MAKE MDPI

?? ?? We are excited to share the news that the Impact Factor of MAKE has reached 4.0! @MDPIOpenAccess @ComSciMath_Mdpi https://lnkd.in/gXuFvJ-a ?? This achievement is a direct result of the dedicated efforts and strategic guidance of our esteemed EiC Prof. Dr. Andreas Holzinger, all the Editorial Board Members, Authors, Reviewers, and Readers. Thank you to everyone who has contributed to MAKE. To view more data, please visit ?? https://lnkd.in/gHEJMzPw

?? This study addresses the challenges of analyzing electrocardiogram (#ECG) data from implantable cardiac monitors (#ICMs), which are increasingly used to track heart rhythms. ICMs rely on energy-efficient, rule-based algorithms that often produce high false-positive rates, leading to a growing data burden for #healthcare professionals (HCPs). The authors propose an efficient pipeline for automated multi-label classification of ICM data, leveraging semi-supervised learning, noise detection, segmentation, and dimension-reduction techniques to handle the unique characteristics of ICM signals. The method demonstrates superior performance compared to state-of-the-art techniques, achieving an F1 score of 0.51 in detecting atrial fibrillation, significantly improving accuracy and reducing HCP workloads. Title "Enhancing Electrocardiogram (ECG) Analysis of Implantable Cardiac Monitor Data: An Efficient Pipeline for Multi-Label Classification" By Amnon Bleich, Antje Linnemann, Benjamin Jaidi, Dr. med. Bj?rn Diem and Tim O. F. Conrad ?? https://lnkd.in/gNT9wXK4

?? MDPI journals will be attending #TENCON2024 as exhibitors. This meeting will be held in Marina Bay Sands, #Singapore, from 1 to 4 December 2024. Conference:?IEEE Region 10 Conference 2024 (TENCON 2024) Organization:?IEEE Singapore Section Place:?Marina Bay Sands, Singapore Booth ID: #B3 If you will be attending this conference, please feel free to start a conversation with us. Our delegates look forward to meeting you in person and answering any questions you may have. For more information about the conference, please visit the following website:?https://tencon2024.org/.

?? ?? Check the new published paper in MAKE: Title "Application of Bayesian Neural Networks in Healthcare: Three Case Studies" ?? https://lnkd.in/g9Ai9MY6

?????? We are thrilled to announce that one of our esteemed Editorial Board Members Prof. Dr. Francisco Herrera has been named a Highly Cited Researcher 2024 by Clarivate! ?? A well-deserved recognition for his impactful contributions to the field. #HighlyCitedResearchers2024 #MAKE ?? https://lnkd.in/ghBTnQVW

?? The paper presents FairCaipi, a novel framework combining explanatory, interactive machine learning and fairness enhancement to reduce bias in machine learning models. Recognizing that fairness is context-dependent, FairCaipi allows users to iteratively provide feedback on model predictions and explanations, enabling dynamic model adjustments. Building upon the interactive learning approach of Caipi, FairCaipi integrates human input to enhance both fairness and predictive performance. Experimental evaluations show that FairCaipi surpasses a leading pre-processing bias mitigation method, effectively identifying and mitigating machine bias while also uncovering human bias. The approach highlights the potential of interactive learning in addressing fairness challenges in critical applications. #fairmachinelearning, #interactivemachinelearning, #biasreduction, #explainability. By Louisa Heidrich, Emanuel Slany, Stephan Scheele and Ute Schmid ?? https://lnkd.in/eZ3KYMni

?? Cover Story-Mach. Learn. Knowl. Extr., Volume 6, Issue 4 https://lnkd.in/gnY7zfra ?? #Braintumors are among the deadliest elements of #cancers, and early detection is crucial for improving patient outcomes. Although an #MRI is the gold standard for diagnosing brain tumors, manual analysis is often affected by radiologist fatigue and subjectivity. This study introduces a novel computer-aided diagnosis (#CAD) framework for multi-class brain tumor classification from MRI scans. The framework leverages pre-trained #deeplearning models and #explainableAI techniques to enhance both diagnostic accuracy and interpretability. A user-friendly detection system ensures seamless clinical integration. Evaluated on a public benchmark dataset, the system achieves nearly 99% accuracy, offering significant promise in improving diagnostic precision and facilitating timely interventions. By Zhengkun Li and Omar DIB, Ph.D ?? https://lnkd.in/gcwTWdtc

?? This paper explores #deeplearning techniques for continuous human activity recognition (#HAR) using #mm-wave Doppler #radar, targeting applications in #elderlycare. Two strategies for detecting daily activities were developed: one handling un-equalized activity sequences and another using a gradient-based equalization approach. For classification, dynamic time warping (DTW) and long short-term memory (LSTM) models were employed. The study evaluated feature extraction methods, including pixel-level data, unsupervised encoded features (UnSup-EnLevel), supervised encoded features (Sup-EnLevel), convolutional neural networks (CNN), and principal component analysis (PCA). A novel supervised feature extraction pipeline (Sup-EnLevel-DTW and Sup-EnLevel-LSTM) outperformed state-of-the-art unsupervised methods. Surprisingly, the UnSup-PLevel approach achieved strong results without requiring annotations or frame equalization. This work highlights the potential of mm-wave radar and deep learning for non-invasive, continuous HAR. Title "Deep Learning Techniques for Radar-Based Continuous Human Activity Recognition" By Ruchita Mehta, Sara Sharifzadeh, Vasile Palade, Bo Tan, Alireza Daneshkhah and Yordanka Karayaneva ?? https://lnkd.in/gC3sHgFJ

?? DEACON - a novel #algorithm that improves #Transformermodels by diversifying attention heads during training. Shows consistent performance gains across #translation, #summarization, #QA, and #languagemodeling while enabling efficient head pruning. Title "Diversifying Multi-Head Attention in the Transformer Model" By Nicholas Ampazis and Flora Sakketou ?? https://lnkd.in/g4D6UGSq

?? Machine Learning and Knowledge Extraction | Top Viewed Papers in 2023：https://lnkd.in/gBmFXpDt ?? No. 10 "A Survey of Deep Learning for Alzheimer's Disease" Authors: Qinghua Zhou, Jiaji Wang, Xiang Yu, Shuihua Wang and Yudong Zhang ?? Views: 7209 ?? Citations: 13 ?? Downloads: 912 ?? https://lnkd.in/e63AkN6n