Talha Meraj

Realistic leukemia analysis on microscopic slides requires a system that localizes, classifies, and performs WBC morphological analysis. While deep learning has advanced medical imaging, leukemia analysis is hindered by the lack of a large, diverse dataset. Our contribution here is twofold. First, we present a large-scale Leukemia dataset collected through Peripheral Blood Films (PBF) from many patients, through multiple microscopes, multi-cameras, and multi-magnification. To enhance explainability and medical expert acceptance, each leukemia cell is annotated with 7 morphological attributes, ranging from Cell Size to Nuclear Shape. Specifically, we used two microscopes from two different cost spectrums (high-cost: HCM and low-cost: LCM) to capture the dataset at three magnifications (100x, 40x,10x) through different sensors (high-end camera for HCM, middle-level camera for LCM, and mobile phone camera for both). Our dataset has 2.4k annotated images per resolution (in both HCM and LCM), with 10.3K cells annotated for 14 WBC types and 7 morphological properties. Secondly, hematologists typically annotate only well-spread, non-overlapping cell regions within small fields of view (FoV), leaving larger FoVs unannotated. Models trained solely on these annotated areas underutilize available information. To overcome this limitation, we present a novel method for training object detectors using sparse annotations. Along with this, we present a second dataset Leukemia-Sparse-Attri dataset. Curated at 40x FoV, this dataset consists of 1546 sparsely annotated microscopic images, and 185 fully annotated images (used for testing). From explainability to overcoming domain-shift challenges, presented datasets could be used for many challenging aspects of microscopic image analysis.

The Human Activity Recognition (HAR) system is the hottest research area in clinical research. The HAR plays a vital role in learning about a patient’s abnormal activities; based upon this information, the patient’s psychological state can be estimated. An epileptic seizure is a neurological disorder of the human brain and affects millions of people worldwide. If epilepsy is diagnosed correctly and in an early stage, then up to 70% of people can be seizure-free. There is a need for intelligent automatic HAR systems that help clinicians diagnose neurological disorders accurately. In this research, we proposed a Deep Learning (DL) model that enables the detection of epileptic seizures in an automated way, addressing a need in clinical research. To recognize epileptic seizures from brain activities, EEG is a raw but good source of information. In previous studies, many techniques used raw data from EEG to help recognize epileptic patient activities; however, the applied method of extracting features required much intensive expertise from clinical aspects such as radiology and clinical methods. The image data are also used to diagnose epileptic seizures, but applying Machine Learning (ML) methods could address the overfitting problem. In this research, we mainly focused on classifying epilepsy through physical epileptic activities instead of feature engineering and performed the detection of epileptic seizures in three steps. In the first step, we used the open-source numerical dataset of epilepsy of Bonn university from the UCI Machine Learning repository. In the second step, data were fed to the proposed ELM model for training in different training and testing ratios with a little bit of rescaling because the dataset was already pre-processed, normalized, and restructured. In the third step, epileptic and non-epileptic activity was recognized, and in this step, EEG signal feature extraction was automatically performed by a DL model named ELM; features were selected by a Feature Selection (FS) algorithm based on ELM and the final classification was performed using the ELM classifier. In our presented research, seven different ML algorithms were applied for the binary classification of epileptic activities, including K-Nearest Neighbor (KNN), Naïve Bayes (NB), Logistic Regression (LR), Stochastic Gradient Boosting Classifier (SGDC), Gradient Boosting Classifier (GB), Decision Trees (DT), and three deep learning models named Extreme Learning Machine (ELM), Long Short-Term Memory (LSTM), and Artificial Neural Network (ANN). After deep analysis, it is observed that the best results were obtained by our proposed DL model, Extreme Learning Machine (ELM), with an accuracy of 100% accuracy and a 0.99 AUC. Such high performance has not attained in previous research. The proposed model’s performance was checked with other models in terms of performance parameters, namely confusion matrix, accuracy, precision, recall, F1-score, specificity, sensitivity, and the ROC curve.

Internet use resulted in people becoming more reliant on social media. Social media have become the main source of fake news or rumors. They spread uncertainty in each sector of the real world, whether in politics, sports, or celebrities’ lives—all are affected by the uncontrolled behavior of social media platforms. Intelligent methods used to control this fake news in various languages have already been much discussed and frequently proposed by researchers. However, Arabic grammar and language are a far more complex and crucial language to learn. Therefore, work on Arabic fake-news-based datasets and related studies is much needed to control the spread of fake news on social media and other Internet media. The current study uses a recently published dataset of Arabic fake news annotated by experts. Further, Arabic-language-based embeddings are given to machine learning (ML) classifiers, and the Arabic-language-based trained minibidirectional encoder representations from transformers (BERT) is used to obtain the sentiments of Arabic grammar and feed a deep learning (DL) classifier. The holdout validation schemes are applied to both ML classifiers and mini-BERT-based deep neural classifiers. The results show a consistent improvement in the performance of mini-BERT-based classifiers, which outperformed ML classifiers, by increasing the training data. A comparison with previous Arabic fake news detection studies is shown where results of the current study show greater improvement.

Online teaching and learning has been beneficial in facilitating learning of English as a foreign language (EFL). In online EFL learning, YouTube is one of the most utilized information and communication technology (ICT) tools because of its inherent features that make it a unique environment for learners and educators. Many interesting aspects of YouTube-based learning can be beneficial in supplementing conventional classroom methods, and, therefore, such aspects must be identified. Previous scholarly work aimed at improving YouTube learning environment was predominantly conducted manually by gathering learners’ impressions through interviews and questionnaires to analyze the differences between YouTube- and classroom-based EFL learning. However, such methods are tedious and time-consuming and can lead to results that are of less generalizable implications. User comments on YouTube channels are useful in identifying such aspects, as they present a wealth of information related to the quality of the content provided, challenges the targeted audience faces, and areas of potential improvement. Therefore, in our current study, YouTube API is used to collect the comments of three randomly selected and popular YouTube channels. Following a data cleaning process, people’s sentiments about EFL learning were first identified via a TextBlob method. Second, the automated latent semantic analysis (LSA) method of topic finding was used to collect global and open-ended topics of discussion on YouTube-based EFL learning. Users’ sentiments on the most popular topics of discussion are discussed in this paper. Further, based on the results, hypothetical findings on YouTube EFL learning are provided as recommendation for future content, including more variety of the content covered, introduction of the meanings and punctuation following words, the design of the course such that it addresses a multinational audience of any age, and targeted teaching of each variety of English, such as British and American. We also make suggestions for learners of English who wish to utilize online and offline learning, which include finding the course of interest first based on one’s needs which can be discussed with a tutor or any English teacher to optimize the learning experience, participating in fearless educator–learner interaction and engagement, and asking other EFL learners for their previous experiences with learning online in order for the learner to maximize benefit.