Multi-Attentional U-Net for Medical Image Segmentation

Deep learning (DL) approaches for image segmentation have been gaining state-of-the-art performance in recent years. Particularly, in deep learning, U-Net model has been successfully used in the field of image segmentation. However, traditional U-Net methods extract features, aggregate remote information, and reconstruct images by stacking convolution, pooling, and up sampling blocks. The traditional approach is very inefficient due of the stacked local operators. In this paper, we propose the multi-attentional U-Net that is equipped with non-local blocks based self-attention, channel-attention, and spatial-attention for image segmentation. These blocks can be inserted into U-Net to flexibly aggregate information on the plane and spatial scales. We perform and evaluate the multi-attentional U-Net model on three benchmark data sets, which are COVID-19 segmentation, skin cancer segmentation, thyroid nodules segmentation. Results show that our proposed models achieve better performances with faster computation and fewer parameters. The multi-attention U-Net can improve the medical image segmentation results. © 2022 IEEE.

Analyzing the effects of COVID-19 pandemic on supplier performance evaluation factors via fuzzy cognitive map with a hybrid learning system

PurposeThe COVID-19 pandemic has proven that how supply chain management (SCM) can become a crucial process for sustainability of the world's production/service. The global supply chain crisis during pandemic has affected most of the sectors. Home and personal care products manufacturers are among them. In this study (1) the problems at SCM of personal and home care products manufacturers during pandemic are discussed with the help of medium-size manufacturer and (2) the factors affecting suppliers' performance for the relevant sector during COVID-19 are analyzed comprehensively.Design/methodology/approachThe importance of the factors is evaluated using fuzzy cognitive maps that can help to reveal hidden casual relationships with the help of expert knowledge. In order to eliminate subjectivity due to usage of expert knowledge, the maps are trained with a hybrid learning approach that consists of Non-linear Learning and Extended Great Deluge Algorithms to increase robustness of the analysis.FindingsThe findings of the study indicate that the factors such as general quality level of products/services, compliance to delivery time, communication skills and total production capacity of suppliers have been crucial factors during pandemic.Originality/valueWhile the implementation of the hybrid learning approach on supply chain can fill the gap in the relevant literature, the promising results of the study can prove the convenience of the methodology to model the of complex systems like supply chain processes.

A Cross-Corpus Deep Learning Approach to Social Media Emotion Classification

Emotion Detection refers to the identification of emotions from contextual data in the form of written text, such as comments, posts, reviews, publications, articles, recommendations, conversations, and so on. Because of the Internet's exponential uptake and the recent coronavirus outbreak, social media platforms have become a crucial means of sharing thoughts and ideas throughout the entire globe, creating rapid data growth through users' contributions on various platforms. The necessity to acquire knowledge of their behaviors is a matter of great concern for both internet safety and privacy. In this study, we categorize emotional sentiments using deep learning models along with hybrid approaches such as LSTM, Bi-LSTM, and CNN+LSTM. When compared to existing state-of-the-art methods, the experiments showed that the suggested strategy is more robust and achieves an expressively higher quality of emotion detection with an accuracy rate of 94.16%, including strong F1-scores on complex and difficult emotion categories such as Fear (93.85%) and Anger (94.66%) through CNN+LSTM. © 2022 IEEE.

A Deep Learning Approach for Sentiment Classification of COVID-19 Vaccination Tweets

Now-a-days, social media platforms enable people to continuously express their opinions and thoughts about different topics. Monitoring and analyzing the sentiments of people is essential for governments and business organizations to better understand people's feelings and thoughts. The Coronavirus disease 2019 (COVID-19) has been one of the most trending topics on social media over the last two years. Consequently, one of the preventative measures to control and prevent the spread of the virus was vaccination. A dataset was formed by collecting tweets from Twitter for over a month from November 13th to December 31st, 2021. After data cleaning, the tweets were assigned a positive, negative, or neutral label using a natural language processing (NLP) sentiment analysis tool. This study aims to analyze people's public opinion towards the vaccination process against COVID-19. To fulfil this goal, an ensemble model based on deep learning (LSTM-2BiGRU) is proposed that combines long short-term memory (LSTM) and bidirectional gated recurrent unit (BiGRU). The performance of the proposed model is compared to five traditional machine learning models, two deep learning models in addition to state-of-the-art models. By comparing the results of the models used in this study, the results reveal that the proposed model outperforms all the machine and deep learning models employed in this work with a 92.46% accuracy score. This study also shows that the number of tweets that involve neutral, positive, and negative sentiments is 517496 (37%) tweets, 484258 (34%) tweets, and 409570 (29%) tweets, respectively. The findings indicate that the number of people carrying neutral sentiments towards COVID-19 immunization through vaccines is the highest among others. © 2023, International Journal of Advanced Computer Science and Applications. All Rights Reserved.

A DEEP LEARNING APPROACH LUNG SEGMENTATION AND PNEUMONIA DETECTION FROM X-RAYS

Lung segmentation is a process of detection and identification of lung cancer and pneumonia with the help of image processing techniques. Deep learning algorithms can be incorporated to build the computer-aided diagnosis (CAD) system for detecting or recognizing broad objects like acute respiratory distress syndrome (ARDS), Tuberculosis, Pneumonia, Lung cancer, Covid, and several other respiratory diseases. This paper presents pneumonia detection from lung segmentation using deep learning methods on chest radiography. Chest X-ray is the most useful technique among other existing techniques, due to its lesser cost. The main drawback of a chest x-ray is that it cannot detect all problems in the chest. Thus, implementing convolutional neural networks (CNN) to perform lung segmentation and to obtain correct results. The 'lost' regions of the lungs are reconstructed by an automatic segmentation method from raw images of chest X-ray. © 2022 IEEE.

A systematic review of programmed learning approach in science education

Natural science subjects have always been the most challenging for students in schools and universities. While the pandemic brought about a lot of new challenges, it also gave academics the chance to test out evaluation methodologies they had previously thought about but hadn't used in a relatively low-risk setting. The programmed learning approach is a teaching and learning pedagogy that creates better learning experiences. Therefore, this systematic literature review focuses on the impact of programmed instruction on the learning process. The analysis was made based on the PRISMA review methodology. Five databases were searched to find 33 articles about the benefits of programmed instruction in science education published between 1970 and 2022. In terms of research participants, the majority of the studies (14 studies) focused on undergraduate students, college students (5 studies), lecturers/teachers (3 studies), mixed (2 studies), and adults (1 study). Our systematic review found the following benefits of programmed learning: effective and fun teaching approaches, proven favourable impacts on behaviour change, increased scores for college and secondary school students, and raised students' interest.

Automated COVID-19 screening framework via Deep Convolutional Neural Network with Chest X-ray Medical Images

COVID-19 screening using chest X-rays plays a significant role in the early diagnosis of COVID-19 illness during the ongoing pandemic. Manually identifying this infection from chest X-ray films is a challenging and time-consuming technique due to time restrictions and the competence of radiologists. Also, the manual Covid-19 identification technique is made much more difficult and opaquer by the feature similarity between positive and negative chest X-ray images. Therefore, we propose an automated COVID-19 screening framework that utilizes artificial intelligence techniques with a transfer learning approach for COVID-19 diagnosis using chest X-ray images. Specifically, we employ the transfer learning concept for feature extraction before further processing with modified deep neural networks. Also, Grad-CAM visualization is used for our case study to support the predicted diagnosis. The results of the experiments on the publicly accessible dataset show that the convolutional neural network model, which is simple yet effective, performs significantly better than other deep learning techniques across all metrics, including accuracy, precision, recall, and F-measure. © 2022 IEEE.

Study of Deep Learning Approaches for Diagnosing Covid-19 Disease using Chest CT Images

Since March 2020, the World Health Organization (WHO) has declared COVID-19 a pandemic. An evolving viral infection with respiratory tropism causes atypical pneumonia. Experts believe that detecting COVID-19 early stage is crucial. Early diagnosis and tracking techniques have become increasingly important to ensure an accelerated treatment process and avoid virus spread. Images from Computed Tomography (CT) scans can provide quick and precise COVID-19 screening. A subdivision of Machine Learning (ML) called Deep Learning (DL) can improve diagnostic accuracy and speed by automating screening via medical imaging in collaborative efforts with radiologists and physicians This study aims to investigate the recently popularized and extensively discussed deep learning algorithms for COVID-19 diagnosis in connection to the sequence phases involved in image processing. Getting rid of the noise in these images requires some preprocessing. Histogram equalization, fuzzy histogram equalisation, Adaptive Histogram Equalization (AHE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) are used to improve the image quality and therefore increase the identification of the image. Afterwards, necessary features for disease detection are segmented using various deep models like U-Net, U-Net + FPN (Feature Pyramid Network), COVID-SegNet and Dense GAN. Once these distinct deep characteristics have been identified, they are extracted using a variety of different deep models. Finally, an illness is diagnosed using popular models such as SVM, ResNet-50, AlexNet, VGG16, DenseNet, and SqueezeNet. The deep learning models with a better optimization algorithm to be effective in the diagnosis of COVID-19 and also obtain a reduced and efficient feature set for image classification and feature extraction. © 2023 IEEE.

DuaNet: A Novel Lightweight CNN Model for Classifying Five-class Lung Diseases

Lung diseases rank among the world's top killers and disablers. Therefore, early identification is crucial for improving long-term survival rates and boosting the chances of recovery. Unlike the traditional method, machine learning (ML) showed great success in the medical field, mainly detecting and diagnosing different diseases. Most recently, the deep learning approach enhanced classification accuracy and eliminated the difficulty of manual feature extraction. As a literature conclusion, the model performance accuracy is inversely proportional to the number of lung diseases under consideration. In addition, no more than four classes (including normal) were considered previously. This work developed a lightweight CNN model, identified as DuaNet, with higher accuracy than the up-to-the-date models. The dataset has 930 X-ray images, categorized into five-class lung diseases: normal, tuberculosis, pneumonia COVID-19, pneumonia viral, and pneumonia bacterial. DuaNet comprises fifteen layers involving input, seven convolutional blocks, three max-pooling, three fully connected, and one output (Softmax) layer. Each convolutional block consists of a convolutional layer, Batch normalization, and ReLU activation function. The final model (DuaNet) obtained a performance accuracy of 99.87%, with 100% for other metrics. © 2022 IEEE.

NFNets-CNN for Classification of COVID-19 from CT Scan Images

Coronavirus disease (COVID-19) is an infectious disease caused by the coronavirus was first found in Wuhan, China in December 2019. It has infected more than 300 million people with more than 5 million of death cases. Until now, the virus is still evolving producing new variants of concern contributes to the increase the infection rate around the world. Thus, various diagnostic procedures are in need to help physicians in diagnosis disease certainly and rapidly. In this study, deep learning approach is used to classify normal and COVID-19 cases from CT scan images. Normalizer Free CNN network (NFNets) model is implemented on the images. Statistical measures such as accuracy, precision, sensitivity (also known as recall) are used to evaluate the performance of the model against the previous studies. Loss of 0.0842, accuracy of 0.7227, precision of 0.9751 and recall of 0.9727 are achieved. Thus, further optimization on the NFNets learning algorithm is required to improve the classification performanceClinical Relevance-Implementation of deep learning technique to automate diagnosis of diseases such as COVID-19 cases from CT scan images will simplify the clinical flow towards providing reliable intelligent aids for patient care. © 2022 IEEE.

Federated Learning for Detecting COVID-19 in Chest CT Images: A Lightweight Federated Learning Approach

The novel coronavirus is spreading rapidly worldwide, and finding an effective and rapid diagnostic method is apriority. Medical data involves patient privacy, and the centralized collection of large amounts of medical data is impossible. Federated learning is a privacy-preserving machine learning paradigm that can be well applied to smart healthcare by coordinating multiple hospitals to perform deep learning training without transmitting data. This paper demonstrates the feasibility of a federated learning approach for detecting COVID-19 through chest CT images. We propose a lightweight federated learning method that normalizes the local training process by globally averaged feature vectors. In the federated training process, the models' parameters do not need to be transmitted, and the local client only uploads the average of the feature vectors of each class. Clients can choose different local models according to their computing capabilities. We performed a comprehensive evaluation using various deep-learning models on COVID-19 chest CT images. The results show that our approach can effectively reduce the communication load of federated learning while having high accuracy for detecting COVID-19 on chest CT images. © 2022 IEEE.

Toward a Transfer Learning Approach to Detect Face Mask Type in Real-time

Face masks are considered protective equipment that has the ability to safeguard humans from vulnerable situations. Although there exists a wide range of masks specifically designed for diverse purposes, there is a terrible lack of concern regarding proper usage. Consequently, the generalization of their usage can cause many life-threatening problems. As a result, a system that can detect the type of face mask can play a life-saving role to ensure the proper usage of these safety gear. With this aim, a custom dataset was built by manually labeling face mask images which include 8 classes. Scratch CNN and four transfer learning models have been implemented and their performance was thoroughly evaluated and assessed on multiple criteria to select the best one. Based on the investigation, it is found that SSD MobNet V2 achieved the highest accuracy of 83%. The developed system takes real-time video stream input from the camera and can detect the type of mask in different conditions. © 2023 IEEE.

A Deep Learning Approach for Hand Gestures Recognition

Hand gestures are part of communication tools that allows people to express their ideas and feelings. Those gestures can be used to insure a communication not only between people but also to replace traditional devices in human-machine interaction (HCI). This last leads us to use this technology in the E-learning domain. COVID'19 pandemic has attest the importance of E-learning. However, the Practical Activities (PA), as an important part of the learning process, are absent in the majority of E-learning plateforms. Therefore, this paper proposes a convolution neural network (CNN) method to ensure the detection of the hand gestures so the user can control and manipulate the virtual objects in the PA environment using a simple camera. To achieve this goal two datasets have been merged. Also the skin model and background subtraction were applied to obtain a performed training and testing datasets for the CNN. Experimental evaluation shows an accuracy rate of 97,2.%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Attention-Based Deep Learning Approach for Semantic Analysis of Chest X-Ray Images Modality

The world today is suffering from a huge pandemic COVID-19 that has infected 106M people around the globe causing 2.33M deaths, as of February 9, 2021. To control the disease from spreading more and to provide accurate healthcare to existing patients, detection of COVID-19 at an early stage is important. As per the World Health Organization, diagnosing pneumonia is a common way of detecting COVID-19. In many situations, a chest X-ray is used to determine the type of pneumonia. However, writing a report for every chest X-ray becomes a tedious and time-taking task for physicians. We propose a novel method of creating reports from chest X-rays images automatically via a deep learning model using image captioning with an attention mechanism employed through CNN–LSTM architecture. On comparing the model that does not use an attention mechanism with our approach, we found that accuracy was increased from 80% to 87.5%. In conclusion, we found that results generated with attention mechanism are better, and the report thus produced can be utilized by doctors and researchers worldwide to analyze new X-rays in lesser time. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Ensemble Learning Approach for Predicting Job Satisfaction on Freelancing Jobs in Sri Lanka

Due to the recent social and economic problems that have occurred locally and globally, Freelance work has gained more attention recently. Specially, working from home or other appropriate workspaces has become more popular during the Covid-19 pandemic situation. Freelancing is a profession worker working for themselves who can perform contract work or tasks either full-or part-time in a range of job fields. to get more accurate Because of the infrastructure facilities like internet, and the situations like pandemic, it is now possible to earn money online. Online freelancing assigns straightforward jobs to workers via online platforms with greater cost effectiveness. The main objective of this study is to build a model through Machine Learning (ML) to predict job satisfaction in freelancing jobs. Primary data used in this research is gathered with help of current freelancers results. After the pre-processing is completed, individual algorithms Naïve Bayes, Support Vector Machine (SVM), Decision Tree (J48), Random Forest, and Multilayer Perception (MLP) separate algorithms and Ensemble Learning approach used as a combination of the above five algorithms. Among them, the best accuracy, precision, recall, and f-measure values as well as lower error rates were obtained through the Ensemble Learning algorithm. The evaluation result proved the effectiveness of our proposed approach. © 2022 IEEE.

Deep Learning Approach for Loneliness Identification from Speech using DNN-LSTM

Perceived loneliness and social isolation have been on the rise over the past decade, especially in countries with rapidly ageing populations and, most notably, as a result of the stress of dealing with the COVID-19 outbreak over the past two years. By using a natural language processing (NLP) approach to quantify sentiment and variables that signal loneliness in transcribed spoken text of older persons, this paper investigates the use of deep learning technology in the evaluation of interviews on loneliness. We conducted loneliness state detection using Deep Neural Network (DNN) and Long Short-Term Memory (LSTM). Participants who were lonely and those who weren't were compared (using both qualitative and quantitative measures). Individuals who were lonelier (as determined by qualitative measures) took longer to respond to questions about their loneliness and expressed more grief in their answers. When asked about loneliness, more women than men admitted it during the qualitative interview. When responding, men were more likely to utilize expressions of dread and happiness. When trained on textual data, DNN models were 100% accurate at predicting qualitative loneliness and LSTM models were 75.42% accurate at predicting loneliness on textual data. © 2022 IEEE.

Diagnosis of Pulmonary Diseases from Chest X-ray Using Deep Learning Approaches

In recent years, a severe pandemic has struck worldwide with the utmost shutter, enforcing a lot of stress in the medical industry. Moreover, the increasing population has brought to light that the work bestowed upon the healthcare specialists needs to be reduced. Medical images like chest X-rays are of utmost importance for the diagnosis of diseases such as pneumonia, COVID-19, thorax, and many more. Various manual image analysis techniques are time-consuming and not always efficient. Deep learning models for neural networks are capable of finding hidden patterns, assisting the experts in specified fields. Therefore, collaborating these medical images with deep learning techniques has paved the path for enormous applications leading to the reduction of pressure embarked upon the health industry. This paper demonstrates an approach for automatic lung diagnosing of COVID-19 (coronavirus) and thorax diseases from given CXR images, using deep learning techniques. The previously proposed model uses the concept of ResNet-18, ResNet-50, and Xception algorithms. This model gives the highest accuracy of 98% without segmentation and 95% with segmentation. Whereas, the proposed model uses CNN and CLAHE algorithms which achieves an accuracy of 99.22% without segmentation and 98.39% with segmentation. Therefore, this model will be able to provide assistance to health workforces and minimize manual errors precisely. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Challenges of Hybrid Flexible (HyFlex) Learning on the Example of a University of Applied Sciences

Due to the global coronavirus pandemic, it became increasingly necessary to rearrange the teaching process at all school levels. Higher education institutions all over the world have been facing the challenge since 2020, to find blended teaching formats and activities to provide higher education without compromising the quality of education, but at the same time mitigating health risks. This article deals with the HyFlex learning model. The aim of this paper is to identify problems that may arise when implementing HyFlex teaching and learning in higher education. Identifying problems also provides an opportunity to offer solutions to these problems and to introduce possible solutions more widely. In order to answer the research question an online survey was conducted in spring 2021 (n = 570). The survey consisted of both closed and open questions. The fact that Estonia was one of those countries, where periods of F2F classes during the first and second waves of the COVID-19 pandemic were possible, speaks in favor of conducting the research in Estonia. In conclusion, most of the students (75%) participating in the survey were rather positive, rating the learning experience to be good or even excellent. However, some problems were pointed out too: difficulties in concentrating, decrease of learning motivation/self-discipline, lack of depth in learning, and insufficient self-directed learning skills;followed by communication barriers and problems related to digital competencies and skills for both teachers and students. Based on the above, almost a quarter of the respondents found that the volume of learning increased. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Privacy-Preserving Federated Learning in Healthcare

Federated learning (FL) has received great attention in healthcare primarily due to its decentralized, collaborative nature of building a machine learning (ML) model. Over the years, the FL approach has been successfully applied for enhancing privacy preservation in medical ML applications. This study aims to review prevailing applications in healthcare for the future landing FL application. We identified the emerging applications of FL in key healthcare domains, including COVID-19, brain tumor segmentation, mammogram, sleep quality prediction, and smart healthcare system. Finally, we discuss privacy concerns in federated setting and provide current methods to increase the data privacy capabilities of FL. © 2023 IEEE.

Digital Global Classroom, a Collaborative Online International Learning (COIL) Approach: An Innovative Pedagogical Strategy for Sustainable Competency Development and Dissemination of SDGs in Engineering Higher Education

One of the most popular strategies to develop skills such as collaborative work, critical thinking, and problem-solving is the application of Collaborative Online International Learning (COIL), in which Professors from at least two universities from different countries and cultures develop a period known as "Global Classroom” (GC) in which, through the Challenge-Based Learning (CBL) approach, they solve a real challenge, using digital communication tools. This study held four-week global courses between groups from the Tecnológico de Monterrey in Mexico and groups from the Corporación Universitaria Minuto de Dios in Colombia. The challenges were related to two fundamental issues in sustainability: 1) Management of natural resources and climate change and 2) Biomimetics. Students were able to solve the challenges, develop skills to communicate effectively through online interaction with people from different cultures and disciplines, and use technological tools that facilitate distance learning in multicultural virtual environments. Current teaching models involve active and experiential learning, developing soft and hard skills. The GC experience is a tool that allowed continuity in the preparation of students during the COVID-19 pandemic. The use of GC is available to those interested as a valuable tool to provide students with the opportunity to live sustainable international experiences and promote the Sustainable Development Goals (SDG). © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.