, but some of the most prevalent forms of maritime collisions include side collisions, bow-on collisions, stern collisions, and allision. Any of these errors can rapidly turn catastrophic for the crew or passengers on board the implicated boats. Case studies have revealed that, contrary to common assumption, the majority of crashes are caused by the bridge team’s carelessness and inability to fulfil fundamental navigational responsibilities. In this study, a Maritime Law of Tort Collision Regulations Mobile Apps was designed to determine whether the navigator or master is negligent or not by examining the navigator’s or master’s actions that are either above or below the standard of care. This mobile-based solution was created using the Agile Methodology. The key rationale for implementing agile is that the main characteristics of mobile applications are that user requirements change over time, are constantly altered, development time is short, and the emphasis is more on the user interface. Based on continuous client feedback, the agile process paradigm entails iteratively enhancing and deploying a software system. This app is intended to make determining a person’s negligence during navigation easier and faster, while not bypassing the judge’s decision.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A new system of singular integral equations for a curvilinear crack in bonded materials 28

A new system of singular integral equations for a curvilinea...

引用

28th Simposium Kebangsaan Sains Matematik, SKSM 2021

作者： Hamzah, K.B. Nik Long, N.M.A. Senu, N. Eshkuvatov, Z.K. Fakulti T Eknologi Kejuruteraan Mekanikal Dan Pembuatan Universiti T Eknikal Malaysia Melaka Hang T uah Jaya Durian T unggal Melaka76100 Malaysia Laboratory of Computational Sciences and Mathematical Physics Institute for Mathematical Research Universiti Putra Malaysia Serdang Selangor43400 Malaysia Mathematics Department Faculty of Science Universiti Putra Malaysia Serdang Selangor43400 Malaysia Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala T erengganu21030 Malaysia

The modified complex potentials (MCPs) functions are used to develop a new system of singular integral equations (SIEs) for a curvilinear crack in the upper part of bonded materials subjected to shear mode stress with the help of continuity conditions for resultant force and displacement functions. The unknown dislocation distribution function is mapped into a square root singularity function by using curved length coordinate method and the traction along the crack as the right hand term. The Gaussian quadrature rules were used to obtain the numerical solution for a new system of SIEs in order to compute the nondimensional stress intensity factors (SIFs) for these problems. Our results agree with those of the previous works. The findings have revealed that the nondimensional SIFs depend on the elastic constant ratio, crack geometries and the position of the cracks. © Published under licence by IOP Publishing Ltd.

关键词： Distribution functions

来源：评论

学校读者我要写书评

暂无评论

Shape Corner Detection through Enhanced Curvature Properties

Shape Corner Detection through Enhanced Curvature Properties

引用

Computing, Communication and Electronics (ETCCE), Emerging technology in

作者： Suraya Abu Bakar Muhammad Suzuri Hitam Wan Nural Jawahir Hj Wan Yussof Marufa Yeasmin Mukta Faculty of Computing Universiti Malaysia Pahang Pekan Pahang Malaysia Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Terengganu Malaysia

ISBN: (数字)9781665419628

ISBN: (纸本)9781665419635

Image corner detection is a principal task for successful pattern recognition and identification. Finding corners of a shape usually involve two steps, firstly, shape segmentation and, secondly, locating corners in its boundary. This paper presents a robust method for detecting shape corner points using enhanced curvature properties. Numerous applications like image retrieval, object recognition, and motion tracking uses these corner points, which contain essential information about their location or position in a particular shape. Six existing shape detectors and descriptors, i.e., the Harris, SUSAN, Harris-Laplace, CSS, SIFT, and global and local curvature properties (GLCP), have been compared with the proposed shape detection method yielding its performance. The binary image dataset has been utilised as a benchmark to test the experiment. The experiment exhibits a significant number of true corners of the shape and outperforms the existing methods in terms of accuracy and reliability.

关键词： Shape Tracking Pattern recognition Object recognition Reliability Task analysis Corner detection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：