Augmenting Radiological Diagnostics with AI for Tuberculosis and COVID-19 Disease Detection: Deep Learning Detection of Chest Radiographs.

In this research, we introduce a network that can identify pneumonia, COVID-19, and tuberculosis using X-ray images of patients' chests. The study emphasizes tuberculosis, COVID-19, and healthy lung conditions, discussing how advanced neural networks, like VGG16 and ResNet50, can improve the detection of lung issues from images. To prepare the images for the model's input requirements, we enhanced them through data augmentation techniques for training purposes. We evaluated the model's performance by analyzing the precision, recall, and F1 scores across training, validation, and testing datasets. The results show that the ResNet50 model outperformed VGG16 with accuracy and resilience. It displayed superior ROC AUC values in both validation and test scenarios. Particularly impressive were ResNet50's precision and recall rates, nearing 0.99 for all conditions in the test set. On the hand, VGG16 also performed well during testing-detecting tuberculosis with a precision of 0.99 and a recall of 0.93. Our study highlights the performance of our deep learning method by showcasing the effectiveness of ResNet50 over traditional approaches like VGG16. This progress utilizes methods to enhance classification accuracy by augmenting data and balancing them. This positions our approach as an advancement in using state-of-the-art deep learning applications in imaging. By enhancing the accuracy and reliability of diagnosing ailments such as COVID-19 and tuberculosis, our models have the potential to transform care and treatment strategies, highlighting their role in clinical diagnostics.

AI-Driven Real-Time Classification of ECG Signals for Cardiac Monitoring Using i-AlexNet Architecture.

The healthcare industry has evolved with the advent of artificial intelligence (AI), which uses advanced computational methods and algorithms, leading to quicker inspection, forecasting, evaluation and treatment. In the context of healthcare, artificial intelligence (AI) uses sophisticated computational methods to evaluate, decipher and draw conclusions from patient data. AI has the potential to revolutionize the healthcare industry in several ways, including better managerial effectiveness, individualized treatment regimens and diagnostic improvements. In this research, the ECG signals are preprocessed for noise elimination and heartbeat segmentation. Multi-feature extraction is employed to extract features from preprocessed data, and an optimization technique is used to choose the most feasible features. The i-AlexNet classifier, which is an improved version of the AlexNet model, is used to classify between normal and anomalous signals. For experimental evaluation, the proposed approach is applied to PTB and MIT_BIH databases, and it is observed that the suggested method achieves a higher accuracy of 98.8% compared to other works in the literature.

Wearable Sensor Data Classification for Identifying Missing Transmission Sequence Using Tree Learning.

Wearable Sensor (WS) data accumulation and transmission are vital in analyzing the health status of patients and elderly people remotely. Through specific time intervals, the continuous observation sequences provide a precise diagnosis result. This sequence is however interrupted due to abnormal events or sensor or communicating device failures or even overlapping sensing intervals. Therefore, considering the significance of continuous data gathering and transmission sequence for WS, this article introduces a Concerted Sensor Data Transmission Scheme (CSDTS). This scheme endorses aggregation and transmission that aims at generating continuous data sequences. The aggregation is performed considering the overlapping and non-overlapping intervals from the WS sensing process. Such concerted data aggregation generates fewer chances of missing data. In the transmission process, allocated first-come-first-serve-based sequential communication is pursued. In the transmission scheme, a pre-verification of continuous or discrete (missing) transmission sequences is performed using classification tree learning. In the learning process, the accumulation and transmission interval synchronization and sensor data density are matched for preventing pre-transmission losses. The discrete classified sequences are thwarted from the communication sequence and are transmitted post the alternate WS data accumulation. This transmission type prevents sensor data loss and reduces prolonged wait times.

A Novel Approach for Multichannel Epileptic Seizure Classification Based on Internet of Things Framework Using Critical Spectral Verge Feature Derived from Flower Pollination Algorithm.

A novel approach for multichannel epilepsy seizure classification which will help to automatically locate seizure activity present in the focal brain region was proposed. This paper suggested an Internet of Things (IoT) framework based on a smart phone by utilizing a novel feature termed multiresolution critical spectral verge (MCSV), based on frequency-derived information for epileptic seizure classification which was optimized using a flower pollination algorithm (FPA). A wireless sensor technology (WSN) was utilized to record the electroencephalography (EEG) signal of epileptic patients. Next, the EEG signal was pre-processed utilizing a multiresolution-based adaptive filtering (MRAF) method. Then, the maximal frequency point at which the power spectral density (PSD) of each EEG segment was greater than the average spectral power of the corresponding frequency band was computed. This point was further optimized to extract a point termed as critical spectral verge (CSV) to extract the exact high frequency oscillations representing the actual seizure activity present in the EEG signal. Next, a support vector machine (SVM) classifier was used for channel-wise classification of the seizure and non-seizure regions using CSV as a feature. This process of classification using the CSV feature extracted from the MRAF output is referred to as the MCSV approach. As a final step, cloud-based services were employed to analyze the EEG information from the subject's smart phone. An exhaustive analysis was undertaken to assess the performance of the MCSV approach for two datasets. The presented approach showed an improved performance with a 93.83% average sensitivity, a 97.94% average specificity, a 97.38% average accuracy with the SVM classifier, and a 95.89% average detection rate as compared with other state-of-the-art studies such as deep learning. The methods presented in the literature were unable to precisely localize the origination of the seizure activity in the brain region and reported a low seizure detection rate. This work introduced an optimized CSV feature which was effectively used for multichannel seizure classification and localization of seizure origination. The proposed MCSV approach will help diagnose epileptic behavior from multichannel EEG signals which will be extremely useful for neuro-experts to analyze seizure details from different regions of the brain.

Effect of social media use on learning, social interactions, and sleep duration among university students.

BACKGROUND: Social networking sites are widely used by university students. This study investigated the purposes for which social networking sites are used and their effects on learning, social interaction, and sleep duration. MATERIAL AND METHODS: A cross-sectional study was conducted among 300, 17-29-year-old female students at Prince Sattam bin Abdul Aziz University. A questionnaire was used to collect data. Chi-squared (Fisher's exact test) test was used to analyze the data. RESULTS: The results showed that 97% of the students used social media applications. Only 1% of them used social media for academic purposes. Whereas 35% of them used these platforms to chat with others, 43% of them browsed these sites to pass time. Moreover, 57% of them were addicted to social media. Additionally, 52% of them reported that social media use had affected their learning activities, 66% of them felt more drawn toward social media than toward academic activities, and 74% of them spent their free time on social media platforms. The most popular applications (i.e., based on usage) were Snapchat (45%), Instagram (22%), Twitter (18%), and WhatsApp (7%). Further, 46% and 39% of them reported going to bed between 11 pm and 12 am and between 1 am and 2 am, respectively. Finally, 68% of them attributed their delayed bedtime to social media use, and 59% of them reported that social media had affected their social interactions. CONCLUSIONS: A majority of the participants reported prolonged use of social networking sites for nonacademic purposes. These habitual behaviors can distract students from their academic work, adversely affect their academic performance, social interactions, and sleep duration, and lead to a sedentary lifestyle and physical inactivity, which in turn can render them vulnerable to non-communicable diseases and mental health problems.

University learning with anti-plagiarism systems.

We have designed an anti-plagiarism software to detect plagiarism in students' assignments, especially written assignments, homework, and research reports, which will hereinafter be collectively referred to as student work. We used our university network to gather student work to detect plagiarism. . To collect data, we used a domain name system to store the student work data based on the respective location, time, and the subject on which each student was assigned work. Once the student work data were collected, they were sent to an extraction module to remove unwanted data. The remaining data were then fed to a similarity index module, which produced similarity values based on comparisons between the collected data and the student work. This module uses mathematical equations that are built using semantic and syntactic similarity reports. Furthermore, in this study, we recommended procedures that can be applied to avoid plagiarism using the programming approach. This approach can raise awareness of plagiarism among students and encourage them to generate innovative ideas instead of plagiarizing. To attract faculty members to use the software, promotional materials can be customized based on the actual control factors that directly affect their adoption of the software. For example, the campaign should provide information highlighting the ease of implementation of the software for senior faculty members.

A Three Layered Decentralized IoT Biometric Architecture for City Lockdown During COVID-19 Outbreak.

In this article, we have built a prototype of a decentralized IoT based biometric face detection framework for cities that are under lockdown during COVID-19 outbreaks. To impose restrictions on public movements, we have utilized face detection using three-layered edge computing architecture. We have built a deep learning framework of multi-task cascading to recognize the face. For the face detection proposal we have compared with the state of the art methods on various benchmarking dataset such as FDDB and WIDER FACE. Furthermore, we have also conducted various experiments on latency and face detection load on three-layer and cloud computing architectures. It shows that our proposal has an edge over cloud computing architecture.

A Proposal to Detect the Double Submission of a Manuscript Sent for Review.

Along with the rapid growth of editorial systems and publishers, the number of research articles is increasing, which creates a need for an effective dissemination strategy. Researchers commonly use editorial systems in a candid manner. However, when researchers concurrently submit the same contribution in more than one editorial system, it is considered unethical. In this paper, we propose a novel approach called DeMSum for detecting such duplicate submissions. DeMSum verifies a manuscript (MS) by processing the MS attributes that are accessed through the editorial system. To the best of our knowledge, DeMSum is the first system to address the double submission issue, thus enabling the use of diverse editorial systems for MS review. We implemented a prototype, and our evaluation of the prototype produced excellent results.

E-commerce Review System to Detect False Reviews.

E-commerce sites have been doing profitable business since their induction in high-speed and secured networks. Moreover, they continue to influence consumers through various methods. One of the most effective methods is the e-commerce review rating system, in which consumers provide review ratings for the products used. However, almost all e-commerce review rating systems are unable to provide cumulative review ratings. Furthermore, review ratings are influenced by positive and negative malicious feedback ratings, collectively called false reviews. In this paper, we proposed an e-commerce review system framework developed using the cumulative sum method to detect and remove malicious review ratings.

An Online Lab Examination Management System (OLEMS) to Avoid Malpractice.

Examination and evaluation are two important phases of education at any level of a student's curriculum. However, these assessment processes are problematic in the sense that they encourage learners to devise ways to be dishonest. The traditional way of conducting exams is particularly conducive to dishonesty. In view of this, this letter proposes an online lab examination management system to prevent misconduct and to secure the process of lab examination.