Learning Methods Research Articles

Machine Learning Methods in Detecting Heart Related Diseases

Machine Learning Methods in Detecting Heart Related Diseases

A soft prompt learning method for medical text classification with simulated human cognitive capabilities

A soft prompt learning method for medical text classification with simulated human cognitive capabilities

Semi-supervised learning-based identification of the attachment between sludge and microparticles in wastewater treatment.

Monitoring the microparticle transfer process in wastewater treatment systems is crucial for improving treatment performance. Supervised deep learning methods show high performance to automatically detect particles, but they rely on vast amounts of labeled data for training. To overcome this issue, we proposed a semi-supervised learning (SSL) method based on the Simple framework for Contrastive Learning of visual Representations (SimCLR), to detect microparticles free from sludge and attached to sludge. First, we pre-trained a ResNet50 backbone by SimCLR, to extract features from much unlabeled data (1,000 images). Then, we constructed a Mask R-CNN architecture based on the pre-trained ResNet50, and fine-tuned it on a small quantity of labeled data (≈200 images with ≈600 annotated particles) in supervised learning fashion. We showcased its performance and practical applicability for microscopy images obtained from the water lab of TU Delft. The results demonstrate that the SSL methods obtain a significant improvement in mean average precision of up to 5% compared to the conventional supervised learning method, when a limited amount of labeled data is available (e.g., 91 labeled images). Furthermore, these methods improve the average precision for detecting attached particles by over 12%. With the detection results from the SSL methods, we measured the attachment efficiency of microparticles to sludge under varying mixed liquor suspended solids concentration and aeration intensity. The precise measurements demonstrate the effectiveness and practical applicability of the SSL method in facilitating long-term monitoring of particle transfer processes in biological wastewater treatment systems.

Long-term care plan recommendation for older adults with disabilities: a bipartite graph transformer and self-supervised approach.

With the global population aging and advancements in the medical system, long-term care in healthcare institutions and home settings has become essential for older adults with disabilities. However, the diverse and scattered care requirements of these individuals make developing effective long-term care plans heavily reliant on professional nursing staff, and even experienced caregivers may make mistakes or face confusion during the care plan development process. Consequently, there is a rigid demand for intelligent systems that can recommend comprehensive long-term care plans for older adults with disabilities who have stable clinical conditions. This study aims to utilize deep learning methods to recommend comprehensive care plans for the older adults with disabilities. We model the care data of older adults with disabilities using a bipartite graph. Additionally, we employ a prediction-based graph self-supervised learning (SSL) method to mine deep representations of graph nodes. Furthermore, we propose a novel graph Transformer architecture that incorporates eigenvector centrality to augment node features and uses graph structural information as references for the self-attention mechanism. Ultimately, we present the Bipartite Graph Transformer (BiT) model to provide personalized long-term care plan recommendation. We constructed a bipartite graph comprising of 1917 nodes and 195240 edges derived from real-world care data. The proposed model demonstrates outstanding performance, achieving an overall F1 score of 0.905 for care plan recommendations. Each care service item reached an average F1 score of 0.897, indicating that the BiT model is capable of accurately selecting services and effectively balancing the trade-off between incorrect and missed selections. The BiT model proposed in this paper demonstrates strong potential for improving long-term care plan recommendations by leveraging bipartite graph modeling and graph SSL. This approach addresses the challenges of manual care planning, such as inefficiency, bias, and errors, by offering personalized and data-driven recommendations. While the model excels in common care items, its performance on rare or complex services could be enhanced with further refinement. These findings highlight the model's ability to provide scalable, AI-driven solutions to optimize care planning, though future research should explore its applicability across diverse healthcare settings and service types. Compared to previous research, the novel model proposed in this article effectively learns latent topology in bipartite graphs and achieves superior recommendation performance. Our study demonstrates the applicability of SSL and graph transformers in recommending long-term care plans for older adults with disabilities.

Effective Use of an Innovative Learning Method: A Perspective from a Sri Lankan Setting

Introduction: Numerous medical schools have incorporated humanities and narrative medicine into their curricula to cultivate compassion and foster essential interpersonal abilities in medical students. These progressive educational approaches prove effective in cultivating empathy, ethical conduct, and professionalism among future healthcare practitioners. Methods: This qualitative study was conducted at the Faculty of Medicine, University of Kelaniya to study the effectiveness of an innovative learning method in enhancing active learning, critical thinking and personal professional development amongst first-year medical students. Newly graduated medical students, following exposure to a Training of the Trainer (TOT) program, served as facilitators for the training program, and insights from facilitators were gathered through audio-recorded focus group discussions. Following this, a thematic analysis was conducted to explore the interplay and correlations among the identified domains. Results: The study revealed that facilitators experienced a sense of empowerment after participating in the facilitator training program. They acknowledged that learning about learning itself was a novel experience, which they hadn't encountered during their time as students. Further, the findings indicated that junior medical graduates can successfully undergo training to facilitate a combination of five innovative active learning methods aimed to boost critical thinking and personal professional development among fresh medical students, resulting in high levels of acceptance and satisfaction among the facilitators. Conclusion: The results of this study support the idea that training facilitators can improve their skills in delivering programs that promote critical thinking and active learning among first-year medical graduates. Feedback from newly graduated medical professionals acting as facilitators indicated that with enthusiasm and motivation, junior healthcare workers could be successfully trained to facilitate in settings with limited resources.

Mitigating DDoS Attacks in Virtual Machine Migration: An In-Depth Security Framework Utilizing Deep Learning and Advanced Encryption Techniques

Safeguarding virtual machines (VMs) during migration is essential to avert Service Level Agreement (SLA) violations. This research article presents a robust security framework that utilizes deep learning and advanced encryption methods to reduce the impact of Distributed Denial of Service (DDoS) attacks during virtual machine migration. The study introduces an Improved Sparrow Search Algorithm-based Deep Neural Network (ISSA-DNN) for the classification of DDoS attacks and utilizes Advanced Encryption Standard-Elliptic Curve Cryptography (AES-ECC) to safeguard virtual machine images. The primary objective is to mitigate the risks associated with VM migration by identifying DDoS attacks and safeguarding VMs using advanced cryptographic techniques. The research employs the Canadian Institute for Cybersecurity Distributed Denial of Service (CICDDoS) dataset, implementing preprocessing procedures like duplication elimination, feature selection via Random Forest, and normalization to improve the precision of the DNN classifier. The ISSA-DNN approach enhances hyperparameter optimization by inverse mutation-based sparrow search, yielding a precise attack classification model. Furthermore, the research incorporates AES-ECC for encrypting VM images, amalgamating AES's computational efficiency with ECCs improved security. In contrast to conventional methods, this hybrid encryption approach enhances throughput and decreases encryption and decryption durations, rendering it appropriate for high-throughput and real-time applications. Experimental findings indicate that the proposed ISSA-DNN attains a classification accuracy of 98.79%, surpassing current state-of-the-art techniques. The AES-ECC encryption technique markedly enhances performance metrics, safeguarding the security of virtual machines during migration. This proactive security policy safeguards sensitive data and guarantees adherence to regulatory standards. In conclusion, the established framework offers a comprehensive solution for mitigating DDoS attacks and safeguarding VM migration via advanced deep learning and encryption methodologies. Integrating ISSA-DNN for attack classification and AES-ECC for encryption offers a robust strategy for improving cybersecurity in cloud environments.

Biomedical named entity recognition using improved green anaconda-assisted Bi-GRU-based hierarchical ResNet model

BackgroundBiomedical text mining is a technique that extracts essential information from scientific articles using named entity recognition (NER). Traditional NER methods rely on dictionaries, rules, or curated corpora, which may not always be accessible. To overcome these challenges, deep learning (DL) methods have emerged. However, DL-based NER methods may need help identifying long-distance relationships within text and require significant annotated datasets.ResultsThis research has proposed a novel model to address the challenges in natural language processing. The Improved Green anaconda-assisted Bi-GRU based Hierarchical ResNet BNER model (IGa-BiHR BNERM) is the model. IGa-BiHR BNERM model has shown promising results in accurately identifying named entities. The MACCROBAT dataset was obtained from Kaggle and underwent several pre-processing steps such as Stop Word Filtering, WordNet processing, Removal of non-alphanumeric characters, stemming Segmentation, and Tokenization, which is standardized and improves its quality. The pre-processed text was fed into a feature extraction model like the Robustly Optimized BERT –Whole Word Masking model. This model provides word embeddings with semantic information. Then, the BNER process utilized an Improved Green Anaconda-assisted Bi-GRU-based Hierarchical ResNet BNER model (IGa-BiHR BNERM).ConclusionTo improve the training phase of the IGa-BiHR BNERM, the Improved Green Anaconda Optimization technique was used to select optimal weight parameter coefficients for training the model parameters. After the model was tested using the MACCROBAT dataset, it outperformed previous models with a tremendous accuracy rate of 99.11%. This model effectively and accurately identifies biomedical names within the text, significantly advancing this field.

Classification of the Condition of Cancer Patients Receiving Home Health Care with Machine Learning Methods

Determining the health status of cancer patients is of vital importance in the cancer treatment process. This process plays a critical role in assessing patients' quality of life and supporting the treatment process. We thought that the use of machine learning in the field of cancer treatment and patient care could contribute to better patient outcomes and increased quality of life. Evaluation results of cancer patients who received home health care from XXXXXX and Research Hospital between January 2013 and August 2017 were discussed and 1000 patient files in home health service patient records were prospectively examined. In this article, cancer types were classified with machine learning methods using the Visual Analog Scale (VAS), Karnofsky performance scale, ECOG, Katz and Bartel scores to determine the quality of life of cancer patients receiving home health care. This study includes the evaluation results of 132 patients, 69 women (mean age 60.31±9.61) and 63 men (mean age 62.36±9.58). The DT classifier was noted to exhibit 83.3% accuracy and had the highest sensitivity in the lung cancer type, with a sensitivity of 88.9%. SVM classifier reached the highest accuracy compared to other classifiers with 90.2% accuracy. SVM has the highest sensitivity in lung cancers, with a sensitivity of 97.8%. The ANN classifier achieved 88.6% accuracy for all cancer types.The use of machine learning algorithms may provide a more sensitive and objective way to evaluate patients' response to treatment. The machine learning model allows determining the type of cancer using the feature space based on VAS, Karnofsky performance scale, ECOG, Katz and Bartel scores. This situation can also be constructed as an indicator in early diagnosis or risk group determination, and thus can contribute to improving home health services and increasing the quality of life of cancer patients. The results of this study may contribute to studies aimed at developing more effective strategies for the care and treatment of cancer patients.

Detecting the Number of Students Using YOLOv11 to Prevent Proxy Attendance at Universitas Dinamika Bangsa

Attendance is an important criterion for passing courses at Universitas Dinamika Bangsa Jambi. According to the academic regulations of Universitas Dinamika Bangsa Jambi, the minimum attendance requirement for course completion is 75%. The attendance process at the university utilizes an academic information system (SIAKAD) where students log in using a username and password, then scan an attendance barcode or input a unique code. Students often engage in proxy attendance practices, where they are marked present in the system despite being absent in reality. This study discusses the prevention of proxy attendance by employing a human detection system based on YOLOv11, capable of counting the number of students present in the classroom at Universitas Dinamika Bangsa Jambi. The research method involves the design, implementation, and evaluation of the system. This study adopts a deep learning approach using supervised learning methods for model training. The model is trained on a labeled dataset from Roboflow and implemented using the YOLOv11 algorithm. Based on the research results, the authors conclude that the human detection system is effective in counting the number of students in the classroom. However, the system still requires further development to detect criteria or features that can distinguish the detected individuals' status, specifically between students and lecturers.

Evaluation of the implementation of the operational curriculum of the education unit (KOSP) of the school mover of Indonesian language subject in grade 7 SMP Negeri 2 Wanggarasi Pohuwato District, Indonesia

This study examines the implementation of the Kurikulum Operasional Satuan Pendidikan (KOSP) for Bahasa Indonesia in Grade 7 at SMP Negeri 2 Wanggarasi, a participant in the Kurikulum Merdeka reform initiative in Indonesia. The study aims to evaluate how KOSP facilitates curriculum alignment, instructional practices, and assessment strategies while identifying challenges and proposing actionable solutions. Using a qualitative descriptive approach, data were collected through observations, semi-structured interviews, and document analysis to provide an in-depth understanding of curriculum implementation in a real-world educational context. The findings reveal progress in adopting student-centered and project-based learning methods, fostering critical thinking and creativity among students. However, challenges persist, including limited digital literacy among teachers, inconsistent assessment practices, and insufficient resource alignment with curriculum objectives. The integration of technology and the Pelajar Pancasila profile into instruction was uneven, highlighting the need for enhanced professional development and institutional support. This study contributes to the growing body of knowledge on curriculum reform by offering localized insights into the operationalization of the Kurikulum Merdeka. It underscores the importance of teacher readiness, resource accessibility, and collaborative practices in achieving successful implementation. The findings have implications for policymakers and educators and point to future research exploring scalable strategies to address these challenges.

Association between triglyceride-glucose index and carotid atherosclerosis in Chinese steelworkers: a cross-sectional study

This study aims to explore the association between the triglyceride-glucose (TyG) index and the risk of carotid atherosclerosis (CAS) among Chinese steelworkers. This is a cross-sectional study involving a total of 4,203 Chinese steelworkers. The TyG index was calculated using the formula: TyG = Ln [fasting triglycerides (mg/dL) × fasting glucose (mg/dL) / 2]. The association between the TyG index and CAS was analyzed using multivariable logistic regression and restricted cubic spline (RCS) models. The association between TyG and CAS was evaluated across different subgroups, including sex, age, lifestyle, medical history, and the state of occupational exposure. In addition, the TyG index was used to perform calibration and risk reclassification analyses on the fully adjusted model. Feature importance and predictive models were generated using LASSO regression and machine learning methods. In the fully adjusted model, compared to the lowest quartile group, the odds ratios (OR, 95% CI) for CAS, increased CIMT, and plaque in the highest quartile group of the TyG index were 3.199 (2.423 ~ 4.223), 2.877 (2.149 ~ 3.851), and 3.738 (2.700 ~ 5.177), respectively. Steelworkers exposed to occupational hazards had a higher risk of CAS compared to those not exposed. There was a nonlinear positive correlation between the TyG index and CAS (P < 0.05), and the risk of CAS increased when TyG > 8.72. Additionally, the TyG index demonstrated additional predictive capability beyond existing risk factors, significantly improving discriminatory performance (P < 0.05). In LASSO regression, TyG index and other covariables are screened as important feature variables to be incorporated into the development of machine learning models. The TyG index is associated with an increased risk of CAS among steelworkers, underscoring its potential as a reliable and practical predictive tool for assessing CAS risk in this population. Steelworkers with a TyG index>8.72 should receive additional CAS screening and health interventions. In addition, attention should be paid to those exposed to occupational hazards. The TyG index may serve as a simple, rapid, and reliable assessment tool for identifying high-risk individuals with CAS among steelworkers.

Integrating multiomics analysis and machine learning to refine the molecular subtyping and prognostic analysis of stomach adenocarcinoma

Stomach adenocarcinoma (STAD) is a common malignancy with high heterogeneity and a lack of highly precise treatment options. We downloaded the multiomics data of STAD patients in The Cancer Genome Atlas (TCGA)-STAD cohort, which included mRNA, microRNA, long non-coding RNA, somatic mutation, and DNA methylation data, from the sxdyc website. We synthesized the multiomics data of patients with STAD using 10 clustering methods, construct a consensus machine learning-driven signature (CMLS)-related prognostic models by combining 10 machine learning methods, and evaluated the prognosis models using the C-index. The prognostic relationship between CMLS and STAD was assessed using Kaplan-Meier curves, and the independent prognostic value of CMLS was determined by univariate and multivariate regression analyses. we also evaluated the immune characteristics, immunotherapy response, and drug sensitivity of different CMLS groups. The results of the multiomics analysis classified STAD into three subtypes, with CS1 resulting in the best survival outcome. In total, 10 hub genes (CES3, AHCYL2, APOD, EFEMP1, CYP1B1, ASPN, CPE, CLIP3, MAP1B, and DKK1) were screened and constructed the CMLS was significantly correlated with prognosis in patients with STAD and was an independent prognostic factor for patients with STAD. Using the CMLS risk score, all patients were divided into a high CMLS group and a low CMLS group. Patients in the low-CMLS group had better survival, more enriched immune cells, and higher tumor mutation load scores, suggesting better immunotherapy responsiveness and a possible “hot tumor” phenotype. Patients in the high-CMLS group had a significantly poorer prognosis and were less sensitive to immunotherapy but were likely to benefit more from chemotherapy and targeted therapy. In this study, 10 clustering methods and 10 machine learning methods were combined to analyze the multiomics of STAD, classify STAD into three subtypes, and constructed CMLS-related prognostic model features, which are important for accurate management and effective treatment of STAD.

Benefits and Limitations of Flipped Classroom

Abstract In the digital age of learning, new learning ecologies provide students with new web-based learning opportunities and resources. Medical education is reaching a new trend in teaching–learning methods by providing student-centered teaching. Flipped classroom is one among the teaching–learning methods. The contribution of the flipped classroom to education is discussed in relation to the changes in students’ and instructors’ roles. Subsequently, flipped classroom advantages and drawbacks are illustrated. For the current article literature was searched in databases PubMed and Scopus and only articles related to medical teaching were included. Studies on non-academic or informal settings without relevance to flipped classrooms were excluded. The study’s findings suggest that creating successful flipped classroom environments may be aided by carefully considering the cautions and suggestions given in the literature and also this article attempts to inform those who are thinking of using new technologies and approaches to deliver courses.

Insights into breast cancer: A simple machine learning method for early disease detection

Insights into breast cancer: A simple machine learning method for early disease detection

Carbon Dioxide Sensing Based on Off-Axis Integrated Cavity Absorption Spectroscopy Combined with the Informer and Multilayer Perceptron Models.

Off-axis integrated cavity output spectroscopy (OA-ICOS) allows the laser to be reflected multiple times inside the cavity, increasing the effective absorption path length and thus improving sensitivity. However, OA-ICOS systems are affected by various types of noise, and traditional filtering methods offer low processing efficiency and perform limited feature extraction. Deep learning models enable us to extract important features from large-scale, complex spectral data and analyze them efficiently and accurately. We propose a carbon dioxide (CO2) sensor operating in the near-infrared spectral region (1.602 μm) based on OA-ICOS and deep learning models. A radiofrequency (RF) noise source is employed to reduce the cavity-mode noise in OA-ICOS and thus improve the signal-to-noise ratio (SNR). A time-series-based neural network, known as the informer, is employed for filtering CO2 spectral time series. After filtering, spectral features are directly extracted from the filtered spectral data and CO2 concentrations are predicted using a multilayer perceptron (MLP) model. Our results showed that the SNR attained using informer filtering approximately double those obtained using traditional filtering methods (Savitzky-Golay filtering, Kalman filtering, and wavelet threshold). The linear correlation coefficient (R2) between measured concentrations and standard concentrations was increased from 79.74% (obtained by using the absorption-peak-fitting method) to 98.52% (obtained by using the proposed MLP model). Moreover, the detection limit of the CO2 sensor using the MLP model reached 1.38 ppm at 224.4 s, a 3.79-fold improvement compared to that obtained by using the absorption-peak-fitting method. Our results demonstrate the feasibility of integrating deep learning methods in the field of spectroscopy-based sensing and provide a promising approach for spectral data processing.

Machine learning methods for predicting the durability of concrete materials: A review

Machine learning methods for predicting the durability of concrete materials: A review

Innovative Online Teaching and Learning Methods for a Post-Pandemic Period

Innovative Online Teaching and Learning Methods for a Post-Pandemic Period

Few-shot transfer learning for individualized braking intent detection on neuromorphic hardware.

This work explores use of a few-shot transfer learning method to train and implement a convolutional spiking neural network (CSNN) on a BrainChip Akida AKD1000 neuromorphic system-on-chip for developing individual-level, instead of traditionally used group-level, models using electroencephalographic data. The efficacy of the method is studied on an advanced driver assist system related task of predicting braking intention. &#xD;\emph{Approach}: Data are collected from participants operating an NVIDIA JetBot on a testbed simulating urban streets for three different scenarios. Participants receive a braking indicator in the form of: 1) an audio countdown in a nominal baseline, stress-free environment; 2) an audio countdown in an environment with added elements of physical fatigue and active cognitive distraction; 3) a visual cue given through stoplights in a stress-free environment. These datasets are then used to develop individual-level models from group-level models using a few-shot transfer learning method, which involves: 1) creating a group-level model by training a CNN on group-level data followed by quantization and recouping any performance loss using quantization-aware retraining; 2) converting the CNN to be compatible with Akida AKD1000 processor; and 3) training the final decision layer on individual-level data subsets to create individual-customized models using an online Akida edge-learning algorithm.&#xD;Main Results: Efficacy of the above methodology to develop individual-specific braking intention predictive models by rapidly adapting the group-level model in as few as three training epochs while achieving at least 90\% accuracy, true positive rate and true negative rate is presented. Further, results show the energy-efficiency of the neuromorphic hardware through a power reduction of over 97\% with only a $1.3\times$ increase in latency when using the Akida AKD1000 processor for network inference compared to an Intel Xeon central processing unit. Similar results were obtained in a subsequent ablation study using a subset of five out of 19 channels. &#xD;Significance: Especially relevant to real-time applications, this work presents an energy-efficient, few-shot transfer learning method that is implemented on a neuromorphic processor capable of training a CSNN as new data becomes available, operating conditions change, or to customize group-level models to yield personalized models unique to each individual.

A Decomposition-Integration Framework of Carbon Price Forecasting Based on Econometrics and Machine Learning Methods

A Decomposition-Integration Framework of Carbon Price Forecasting Based on Econometrics and Machine Learning Methods

Quantifying the Relationship Between At-Home Shoulder Physiotherapy Participation and Outcome: What can a Watch Tell Us?

Exercise-based physiotherapy is an established treatment of rotator cuff injury. Objective assessment of at-home exercise is critical to understand its relationship with clinical outcomes. This study uses the Smart Physiotherapy Activity Recognition System to measure at-home physiotherapy participation in patients with rotator cuff injury based on inertial sensor data captured from smart watches. Relationships between participation and clinical outcomes, long-term durability of outcome improvements, and factors predictive of participation were evaluated. Patients participated in a 12-week rotator cuff physiotherapy program in a prospective single-center study. Patients wore smart watches during supervised weekly in-clinic physiotherapy sessions and while performing exercises at home. Demographic information and rotator-cuff diagnosis were collected at baseline and assessed as predictors of physiotherapy participation. Outcome measures (pain, disability [Disabilities of the Arm, Shoulder and Hand], strength, range of motion) were collected over duration of treatment and at 12-month follow-up (pain and disability). Machine learning algorithms identified and classified periods of exercise to evaluate participation and adherence. One hundred ten patients enrolled and initiated treatment, with 92 patients included in the analysis. All outcomes showed significant improvements from baseline at each time point. Mean total weekly at-home participation decreased from 35.6 ± 28.9 minutes in weeks 0 to 4 to 28.9 ± 25.7 minutes in weeks 8 to 12 (t = 2.23, P = 0.023). For the full cohort, significant relationships were found between physiotherapy participation and disability, manual strength, external rotation, internal rotation, and abduction. Significant predictors of participation included greater age, being unmarried, diagnosed rotator cuff tear, and measures of self-efficacy, social support, and comorbidity. Higher participation rates led to significant improvements in outcomes for partial thickness/no-tear patients but not for full-thickness tears. Machine learning methods applied to data collected from smart watches enabled objective assessment of physiotherapy participation in the home setting. Although most patients improved with physiotherapy, patients with full-thickness rotator cuff tears were not similarly responsive to higher exercise volumes.