Search Results - (( model validation case algorithm ) OR ( gender classification system algorithm ))

Gender classification based on asian faces using deep learning by Janahiraman T.V., Subramaniam P.

“…Face recognition; Human computer interaction; Image classification; Learning algorithms; Natural language processing systems; Neural networks; Speech recognition; Systems engineering; Convolutional neural network; Gender classification; Learning architectures; Learning frameworks; NAtural language processing; Recognition accuracy; Recognition process; TensorFlow; Deep learning…”

Gender identification using support vector machines by Nur Ayuni Binti Jalaluddin

Multilanguage speech-based gender classification using time-frequency features and SVM classifier by Wani, Taiba, Gunawan, Teddy Surya, Mansor, Hasmah, Ahmad Qadri, Syed Asif, Sophian, Ali, Ambikairajah, Eliathamby, Ihsanto, Eko

Get full text
Get full text
Get full text
Get full text
Get full text

Embedded fuzzy classifier for detection and classification of preseizure state using real EEG data by Qidwai, U., Malik, A.S., Shakir, M.

“…Therefore, the work presented here includes embedded hardware system that works with classification algorithm on real EEG signals, in a ubiquitous setting. …”
Get full text
Get full text

Human body radiation wave analysis and classification for gender and body segments recognition / Siti Zura A. Jalil @ Zainuddin by A. Jalil @ Zainuddin, Siti Zura

“…Multivariate analysis of variance (MANOVA) is employed to compare the differences of frequency radiation characteristics between genders. Then, the classification algorithm of A:-nearest neighbor (KNN) is employed to discriminate between genders, and between body segments. …”
Get full text
Get full text

Embedded Fuzzy Classifier for Detection and Classification of Preseizure state using Real EEG data by Qidwai, Uvais, Malik, Aamir Saeed, Shakir, Mohamed

“…Therefore, the work presented here includes embedded hardware system that works with classification algorithm on real EEG signals, in a ubiquitous setting. …”
Get full text
Get full text

Optimization of assembly line balancing with energy efficiency by using tiki-taka algorithm by Ariff Nijay, Ramli

“…Lastly, a study of the industrial case was performed as a validation of the developed model and algorithm. …”
Get full text
Get full text

Embedded Fuzzy Classifier for Detection and Classification of Preseizure State Using Real EEG Data by Qidwai, Uvais, Malik, Aamir Saeed, Shakir, Mohamed

“…Therefore, the work presented here includes embedded hardware system that works with classification algorithm on real EEG signals, in a ubiquitous setting. …”
Get full text
Get full text
Get full text

Development of gender and race recognition system using speech and recognition by using frequency spectrum by Ng Siew Fong

“…In this thesis, the development of an algorithm and system that is able to recognize gender and races by using the speech frequency spectrum is presented. …”
Get full text

Development of Malay word pronunciation application using vowel recognition by Mohd Yusof, Shahrul Azmi

“…In Malaysia, many researchers focus on developing speaker independent systems for training or articulation therapy or to assist language learners to learn about Malay Language or Bahasa Malaysia.Accuracy, noise robustness and processing time are concerns when developing speech therapy systems.In this study, a Malay word pronunciation test application was developed using the first 3 format and fundamental frequencies in an effort to improve pronunciation in Malay.This application was developed using Matlab and uses a vowel recognition algorithm classified using MLP classification technique.The application was developed and tested on UUM undergraduate students.For vowel classification, when fundamental frequency was added, 3-format feature vowel classification rate increased by 1.55% for male gender and 1.48% for female. …”
Get full text
Get full text
Get full text

Facial geometry and speech analysis for depression detection by Pampouchidou, A., Simantiraki, O., Vazakopoulou, C.-M., Chatzaki, C., Pediaditis, M., Maridaki, A., Marias, K., Simos, P., Yang, F., Meriaudeau, F., Tsiknakis, M.

“…The proposed system has been tested both in gender independent and gender based modes, and with different fusion methods. …”
Get full text
Get full text

Customer analysis with machine vision by Tiong, Wei Jie

“…When the customer passes through a counting line drawn by the system, customer counting occurs, and the system will crop their faces for facial recognition and gender classification. …”
Get full text
Get full text

Modeling of cardiovascular diseases (CVDs) and development of predictive heart risk score by Mirza Rizwan, Sajid

“…However, the conversion of a complex form of ML algorithms into a simple statistical model is the prime concern. …”
Get full text
Get full text

Early autism spectrum disorder detection using machine learning / Muhammad Shahmi Shahron Nizan by Shahron Nizan, Muhammad Shahmi

“…The project follows a modified waterfall approach, focusing on creating a user-friendly interface and integrating the Random Forest Classification Algorithm for accurate detection. The results show the algorithm's impressive performance with an 86% precision in predicting ASD traits. …”
Get full text
Get full text

Hybrid Artificial Bees Colony algorithms for optimizing carbon nanotubes characteristics by Mohammad Jarrah, Mu'ath Ibrahim

“…Chemical Vapor Deposition (CVD) is the most efficient method for CNTs production.However,using CVD method encounters crucial issues such as customization,time and cost.Therefore,Response Surface Methodology (RSM) is proposed for modeling and the ABC-βHC is proposed for optimization purpose to address such issues.The selected CNTs characteristics are CNTs yield and quality represented by the ratio of the relative intensity of the D and G-bands (ID/IG).Six case studies are generated from collected dataset including four cases of CNTs yield and one case of ID/IG as single objective optimization problems,while the sixth case represents multi-objective problem.The input parameters of each case are a subset from the set of input parameters including reaction temperature,duration,carbon dioxide flow rate,methane partial pressure,catalyst loading,polymer weight and catalyst weight.The models for the first three case studies were mentioned in the original work.RSM is proposed to develop polynomial models for the output responses in the other three cases and to identi significant process parameters and interactions that could affect the CNTs output responses.The developed models are validated using t-test,correlation and pattern matching.The predictive results have a good agreement with the actual experimental data.The models are used as objective functions in optimization techniques.For multi-objective optimization,this study proposes Desirability Function Approach (DFA) to be integrated with other proposed algorithms to form hybrid techniques namely RSM-DFA,ABC-DFA and ABC-βHC-DFA.The proposed algorithms and other selected well-known algorithms are evaluated and compared on their CNTs yield and quality.The optimization results reveal that ABC-βHC and ABC-βHC-DFA obtained significant results in terms of success rate,required time,iterations,and function evaluations number compared to other well-known algorithms.Significantly,the optimization results from this study are better than the results from the original work of the collected dataset.…”
Get full text
Get full text
Get full text

Development of bi-objective optimization model for supply chain network design using data envelopment analysis by Rahimi, Iman

“…An example from the real case was considered to verify and validate the proposed model. …”
Get full text
Get full text

Speaker identification through feature fusion based deep learning / Rashid Jahangir by Rashid , Jahangir

“…In addition, DNN obtained better classification results compared with the other five machine learning algorithms that were recently utilised in speaker recognition. …”
Get full text
Get full text

Development of classification model between clean water and polluted water based on capacitance properties using Levenberg Marquardt (LM) algorithm of artificial neural network / M... by Mohamad Salehuddin, Mohamad Firdaus

“…These measurement inputs were then going through the process of classification in ANN to generate the optimized models by using LM algorithm. The model is being trained, tested, and validated to differentiate between clean water and polluted water. …”
Get full text
Get full text

A self-adaptive agent-based simulation modelling framework for dynamic processes by Ling, Loo Yim, Dr.

“…Key parameters for dynamic processes of different domains were formulated for the construction of self-adaptive simulation algorithms and modelling. Self-adaptive simulation algorithms were formulated to enable the model’s adaptive capability. …”

A FUZZY LOGIC ALGORITHM FOR HEART RATE MONITORING by NIK ABDULLAH, NIK MUHAMAD LUKMAN NULHAKIM

Get full text
Get full text