Wei Hong Lim

Wei Hong Lim

UCSI University

H-index: 32

Asia-Malaysia

About Wei Hong Lim

Wei Hong Lim, With an exceptional h-index of 32 and a recent h-index of 26 (since 2020), a distinguished researcher at UCSI University, specializes in the field of Computational Intelligence, Machining Optimization, Smart G.

His recent articles reflect a diverse array of research interests and contributions to the field:

Simulation-Based Enhancement of SNR in Drone Communication through Uniform Linear Array Configurations

Hyperparameter Optimization of Deep Learning Model: A Case Study of COVID-19 Diagnosis

Object Detection in Autonomous Vehicles: A Performance Analysis

A Comprehensive Approach to Design and Implement an IoT-Enabled Intelligent Shopping Cart System with Obstacle-Aware Navigation and Enhanced Customer Engagement for Elevated …

Deep Learning for Breast Cancer Detection from Mammograms Images

Wrapper-Based Feature Selection Using Sperm Swarm Optimization: A Comparative Study

Enhancing Global Optimization Performance of Arithmetic Optimization Algorithm with a Modified Population Initialization Scheme

Optimization Strategies for Training Artificial Neural Network: A Case Study in Medical Classification

Wei Hong Lim Information

University

UCSI University

Position

___

Citations(all)

2625

Citations(since 2020)

2163

Cited By

932

hIndex(all)

32

hIndex(since 2020)

26

i10Index(all)

52

i10Index(since 2020)

52

Email

University Profile Page

UCSI University

Wei Hong Lim Skills & Research Interests

Computational Intelligence

Machining Optimization

Smart G

Top articles of Wei Hong Lim

Simulation-Based Enhancement of SNR in Drone Communication through Uniform Linear Array Configurations

Authors

Gershom Phiri,Mastaneh Mokayef,MHD Amen Summakieh,MKA Ahamed Khan,Sew Sun Tiang,Wei Hong Lim,Abdul Qayyum

Journal

Small

Published Date

2024

As drones navigate through shared airspace, they often encounter other drones, wireless devices, and communication systems. This coexistence creates potential sources of interference that can degrade the signal-to-noise ratio (SNR). To maintain reliable communication in drone systems, it is crucial to effectively manage and mitigate interference from other drones and wireless devices operating on the same frequency bands. By addressing these challenges, we can ensure a stable and dependable SNR for seamless communication among drones. This paper sheds light on the history of applications and challenges of utilizing flying base stations for wireless networks and analyzes different factors that affect signal-to-noise ratio (SNR) to enhance the performance of drone communication.

Hyperparameter Optimization of Deep Learning Model: A Case Study of COVID-19 Diagnosis

Authors

Félix Morales,Carlos Sauer,Hans Mersch,Diego Stalder,Miguel García Torres

Published Date

2022

Short-term electricity demand forecasting represents a fundamental tool for decision-making by entities engaged in electricity management since it allows the development of strategies to meet variations in electricity demand in short periods. The accuracy of predictive models is an important factor for energy operations and the scheduling of energy generation sources to meet the demand at each instant. Intelligent models based on Recurrent Neural Networks (RNN) require hyperparameter adjustment. These models have several hyperparameters that substantially affect their performance. Our paper implements a Long-Short Term Memory (LSTM) model and four search methods to adjust its hyperparameters. First, we select the length of historical window and the hidden state size of LSTM cells for optimization. Second, we draw comparisons between the grid search, random search, a Bayesian scheme, and a genetic algorithm. The data set used for training and validation of the model includes hourly electricity consumption and meteorological variables recorded in Paraguay from 2015 to 2021. The proposed model was evaluated through numerical experiments with classical error measures such as the root mean square error (RMSE), the correlation, the runtime, and the mean absolute percentage error (MAPE). Our comparative study shows that grid search and genetic algorithm give the optimal hyperparameters with high validation accuracy on the test dataset. However, it is important to note that grid search may require much more evaluations and computational resources.

Object Detection in Autonomous Vehicles: A Performance Analysis

Authors

Yuxiang Lim,Sew Sun Tiang,Wei Hong Lim,Chin Hong Wong,Mokayef Mastaneh,Kim Soon Chong,Bo Sun

Published Date

2023/8/22

Automotive manufacturers are investing in smart cars, driverless processes, and pre-collision technologies to deliver safe and fuel-efficient mobility solutions. This paper aims to develop an advanced object detection model which incorporate more sophisticated techniques or architectures to identify commonly found objects on roads using one-stage (Single-Shot Detector) and two-stage object detectors (Faster R-CNN). The models are trained using TensorFlow and the Open Image Dataset V7, with ResNet50 architecture as the backbone. The Faster R-CNN models outperformed the SSD models, achieving a mean average precision of 92.5% at IoU 0.50. This paper presents the theory, methodology, and performance results of the work, which focuses on five classes of objects commonly found on roads (bus, car, motorcycle, stop sign, truck). The detection model exhibited an overall good performance in terms of …

A Comprehensive Approach to Design and Implement an IoT-Enabled Intelligent Shopping Cart System with Obstacle-Aware Navigation and Enhanced Customer Engagement for Elevated …

Authors

Yao Chen,Jiacheng Du,Bo Peng,Ningfei Wang,Zehan Huang,Wei Hong Lim,Sew Sun Tiang,Mastaneh Mokayef,Chin Hong Wong

Published Date

2024

Supermarket shopping is an experience that everyone has in life. This project aims to design an intelligent and userfriendly shopping cart and interactive web page, to elevate the overall customer shopping experience. The shopping cart designed in this project integrates multiple functionalities that allow users to access information about the items within the cart via the interactive web page and exert control over the movement of the cart. While moving, the shopping cart can autonomously detect obstacles in its path and navigate around them. Simultaneously, users can check the total cost of their selected items by reviewing the cart's contents, enabling them to decide whether the cart should continue following them. The project primarily utilizes an ultrasonic module to determine the cart's location and trail a specific customer. The shopping cart employs automatic barcode scanning to identify various products, and the WiFi module facilitates communication with the server via the MQTT protocol, enabling seamless interaction. The fruition of this project serves as a tangible representation of the Internet of Things application, demonstrating how connectivity through the internet enhances people's lives with greater convenience.

Deep Learning for Breast Cancer Detection from Mammograms Images

Authors

Juen Jet Choy,Sew Sun Tiang,Wei Hong Lim,Chin Hong Wong,Mokayef Mastaneh,Li Sze Chow,Kim Soon Chong,Bo Sun

Published Date

2023/8/22

Mammograms has been widely used for early detection of breast cancer; however, radiologists are prone to error which could lead to unnecessary tests or missed treatment window. With the advancement of state-of-the-art CNN models, transfer learning has become a popular technique for CAD development. In this study, a total of six state-of-the-art models are used, namely VGG16, Inception V3, ResNet50, EfficientNet B3, EfficientNet V2M and ConvNext were used to classify mammograms from two public datasets, INbreast and CBIS-DDSM. Prior to training and validation, the datasets were preprocessed with artefact removal, median filter, CLAHE and ROI extraction. The best performance was achieved by the ConvNext model trained on INbreast dataset, with an accuracy, sensitivity, specificity, precision, f1-score and AUC of 0.81, 0.8, 0.82, 0.67, 0.73 and 0.88, respectively. The results indicate that the model has …

Wrapper-Based Feature Selection Using Sperm Swarm Optimization: A Comparative Study

Authors

Wy-Liang Cheng,Li Pan,Nor Ashidi Mat Isa,Meng Choung Chiong,Chin Hong Wong,MKA Ahmed Khan,Sew Sun Tiang,Wei Hong Lim

Published Date

2023/8/22

Feature selection is a vital technique that enhances the quality of input datasets by reducing redundancy, noise, and inaccuracies without compromising classifier accuracy. The integration of metaheuristic search algorithms (MSAs) into feature selection enables the discovery of relevant features, thereby simplifying dataset representation. However, despite the proliferation of MSAs based on diverse sources of inspiration in recent years, their application to solve real-world optimization problems, such as feature selection, remains largely unexplored. This paper introduces a novel MSA called sperm swarm optimization (SSO), inspired by the mobility behavior of sperms during the fertilization process, to develop a robust wrapper-based feature selection method. To evaluate the effectiveness of SSO in solving feature selection problems, extensive simulations are conducted using ten datasets from the UCI Machine …

Enhancing Global Optimization Performance of Arithmetic Optimization Algorithm with a Modified Population Initialization Scheme

Authors

Tin Chang Ting,Hameedur Rahman,Meng Choung Chiong,Mohamed Khan Afthab Ahamed Khan,Cik Suhana Hassan,Farah Adilah Jamaludin,Sew Sun Tiang,Wei Hong Lim

Published Date

2024

Arithmetic Optimization Algorithm (AOA) is widely used to solve global optimization problems. However, it often faces premature convergence challenges in complex optimization scenarios. A key factor affecting AOA's performance is the solution quality of the initial population. The conventional initialization scheme, despite its prevalence, lacks reliability in ensuring high-quality solutions due to inherent stochastic processes. To address this issue, we propose a modified initialization scheme that improves initial population quality by integrating chaotic maps and oppositional-based learning. Through extensive simulation studies, we demonstrate that the enhanced AOA, equipped with this new initialization scheme, exhibits superior performance in solving a range of benchmark functions with improved accuracy.

Optimization Strategies for Training Artificial Neural Network: A Case Study in Medical Classification

Authors

Koon Meng Ang,Nor Ashidi Mat Isa,Ching Hong Wong,Elango Natarajan,Mahmud Iwan Solihin,Meng Choung Chiong,Sew Sun Tiang,Wei Hong Lim

Published Date

2023/8/22

Backpropagation (BP) is a widely embraced method for training artificial neural networks (ANNs) in classification and regression tasks. However, its efficacy diminishes when confronted with complex problems due to susceptibility to local optima, sensitivity to initial parameters, and slow convergence. Arithmetic optimization algorithm (AOA) has emerged as a promising solution for achieving global optimization in ANNs. Nonetheless, similar to other metaheuristic search algorithms (MSAs), AOA grapples with inconsistent solution quality resulting from random initialization, impeding its effectiveness in intricate optimization tasks. This paper introduces a modified initialization scheme for AOA that incorporates chaotic maps and oppositional-based learning (OL) to yield a superior initial population, leading to a new AOA variant known as AOA-COIS. Serving as a training algorithm for ANNs, AOA-COIS optimizes the …

Deep Learning-Based Silicon Wafer Defect Classification: A Performance Comparison of Pretrained Networks

Authors

Koon Hian Ang,Koon Meng Ang,Chun Kit Ang,Kim Soon Chong,Abhishek Sharma,Tiong Hoo Lim,Sew Sun Tiang,Wei Hong Lim

Published Date

2023/8/22

Semiconductor processing technology heavily relies on defect inspection to enhance yield by identifying surface defects in the manufacturing process. However, manual inspection is prone to errors and can be a tedious process, which necessitates automated methods to replace human eyes. Deep learning techniques, such as convolutional neural networks (CNNs), are promising for automated wafer defect classification. In this study, a comparative analysis is performed on different pretrained deep learning networks to identify the most accurate and efficient network architecture for wafer defect classification. Five pretrained deep learning models, including GoogleNet, MobileNet-v2, ResNet-18, ResNet-50, and ShuffleNet, are trained and evaluated. Simulation results show that MobileNet-v2 outperforms four other pretrained networks in terms of accuracy, recall, precision, and F1-score values. The findings …

Deep learning applied solid waste recognition system targeting sustainable development goal

Authors

Kok Jin Lee,Meng-Choung Chiong,Cik Suhana Hassan,Elango Natarajan,Mahmud Iwan Solihin,Wei Hong Lim

Published Date

2024/1/1

In Malaysia, it was estimated that approximately 250,000 tons of municipal solid garbage were produced every day because of our daily activities. Categorizing these municipal solid trashes efficiently into respective types for recycling purposes has been imminent to minimize their adverse effects on our environment. This chapter presented a solid waste sorting system to distinguish three different types of solid waste by using a deep learning method. The YOLOv3 was proposed as a real-time object identification module to differentiate solid trash. YOLOv3 and YOLOv3-tiny were trained to recognize plastic bottles, paper, and metal with 150 distinct photos. When compared to the YOLOv3-tiny model, the YOLOv3 model produced a notably higher mean average precision (mAP). Due to the greater numbers of the convolutional layer in the latter, the mAP for YOLOv3 was averaging 81.93%, whereas the mAP for …

Enhancing Precision Object Detection and Identification for Autonomous Vehicles through YOLOv5 Refinement with YOLO-ALPHA

Authors

Guandong Li,Yanzhe Xie,Yuhao Lu,Zongyan Wen,Jingzhen Fan,Yuankui Huang,Qinghong Ma,Wei Hong Lim,Chin Hong Wong

Published Date

2024

Advancing swiftly in contemporary society, the rapid growth of autonomous driving technology suggests its potential adoption across continents. The realization of fully autonomous driving relies on proficiently detecting, classifying, and tracking road objects such as pedestrians and vehicles. This research employs the YOLOv5 neural network, enhancing it with YOLO-ALPHA. Modifications, encompassing freeze and attention mechanisms, serve to refine accuracy and expedite training. Furthermore, adjustments to the activation function aim to stabilize precision and recall. The integration of an FCN based on semantic segmentation theory contributes to improved accuracy in detecting road conditions during autonomous driving. Consequently, this enables the successful and highly accurate functionality of automatic identification.

A Modified African Vultures Optimization Algorithm for Enhanced Feature Selection

Authors

Wy-Liang Cheng,Li Pan,Abhishek Sharma,Tiong Hoo Lim,Chun Kit Ang,Kim Soon Chong,Sew Sun Tiang,Wei Hong Lim

Published Date

2023/8/22

Feature selection is a reliable technique for reducing redundant, noisy, or inaccurate features in raw input datasets without compromising classifier accuracy. Integrating metaheuristic search algorithms (MSAs) into feature selection enables the discovery of pertinent features, simplifying dataset representation. However, traditional MSAs, such as the African Vultures Optimization Algorithm (AVOA) encounter limitations with their initialization scheme, leading to a higher likelihood of local optima trapping when handling datasets with numerous features. To address this issue, a modified MSA called Multi-Chaotic African Vultures Optimization (MCAVOA) is proposed for more effective feature selection. Specifically, multiple chaotic maps are employed to generate the initial population of MCAVOA, enhancing its robustness against premature convergence in complex optimization problems like feature selection. The …

Design and Performance Study of LCC-LCC and LCC-S Compensation Network for Wireless Charging of EV Battery

Authors

C. Balaji,R. Venugopal,Jayachitra Selvaraj,G. Balasundaram,A. Dominic Savio,Wei Hong Lim

Published Date

2024/4/25

This work aims to study the compensation techniques used in wireless power transfer for Electric Vehicle (EV) charging application. Though there are several topologies for wireless power conversion Dual Active Bridge (DAB) configuration, better suits with wireless power transfer for its bidirectionality, high power density, ease of implementation and so on. Compensation network enhances the performance of the DAB in providing the constant current (CC) or constant voltage (CV) according to the battery charging status. This paper details the study on the performance of LCC-LCC topology and LCC- S topologies. The design values of magnetic elements of the compensation network are calculated analytically. The LCC-LCC and LCC- S compensations implementation in DAB converter is simulated in MATLAB/Simulink. The results were obtained and compared with the symmetrical LCC and LCC- S compensation …

Predictive Analytics and Machine Learning in Direct Marketing for Anticipating Bank Term Deposit Subscriptions

Authors

Ahmed Mohamed Zaki,Nima Khodadadi,Wei Hong Lim,SK Towfek

Journal

American Journal of Business and Operations Research

Published Date

2024

Direct marketing strategies in the banking sector have undergone evolution with the integration of predictive analytics and machine learning techniques. The focus of this study is on the utilization of these technologies to foresee bank term deposit subscriptions. The methodology encompasses data exploration, visualization, and the implementation of machine learning models. Datasets from Kaggle are employed, relationships within the data are explored through crosstabulations and heat maps, and feature engineering and preprocessing techniques are applied. The study individually implements models such as SGD Classifier, k-nearest neighbor Classifier, and Random Forest Classifier. The results indicate that the best performance among the evaluated models was exhibited by the Random Forest Classifier, achieving an accuracy of 87.5%, a negative predictive value (NPV) of 92.9972%, and a positive predictive value (PPV) of 87.8307%. These findings provide valuable insights for banks seeking to optimize their marketing strategies within the dynamic landscape of the financial industry.

Deep Learning in Manufacturing: A Focus on Welding Defect Classification with CNNs

Authors

Tin Chang Ting,Hameedur Rahman,Tiong Hoo Lim,Chin Hong Wong,Chun Kit Ang,Mohamed Khan Afthab,Ahamed Khan,Sew Sun Tiang,Wei Hong Lim

Published Date

2024

Welding is integral to modern manufacturing, yet the complex process often leads to defects, impacting the quality of the final product. Recent advances in deep learning, particularly Convolutional Neural Networks (CNNs), have shown remarkable results in applications like defect recognition. This study evaluated AlexNet, ResNet-18, ResNet-50, ResNet-101, MobileNet-v2, ShuffleNet, and SqueezeNet for their effectiveness in identifying welding defects, using accuracy, precision, sensitivity, specificity, and F-score as metrics. The dataset covered defects like cracks, lack of penetration, porosity, and a no-defect class. Our analysis shows that most of these architectures deliver promising results in accuracy, sensitivity, specificity, precision, and F1-score, highlighting their potential in defect recognition.

Character Recognition Based on k-Nearest Neighbor, Simple Logistic Regression, and Random Forest

Authors

Zheyi Zheng,Yiwei Zhong,Zhenkai Xiao,Wei Hong Lim,Sew Sun Tiang,Mastaneh Mokayef,Chin Hong Wong

Published Date

2023/8/22

Characters recognition has gained significant attention in recent years within the field of artificial intelligence and computer vision as robots increasingly engage in activities that involve collecting and processing texture information. This paper presents a performance comparison among three algorithms: k-nearest neighbor, simple logistic regression, and random forest, for recognizing the alphabet and numeric characters. The proposed method involves obtaining random eigenvalues through random sampling of the training sets. Subsequently, a decision tree is constructed based on the obtained eigenvalues, and multiple decision trees are combined to yield the final judgment result, thus mitigating the risk of overfitting. The implementation of these algorithms is feasible using Python and existing frameworks. The experimental results demonstrate that the random forest algorithm model achieved accurate …

A Real-time Deterministic Peak Hopping Maximum Power Point Tracking Algorithm for Complex Partial Shading Condition

Authors

Jia Shun Koh,Rodney H. G. Tan,Wei Hong Lim,Nadia M. L. Tan

Journal

IEEE Access

Published Date

2024/3/28

Conventional perturb and observe (P&O) algorithm fails to track global maximum power point (GMPP) under complex partial shading conditions (PSC) in photovoltaic (PV) system. While many of the latest maximum power point tracking (MPPT) algorithms are designed to handle simpler PSCs with fewer peaks, their capability to handle highly complex PSCs remains uncertain. This study presented more practical, challenging, and complex PSCs that have over five peaks and extremely close peak values. A new deterministic peak hopping (PH)-based MPPT algorithm with simple mechanisms is proposed to address these complex PSCs. An agent is utilized to scan and hop between the lower and higher duty cycle regions of P-V curve with optimum step size, thereby effectively narrowing down the tracking region, moving towards the GMPP. Additionally, the proposed algorithm utilizes an adjustable sampling time …

Overview of swarm intelligence techniques for harvesting solar energy

Authors

Wei Hong Lim,Abhishek Sharma

Published Date

2023/6/19

Photovoltaic systems are becoming increasingly popular in the energy production business. In spite of the advantages, photovoltaic (PV) systems have four major downsides: limited conversion precision, interrupted power supply, elevated manufacturing costs, and discontinuities of PV system output power. Numerous optimisation and control strategies have been suggested to address these issues. Numerous authors, however, trusted on traditional techniques that were based on instinctive, numerical, or analytical procedures. More effective optimisation approaches would improve the effectiveness of PV systems while lowering the price of energy produced. In this chapter, we will look at how Swarm Intelligence (SI) techniques can benefit PV systems. Specific attention is dedicated to two key areas: (1) active response and power quality enrichment of AC microgrids and (2) global maximum power point tracking.

Table Tennis Tournament Scores and Statistics Web Application

Authors

Khaled Belal,Mokayef Mastaneh,Wong Chin Hong,Tiang Sew Sun,Lim Wei Hong,Summakieh Mhd Amen,Mokayef Miad

Journal

人工生命とロボットに関する国際会議予稿集

Published Date

2023/2/9

Table tennis is a popular sport that involves two or four players to hit a lightweight ball back and forth across a tennis table using small rackets. The scores are generated based on the tournament results. These scores were not digitized in the early days, therefore, the match referees had to record them manually while most of the competitors provided only basic information and real-time scores online. Over the years of technological advancements, the modern development of software applications has helped users perform useful tasks and retrieve useful data based on the requests. The objective of this project is to develop a functional web application that will retrieve or store table tennis tournament statistical data and visualize them using tables, bar charts, pie charts, histograms as a medium of demonstration for the user. Moreover, the application will perform specific analysis on the scores and display insightful data about the tournament for league structures investigation. The developed system will include a database to store and retrieve data for display on the user interface. The development of the project is fully stacked (front-end and back-end), so it is built with the appropriate web technologies to function in the background (PHP, MySQL, Apache) while displaying results (HTML, CSS, JavaScript) on the page for the user. The project is managed using effective project management methods to plan, design, implement, develop, and maintain the application.

Training Feedforward Neural Networks Using Arithmetic Optimization Algorithm for Medical Classification

Authors

Koon Meng Ang,Wei Hong Lim,Sew Sun Tiang,Hameedur Rahman,Chun Kit Ang,Elango Natarajan,Mohamed Khan Afthab Ahamed Khan,Li Pan

Published Date

2023/3/22

Feedfoward neural network (FNN) is popular machine learning technique widely implemented for image classification, data clustering, object recognition, etc. due to its outstanding capability in processing data. Backpropagation is commonly employed as a conventional method to adjust the weights and biases of FNNs. As a gradient-based algorithm, backpropagation tends to have slow convergence rate and highly dependent on the initial solution generated. Arithmetic optimization algorithm (AOA) emerges as a promising metaheuristic search algorithm (MSA) to replace conventional method in training FNNs due to its outstanding global search ability. In this paper, AOA is designed to optimize the weights, biases and selection of activation functions of FNN for image classification. Medical datasets are extracted from UCI Machine Learning Repository to assess the capability of AOA in training FNN. Comparative …

See List of Professors in Wei Hong Lim University(UCSI University)

Wei Hong Lim FAQs

What is Wei Hong Lim's h-index at UCSI University?

The h-index of Wei Hong Lim has been 26 since 2020 and 32 in total.

What are Wei Hong Lim's top articles?

The articles with the titles of

Simulation-Based Enhancement of SNR in Drone Communication through Uniform Linear Array Configurations

Hyperparameter Optimization of Deep Learning Model: A Case Study of COVID-19 Diagnosis

Object Detection in Autonomous Vehicles: A Performance Analysis

A Comprehensive Approach to Design and Implement an IoT-Enabled Intelligent Shopping Cart System with Obstacle-Aware Navigation and Enhanced Customer Engagement for Elevated …

Deep Learning for Breast Cancer Detection from Mammograms Images

Wrapper-Based Feature Selection Using Sperm Swarm Optimization: A Comparative Study

Enhancing Global Optimization Performance of Arithmetic Optimization Algorithm with a Modified Population Initialization Scheme

Optimization Strategies for Training Artificial Neural Network: A Case Study in Medical Classification

...

are the top articles of Wei Hong Lim at UCSI University.

What are Wei Hong Lim's research interests?

The research interests of Wei Hong Lim are: Computational Intelligence, Machining Optimization, Smart G

What is Wei Hong Lim's total number of citations?

Wei Hong Lim has 2,625 citations in total.

What are the co-authors of Wei Hong Lim?

The co-authors of Wei Hong Lim are Abdelhameed Ibrahim, Nor Ashidi Mat Isa, Dr. S. Parasuraman, Abhishek Sharma, Ph.D., Mahmud Iwan Solihin, ss tiang.

    Co-Authors

    H-index: 61
    Abdelhameed Ibrahim

    Abdelhameed Ibrahim

    Mansoura University

    H-index: 49
    Nor Ashidi Mat Isa

    Nor Ashidi Mat Isa

    Universiti Sains Malaysia

    H-index: 20
    Dr. S. Parasuraman

    Dr. S. Parasuraman

    Monash University

    H-index: 17
    Abhishek Sharma, Ph.D.

    Abhishek Sharma, Ph.D.

    University of Petroleum and Energy Studies

    H-index: 16
    Mahmud Iwan Solihin

    Mahmud Iwan Solihin

    UCSI University

    H-index: 13
    ss tiang

    ss tiang

    UCSI University

    academic-engine

    Useful Links