Optimization of Neural Networks Based on Modified Multi-Sonar Bat Units Algorithm

Tawfeeq, Mohammed Ali

doi:10.15676/ijeei.2020.12.1.9

Cited by 3 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The formula of the associated values used in [27] is modified to accommodate the requirement of this work. The extracted associative value Avi for i = 1, 2, …, N, is equal to the square of the product of (Ei and dni) normalized by the product of the sum of the squared residual energy vector E and the sum of the squared distances vector dn, that is;…”

Section: Extracting Best Associative Valuesmentioning

confidence: 99%

Prolonging WSNs lifetime in IoT applications based on consistent algorithm

Tawfeeq

Abdullah

2021

TELKOMNIKA

Self Cite

View full text Add to dashboard Cite

The rapid expansion in the use of IoT imposes the importance of developing its infrastructure. One of the most important components in IoT infrastructures is the wireless sensor networks. The development of these networks largely depends on how to extend their life. As one of the effective options adopted in this field is the use of cluster heads (CHs). This paper introduces an algorithm that efficiently determine the CHs by iteratively extracting an associative value for each node depending on two factors; node's residual energy, and geometrical distances between nodes and base station. In light of the extracted values, the nodes with the best associative values are elected as CHs based on adjustable threshold determined according to the network usage requirements. The algorithm has proven a significant increase in the lifetime of the network, as well as, it has proven its ability to maintain a high level of energy for long period of time. The proposed algorithm outperformed similar protocols like low energy adaptive clustering hierarchy (LEACH) and region based low energy adaptive clustering hierarchy (R-LEACH) by prolonging the network lifetime and increasing network stability, as well as enhances the throughput significantly.

show abstract

Section: Extracting Best Associative Valuesmentioning

confidence: 99%

Prolonging WSNs lifetime in IoT applications based on consistent algorithm

Tawfeeq

Abdullah

2021

TELKOMNIKA

Self Cite

View full text Add to dashboard Cite

show abstract

Syllable-Based Indonesian Automatic Speech Recognition

Galatang¹,

Suyanto²

2020

ijeei

View full text Add to dashboard Cite

The syllable-based automatic speech recognition (ASR) systems commonly perform better than the phoneme-based ones. This paper focuses on developing an Indonesian monosyllable-based ASR (MSASR) system using an ASR engine called SPRAAK and comparing it to a phoneme-based one. The Mozilla DeepSpeech-based end-to-end ASR (MDSE2EASR), one of the state-of-the-art models based on character (similar to the phoneme-based model), is also investigated to confirm the result. Besides, a novel Kaituoxu SpeechTransformer (KST) E2EASR is also examined. Testing on the Indonesian speech corpus of 5,439 words shows that the proposed MSASR produces much higher word accuracy (76.57%) than the monophone-based one (63.36%). Its performance is comparable to the character-based MDS-E2EASR, which produces 76.90%, and the character-based KST-E2EASR (78.00%). In the future, this monosyllable-based ASR is possible to be improved to the bisyllable-based one to give higher word accuracy. Nevertheless, extensive bisyllable acoustic models must be handled using an advanced method.

show abstract