Search Results - (( model evaluation case algorithm ) OR ( user identification learning algorithm ))*

Zero distortion-based steganography for handwritten signature by Iranmanesh, Vahab

“…In this thesis, the human handwritten signature is introduced as a novel cover media (c) in conjunction with a steganography algorithm since there is a level of variability (i.e intra-user variability) within handwritten signature samples of an individual. …”
Get full text
Get full text
Get full text

Keylogger detection analysis using machine learning algorithm / Muhammad Faiz Hazim Abdul Rahman by Abdul Rahman, Muhammad Faiz Hazim

“…Early identification of a keylogger malware attack could prevent hackers from accessing personal user data and reduce the likelihood of infiltration, which could reveal account information, credit cards, usernames, passwords, and other data. …”
Get full text
Get full text

Effects of user selected conditions on modeling of dynamic systems using adaptive fuzzy model by Yaacob, Mohd. Shafiek, Jamaluddin, Hishamuddin

“…The implementation and the computational aspects of the training algorithm are also highlighted. Three examples of discrete-time nonlinear systems are used in the simulation study to show the effects of user selected conditions on the identification process. …”
Get full text
Get full text
Get full text

Deep Learning Based Face Attributes Recognition by Saidi, Mohamad Hazim

“…The automated face identification application is helpful in assisting forensic to survey an area with the implementation of Machine Learning (ML). …”
Get full text
Get full text

Investigating optimal smartphone placement for identifying stairs movement using machine learning by Muhammad Ruhul Amin, Shourov, Husman, Muhammad Afif, Toha, Siti Fauziah, Jasni, Farahiyah

“…Accurate identification of human activities is crucial in conveying essential gait information to users for the recognition of human movement activities. …”
Get full text
Get full text
Get full text
Get full text

Age detection from face using Convolutional Neural Network (CNN) / Hanin Hanisah Usok @ Yusoff by Usok @ Yusoff, Hanin Hanisah

“…The results show a high 85% accuracy rate in determining the age of individuals. A user-friendly desktop system is created for input of facial photos and receiving immediate age estimation results, illustrating machine learning's assure in age identification. …”
Get full text
Get full text

Effective query structuring with ranking using named entity categories for XML retrieval by Roko, Abubakar

“…Furthermore, it employs Predicates Identification Algorithm (PIA) and Entity Identification Algorithm (EIA) to identify user search intention. …”
Get full text
Get full text
Get full text

Dyslexia handwriting detection using Convolutional Neural Network (CNN) algorithm / Sofea Najihah Mohd Zaki by Mohd Zaki, Sofea Najihah

“…Convolutional Neural Network (CNN) algorithm was chosen as one of the possible solutions after a thorough analysis of many algorithms for dyslexic handwriting identification. …”
Get full text
Get full text

A Machine Learning Classification Application to Identify Inefficient Novice Programmers by Khan I., Al-Mamari A., Al-Abdulsalam B., Al-Abdulsalam F., Al-Khansuri M., Iqbal Malik S., Ahmad A.R.

New hybrid deep learning method to recognize human action from video by Md Shofiqul, Islam, Sunjida, Sultana, Md Jabbarul, Islam

“…This video content must be examined in order to classify it for different purposes for users. Several machine learning approaches for video classification have been developed to save users time and energy. …”
Get full text
Get full text
Get full text

Investigation of An Early Prediction System of Cardiac Arrest Using Machine Learning Techniques by Muhammad Afnan, Mohammad Nasir

“…An effective machine learning approach created from a separate examination of many machine learning algorithms in WEKA should be applied for the correct identification of heart disease. …”
Get full text
Get full text

A resource-aware content adaptation approach for e-learning environment / Mohd Faisal Ibrahim by Ibrahim, Mohd Faisal

“…Besides reducing the processing overhead it also achieves better results in terms of accuracy compared to the user agent approach. Second, network aware applications architecture for E-Learning system was also proposed to dynamically adjust the users' demand based on network resources. …”
Get full text
Get full text

Penentuan Kerelevanan Dokumen Menggunakan Rangkaian Rambatan Balik by Fadhilah, Mat Yamin

“…Backpropagation learning algorithm has been used as a basis for learning in this study. …”
Get full text
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

Faulty classification system for VTOL UAV acoustic signal using machine learning by Makhtar, Siti Noormiza, Mohd Sani, Fareisya Zulaikha, Nor, Elya Mohd, Kamarudin, Nur Diyana, Md Ali, Syaril Azrad

“…Users can select their preferred features for faulty prediction using a specified supervised machine learning algorithm. …”
Get full text
Get full text
Get full text

Personal identification by Keystroke Pattern for login security by Abdullah, Norhayati

Get full text
Get full text

Identification of non-linear dynamic systems using fuzzy system with constrained membership functions by Yaakob, Mohd. Shafiek

“…In this study, the identification performance of the SFS trained by the back-propagation (BP) algorithm forms the basis of comparison when evaluations were made on the performance of the newly proposed CFS models. …”
Get full text
Get full text
Get full text

Unifying the evaluation criteria of many objectives optimization using fuzzy Delphi method by Mohammed, Rawia Tahrir, Yaakob, Razali, Mohd Sharef, Nurfadhlina, Abdullah, Rusli

“…Lastly, the most suitable criteria outcomes are formulated in the unifying model and evaluate by experts to verify the appropriateness and suitability of the model in assessing the MaOO algorithms fairly and effectively.…”
Get full text
Get full text

Deep learning in public health: Comparative predictive models for COVID-19 case forecasting by Muhammad Usman Tariq, Muhammad Usman Tariq, Ismail, Shuhaida

“…These models were calibrated and evaluated using a comprehensive dataset that includes confirmed case counts, demographic data, and relevant socioeconomic factors. …”
Get full text
Get full text
Get full text

Spotted hyena optimizer with deep learning driven cybersecurity for social networks by Mustafa Hilal, Anwer, Hassan Abdalla Hashim, Aisha, G. Mohamed, Heba, A. Alharbi, Lubna, K. Nour, Mohamed, Mohamed, Abdullah, S. Almasoud, Ahmed, Motwakel, Abdelwahed

“…Current advancements in machine learning (ML), deep learning (DL), and natural language processing (NLP) tools enable to detect and classify CB in social networks. …”
Get full text
Get full text
Get full text
Get full text