Preferred Language
Articles
/
alkej-814
Comparative Transfer Learning Models for End-to-End Self-Driving Car
...Show More Authors

Self-driving automobiles are prominent in science and technology, which affect social and economic development. Deep learning (DL) is the most common area of study in artificial intelligence (AI). In recent years, deep learning-based solutions have been presented in the field of self-driving cars and have achieved outstanding results. Different studies investigated a variety of significant technologies for autonomous vehicles, including car navigation systems, path planning, environmental perception, as well as car control. End-to-end learning control directly converts sensory data into control commands in autonomous driving. This research aims to identify the most accurate pre-trained Deep Neural Network (DNN) for predicting the steering angle of a self-driving vehicle that is suitable to be applied to embedded automotive technologies with limited performance. Three well-known pre-trained models were compared in this study: AlexNet, ResNet18, and DenseNet121.

Transfer learning was utilized by modifying the final layer of pre-trained models in order to predict the steering angle of the vehicle. Experiments were conducted on the dataset collected from two different tracks. According to the study's findings, ResNet18 and DenseNet121 have the lowest error percentage for steering angle values. Furthermore, the performance of the modified models was evaluated on predetermined tracks. ResNet18 outperformed DenseNet121 in terms of accuracy, with less deviation from the center of the track, while DenseNet121 demonstrated greater adaptability across multiple tracks, resulting in better performance consistency.

Scopus Crossref
View Publication Preview PDF
Quick Preview PDF
Publication Date
Thu Oct 15 2015
Journal Name
Al Mustansyriah Journal Of Science
Comparison between (ARIMA) and (ANNs) models for estimating the relative humidity for Baghdad city
...Show More Authors

The aim of the research is to study the comparison between (ARIMA) Auto Regressive Integrated Moving Average and(ANNs) Artificial Neural Networks models and to select the best one for prediction the monthly relative humidity values depending upon the standard errors between estimated and observe values . It has been noted that both can be used for estimation and the best on among is (ANNs) as the values (MAE,RMSE, R2) is )0.036816,0.0466,0.91) respectively for the best formula for model (ARIMA) (6,0,2)(6,0,1) whereas the values of estimates relative to model (ANNs) for the best formula (5,5,1) is (0.0109, 0.0139 ,0.991) respectively. so that model (ANNs) is superior than (ARIMA) in a such evaluation.

Publication Date
Thu Aug 01 2019
Journal Name
Journal Of Economics And Administrative Sciences
Some Estimation methods for the two models SPSEM and SPSAR for spatially dependent data
...Show More Authors

ABSTRUCT

In This Paper, some semi- parametric spatial models were estimated, these models are, the semi – parametric spatial error model (SPSEM), which suffer from the problem of spatial errors dependence, and the semi – parametric spatial auto regressive model (SPSAR). Where the method of maximum likelihood was used in estimating the parameter of spatial error          ( λ ) in the model (SPSEM), estimated  the parameter of spatial dependence ( ρ ) in the model ( SPSAR ), and using the non-parametric method in estimating the smoothing function m(x) for these two models, these non-parametric methods are; the local linear estimator (LLE) which require finding the smoo

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Mon Nov 09 2020
Journal Name
Construction Research Congress 2020
Alternative Risk Models for Optimal Investment in Portfolio-Based Community Solar
...Show More Authors

View Publication
Scopus Crossref
Publication Date
Thu Jan 01 2015
Journal Name
Mj Journal On Applied Mathematics
Mathematical models for estimation the concentration of heavy metals in soil
...Show More Authors

Publication Date
Sun May 01 2022
Journal Name
Expert Systems With Applications
Novel large scale brain network models for EEG epileptic pattern generations
...Show More Authors

Background: Unlike normal EEG patterns, the epileptiform abnormal pattern is characterized by different mor phologies such as the high-frequency oscillations (HFOs) of ripples on spikes, spikes and waves, continuous and sporadic spikes, and ploy2 spikes. Several studies have reported that HFOs can be novel biomarkers in human epilepsy study. S) Method: To regenerate and investigate these patterns, we have proposed three large scale brain network models (BNM by linking the neural mass model (NMM) of Stefanescu-Jirsa 2D (S-J 2D) with our own structural con nectivity derived from the realistic biological data, so called, large-scale connectivity connectome. These models include multiple network connectivity of brain regions at different

... Show More
View Publication
Scopus (2)
Crossref (1)
Scopus Clarivate Crossref
Publication Date
Thu Feb 07 2019
Journal Name
Iraqi Journal Of Laser
Gingival Enlargement Management using Diode Laser 940 nm and Conventional Scalpel Technique (A Comparative Study)
...Show More Authors

Diode lasers are becoming popular in periodontal surgery due to their highly absorption by pigments such as melanin and hemoglobin their weak absorption by water and hydroxyapatite makes them safe to be used around dental hard tissues. Objective: The aim of the present study was to evaluate the efficiency of diode laser in performing gingivectomy in comparison to conventional scalpel technique in patients with chronic inflammatory enlargement. Materials and methods: Thirty patients were selected for this study. All of them required surgical treatment of gingival enlargements and were randomly divided into two groups: Control group (treated by scalpel and include sixteen patients) and study group (treated with diode laser 940nm and includ

... Show More
View Publication Preview PDF
Publication Date
Tue Dec 01 2020
Journal Name
Journal Of Economics And Administrative Sciences
The impact of strategic leadership skills on effective environmental management according to the (VUCA Prime) model
...Show More Authors

Purpose: clarify the integrative relationship of strategic leadership skills and effective management and the role of those skills combined or individually in achieving effective management.

Research design: The researchers used the quantitative method by surveying a class sample from the heads of the executive departments in a group of Iraqi private banks, consisting of (106) individuals according to the (VUCA Prime) methodology for effective management and the ten skills model for Johansen. The questionnaire was analyzed using a model of the structural equation.

Findings: The most prominent results of the research were the presence of a weak ro

... Show More
View Publication Preview PDF
Crossref
Publication Date
Wed Mar 30 2022
Journal Name
Journal Of Economics And Administrative Sciences
The Role Of Smart Leadership Dimensions In Crisis Management- A study For Opinions Of Sample Of Administrative Leaderships In A number Of Humanities Colleges At The University Of Mosul
...Show More Authors

This research aims at answering many questions raised by the research problem concerning the view of the organizations under consideration for the concept of smart leadership and its most important dimensions, as well as the view of crisis management and its concept and most important methods through research objectives that define and clarify the smart leadership with its dimensions and methods of crisis management.

For the purpose of reaching the results of the research and testing the assumptions about the relationship between smart leadership and methods of crisis management, the researcher adopted a questionnaire, designed especially to be a criterion for the research, as the main tool for data coll

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Fri Dec 01 2023
Journal Name
Applied Energy
Deep clustering of Lagrangian trajectory for multi-task learning to energy saving in intelligent buildings using cooperative multi-agent
...Show More Authors

The intelligent buildings provided various incentives to get highly inefficient energy-saving caused by the non-stationary building environments. In the presence of such dynamic excitation with higher levels of nonlinearity and coupling effect of temperature and humidity, the HVAC system transitions from underdamped to overdamped indoor conditions. This led to the promotion of highly inefficient energy use and fluctuating indoor thermal comfort. To address these concerns, this study develops a novel framework based on deep clustering of lagrangian trajectories for multi-task learning (DCLTML) and adding a pre-cooling coil in the air handling unit (AHU) to alleviate a coupling issue. The proposed DCLTML exhibits great overall control and is

... Show More
View Publication
Scopus (31)
Crossref (23)
Scopus Clarivate Crossref
Publication Date
Fri Jan 01 2016
Journal Name
Journal Of Engineering
Some Properties of Polymer Modified Self-Compacting Concrete Exposed to Kerosene and Gas Oil
...Show More Authors

This thesis aims to study the effect of addition polymer materials on mechanical properties of self-compacting concrete, and also to assess the influence of petroleum products (kerosene and gas oil) on mechanical properties of polymer modified self-compacting concrete (PMSCC) after different exposure periods of (30 ,60 ,90 ,and 180 days).

Two type of curing are used; 28 days in water for SCC and 2 days in water followed 26 days in air for PMSCC.

The test results show that the PMSCC (15% P/C ratio) which is exposed to oil products recorded a lower deterioration in compressive strength's values than reference concrete. The percentages of reduction in compressive strength values of PMSCC (15% P/C ratio) was

... Show More
View Publication Preview PDF