The quality of features is one of the main factors that affect classification performance. Feature selection aims to remove irrelevant and redundant features from data in order to increase classification accuracy. However, identifying these features is not a trivial task due to a large search space. Evolutionary algorithms have been proven to be effective in many optimization problems, including feature selection. These algorithms require an initial population to start their search mechanism, and a poor initial population may cause getting stuck in local optima. Diversifying the initial population is known as an effective approach to overcome this issue; yet, it may not suffice as the search space grows exponentially with increasing feature sizes. In this study, we propose an enhanced initial population strategy to boost the performance of the feature selection task. In our proposed method, we ensure the diversity of the initial population by partitioning the candidate solutions according to their selected number of features. In addition, we adjust the chances of features being selected into a candidate solution regarding their information gain values, which enables wise selection of features among a vast search space. We conduct extensive experiments on many benchmark datasets retrieved from UCI Machine Learning Repository. Moreover, we apply our algorithm on a real-world, large-scale dataset, i.e., Stanford Sentiment Treebank. We observe significant improvements after the comparisons with three off-the-shelf initialization strategies.

Abstract The COVID‐19 pandemic has huge effects on the global community and an extreme burden on health systems. There are more than 185 million confirmed cases and 4 million deaths as of July 2021. Besides, the exponential rise in COVID‐19 cases requires a quick prediction of the patients' severity for better treatment. In this study, we propose a Multi‐threaded Genetic feature selection algorithm combined with Extreme Learning Machines (MG‐ELM) to predict the severity level of the COVID‐19 patients. We conduct a set of experiments on a recently published real‐world dataset. We reprocess the dataset via feature construction to improve the learning performance of the algorithm. Upon comprehensive experiments, we report the most impactful features and symptoms for predicting the patients' severity level. Moreover, we investigate the effects of multi‐threaded implementation with statistical analysis. In order to verify the efficiency of MG‐ELM, we compare our results with traditional and state‐of‐the‐art techniques. The proposed algorithm outperforms other algorithms in terms of prediction accuracy.

With the advance in technology, the volume of available data grows massively. Therefore, feature selection has become an essential preprocessing step to extract valuable information. Feature selection is the task of reducing the number of features by removing redundant features from data while preserving the classification accuracy. It is a multiobjective problem as there are two objectives. In general, multiobjective selection algorithms with machine learning techniques are utilized to find the most promising feature subsets; however, classification performances of these machine learning techniques are analyzed separately. In this study, we propose a new multiobjective selection model that dynamically searches for the best ensemble of five classifiers to extract the best representative feature subsets. We present the experiment results on 12 well-known datasets. The results show that the proposed method performs significantly better than all the machine learning techniques when they are executed separately. Moreover, the proposed method outperforms two existing ensemble algorithms, namely AdaBoost and Gradient Boosting.

Human-interaction proofs (HIPs) are used to mitigate automated attacks. Security and usability have always been a critical problem for HIPs, especially when “accessibility” is a system requirement. Pure-text HIPs are more favorable from the usability perspective, but they are not secure. Audio HIPs usually cannot reliably distinguish attacks from legitimate use; they are either easy, and can be automatically solved, or hard, even for humans. In this study, we first compare the usability of a currently used pure-text HIP service, textCAPTCHA, against Google's reCAPTCHA. After analyzing the results, we propose a new HIP system (SMARTCHA). In this system, by using human computation we generate around 21 000 HIP tests. We conduct a user study among 31 visually impaired users to compare SMARTCHA against the latest version of audio reCAPTCHA HIPs. The study results show that SMARTCHA takes less time and is more enjoyable to solve, which suggests that pure-text HIPs could be a promising solution for secure, usable, and accessible HIPs.

Human-Interaction Proof (HIP) systems are widely used to prevent malicious acts of abusers. Legitimate users, however, are not satisfied with their ease of use. The response of Google to the complaints of difficulty in solving audio reCAPTCHAs was to introduce a much simpler version. But now we are back at the position where we have an accessible and usable but insecure solution. In this work, we propose a pure-text HIP system as an attempt to satisfy accessibility, security, usability requirements altogether. We conduct a user study involving 31 blind or partially sighted users which compares the usability of our pure-text HIP system (SMARTCHA) against Google's new audio reCAPTCHA. The results of the user study show that visually impaired users enjoy solving SMARTCHA more and prefer it against audio reCAPTCHA.