Search results

Computed tomography (CT) scan can provide valuable information in the diagnosis of lung diseases. To detect the location of the cancerous lung nodules, this work uses novel deep learning methods. The majority of the early investigations used CT, magnetic resonance and mammography imaging. Using appropriate procedures, the professional doctor in this sector analyses these images to discover and diagnose the various degrees of lung cancer. All of the methods used to discover and detect cancer illnesses are time-consuming, expensive and stressful for the patients. To address all of these issues, appropriate deep learning approaches for analyzing these medical images, which included CT scan images, were utilized.

Radiologists currently employ chest CT scans to detect lung cancer at an early stage. In certain situations, radiologists' perception plays a critical role in identifying lung melanoma which is incorrectly detected. Deep learning is a new, capable and influential approach for predicting medical images. In this paper, the authors employed deep transfer learning algorithms for intelligent classification of lung nodules. Convolutional neural networks (VGG16, VGG19, MobileNet and DenseNet169) are used to constrain the input and output layers of a chest CT scan image dataset.

The collection includes normal chest CT scan pictures as well as images from two kinds of lung cancer, squamous and adenocarcinoma impacted chest CT scan images. According to the confusion matrix results, the VGG16 transfer learning technique has the highest accuracy in lung cancer classification with 91.28% accuracy, followed by VGG19 with 89.39%, MobileNet with 85.60% and DenseNet169 with 83.71% accuracy, which is analyzed using Google Collaborator.

The proposed approach using VGG16 maximizes the classification accuracy when compared to VGG19, MobileNet and DenseNet169. The results are validated by computing the confusion matrix for each network type.

With the development of intelligent technology, deep learning has made significant progress and has been widely used in various fields. Deep learning is data-driven, and its training process requires a large amount of data to improve model performance. However, labeled data is expensive and not readily available.

To address the above problem, researchers have integrated semi-supervised and deep learning, using a limited number of labeled data and many unlabeled data to train models. In this paper, Generative Adversarial Networks (GANs) are analyzed as an entry point. Firstly, we discuss the current research on GANs in image super-resolution applications, including supervised, unsupervised, and semi-supervised learning approaches. Secondly, based on semi-supervised learning, different optimization methods are introduced as an example of image classification. Eventually, experimental comparisons and analyses of existing semi-supervised optimization methods based on GANs will be performed.

Following the analysis of the selected studies, we summarize the problems that existed during the research process and propose future research directions.

This paper reviews and analyzes research on generative adversarial networks for image super-resolution and classification from various learning approaches. The comparative analysis of experimental results on current semi-supervised GAN optimizations is performed to provide a reference for further research.

Photogrammetry enables scientists and engineers to make accurate and precise measurements from optical images and other patterns of reflected electromagnetic energy. Photogrammetry is taught in surveying, geomatics and similar academic programs. For a long time, it has been observed that there is a lack of diversity and underrepresentation of different groups in the surveying and geomatics workforces for various reasons. Diversity fosters more innovative environments, helps employees be more engaged and boosts productivity rates. Although efforts are being made to solve this problem, most attempts did not significantly improve the diversity issues in this field. To address this problem, we designed a new curriculum for a photogrammetry course, which integrates entrepreneurial mindset (EM), bio-inspired design and Science, Technology, Engineering, Arts and Mathematics (STEAM) into the photogrammetry course for this study.

In this study, the participatory action research method, Photovoice, was used to gather data. Students were asked to respond to photovoice and metacognitive reflection prompts to understand student perceptions about the importance of Unmanned Aerial Vehicles (UAVs) in photogrammetric mapping. Students were required to respond to each prompt with three pictures and a narrative. These reflections were analyzed using thematic analysis.

The analysis of the photovoice and metacognitive reflections resulted in six themes: promoting digital literacy, promoting job readiness and awareness, improving perceived learning outcomes, increasing interest in pursuing careers in surveying/geomatics, encouraging learner engagement and increasing awareness of the role of art in map making.

This is the first study conducted at our Hispanic Serving Institution, which specifically designed a curriculum integrating EM, bio-inspired design and STEAM concepts to address diversity issues in surveying and geomatics engineering disciplines.

This study aims to evaluate the knowledge and consumption of healthy foods, respectively, of oils as sources of omega-3 and dietary supplements with omega-3, among a population of young people in the center of Romania. With the objectives of identifying the factors that can influence the consumption of healthy fats and the orientation toward actions to promote less known food resources, in order to diversify the healthy food intake, the long-term improvement of the health-related effects of food.

One of the most important aspects of health is nutrition and its role in reducing the incidence of chronic diseases is supported by scientific data. In this research, the authors analyzed the level of information and the factors determining food choices with particular reference to the consumption of healthy fats and/or supplements from these fats, in order to highlight the behavior of individuals in relation to food. For this purpose, a questionnaire about food and healthy fats (omega-3) consumption and frequency was applied to the food groups of interest, along with other factors pertaining to lifestyle. The questionnaire distributed online mainly included questions related to the consumption of fats and the respondents' knowledge about them. The interest in participating in the study was manifested mainly in the young age segment. The collected data were analyzed statistically was done through Graph Pad Prism ver. 9 software with the establishment of a statistical significance threshold of 0.05.

There is a certain degree of superficiality in the knowledge of the importance and use of foods rich in omega-3. The statistically significant association has been identified both between age and the rules established in the family for observing the schedule of meals and between age and benefiting from an evaluation of the eating behavior. Statistically significant association has also been observed between the level of education and the knowledge on the health benefits of vegetable oils. The statistically significant association was also present between the level of education and the respondents' appreciation of the essential role of eating behavior in disease prevention.

Identifying the consumer profile in relation to their attitude toward healthy foods, especially fats, in order to adapt nutritional interventions with the aim to promote healthy food choices that have an impact on the health of the individual and also of the population.

This paper aims to realize an in-situ quality inspection system rapidly for new injection molding (IM) tasks via transfer learning (TL) approach and automation technology.

The proposed in-situ quality inspection system consists of an injection machine, USB camera, programmable logic controller and personal computer, interconnected via OPC or USB communication interfaces. This configuration enables seamless automation of the IM process, real-time quality inspection and automated decision-making. In addition, a MobileNet-based deep learning (DL) model is proposed for quality inspection of injection parts, fine-tuned using the TL approach.

Using the TL approach, the MobileNet-based DL model demonstrates exceptional performance, achieving validation accuracy of 99.1% with the utilization of merely 50 images per category. Its detection speed and accuracy surpass those of DenseNet121-based, VGG16-based, ResNet50-based and Xception-based convolutional neural networks. Further evaluation using a random data set of 120 images, as assessed through the confusion matrix, attests to an accuracy rate of 96.67%.

The proposed MobileNet-based DL model achieves higher accuracy with less resource consumption using the TL approach. It is integrated with automation technologies to build the in-situ quality inspection system of injection parts, which improves the cost-efficiency by facilitating the acquisition and labeling of task-specific images, enabling automatic defect detection and decision-making online, thus holding profound significance for the IM industry and its pursuit of enhanced quality inspection measures.

This chapter critically explores the colonial model of education in a Buddhist society in postcolonial Bangladesh, as the Buddhist value-based contemplative learning and ethical practices have been constantly challenged due to the fact that the western value-based cultural knowledge is considered for economic development. In such a context, Buddhist learners are unable to learn the social history, cultural heritage, Buddhist/social economy, and spiritual values and practices in the educational institutions. Even teachers are not trained in preparing learners for cultivation of wisdom (Paññā in Pāli) and ecocentric development of the community in the country. On the other hand, Buddhist notion of contemplative learning pedagogy believes in decolonization of the mind and reflective practice for social transformation and development of wisdom through deep meditative mind by nurturing critical dialogue as opposed to capital accumulation and greed-based society. The Buddhist pedagogical approach focuses on mindful concentration (bhavana) and ethical (sila) practice within the learning context and environment, as emancipatory ideology to promote cultural diversity instead of political and social imposition. Such mindfulness would allow both the learners and teachers to create collaborative learning opportunities for life-sustaining practice and wholesome (kusala karma) activity in the community setting. The Buddhist learning pedagogy tends to nurture nonviolence (ahimsa) in order to develop mutual respect among the diverse communities to renewing ground for mind-expanding pursuits in the learning institutions for the wellbeing of all community members in the country.

This exploratory study aims to discover the different forms of challenges encountered by school stakeholders, including students, teachers, parents and management due to the coronavirus disease 2019 (COVID-19) pandemic.

Qualitative methodology was deployed for the study. A purposive sampling technique was used to select the respondents for a semi-structured interview. Data were examined using interpretative phenomenological analysis (IPA).

It was found that each stakeholder faced four different challenges: mental distress, physical immobility, financial crunches and technological concerns. Findings suggest that teachers are experiencing higher financial, technological and physical challenges as compared to other stakeholders followed by parents.

This paper discusses the major challenges faced by each stakeholder along with the opportunities. These findings will be useful for educationists, regulatory authorities, policymakers and management of educational institutions in developing countries to revisit their policy frameworks to develop new strategies and processes for the smooth implementation of remote learning during a period of uncertainty.

The purpose of this paper is to analyze the effects of scaling on the impact ionization and subthreshold current in submicron MOSFETs.

The effects of the various scaling techniques on a 100 nm device performances and the dependence of subthreshold current parameters on applied scaling technique are analyzed.

The results show that as the channel length is scaled down, multiplication factor increases slowly in the higher regime and rises rapidly in the lower regime of channel length. This result also justifies the inclusion of impact‐ionization effect on subthreshold current. The analysis shows that there is insignificant dependence of multiplication factor on the method of scaling. Similar variations in subthreshold current with channel length scaling have been observed in the analytical results for different scaling techniques.

The paper offers insight into the challenges of MOSFET scaling.

This chapter focuses on unearthing the metaverse technology impacts on banking services, both the underlying opportunities it brings and the challenges it imposes, along with its long-term effects on the industry. The tremendous strides made in the field of technology have impacted every industry, and banking is no different. Metaverse technology further catapults banking services into an unknown realm of possibilities and challenges since the advent of modern technology. Metaverse technology is an upcoming virtual interconnected universe where users can connect with each other and digital entities at the same time in real time. Banking will open up a lot of avenues to redefine customer experience, build new financial products and make the customers sticky. Deploying metaverse technology in a banking system comes with a whole host of challenges, including technical complexity, security, privacy and compliance. More insights on the dos and don'ts of this as well as what to measure in terms of success would be found by looking at cases from those banks that have successfully rolled out metaverse technology. So, for banks to come out of their shells and sustain themselves in a competitive world of financial services, understanding metaverse technology in banking is essential. This chapter attempts to uncover the subtlety of metaverse technology on banking services, their promise and perils and the consequences that may stick with this industry forever.