Hossein Mirshojaee, Behrooz Masoumi, Esmaeel Zeinali,
Volume 28, Issue 1 (IJIEPR 2017)
Abstract
Given the increasing number of documents, sites, online sources, and the users’ desire to quickly access information, automatic textual summarization has caught the attention of many researchers in this field. Researchers have presented different methods for text summarization as well as a useful summary of those texts including relevant document sentences. This study selects extractive method out of different summarizing methods (e.g. abstract method). Extractive method involves summarizing text through objective extraction of some parts of a text like word, sentence, and paragraph. A summarization issue would be unsolvable by exact methods in a reasonable time with considering documents with high amount of information (NP complete). These kinds of issues are usually solved using metaheuristic methods. A biogeography-based optimization algorithm (BBO), which is a new metaheuristic method in the domain of extractive text summarization, is used in this article.
Amirhossein Masoumi, Rouzbeh Ghousi, Ahmad Makui,
Volume 33, Issue 3 (IJIEPR 2022)
Abstract
Purpose: Non-cancerous prostate lesions such as prostate calcification, prostate enlargement, and prostate inflammation cause too many problems for men’s health. This research proposes a novel approach, a combination of image processing techniques and deep learning methods for classification and segmentation of the prostate in CT-scan images by considering the experienced physicians’ reports.
Methodology: Due to the various symptoms and nature of these lesions, a three-phases innovative approach has been implemented. In the first phase, using Mask R-CNN, in the second phase, considering the age of each patient and comparison with the standard size of the prostate gland, and finally, using the morphology features, the presence of three common non-cancerous lesions in the prostate gland has investigated.
Findings: A hierarchical multitask approach is introduced and the final amount of classification, localization, and segmentation loss is 1%, 1%, and 7%, respectively. Eventually, the overall loss ratio of the model is about 9%.
Originality: In this study, a medical assistant approach is introduced to increase diagnosis process accuracy and reduce error using a real dataset of abdominal and pelvics’ CT scans and the physicians’ reports for each image. A multi-tasks convolutional neural network; also presented to perform localization, classification, and segmentation of the prostate gland in CT scans at the same time.
Malihe Masoumi, Javad Behnamian,
Volume 35, Issue 1 (IJIEPR 2024)
Abstract
Due to the many applications of the travelling salesman problem, solving this problem has been considered by many researchers. One of the subsets of the travelling salesman problem is the metric travelling salesman problem in which a triangular inequality is observed. This is a crucial problem in combinatorial optimization as it is used as a standard problem as a basis for proving complexity or providing solutions to other problems in this class. The solution is used usually in logistics, manufacturing and other areas for cost minimization. Since this is an NP-hard problem, heuristic and meta-heuristic algorithms seek near-optimal solutions in polynomial time as numerical solutions. For this purpose, in this paper, a heuristic algorithm based on the minimum spanning tree is presented to solve this problem. Then, by generating 20 instances, the efficiency of the proposed algorithm was compared with one of the most famous algorithms for solving the travelling salesman problem, namely the nearest neighbour algorithm and the ant colony optimization algorithm. The results show that the proposed algorithm has good convergence to the optimal solution. In general, the proposed algorithm has a balance between runtime and the solution found compared to the other two algorithms. So the nearest neighbour algorithm has a very good runtime to reach the solution but did not have the necessary convergence to the optimal solution, and vice versa, the ant colony algorithm converges very well to the optimal solution, but, its runtime solution is very longer than the proposed algorithm.
