Faculty Publications

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 5 of 191
  • Item
    Performance evaluation of college laboratories based on fusion of decision tree and BP neural network
    (Sciendo, 2022) Yujie, Chang ; Weimin, Gao ; Chelli, Karim ; Muttar, Ahmed K. H.
    Performance evaluation can promote the continuous improvement of the laboratories in a college. It is necessary to take into account the scientific evaluation method during the process of the performance evaluation. In this paper, a performance evaluation method based on the fusion of the decision tree and BP neural network is presented. In detail, the decision tree model is used to select performance evaluation indexes with high weight. The BP neural network was adopted aiming to reduce the impact of assessment prediction of classification by non-core factors. First, the data were pre-processed by trapezoidal membership function. Then, the decision tree was generated by the C4.5 algorithm to select the evaluation indexes with high weight. Then, the BP neural network was trained with as many samples as possible by evaluation indexes; it possesses experts' experience which can be used to predict the performance evaluation results. The method overcomes the shortages of the separate model, eliminates the disturbance of human factors and improves the accuracy of the evaluation. Experiments show that the model is feasible and effective in performance evaluation of college laboratories. The outcomes of this work can provide a scientific evaluation method for people such as researchers, college administrators and laboratory managers. Also, this paper will help them to improve the management of laboratories and provide them with decision references for constructing the laboratories. © 2021 Chang Yujie et al., published by Sciendo 2021.
  • Item
    Adaptively Intelligent Meta-search Engine with Minimum Edit Distance
    (Institute of Electrical and Electronics Engineers Inc., 2022) Kanwal, Asma ; Septyanto, Arif Wicaksono ; Muhammad, Muhammad Hassan Ghulam ; Said, Raed A. ; Farrukh, Muhammad ; Ibrahim, Muhammad
    In current era retrieval of information has attained high demand due to spectra from websites has abundantly increased. Search Engines are basic tools to get information from the web of data and show irrelevant data causing wastage of time. Considering the fact that time is a precious commodity and is the hallmark of everything around us. To overcome the wastage of time and for its optimum utilization meta-search engines are design. Meta-Search Engine use to fetch relevant data. Existing meta-search engine shows their relevant data based on keywords as well as a semantic query. Semantic query-based results still have some irrelevancy in the results. In this paper, we analyze the semantic query based on machine learning algorithms. This paper hypothesizes improved results through the query expansion mechanism. Author also remove duplicated URLs that come from multiple search engines. Minimum Edit Distance algorithm is used to measure the similarity between titles, snippets and if measuring similarity is more than 0.6 then it must remove that title and snippet. Ranking process, generated retrieval of the relevant document at the top relevant document. Comparative analysis of proposed work is done with existing meta-search engines, overall performance of Intelligent Meta-Search Engine (IMSE) remains 74.17%. © 2022 IEEE.
  • Item
    Application of Computational Intelligence and Machine Learning to Conventional Operational Research Methods
    (Institute of Electrical and Electronics Engineers Inc., 2022) Ali, Atif ; Said, Raed A. ; Rizwan, Hafiz Muhammad Amir ; Shehzad, Khurram ; Naz, Imran
    Machine learning and computational intelligence are two methods for achieving this (CI); traditional operational research methods are combined with machine learning-based computational techniques (OR). Students can handle complex decision-making problems thanks to the synergy between those methods and techniques. This research's primary goal is to present and demonstrate potential connections amid the two computational arenas. Using applications, we show how machine learning techniques like fuzzy logic, neural networks and reinforcement learning can be combined to provide a simpler solution to more complex problems than traditional OR methods., which is a research contribution in and of itself. © 2022 IEEE.
  • Item
    Detection of Benign and Malignant Tumors in Skin Empowered with Transfer Learning
    (Hindawi Limited, 2022) Ghazal, Taher M. ; Hussain, Sajid ; Khan, Muhammad Farhan ; Khan, Muhammad Adnan ; Said, Raed A. T. ; Ahmad, Munir
    Skin cancer is a major type of cancer with rapidly increasing victims all over the world. It is very much important to detect skin cancer in the early stages. Computer-developed diagnosis systems helped the physicians to diagnose disease, which allows appropriate treatment and increases the survival ratio of patients. In the proposed system, the classification problem of skin disease is tackled. An automated and reliable system for the classification of malignant and benign tumors is developed. In this system, a customized pretrained Deep Convolutional Neural Network (DCNN) is implemented. The pretrained AlexNet model is customized by replacing the last layers according to the proposed system problem. The softmax layer is modified according to binary classification detection. The proposed system model is well trained on malignant and benign tumors skin cancer dataset of 1920 images, where each class contains 960 images. After good training, the proposed system model is validated on 480 images, where the size of images of each class is 240. The proposed system model is analyzed using the following parameters: accuracy, sensitivity, specificity, Positive Predicted Values (PPV), Negative Predicted Value (NPV), False Positive Ratio (FPR), False Negative Ratio (FNR), Likelihood Ratio Positive (LRP), and Likelihood Ratio Negative (LRN). The accuracy achieved through the proposed system model is 87.1%, which is higher than traditional methods of classification. © 2022 Taher M.
  • Item
    A Web-Based Benchmarking Tool and Database for SMEs: Research in Progress
    (Springer Science and Business Media B.V., 2017) Ahmad, Norita ; Maarof, Fariedah ; Elshareif, Elgilani Eltahir ; Opulencia, Jade
    This research focuses on developing a standard benchmarking tool and database that can be used by SMEs in the UAE to evaluate themselves against their competitors. The project presents an adaptation of an existing tool, QuickView, already in use in the USA. The short-term objectives of the project are to determine whether QuickView could be usable in the UAE, and to test whether SMEs in the UAE could be evaluated against the 4000 US SMEs on the QuickView database. Eventually, the goal is to help SMEs in the UAE improve bottom-line performance by transforming their practices for competitive advantage. © 2017, Springer International Publishing Switzerland.