This page has only limited features, please log in for full access.
This paper releases and describes the creation of the Massive Arabic Speech Corpus (MASC). This corpus is a dataset that contains 1,000 hours of speech sampled at 16~kHz and crawled from over 700 YouTube channels. MASC is multi-regional, multi-genre, and multi-dialect dataset that is intended to advance the research and development of Arabic speech technology with the special emphasis on Arabic speech recognition. In addition to MASC, a pre-trained 3-gram language model and a pre-trained automatic speech recognition model are also developed and made available for interested researches. For a better language model, a new and unified Arabic speech corpus is required, and thus, a dataset of 12~M unique Arabic words is created and released. To make practical and convenient use of MASC, the whole dataset is stratified based on dialect into clean and noisy portions. Each of the two portions is then stratified and divided into three subsets: development, test, and training sets. The best word error rate achieved by the speech recognition model is 19.8% for the clean development set and 21.8% for the clean test set.
Mohammad Al-Fetyani; Muhammad Al-Barham; Gheith Abandah; Adham Alsharkawi; Maha Dawas. Massive Arabic Speech Corpus (MASC). 2021, 1 .
AMA StyleMohammad Al-Fetyani, Muhammad Al-Barham, Gheith Abandah, Adham Alsharkawi, Maha Dawas. Massive Arabic Speech Corpus (MASC). . 2021; ():1.
Chicago/Turabian StyleMohammad Al-Fetyani; Muhammad Al-Barham; Gheith Abandah; Adham Alsharkawi; Maha Dawas. 2021. "Massive Arabic Speech Corpus (MASC)." , no. : 1.
The scope of this paper is focused on the multidimensional poverty problem in Jordan. Household expenditure and income surveys provide data that are used for identifying and measuring the poverty status of Jordanian households. However, carrying out such surveys is hard, time consuming, and expensive. Machine learning could revolutionize this process. The contribution of this work is the proposal of an original machine learning approach to assess and monitor the poverty status of Jordanian households. This approach takes into account all the household expenditure and income surveys that took place since the early beginning of the new millennium. This approach is accurate, inexpensive, and makes poverty identification cheaper and much closer to real-time. Data preprocessing and handling imbalanced data are major parts of this work. Various machine learning classification models are applied. The LightGBM algorithm has achieved the best performance with 81% F1-Score. The final machine learning classification model could transform efforts to track and target poverty across the country. This work demonstrates how powerful and versatile machine learning can be, and hence, it promotes for adoption across many domains in both the private sector and government.
Adham Alsharkawi; Mohammad Al-Fetyani; Maha Dawas; Heba Saadeh; Musa Alyaman. Poverty Classification Using Machine Learning: The Case of Jordan. Sustainability 2021, 13, 1412 .
AMA StyleAdham Alsharkawi, Mohammad Al-Fetyani, Maha Dawas, Heba Saadeh, Musa Alyaman. Poverty Classification Using Machine Learning: The Case of Jordan. Sustainability. 2021; 13 (3):1412.
Chicago/Turabian StyleAdham Alsharkawi; Mohammad Al-Fetyani; Maha Dawas; Heba Saadeh; Musa Alyaman. 2021. "Poverty Classification Using Machine Learning: The Case of Jordan." Sustainability 13, no. 3: 1412.
Nowadays, quadcopters are presented in many life applications which require the performance of automatic takeoff, trajectory tracking, and automatic landing. Thus, researchers are aiming to enhance the performance of these vehicles through low-cost sensing solutions and the design of executable and robust control techniques. Due to high nonlinearities, strong couplings and under-actuation, the control design process of a quadcopter is a rather challenging task. Therefore, the main objective of this work is demonstrated through two main aspects. The first is the design of an adaptive neuro-fuzzy inference system (ANFIS) controller to develop the attitude and altitude of a quadcopter. The second is to create a systematic framework for implementing flight controllers in embedded systems. A suitable model of the quadcopter is also developed by taking into account aerodynamics effects. To show the effectiveness of the ANFIS approach, the performance of a well-trained ANFIS controller is compared to a classical proportional-derivative (PD) controller and a properly tuned fuzzy logic controller. The controllers are compared and tested under several different flight conditions including the capability to reject external disturbances. In the first stage, performance evaluation takes place in a nonlinear simulation environment. Then, the ANFIS-based controllers alongside attitude and position estimators, and precision landing algorithms are implemented for executions in a real-time autopilot. In precision landing systems, an IR-camera is used to detect an IR-beacon on the ground for precise positioning. Several flight tests of a quadcopter are conducted for results validation. Both simulations and experiments demonstrated superior results for quadcopter stability in different flight scenarios.
Mohammad Al-Fetyani; Mohammad Hayajneh; Adham Alsharkawi. Design of an Executable ANFIS-based Control System to Improve the Attitude and Altitude Performances of a Quadcopter Drone. International Journal of Automation and Computing 2020, 18, 124 -140.
AMA StyleMohammad Al-Fetyani, Mohammad Hayajneh, Adham Alsharkawi. Design of an Executable ANFIS-based Control System to Improve the Attitude and Altitude Performances of a Quadcopter Drone. International Journal of Automation and Computing. 2020; 18 (1):124-140.
Chicago/Turabian StyleMohammad Al-Fetyani; Mohammad Hayajneh; Adham Alsharkawi. 2020. "Design of an Executable ANFIS-based Control System to Improve the Attitude and Altitude Performances of a Quadcopter Drone." International Journal of Automation and Computing 18, no. 1: 124-140.