3 research outputs found
A Deep Belief Network Classification Approach for Automatic Diacritization of Arabic Text
No full textDeep learning has emerged as a new area of machine learning research. It is an approach that can learn features and hierarchical representation purely from data and has been successfully applied to several fields such as images, sounds, text and motion. The techniques developed from deep learning research have already been impacting the research on Natural Language Processing (NLP). Arabic diacritics are vital components of Arabic text that remove ambiguity from words and reinforce the meaning of the text. In this paper, a Deep Belief Network (DBN) is used as a diacritizer for Arabic text. DBN is an algorithm among deep learning that has recently proved to be very effective for a variety of machine learning problems. We evaluate the use of DBNs as classifiers in automatic Arabic text diacritization. The DBN was trained to individually classify each input letter with the corresponding diacritized version. Experiments were conducted using two benchmark datasets, the LDC ATB3 and Tashkeela. Our best settings achieve a DER and WER of 2.21% and 6.73%, receptively, on the ATB3 benchmark with an improvement of 26% over the best published results. On the Tashkeela benchmark, our system continues to achieve high accuracy with a DER of 1.79% and 14% improvement
Expanding the activated sludge model no.1 to describe filamentous bulking : The filamentous model
No full textFunding Information: This work was financially supported by the Education, Audiovisual and Culture Executive Agency of the European Commission (Erasmus Mundus Specific Grant Agreement nr 2017-1957/001-001-EMJMD) and the Dutch Ministry of Foreign Affairs (DUPC2/SCARCE project). Lobna Amin gratefully acknowledges the support given by Dr. Naser Almanaseer and Eng. Mohammad Jadallah of Al Balqa Applied University and Eng. Yazan Ziadat of the Miyahuna company for the information related to the Fuhais WWTP. Funding Information: This work was financially supported by the Education, Audiovisual and Culture Executive Agency of the European Commission (Erasmus Mundus Specific Grant Agreement nr 2017-1957/001-001-EMJMD ) and the Dutch Ministry of Foreign Affairs (DUPC2/SCARCE project). Lobna Amin gratefully acknowledges the support given by Dr. Naser Almanaseer and Eng. Mohammad Jadallah of Al Balqa Applied University and Eng. Yazan Ziadat of the Miyahuna company for the information related to the Fuhais WWTP. Publisher Copyright: © 2022 The Author(s)Several wastewater treatment plants (WWTPs) worldwide have documented the occurrence of filamentous bulking in full-scale systems despite the efforts made for filamentous bulking control. The Activated Sludge Models (ASM) can neither describe nor predict filamentous bulking at WWTPs. This research aims to expand the ASM No. 1 to be able to describe filamentous bulking sludge and to model the effects of incorporating an aerobic selector on filamentous bulking. Four theories (hydrolysis of slowly biodegradable organics theory, kinetic selection theory, substrate diffusion limitation theory, and filamentous backbone theory) were combined to expand the ASM1. The results showed that this combination was successful to distinguish between the substrate uptake by filamentous organisms and by floc forming organisms. Moreover, the concentrations of filamentous and floc forming organisms inside the reactor were converted to a “filamentous score” that predicted the outcome of filamentous bulking. Filamentous bulking would occur if the filamentous score was higher than 3, in a range of 1–6. As a case study, the Fuhais WWTP in Jordan was modelled using the expanded-ASM1 “filamentous model” and the filamentous score of 4.2 was in accordance to the visually observed bulking. However, when an aerobic selector with 3 compartments would be added before the aeration tank, the filamentous score decreased to 1.5. The selector changed the hydraulic behaviour from a completely mixed mode to a plug flow mode, which created a substrate gradient in the model, making the floc forming organisms to outcompete the filamentous organisms. Additional experimental results are required to further calibrate and validate the filamentous model.Peer reviewe
Accelerated Arithmetic Optimization Algorithm by Cuckoo Search for Solving Engineering Design Problems
No full textSeveral metaheuristic algorithms have been implemented to solve global optimization issues. Nevertheless, these approaches require more enhancement to strike a suitable harmony between exploration and exploitation. Consequently, this paper proposes improving the arithmetic optimization algorithm (AOA) to solve engineering optimization issues based on the cuckoo search algorithm called AOACS. The developed approach uses cuckoo search algorithm operators to improve the ability of the exploitation operations of AOA. AOACS enhances the convergence ratio of the presented technique to find the optimum solution. The performance of the AOACS is examined using 23 benchmark functions and CEC-2019 functions to show the ability of the proposed work to solve different numerical optimization problems. The proposed AOACS is evaluated using four engineering design problems: the welded beam, the three-bar truss, the stepped cantilever beam, and the speed reducer design. Finally, the results of the proposed approach are compared with state-of-the-art approaches to prove the performance of the proposed AOACS approach. The results illustrated an outperformance of AOACS compared to other methods of performance measurement
