A Hybrid Genetic Algorithm for Course Scheduling and Teaching Workload Management

The problem of university course scheduling is a complicated job to do because of the many constraints that must be considered, such as the number of courses, the number of rooms available, the number of students, lecturer preferences, and time slots. The more courses that will be scheduled, the scheduling problem becomes more complex to solve. Therefore, it is necessary to set an automatic course schedule based on optimization method. The aim of this research is to gain an optimal solution in the form of schedule in order to decrease the number of clashed courses, optimize room utilization and consider the preferences of lecturer-course. In this research, a hybridization method of Genetic Algorithm (GA) and Pattern Search (PS) is investigated for solving university course scheduling problems. The main algorithm is GA to find the global optimum solution, while the PS algorithm is used to find the local optimum solution that is difficult to obtain by the GA method. The simulation results with 93 courses show that the Hybrid GA-PS method works better than does the GA method without hybrid, as evidenced by the better fitness value of the hybrid GA-PS method which is -3528.62 and 99.24% of the solutions achieved. While the GA method without hybrid is only able to reach a solution of around 65% and has an average fitness value of -3100.76.

Download Full-text

Evaluation of Accidental Death Records Using Hybrid Genetic Algorithm

SSRN Electronic Journal ◽

10.2139/ssrn.3563084 ◽

2020 ◽

Cited By ~ 2

Author(s):

Nikhil Sharma ◽

Ila Kaushik ◽

Rajat Rathi ◽

Santosh Kumar

Keyword(s):

Genetic Algorithm ◽

Hybrid Genetic Algorithm ◽

Accidental Death

Download Full-text

Design of GA and Ontology based NLP Frameworks for Online Opinion Mining

Recent Patents on Engineering ◽

10.2174/1872212112666180115162726 ◽

2019 ◽

Vol 13 (2) ◽

pp. 159-165

Author(s):

Manik Sharma ◽

Gurvinder Singh ◽

Rajinder Singh

Keyword(s):

Genetic Algorithm ◽

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Opinion Mining ◽

Hybrid Genetic Algorithm ◽

Online Reviews ◽

Middle Tier ◽

Complete Set ◽

Mining Model

Background: For almost every domain, a tremendous degree of data is accessible in an online and offline mode. Billions of users are daily posting their views or opinions by using different online applications like WhatsApp, Facebook, Twitter, Blogs, Instagram etc. Objective: These reviews are constructive for the progress of the venture, civilization, state and even nation. However, this momentous amount of information is useful only if it is collectively and effectively mined. Methodology: Opinion mining is used to extract the thoughts, expression, emotions, critics, appraisal from the data posted by different persons. It is one of the prevailing research techniques that coalesce and employ the features from natural language processing. Here, an amalgamated approach has been employed to mine online reviews. Results: To improve the results of genetic algorithm based opining mining patent, here, a hybrid genetic algorithm and ontology based 3-tier natural language processing framework named GAO_NLP_OM has been designed. First tier is used for preprocessing and corrosion of the sentences. Middle tier is composed of genetic algorithm based searching module, ontology for English sentences, base words for the review, complete set of English words with item and their features. Genetic algorithm is used to expedite the polarity mining process. The last tier is liable for semantic, discourse and feature summarization. Furthermore, the use of ontology assists in progressing more accurate opinion mining model. Conclusion: GAO_NLP_OM is supposed to improve the performance of genetic algorithm based opinion mining patent. The amalgamation of genetic algorithm, ontology and natural language processing seems to produce fast and more precise results. The proposed framework is able to mine simple as well as compound sentences. However, affirmative preceded interrogative, hidden feature and mixed language sentences still be a challenge for the proposed framework.

Download Full-text