Yazar "Shehu, Harisu Abdullahi" seçeneğine göre listele

Listeleniyor 1 - 5 / 5
  • Küçük Resim
    Öğe
    Classification of breast cancer histopathological images using DenseNet and transfer learning
    (Hindawi Publishing Corporation, 2022) Wakili, Musa Adamu; Shehu, Harisu Abdullahi; Sharif, Md. Haidar; Sharif, Md. Haris Uddin; Umar, Abubakar; Kusetoğulları, Hüseyin; İnce, İbrahim Furkan; Uyaver, Şahin
    Breast cancer is one of the most common invading cancers in women. Analyzing breast cancer is nontrivial and may lead to disagreements among experts. Although deep learning methods achieved an excellent performance in classification tasks including breast cancer histopathological images, the existing state-of-the-art methods are computationally expensive and may overfit due to extracting features from in-distribution images. In this paper, our contribution is mainly twofold. First, we perform a short survey on deep-learning-based models for classifying histopathological images to investigate the most popular and optimized training-testing ratios. Our findings reveal that the most popular training-testing ratio for histopathological image classification is 70%: 30%, whereas the best performance (e.g., accuracy) is achieved by using the training-testing ratio of 80%: 20% on an identical dataset. Second, we propose a method named DenTnet to classify breast cancer histopathological images chiefly. DenTnet utilizes the principle of transfer learning to solve the problem of extracting features from the same distribution using DenseNet as a backbone model. The proposed DenTnet method is shown to be superior in comparison to a number of leading deep learning methods in terms of detection accuracy (up to 99.28% on BreaKHis dataset deeming training-testing ratio of 80%: 20%) with good generalization ability and computational speed. The limitation of existing methods including the requirement of high computation and utilization of the same feature distribution is mitigated by dint of the DenTnet.
  • Küçük Resim
    Öğe
    Deep sentiment analysis: a case study on stemmed Turkish Twitter data
    (IEEE, 2021) Shehu, Harisu Abdullahi; Sharif, Md. Haidar; Sharif, Md. Haris Uddin; Datta, Ripon; Tokat, Sezai; Uyaver, Şahin; Kusetoğulları, Hüseyin; Ramadan, Rabie A.
    Sentiment analysis using stemmed Twitter data from various languages is an emerging research topic. In this paper, we address three data augmentation techniques namely Shift, Shuffle, and Hybrid to increase the size of the training data; and then we use three key types of deep learning (DL) models namely recurrent neural network (RNN), convolution neural network (CNN), and hierarchical attention network (HAN) to classify the stemmed Turkish Twitter data for sentiment analysis. The performance of these DL models has been compared with the existing traditional machine learning (TML) models. The performance of TML models has been affected negatively by the stemmed data, but the performance of DL models has been improved greatly with the utilization of the augmentation techniques. Based on the simulation, experimental, and statistical results analysis deeming identical datasets, it has been concluded that the TML models outperform the DL models with respect to both training-time (TTM) and runtime (RTM) complexities of the algorithms; but the DL models outperform the TML models with respect to the most important performance factors as well as the average performance rankings.
  • Küçük Resim
    Öğe
    Facial expression recognition using deep learning
    (American Institute of Physics, 2021) Shehu, Harisu Abdullahi; Sharif, Md Haidar; Uyaver, Şahin
    Facial expression recognition has become an increasingly important area of research in recent years. Neural network-based methods have made amazing progress in performing recognition-based tasks, winning competitions set up by various data science communities, and achieving high performance on many datasets. Miscellaneous regularization methods have been utilized by various researchers to help combat over-fitting, to reduce training time, and to generalize their models. In this paper, by applying the Haar Cascade classifier to crop faces and focus on the region of interest, we hypothesize that we would attain a fast convergence without using the whole image to analyze facial expressions. We also apply label smoothing and analyze its effect on the databases of CK+, KDEF, and RAF. The ResNet model has been employed as an example of a neural network model. Label smoothing has demonstrated an improvement of the recognition accuracy up to 0.5% considering CK+ and the KDEF databases. While the application of Haar Cascade has shown to decrease the achieved accuracy on KDEF and RAF databases with a small margin, fast convergence of the model has been observed.
  • [ X ]
    Öğe
    Sentiment Analysis of Turkish Twitter Data
    (Amer Inst Physics, 2019) Shehu, Harisu Abdullahi; Tokat, Sezai; Sharif, Md. Haidar; Uyaver, Sahin
    In this paper, we present a mechanism to predict the sentiment on Turkish tweets by adopting two methods based on polarity lexicon (PL) and artificial intelligence (AI). The method of PL introduces a dictionary of words and matches the words to those in the harvested tweets. The tweets are then classified to be either positive, negative, or neutral based on the result found after matching them to the words in the dictionary. The method of AI uses support vector machine (SVM) and random forest (RF) classifiers to classify the tweets as either positive, negative or neutral. Experimental results show that SVM performs better on stemmed data by achieving an accuracy of 76%, whereas RF performs better on raw data with an accuracy of 88%. The performance of PL method increases continuously from 45% to 57% as data are being modified from a raw data to a stemmed data.
  • [ X ]
    Öğe
    Sentiment analysis of turkish twitter data using polarity lexicon and artificial intelligence
    (Springer Science and Business Media Deutschland GmbH, 2020) Shehu, Harisu Abdullahi; Haidar, Sharif; Uyaver, Şahin; Tokat, Sezai; Ramadan, Rabie A.
    Sentiment analysis is a process of computationally detecting and classifying opinions written in a piece of writer’s text. It determines the writer’s impression as achromatic or negative or positive. Sentiment analysis became unsophisticated due to the invention of Internet-based societal media. At present, usually people express their opinions by dint of Twitter. Henceforth, Twitter is a fascinating medium for researchers to perform data analysis. In this paper, we address a handful of methods to prognosticate the sentiment on Turkish tweets by taking up polarity lexicon as well as artificial intelligence. The polarity lexicon method uses a dictionary of words and accords with the words among the harvested tweets. The tweets are then grouped into either positive tweets or negative tweets or neutral tweets. The methods of artificial intelligence use either individually or combined classifiers e.g., support vector machine (SVM), random forest (RF), maximum entropy (ME), and decision tree (DT) for categorizing positive tweets, negative tweets, and neutral tweets. To analyze sentiment, a total of 13000 Turkish tweets are collected from Twitter with the help of Twitter’s application programming interface (API). Experimental results show that the mean performance of our proposed methods is greater than 72%. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2020.