Interpretable classification of Levantine ceramic thin sections via neural networks by Sara Capriotti, Alessio Devoto, Simone Scardapane, Silvano Mignardi, Laura Medeghini

“…Explainability techniques, including Guided Gradient-based Class Activation Maps and attention maps, were applied to interpret and visualize the models’ decisions, revealing that both CNNs and ViTs successfully focus on key mineralogical features for the classification of the samples into their respective petrographic fabrics . …”
Get full text

Wavelet Decomposition Prediction for Digital Predistortion of Wideband Power Amplifiers by Shaocheng Peng, Jing You

“…Once the nonlinear model is trained, it is frozen to preserve its learned features. …”
Get full text

Robust Automated Mouse Micro-CT Segmentation Using Swin UNEt TRansformers by Lu Jiang, Di Xu, Qifan Xu, Arion Chatziioannou, Keisuke S. Iwamoto, Susanta Hui, Ke Sheng

“…The models were trained and evaluated on open datasets, with data separation based on individual mice. …”
Get full text

Fall Risk Prediction Using Instrumented Footwear in Institutionalized Older Adults by Huanghe Zhang, Chuanyan Wu, Yulong Huang, Rui Song, Damiano Zanotto, Sunil K. Agrawal

“…The importance of each type of data is assessed using a brute-force search method, through which the optimal features are selected. AdaBoost algorithms are then utilized to develop predictive models based on the selected features. …”
Get full text

Predictive value of preclinical models for CAR-T cell therapy clinical trials: a systematic review and meta-analysis by Sebastian Kobold, Carsten Marr, David Andreu-Sanz, Lisa Gregor, Emanuele Carlini, Daniele Scarcella

“…While the logistic regression model accurately predicted clinical outcomes based on clinical or preclinical features (Macro F1 and area under the curve (AUC)>0.8), it failed in predicting preclinical outcomes from preclinical features (Macro F1<0.5, AUC<0.6), indicating that preclinical studies may be influenced by experimental factors not accounted for in the model.Conclusion These findings underscore the need to better understand the experimental factors enhancing the predictive accuracy of mouse models in preclinical settings.…”
Get full text

GTN-GCN: Real-Time Traffic Forecasting Using Graph Convolutional Network and Transformer by Sadia Naj Jinia, Sumaiya Binte Azad, Rima Akter, Taivan Reza Dipto, Md. Khaliluzzaman

“…The DTM dynamically updates graph structures based on real-time traffic conditions, while GATs focus on identifying critical spatial relationships. …”
Get full text

Predictive power demand for energy management of hybrid electric tractors by Christian Varlese, Johannes Konrad, Thomas Volf, Dominik Brunner, Christoph Hametner, Peter Hofmann

“…This work focuses on two main contributions: the statistical analysis of tractor real-duty scenarios in agriculture and the development of a power demand predictor model for tractors. Based on the real-data framework, the characteristics of the farming cycles and relevant prediction features were constructed and selected. …”
Get full text

GDPGO-SAM: An Unsupervised Fine Segmentation of Desert Vegetation Driven by Grounding DINO Prompt Generation and Optimization Segment Anything Model by Shuzhen Hua, Biao Yang, Xinchang Zhang, Ji Qi, Fengxi Su, Jing Sun, Yongjian Ruan

“…The framework combines the Grounding DINO object detector and the pre-trained visual model SAM, employing a task-prior-based prompt optimization mechanism to effectively capture the innate features of desert vegetation. …”
Get full text

Transfer learning drives automatic HER2 scoring on HE-stained WSIs for breast cancer: a multi-cohort study by Xiaoping Li, Zhiquan Lin, Chaoran Qiu, Yiwen Zhang, Chuqian Lei, Shaofei Shen, Weibin Zhang, Chan Lai, Weiwen Li, Hui Huang, Tian Qiu

“…The transfer-learning-based probabilistic aggregation (TL-PA) model and multi-instance learning (MIL)-based models were compared, both of which were trained on Cohort A and validated on Cohorts B–D. …”
Get full text

Mobile Apps Designed for Patients With Polycystic Ovary Syndrome: Content Analysis Using the Mobile App Rating Scale by Zahra Arabkermani, Saeed Barzegari, Atefeh Rouhani, Nilofar Nahavandi, Omer Gibreel, Ibrahim Arpaci

“…These results underscore the need for future app development to incorporate more user-engaging features, reliable evidence-based content, and personalization strategies to enhance user engagement and support effective PCOS self-management. …”
Get full text

Perspectives on Generative Sound Design: A Generative Soundscapes Showcase by Grzegorz Samson

“…Recent advancements in generative neural networks, particularly transformer-based models, have introduced novel possibilities for sound design. …”
Get full text

NevusCheck: A Dysplastic Nevi Detection Model Using Convolutional Neural Networks by Andreluis Ingaroca-Torres, Lucía Heredia-Moscoso, Alvaro Aures-García

“…A specific deep learning technique to identify diseases is convolutional neural networks (CNNs) because of their great capacity to extract features and classify objects. Therefore, the research aims to develop a model to diagnose dysplastic nevi using a deep learning network whose classification is based on the pre-trained architecture EfficientNet-B7, which was selected for its high classification accuracy and low computational complexity. …”
Get full text

A Multicomponent Face Verification and Identification System by Athanasios Douklias, Ioannis Zorzos, Evangelos Maltezos, Vasilis Nousis, Spyridon Nektarios Bolierakis, Lazaros Karagiannidis, Eleftherios Ouzounoglou, Angelos Amditis

“…Face recognition technology is a biometric technology, which is based on the identification or verification of facial features. …”
Get full text

Enhancing smart city sustainability with explainable federated learning for vehicular energy control by Khalid Ishaq Abdullah Almaazmi, Saif Jasim Almheiri, Muhammad Adnan Khan, Asghar Ali Shah, Sagheer Abbas, Munir Ahmad

“…Traditional centralized machine learning models and cloud-based Energy Management Systems (EMSs) struggle with real-time adaptability, high-dimensional data processing, and data privacy risks. …”
Get full text

Predicting Nottingham grade in breast cancer digital pathology using a foundation model by Jun Seo Kim, Jeong Hoon Lee, Yousung Yeon, Doyeon An, Seok Jun Kim, Myung-Giun Noh, Suehyun Lee

“…The model leveraged deep features extracted from a pathology foundation model (UNI) and incorporated 14 distinct multiple instance learning (MIL) algorithms. …”
Get full text

The Necessity of Regulating Drinking Scenes on Social Media Platforms Focusing on YouTube Sulbang Videos: Public Opinion From Surveys and YouTube Content Analysis by HyoRim Ju, HyeWon Lee, Juyoung Choi, EunKyo Kang

“…Two trained coders independently analyzed the videos, achieving high intercoder reliability (Cohen κ=0.92). …”
Get full text

Personalized client-edge-cloud hierarchical federated learning in mobile edge computing by Chunmei Ma, Xiangqian Li, Baogui Huang, Guangshun Li, Fengyin Li

“…This is because the personalized model captures the features of users’ local data more accurately than the unified model. …”
Get full text

INDIVIDUAL AND TYPOLOGICAL APPROACH DURING PSYCHOTHERAPEUTIC AID TO PREGNANT FEMALE WORKERS OF METALLURGICAL PRODUCTION by Марина Васильевна Буркацкая, Павел Николаевич Москвитин, Ольга Ивановна Баран

“…The study of the personal typology of pregnant female workers of the metallurgical enterprise was carried out using the typological test of D. Keirsey, based on the needs of psychological and psychotherapeutic counseling. …”
Get full text

Sport for Development and Psychosocial Wellbeing in Displacement Settings: A Quasi-Experimental Study from the Kurdistan Region of Iraq by Louis Moustakas, Viviane Raub, Karen Petry, Jule Wagner, Mareike Broermann, Jihan Alfindi, Samyan Al-Barwari, Tanya Mohammed, Buthaina Qafisheh, Warhel Asim Mohammed, Dilshad Aldoski

“…Overall, though there are limitations to this intervention, these results likely highlight the importance of long-term interventions featuring well-trained coaches who are sensitive to local context and realities. …”
Get full text

ARC-LIGHT: Algorithm for Robust Characterization of Lunar Surface Imaging for Ground Hazards and Trajectory by Alexander Cushen, Ariana Bueno, Samuel Carrico, Corrydon Wettstein, Jaykumar Ishvarbhai Adalja, Mengxiang Shi, Naila Garcia, Yuliana Garcia, Mirko Gamba, Christopher Ruf

“…Based on these findings, a development timeline, risk analysis, and budget for ARC-LIGHT to be deployed on a lunar landing was created.…”
Get full text