Preferred Language
Articles
/
bsj-6652
Generative Adversarial Network for Imitation Learning from Single Demonstration
...Show More Authors

Imitation learning is an effective method for training an autonomous agent to accomplish a task by imitating expert behaviors in their demonstrations. However, traditional imitation learning methods require a large number of expert demonstrations in order to learn a complex behavior. Such a disadvantage has limited the potential of imitation learning in complex tasks where the expert demonstrations are not sufficient. In order to address the problem, we propose a Generative Adversarial Network-based model which is designed to learn optimal policies using only a single demonstration. The proposed model is evaluated on two simulated tasks in comparison with other methods. The results show that our proposed model is capable of completing considered tasks despite the limitation in the number of expert demonstrations, which clearly indicate the potential of our model.

Scopus Clarivate Crossref
View Publication Preview PDF
Quick Preview PDF
Publication Date
Wed May 10 2023
Journal Name
Journal Of Engineering
EXPERIMENTAL AND NUMERICAL STUDY OF FRICTION STIR SPOT WELDING FOR 2024 ALUMINUM PLATES
...Show More Authors

Friction stir spot welding (FSSW) is a relatively new welding process that may have significant advantages compared to the fusion processes as follows joining of conventionally non-fusion weldable alloys, reduced distortion and improved mechanical properties of weldable alloys joints due to the pure solidstate joining of metals. In this paper, a three-dimensional model based on finite element analysis is used to study the thermal history in the spot-welding of aluminum alloy 2024. The model take place the thermomechanical property on the process of the welded metals. The thermal history and the evolution results with numerical model at the measured point in the friction stirred spot weld have a good matching, then the prediction of the t

... Show More
View Publication Preview PDF
Crossref
Publication Date
Mon Apr 01 2019
Journal Name
2019 International Conference On Automation, Computational And Technology Management (icactm)
Multi-Resolution Hierarchical Structure for Efficient Data Aggregation and Mining of Big Data
...Show More Authors

Big data analysis is essential for modern applications in areas such as healthcare, assistive technology, intelligent transportation, environment and climate monitoring. Traditional algorithms in data mining and machine learning do not scale well with data size. Mining and learning from big data need time and memory efficient techniques, albeit the cost of possible loss in accuracy. We have developed a data aggregation structure to summarize data with large number of instances and data generated from multiple data sources. Data are aggregated at multiple resolutions and resolution provides a trade-off between efficiency and accuracy. The structure is built once, updated incrementally, and serves as a common data input for multiple mining an

... Show More
View Publication
Scopus (4)
Crossref (2)
Scopus Crossref
Publication Date
Wed Feb 11 2026
Journal Name
Chemistryselect
Gelatin Nanoparticles as a Carrier for Acriflavine and Triethylenetetramine: Cytotoxicity and Antibacterial Activity
...Show More Authors
ABSTRACT<p> Despite extensive investigation as biocompatible drug carriers, gelatin nanoparticles (GNPs) have not been thoroughly assessed for carrying chemically distinct cationic molecules such as acriflavine (ACF) and triethylenetetramine (TETA). In this study, we hypothesize that GNPs can effectively encapsulate ACF and TETA, forming stable delivery systems with distinct antibacterial and cytotoxic activities. ACF encapsulated in gelatin was prepared adapting desolvation technique. The procedure involved stirring of an aqueous solution of gelatin and ACF at room temperature, the pH was titrated to eight using NaOH followed by addition of ethanol. The resulting nanopart</p> ... Show More
View Publication
Scopus Crossref
Publication Date
Wed Jan 15 2020
Journal Name
Emerging Trends In Mechatronics
Interactional Modeling and Optimized PD Impedance Control Design for Robust Safe Fingertip Grasping
...Show More Authors

View Publication
Crossref
Publication Date
Thu Jun 01 2017
Journal Name
International Journal Of Engineering Research And Advanced Technology
The Use of First Order Polynomial with Double Scalar Quantization for Image Compression
...Show More Authors

Publication Date
Tue Jan 15 2002
Journal Name
Abhath Al- Yarmouk [basic Sciences And Engineering]
Computer Program for Predicting Ultimate Strength of Structural Concrete Sections of General Shape
...Show More Authors

Publication Date
Mon Dec 05 2022
Journal Name
Baghdad Science Journal
Electron lens Optimization for Beam Physics Research using the Integrated Optics Test Accelerator
...Show More Authors

This study proposed control system that has been presented to control the electron lens resistance in order to obtain a stabilized electron lens power. This study will layout the fundamental challenges, hypothetical plan arrangements and development condition for the Integrable Optics Test Accelerator (IOTA) in progress at Fermilab. Thus, an effective automatic gain  control (AGC) unit has been introduced which prevents fluctuations in the internal resistance of the electronic lens caused by environmental influences to affect the system's current and power values ​​and keep them in stable amounts. Utilizing this unit has obtained level balanced out system un impacted with electronic lens surrounding natural varieties.

View Publication Preview PDF
Scopus Crossref
Publication Date
Mon Dec 02 2013
Journal Name
Iraqi Medical Journal
Etiology and Antibiotic Sensitivity for Otitis Media in A Central Pediatric Teaching Hospital.
...Show More Authors

Publication Date
Mon Jan 28 2013
Journal Name
Spie Proceedings
BER performance enhancement for secure wireless communication systems based on chaotic-MIMO techniques
...Show More Authors

The growing interest in the use of chaotic techniques for enabling secure communication in recent years has been motivated by the emergence of a number of wireless services which require the service provider to provide low bit error rates (BER) along with information security. This paper investigates the feasibility of using chaotic communications over Multiple-Input-Multiple-Output (MIMO) channels. While the use of Chaotic maps can enhance security, it is seen that the overall BER performance gets degraded when compared to conventional communication schemes. In order to overcome this limitation, we have proposed the use of a combination of Chaotic modulation and Alamouti Space Time Block Code. The performance of Chaos Shift Keying (CSK) wi

... Show More
View Publication
Crossref (1)
Scopus Clarivate Crossref
Publication Date
Tue Nov 05 2013
Journal Name
Wit Transaction On Ecology And The Environments, Wit, Press No. 11
Remote sensing of water quality index for irrigation usability of the Euphrates River
...Show More Authors

irrigation use at many stations along the Euphrates River inside the Iraqi lands and to try to correlate the results with the satellite image analyses for the purpose of making a colored model for the Euphrates that can be used to predict the quality classifications of the river for irrigation use at any point along the river. The Bhargava method was used to calculate the water quality index for irrigation use at sixteen stations along the river from its entrance to the Iraqi land at Al-Qaim in Anbar governorate to its union with the Tigris River at Qurna in Basrah governorate. Coordinates of the sixteen stations of the Euphrates River were projected at the mosaic of Iraq satellite image which was taken from LANDSAT satellite for bands 1, 2

... Show More
View Publication Preview PDF