Mohammad Alshibli

Dr. Mohammad Alshibli

Computer Systems, Farmingdale State College, Farmingdale, New York, USA

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 March 2019 in Robotics
Verified
Journal Article
Open access
PDF file
MAMohammad Alshibli
Mohammad Alshibli
AEAhmed ElSayed
Ahmed ElSayed
Elif KongarElif Kongar
Elif Kongar
TSTarek Sobh
Tarek Sobh
SGSurendra Gupta
Surendra Gupta
Disassembly sequence planning (DSP) is a nondeterministic polynomial time (NP) complete problem, making the utilization of metaheuristic approaches a viable alternative. DSP aims at creating efficient algorithms for deriving the optimum or near-optimum disassembly sequence for a given product or a product family. The problem-specific nature of such algorithms, however, requires these solutions to be validated, proving their versatility in accommodating substantial variations in the problem environment. To achieve this goal, this paper utilizes Taguchi’s orthogonal arrays to test the robustness of a previously-proposed Simulated Annealing (SA) algorithm. A comparison with an exhaustive search is also conducted to verify the efficiency of the algorithm in generating an optimum or near-optimum disassembly sequence for a given product. In order to further improve the solution, a distributed task allocation technique is also introduced into the model environment to accommodate multiple robot arms.

26 December 2017 in Journal of Intelligent & Robotic Systems
Verified
Journal Article
Closed access
PDF file
MAMohammad Alshibli
Mohammad Alshibli
AEAhmed ElSayed
Ahmed ElSayed
OTOzden Tozanli
Ozden Tozanli
Elif KongarElif Kongar
Elif Kongar
TSTarek M. Sobh
Tarek M. Sobh
SGSurendra M. Gupta
Surendra M. Gupta

15 November 2024
Verified
Conference Paper
Closed access
JKJack Kollar
Jack Kollar
MAMohammad Alshibli
Mohammad Alshibli
This paper examines the crucial issue of inaccuracies in artificial intelligence (AI) systems and their implications in different applications. The integration of AI into vital sectors shows the need for high accuracy and reliability, as errors can significantly damage trust in these systems and cause harm. Through a thorough review of current literature, this study explores the origins of AI inaccuracies, their wide-ranging impacts, and ongoing efforts to address these challenges. Focusing on the mechanisms for improving the factual accuracy of AI, the discussion extends to a variety of correction strategies beyond specific instances like the editing of knowledge within AI models. Addresses the critical need for AI systems to produce reliable and factually correct outputs, emphasizing the development of verification processes. The study further delves into the challenge of AI systems generating misleading or incorrect information, termed as “artificial hallucinations,” highlighting the essential for approaches that ensure the integrity and accuracy of AI-generated content. The implications of inaccuracies in AI extend to the realm of scientific and academic writing, where the reliability of information is important. This paper shows the necessity for content verification mechanisms to maintain the standards of integrity and factual correctness. By providing a detailed examination of the state of AI inaccuracies and proposing different directions for improvement, this paper aims to promote a more responsible approach to the development and application of AI technologies. In advocating for transparency, accountability, and continuous innovation, the study seeks to contribute to the advancement of AI systems that are not only more accurate and trustworthy but also capable of retaining public confidence in their utility and safety.

3 September 2025 in Sensors
Verified
Journal Article
Open access
PDF file
IAIsmaiel Nooruddeen Albukhari
Ismaiel Nooruddeen Albukhari
AEAhmed ElSayed
Ahmed ElSayed
MAMohammad Alshibli
Mohammad Alshibli
Recently, visual odometry and SLAM (Simultaneous Localization and Mapping) have shown tremendous performance improvements compared to LiDAR and 3D sensor techniques. Unfortunately, attempts to achieve these improvements always face numerous challenges due to their complexity and insufficient compatibility for real-time environments. This paper presents an enhanced deep-learning-based SLAM system, primarily for Monocular Visual SLAM, by utilizing a Mini-GRU (gated recurrent unit). The proposed system, MINI-DROID-SLAM, demonstrates significant improvements and robustness through persistent iteration of the camera position. Similar to the original DROID SLAM, the system calculates pixel-wise depth mapping and enhances it using the BA (Bundle Adjustment) technique. The architecture introduced in this research reduces the time used and computation complexity compared to the original DROID-SLAM network. The introduced model is trained locally on a single GPU using monocular camera images from the TartanAir datasets. The training time and reconstruction metric, assessed using ATE (Absolute Trajectory Error), show robustness and high performance compared to the original DROID-SLAM.

31 January 2024 in Computer and Information Science
Verified
Journal Article
Open access
PDF file
AJAndrew McInnis Jr
Andrew McInnis Jr
MAMohammad Alshibli
Mohammad Alshibli
AAAhmad Alzaghal
Ahmad Alzaghal
SHSamir Hamada
Samir Hamada
This paper introduces a unique perspective. Rather than focusing on improving the already significant achievements of existing artificial intelligence algorithms, it investigates the potential of merging various algorithms to enhance their overall capabilities. Essential design aspects required for this integration are examined, and a prototype system is developed to demonstrate the practical application of these design principles. This method aims to broaden the range of capabilities accessible to a system, addressing the limitation of the narrow focus prevalent in contemporary artificial intelligence.