Bio
Md Riyad Hossain is an emerging researcher in industrial engineering and machine learning optimization. He earned his Bachelor of Science in Industrial & Production Engineering from the University of Texas Rio Grande Valley and has been actively affiliated with the Department of Industrial Engineering and Management at Khulna University of Engineering & Technology in Bangladesh. His work centers on solving complex scheduling problems, such as the flexible job shop scheduling problem using genetic algorithms, and enhancing machine learning model performance through hyperparameter tuning. To date, Hossain has authored three peer-reviewed papers on these topics, collaborating with colleagues including Dr. Douglas Timmer. He also holds a Fellow membership in an academic society, reflecting his growing contributions to the field.
Educational Journey
University of Texas Rio Grande Valley
Bachelor of Science in Industrial & Production Engineering
Experience
Research
Machine Learning Model Optimization with Hyper Parameter Tuning Approach
Hyper-parameters tuning is a key step to find the optimal machine learning parameters. Determining the best hyper-parameters takes a good deal of time, especially when the objective functions are costly to determine, or a large number of parameters are required to be tuned. In contrast to the conventional machine learning algorithms, Neural Network requires tuning hyperparameters more because it has to process a lot of parameters together, and depending on the fine tuning, the accuracy of the model can be varied in between 25%-90%. A few of the most effective techniques for tuning hyper-parameters in the Deep learning methods are: Grid search, Random forest, Bayesian optimization, etc. Every method has some advantages and disadvantages over others. For example: Grid search has proven to be an effective technique to tune hyper-parameters, along with drawbacks like trying too many combinations, and performing poorly when it is required to tune many parameters at a time. In our work, we will determine, show and analyze the efficiencies of a real-world synthetic polymer dataset for different parameters and tuning methods.
Optimization of the Flexible Job Shop Scheduling Problem for Economic Sustainability
The flexible job-shop scheduling problem (FJSP) is one of the challenging optimization problems as they occupy very large search space. Solving this kind of problems with conventional methods are obsolete now as the Internet of Things (IoT) has changed scheduling platform by means of cloud computing and advanced data analytics. Genetic Algorithms (GAs) is a popular modern tool for machine scheduling problems and in this work, a scheduling algorithm has been developed to minimize total tardiness and make span time of parallel machines which is promoting overall economic sustainability. The algorithm consists of a machine selection module (MSM) that helps to select the right machine on the right time with the help of global selection (GS) technique by generating high quality initial population. To represent an optimized solution of the FJSP, an improved chromosome representation is used while adopting uniform crossover and mutation operator. The result showed that proposed algorithm is much more effective and efficient for solving flexible job-shop scheduling problem which is helping to reduce the overall downtime significantly.
