Traditional Learning Approaches Research Articles

Classification of Twitter Vaping Discourse Using BERTweet: Comparative Deep Learning Study.

BackgroundTwitter provides a valuable platform for the surveillance and monitoring of public health topics; however, manually categorizing large quantities of Twitter data is labor intensive and presents barriers to identify major trends and sentiments. Additionally, while machine and deep learning approaches have been proposed with high accuracy, they require large, annotated data sets. Public pretrained deep learning classification models, such as BERTweet, produce higher-quality models while using smaller annotated training sets.ObjectiveThis study aims to derive and evaluate a pretrained deep learning model based on BERTweet that can identify tweets relevant to vaping, tweets (related to vaping) of commercial nature, and tweets with provape sentiment. Additionally, the performance of the BERTweet classifier will be compared against a long short-term memory (LSTM) model to show the improvements a pretrained model has over traditional deep learning approaches.MethodsTwitter data were collected from August to October 2019 using vaping-related search terms. From this set, a random subsample of 2401 English tweets was manually annotated for relevance (vaping related or not), commercial nature (commercial or not), and sentiment (positive, negative, or neutral). Using the annotated data, 3 separate classifiers were built using BERTweet with the default parameters defined by the Simple Transformer application programming interface (API). Each model was trained for 20 iterations and evaluated with a random split of the annotated tweets, reserving 10% (n=165) of tweets for evaluations.ResultsThe relevance, commercial, and sentiment classifiers achieved an area under the receiver operating characteristic curve (AUROC) of 94.5%, 99.3%, and 81.7%, respectively. Additionally, the weighted F1 scores of each were 97.6%, 99.0%, and 86.1%, respectively. We found that BERTweet outperformed the LSTM model in the classification of all categories.ConclusionsLarge, open-source deep learning classifiers, such as BERTweet, can provide researchers the ability to reliably determine if tweets are relevant to vaping; include commercial content; and include positive, negative, or neutral content about vaping with a higher accuracy than traditional natural language processing deep learning models. Such enhancement to the utilization of Twitter data can allow for faster exploration and dissemination of time-sensitive data than traditional methodologies (eg, surveys, polling research).

Three-dimensional (3D) printing: A potentially versatile tool in the field of medicine

Three-dimensional (3D) printing or additive manufacturing, is a relatively recent and rapidly evolving technology that has a far-reaching impact in the current context of medical education. Since its introduction in the 1980s, additive manufacturing has made tremendous progress. In essence, this technology render a computer-assisted design template based on a set of processed data acquired from various imaging sources such as 3D scanning, computed tomography (CT) and Magnetic resonance imaging (MRI), into a physical object which is an accurate representation of the original. The printing is constructed in layers using a diverse array of printing materials. The process is fast, easy, cost-effective, and repeatable. The scopes of application of 3D-printing are increasing by the day with limitless potential in future. Proper implementation of 3D printing with respect to its availability and accessibility will establish it as a perfect complementary modality to the traditional teaching and learning approaches. In this review paper, the concept of 3D printing, its use in medical education, surgical training, patient interaction, potential benefits and shortcomings, and future scope are highlighted.

Exploring the Impact of Online Learning on Youngsters during Covid-19: From the Knowledge Gap Theory Perspective

The sudden emergence of the COVID-19 pandemic caused panic and anxiety among students all over the world. The education institutions were among many that had suffered significant damage as a result of the pandemic. Following the closure of educational institutes, it was a challenging moment for professional education, which was combated by the development of Digital-learning via online classrooms to assure the students' continued participation in the teaching-learning process. The purpose of this study is to see how effective online education is compared to traditional classroom education among university students. A quantitative survey of university students was conducted. This study included 300 students in total. The students were given a questionnaire with 30 questions to rate the efficiency of online learning through e-classes as well as their grasp of online communication.Online classes were proven to be less successful than traditional learning approaches. This manner of education was deemed unsatisfactory by the respondents. It is possible to infer that while e-education can augment the current educational process, it cannot completely replace it.

Diabetes Detection and Management through Photoplethysmographic and Electrocardiographic Signals Analysis: A Systematic Review

(1) Background: Diabetes mellitus (DM) is a chronic, metabolic disease characterized by elevated levels of blood glucose. Recently, some studies approached the diabetes care domain through the analysis of the modifications of cardiovascular system parameters. In fact, cardiovascular diseases are the first leading cause of death in diabetic subjects. Thanks to their cost effectiveness and their ease of use, electrocardiographic (ECG) and photoplethysmographic (PPG) signals have recently been used in diabetes detection, blood glucose estimation and diabetes-related complication detection. This review’s aim is to provide a detailed overview of all the published methods, from the traditional (non machine learning) to the deep learning approaches, to detect and manage diabetes using PPG and ECG signals. This review will allow researchers to compare and understand the differences, in terms of results, amount of data and complexity that each type of approach provides and requires. (2) Method: We performed a systematic review based on articles that focus on the use of ECG and PPG signals in diabetes care. The search was focused on keywords related to the topic, such as “Diabetes”, “ECG”, “PPG”, “Machine Learning”, etc. This was performed using databases, such as PubMed, Google Scholar, Semantic Scholar and IEEE Xplore. This review’s aim is to provide a detailed overview of all the published methods, from the traditional (non machine learning) to the deep learning approaches, to detect and manage diabetes using PPG and ECG signals. This review will allow researchers to compare and understand the differences, in terms of results, amount of data and complexity that each type of approach provides and requires. (3) Results: A total of 78 studies were included. The majority of the selected studies focused on blood glucose estimation (41) and diabetes detection (31). Only 7 studies focused on diabetes complications detection. We present these studies by approach: traditional, machine learning and deep learning approaches. (4) Conclusions: ECG and PPG analysis in diabetes care showed to be very promising. Clinical validation and data processing standardization need to be improved in order to employ these techniques in a clinical environment.

E-Learning and It’s Impacts during Covid-19

While the covid-19 pandemic has impacted the education industry, it has also opened the door to a new approach to education delivery. The traditional classroom-based learning approach has evolved into a technology-based one. In terms of education, this is a once-in-a-lifetime opportunity. And the teachers have risen to the occasion. They have adapted to a new set of alien tools and resources in an environment that no one could have predicted. Science is a sensible activity that income through the testing of theories by suggests that of experimental work and observations. Virtual lab software creates opportunities for alternative access for science education. It is noted that the teaching-learning process gets better outcomes by the integration of emerging technologies and digital content with all their operations.

Multisensor-Based Heavy Machine Faulty Identification Using Sparse Autoencoder-Based Feature Fusion and Deep Belief Network-Based Ensemble Learning

Faulty identification plays a vital role in the area of prognostic and the health management (PHM) of the industrial equipment which offers great support to the maintenance strategy decision. Owing to the complexity of the machine internal component-system structure, the precise prediction of the heavy machine is hard to be obtained, thus full of uncertainty. Moreover, even for a single component, the feature representation of the acquired conditional monitoring signal can be different due to the different deployment of the sensor location and environmental inference, causing difficulty in feature selection and uncertainty in faulty identification. In order to improve the model identification reliability, a novel hybrid machine faulty identification approach based on sparse autoencoder- (SAE-) and deep belief network- (DBN-) based ensemble learning is proposed in this paper. First, six kinds of statistical features are extracted and normalized from multiple sensors monitoring the same target component. Second, the six extracted features are fused by the two-stage SAE proposed in this paper from the sensor dimension and feature dimension, respectively. The composite feature fused in the feature dimension is regarded as the comprehensive representation of the corresponding component. Finally, the fused features containing comprehensive representation of different components are utilized to predict the machine health condition by the ensemble of multiple deep belief classifiers. The effectiveness of the proposed method is validated by the two case studies of wind turbine gearbox and industrial port crane. The experimental result shows that the proposed ensemble learning approach outperforms other traditional deep learning approaches in terms of the prediction accuracy and the prediction stability when dealing with multisensor feature fusion and the precise faulty identification of the industrial heavy machine.

A lightweight approach for network intrusion detection in industrial cyber-physical systems based on knowledge distillation and deep metric learning

With the rapid development of technology and science, machine learning approaches and deep learning methods have been widely applied in industrial Cyber-Physical Systems. However, there are still some challenging issues for anomaly detection to classify various attacks in industrial CPS to ensure the cyber security, especially when dealing with resource-constrained IoT devices. In this paper, we propose a Knowledge Distillation model based on Triplet Convolution Neural Network to improve the model performance and greatly enhance the speed of anomaly detection for industrial CPS as well as reduce the complexity of the model. Specifically, during the training process, we design a robust model loss function to improve the training stability of the model. A new neural network training method called K-fold cross training is also proposed to enhance the accuracy of anomaly detection. A lot of experimental results demonstrate that the performance metrics of KD-TCNN on the benchmark datasets NSL-KDD and CIC IDS2017 have significant advantages over traditional deep learning approaches and the recent state-of-the-art models. Furthermore, when compared to the original model, our model's computational cost and size are both reduced by roughly 86% with just 0.4% accuracy loss.

Just by being here, you aren’t halfway there: Structured active learning and its integration in virtual learning environments and assessment

Flipped learning with the incorporation of certain elements of gamification aims to improve student engagement, motivation and attainment. In this study we present an analysis of two approaches used in consecutive years on two modules. A traditional flipped learning approach “standard learning” where material is released weekly online and there are supporting tutorials and an end of term assessment; and a “structured active learning” strategy where a more scaffolded approach is applied, requiring participation to progress. In this approach students’ work on the virtual learning environment and in tutorials could be used to contribute towards their end of term assessment (no more than 10% of the module credit), connected to a learning outcome on the breadth or range of topics. Students received feedback in rubric form throughout the topic, to see their progression. It was found that for module 1, over 90% of the students had accessed the pre-released material by week 2 in the structured active learning approach while this level of engagement was only reached in week 5 using the standard approach. Participation in learning events was far better using the structured active learning approach when compared to the standard approach, for example rising from 40% to 78% in week 2. The second module, with a different cohort of students, followed similar trends with the active learning approach attracting higher levels of engagement and participation far earlier in the term. Following the increased engagement, the structured active learning approach was beneficial in assessment with improved grade profiles.

Cooperative problem-based learning experience and coaching strategies of engineering course

<span lang="EN-US">The problem-based learning (PBL) methodologies are considered adequate for core engineering courses. The integration between cooperative learning and PBL methodologies establishes an encouraging environment for the students. However, for effective implementation of cooperative problem-based learning (CPBL) environment, close supervision of students’ experiences is vital, and deficient areas are to be improved, as PBL is a dynamic process. A study was conducted for the first-year undergraduate engineering class taught under the PBL environment. The objective was to evaluate the course by the preview of students, for highlighting weak domains in the teaching methodology for future improvements. A course experience questionnaire was designed considering PBL implications, with 35 question items, and 31 responses were collected by the end of the semester. Three different analyses were performed on the collected data, i.e., descriptive statistics and Cronbach’s alpha, Student's t-test, and Pearson Chi-square test. The achieved results supported the effective adoption of the PBL system by the students. However, few areas were highlighted requiring special consideration, such as PBL workload, pressure due to extra course content, and assessment opportunities under the PBL system. It was proved that maximum students considered PBL methodologies convenient and effective for learning than the traditional learning approach.</span>

UNDERSTANDING FEDERATED LEARNING AND ITS APPLICATION IN VIDEO ANOMALY DETECTION

—Federated Learning is a relatively newer approach, and it tries to solve problems such as reluctance of clients to share data. Instead, a model is sent from server to client(s) where training happens on various edge clients who later update the central model. This is a redesign of the traditional approach of learning from data where all data had to be uploaded to a central server. In contrast, federated learning promotes the idea of bringing code to data which can help overcome latency in timecritical operations. Privacy gives every individual a right to prevent release of data, and several machine learning use-cases deal with such sensitive information for e.g., disease prediction (patient data), anomaly detection (security footage) etc. By introducing the use of federated learning, we can overcome the issue of data sharing and all data will be retained at the edge nodes where the training happens. Through this work we walk through a system design of applying federated learning in a real-time use case of video anomaly detection and present our preliminary results where we achieved an accuracy of 83.34% using the federated paradigm, higher than the centralized accuracy of 81.29%.

Noise-reducing attention cross fusion learning transformer for histological image classification of osteosarcoma

The degree of malignancy of osteosarcoma and its tendency to metastasize/spread mainly depend on the pathological grade (determined by observing the morphology of the tumor under a microscope). The purpose of this study is to use artificial intelligence to classify osteosarcoma histological images and to assess tumor survival and necrosis, which will help doctors reduce their workload, improve the accuracy of osteosarcoma cancer detection, and make a better prognosis for patients. The study proposes a typical transformer image classification framework by integrating noise reduction convolutional autoencoder and feature cross fusion learning (NRCA-FCFL) to classify osteosarcoma histological images. Noise reduction convolutional autoencoder could well denoise histological images of osteosarcoma, resulting in more pure images for osteosarcoma classification. Moreover, we introduce feature cross fusion learning, which integrates two scale image patches, to sufficiently explore their interactions by using additional classification tokens. As a result, a refined fusion feature is generated, which is fed to the residual neural network for label predictions. We conduct extensive experiments to evaluate the performance of the proposed approach. The experimental results demonstrate that our method outperforms the traditional and deep learning approaches on various evaluation metrics, with an accuracy of 99.17% to support osteosarcoma diagnosis.

Online learning and assessment during the Covid-19 pandemic: exploring the impact on undergraduate student well-being

Where traditional learning and assessment approaches have previously been found to negatively impact on student well-being, the Covid-19 pandemic provided a novel opportunity to explore alternative online learning and assessment conditions conducive to student well-being and academic performance as part of a whole university strategy. To this end, the present study employed a mixed-methodological approach using a quantitative survey and 10 focus groups to examine the impact of online learning and assessment on the undergraduate students’ well-being. The findings indicate that whilst some students report online learning and assessment to require more effort in comparison to traditional methods, other students value the increased flexibility afforded by online learning and assessment. It is recommended that academic staff scaffold online learning and assessment methods in the curriculum.

An ecological dynamics approach to motor learning in practice: Reframing the learning and performing relationship in high performance sport

For practitioners working in high performance sport, the primary goal is to ensure that precious preparation time is utilised efficiently, effectively and resourcefully to provide maximal impact on the performance potential of the individual or team. To achieve this goal, there is a need to treat athlete learning and development as an integral part of performing with a key focus on increasingly aligning the relation between the perfomer(s) and their environment, which may differ according to practice and performance (Button et al., 2020b). This article critiqued the weaknesses and limitations of traditional learning approaches in sport, seeking to highlight instead the value of adopting a contemporary ecological dynamics perspective, informing how practitioners should design practice to support a greater connectivity between the contexts of performance and learning.

The effect of gender composition and pedagogical approach on major and non-major undergraduates biology students’ achievement

ABSTRACT This study hypothesized whether the gender group composition in traditional learning (TL) versus collaborative learning (CL) classrooms of undergraduate biology majors and nonmajors correlate with students’ achievements. We measured the effect on gender and the gender-specific achievements of the TL versus CL approach in single-gender and mixed-gender classes. A significant gender gap was found in the achievements of both nonmajor and major students. Females achieved higher grades in TL and CL sections in single-gender classes; overall, academic achievements between females (F) and males (M) demonstrated a significant difference at P<.05. The effect size value between TL versus CL indicated that males benefited more than females implementing CL mixed-gender (2F+2M) in nonmajors and majors. While females in single-gender CL and TL classes performed higher than males, females performed relatively low in mix-gender CL (2F+2M). These findings indicate that gender-specific and context-specific learning pedagogies are required since they impact students’ achievement.

A Study on Students’ Perspective towards Cooperative Learning in the ESL Classroom

In this era, there are varieties of approaches to teaching English as Second Language (ESL) learners, and there have been many types of research done to test the effectiveness of these approaches. This research aimed to examine the students’ perspectives on cooperative learning in the ESL classroom. Cooperative learning refers to various instructional practices that encourage students to work together as they apply course material to answer questions, solve problems, or create a project. Therefore, cooperative learning is different from the traditional learning approach because it expands the second language acquisition by providing room for both language input and output. This study employed the quantitative approach where 107 Diploma students from Sultan Idris Education University who underwent a compulsory English course were requested to participate in a survey after completing the activities, which incorporated cooperative learning. The questionnaire was adapted from previous research to ensure reliability in collecting data. Then, the data were tabulated using SPSS software. It focused on the students’ perspectives on learning experience, comprehension, and interaction. The findings revealed that most students had a positive perspective toward cooperative learning in the ESL classroom.

Adaptive Privacy-Preserving Federated Learning for Fault Diagnosis in Internet of Ships

The recent appearance of Internet of Things (IoT) technologies applied in the maritime industry has introduced the Internet of Ships (IoS) paradigm. By leveraging IoS and deep learning (DL), various DL-based fault diagnosis methods have been proposed to improve shipping companies&#x2019; maintenance performance and reduce operational costs. However, the traditional centralized learning approach (CL), which centralizes the data resources of different shipping companies to a cloud server for model training, is restricted in real industrial scenarios due to privacy concerns and business competitions. In this article, we propose a novel adaptive privacy-preserving federated learning approach, named AdaPFL, for fault diagnosis in IoS, which can organize different shipping agents to collaboratively develop a model by sharing model parameters with no risk of data leakage. First, we use two common tasks as examples to demonstrate that a small part of the model parameters might reveal the shipping agents&#x2019; raw information. Based on this, the Paillier-based communication scheme is designed to preserve the raw information of the shipping agents. Furthermore, to deal with the harsh marine environment, a control algorithm is proposed to adaptively change the model aggregation interval during the training process for reducing cryptography computation and communication costs. Theoretical analysis and experiments prove the high effectiveness of the AdaPFL on a real nonindependent and identically distributed (non-i.i.d) fault data set.

The impact of three-dimensional visualisation on midwifery students’ application of knowledge of the third stage of labour to practice: Qualitative findings of a pilot randomised controlled trial

ProblemComplex physiological processes are often difficult for midwifery students to comprehend when using traditional teaching and learning approaches. Online resources for midwifery education are limited. BackgroundFace to face instructional workshops using simulation have had some impact on improving understanding. However, in the 21st century new technologies offer the opportunity to provide alternative learning approaches. Virtual and artificial realities have been shown to increase confidence in decision making during clinical practice. AimExplore the impact of using three-dimensional (3D) visualisation in midwifery education, on student’s application, when educating women about the birth of the placenta, and membranes. MethodsFace to face individual interviews were performed, to collect deep, meaningful experiences of students, learning about the third stage of labour. FindingsPrior clinical experiences impacted on student’s ability to articulate how they would discuss birth of the placenta and membranes, and the process of haemostasis with women. DiscussionThe narrative findings of this pilot study identified ways that students traditionally learn midwifery, through theory, and clinical practice. Interview narratives illustrated how midwifery students who had previous experiences of witnessing birth, had superior ability to discuss the third stage of labour with women. While students with limited birth experiences, found the 3DMVR assisted them in their understanding of the physiology of the third stage of labour. ConclusionIn an environment of increasing technological advances, clinical placements remain an essential component of midwifery education.

Detection of illegal traffic pattern using Hybrid Improved CART and Multiple Extreme Learning Machine Approach

In the proposed hybrid intrusion detection process, misuse detection and anomaly detection model is integrated to detect the attack in traffic pattern. In misuse detection model, the traffic pattern is classified into known attack and not known attack. Each extracted normal data set does not have known attack and it contains small amount of varied connection patterns than overall normal data set. Anomaly detection model classifies the not known attack as normal data set and unknown attack thus improving the performance of normal traffic behavior. Experiment is carried out using NSL –KDD dataset and performance of proposed approach is compared with traditional learning approaches in terms of training time, testing time, false positive ratio and detection ratio. The proposed method detects the known attacks and unknown attacks with ratio of 99.8 % and 52% respectively.

The Convertible Learning System: A Certainty for Uncertain Times

In light of our forced migration to the online world, this article argues in favor of a widespread evolution of our approach to education, drifting from rigid to flexible models. Such an optimal system would be able to change from one form and function to another, even in mid-course, without compromising pedagogy. This system has to be based on evidence-based innovative pedagogies and scholarships of teaching and learning. The article proposes a “Convertible Learning System” (CLS)—a synergistic optimization of relative strengths of traditional and online learning approaches, while simultaneously allowing the flexibility that we realize is now critical. Although the examples lie in the realms of tertiary education, the concepts and implications can be beneficial at educational levels.

A content-based image retrieval system for the diagnosis of lymphoma using blood micrographs: An incorporation of deep learning with a traditional learning approach

Lymphomas, or cancers of the lymphatic system, account for around half of all blood cancers diagnosed each year. Lymphoma is a condition that is difficult to diagnose, and accurate diagnosis is critical for effective treatment. Manual microscopic analysis of blood cells requires the involvement of medical experts, whose precision is dependent on their abilities, and it takes time. This paper describes a content-based image retrieval system that uses deep learning-based feature extraction and a traditional learning method for feature reduction to retrieve similar images from a database to aid early/initial lymphoma diagnosis. The proposed algorithm employs a pre-trained network called ResNet-101 to extract image features required to distinguish four types of cells: lymphoma cells, blasts, lymphocytes, and other cells. The issue of class imbalance is resolved by over-sampling the training data followed by data augmentation. Deep learning features are extracted using the activations of the feature layer in the pre-trained net, then dimensionality reduction techniques are used to select discriminant features for the image retrieval system. Euclidean distance is used as the similarity measure to retrieve similar images from the database. The experimentation uses a microscopic blood image dataset with 1673 leukocytes of the categories blasts, lymphoma, lymphocytes, and other cells. The proposed algorithm achieves 98.74% precision in lymphoma cell classification and 99.22% precision @10 for lymphoma cell image retrieval. Experimental findings confirm our approach's practicability and effectiveness. Extended studies endorse the idea of using the prescribed system in actual medical applications, helping doctors diagnose lymphoma, dramatically reducing human resource requirements.