Computer Science, Information Technology and Telecommunications

Permanent URI for this collection

http://openscience.utm.my/handle/123456789/31

Browse

Browsing Computer Science, Information Technology and Telecommunications by Subject "Algorithms"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    An improved personalized item-based collaborative recommendation algorithm
    (Universiti Teknologi Malaysia, 2022) Ghorbanian, Masoud
    In the increasingly competitive online market, users are presented with a massive number of items to choose. Recommendation algorithms are used to assist users in making shopping decision conveniently. However, the existing recommendation algorithms are still limited in covering the diversity in the recommendation list. This research aims to investigate the recommendation algorithms and design a personalized recommendation algorithm to cover unpopular items and diversity, which leads to more opportunities to create new offerings. This research is divided into three phases: first, to identify the existing recommendation algorithms; second, to design and implement the proposed algorithm; and third, to generate a candidate list, item-based collaborative filtering is used. Then, k-means cluster based on the genre was proposed to rank the items based on the candidate list and user’s interests to increase diversity and coverage. The effects of different methods impacted the diversity level of the developed algorithm, and the effectiveness and shortcomings of the algorithm are identified. Next, the recommendation list was analyzed and compared with other recommendation algorithms. The results of the proposed algorithm showed an improved diversity by 12% in comparison to personal collaborative filtering (PCF), 14% compared to Div-Clust, and 20% compared to the baseline algorithm. The improvement is due to reranking items based on the user’s diversity level and genre clusters which were introduced in the proposed recommendation algorithm. In addition, the coverage percentage has improved by 35% in comparison to PCF and Div-Clust, and 23% compared to the baseline algorithm, which increases the range of offerings to users. The recommendation algorithm demonstrated that it is able to generate a recommendation list that increases the diversity and coverage of items over other algorithms.
  • Thumbnail Image
    Item
    Multistage feature selection methods for data classification
    (Universiti Teknologi Malaysia, 2021) Mohamad, Masurah
    In data analysis process, a good decision can be made with the assistance of several sub-processes and methods. The most common processes are feature selection and classification processes. Various methods and processes have been proposed to solve many issues such as low classification accuracy, and long processing time faced by the decision-makers. The analysis process becomes more complicated especially when dealing with complex datasets that consist of large and problematic datasets. One of the solutions that can be used is by employing an effective feature selection method to reduce the data processing time, decrease the used memory space, and increase the accuracy of decisions. However, not all the existing methods are capable of dealing with these issues. The aim of this research was to assist the classifier in giving a better performance when dealing with problematic datasets by generating optimised attribute set. The proposed method comprised two stages of feature selection processes, that employed correlation-based feature selection method using a best first search algorithm (CFS-BFS) and as well as a soft set and rough set parameter selection method (SSRS). CFS-BFS is used to eliminate uncorrelated attributes in a dataset meanwhile SSRS was utilized to manage any problematic values such as uncertainty in a dataset. Several bench-marking feature selection methods such as classifier subset evaluation (CSE) and principle component analysis (PCA) and different classifiers such as support vector machine (SVM) and neural network (NN) were used to validate the obtained results. ANOVA and T-test were also conducted to verify the obtained results. The obtained averages for two experimental works have proven that the proposed method equally matched the performance of other benchmarking methods in terms of assisting the classifier in achieving high classification performance for complex datasets. The obtained average for another experimental work has shown that the proposed work has outperformed the other benchmarking methods. In conclusion, the proposed method is significant to be used as an alternative feature selection method and able to assist the classifiers in achieving better accuracy in the classification process especially when dealing with problematic datasets.