Artificial Intelligence for Detecting COVID-19 With the Aid of Human Cough, Breathing and Speech Signals: Scoping Review by Mouzzam Husain, Andrew Simpkin, Claire Gibbons, Tanya Talkar, Daniel Low, Paolo Bonato, Satrajit S. Ghosh, Thomas Quatieri, Derek T. O'Keeffe

“…More than half of the included studies reported area-under-the-curve performance of greater than 0.90 on symptomatic and negative datasets while one study achieved 100% sensitivity in predicting asymptomatic COVID-19 from cough-, breathing- or speech-based acoustic features. <italic>Conclusions:</italic> The included studies show that AI has the potential to help detect COVID-19 using cough, breathing and speech samples. …”
Get full text

Improved Multi-Grained Cascade Forest Model for Transformer Fault Diagnosis by Yiyi Zhang, Yuxuan Wang, Jiefeng Liu, Heng Zhang, Xianhao Fan, Dongdong Zhang

“…Firstly, in order to extract features more effectively and reduce memory consumption, the multi-grained scanning of gcForest is replaced by convolutional neural networks. …”
Get full text

A Dataset for Investigations of Amine-Impregnated Solid Adsorbent for Direct Air Capture by Eryu Wang, Liping Luo, Jiachuan Wang, Jiaxin Dai, Shuangyin Li, Lei Chen, Jia Li

“…In addition, two machine learning models were trained to promote dataset reuse by scientists from lab-based research and cheminformatics. …”
Get full text

Efficient Argan Tree Deforestation Detection Using Sentinel-2 Time Series and Machine Learning by Younes Karmoude, Soufiane Idbraim, Souad Saidi, Antoine Masse, Manuel Arbelo

“…Various machine learning models were evaluated for argan tree detection, with LightGBM achieving the highest accuracy when trained on a dataset integrating spectral bands, temporal features, and vegetation indices information. …”
Get full text

Pseudolabel guided pixels contrast for domain adaptive semantic segmentation by Jianzi Xiang, Cailu Wan, Zhu Cao

“…Unsupervised domain adaptation (UDA) for semantic segmentation is a technique that uses virtual data with labels to train a model and adapts it to real data without labels. …”
Get full text

Damage Detection of Seismically Excited Buildings Using Neural Network Arrays with Branch Pruning Optimization by Jau-Yu Chou, Chia-Ming Chang, Chieh-Yu Liu

“…A dense, single-layer neural network array is initially trained with full floor accelerations, then pruned iteratively via the Lottery Ticket Hypothesis to retain only the most effective sub-networks. …”
Get full text

Lightning Damage Detection Method Using Autoencoder: A Case Study on Wind Turbines with Different Blade Damage Patterns by Takuto Matsui, Kazuki Matsuoka, Kazuo Yamamoto

“…The present method selected wind speed and rotational speed as effective features, employing a sliding window for pre-processing, based on previous studies. …”
Get full text

Smart Thermostat Development and Validation on an Environmental Chamber Using Surrogate Modelling by Leonidas Zouloumis, Nikolaos Ploskas, Nikolaos Taousanidis, Giorgos Panaras

“…Finally, the methodology has the potential to meet the requirements of future building energy systems featured in urban-scale RES-based district heating networks.…”
Get full text

A novel framework GRCornShot for corn disease detection using few shot learning with prototypical network by Ruchi Rani, Jayakrushna Sahoo, Sivaiah Bellamkonda, Sumit Kumar

“…However, deep learning techniques demand a large quantity of data to train the models for diagnosis and further classification. …”
Get full text

Convolutional sparse coding network for sparse seismic time-frequency representation by Qiansheng Wei, Zishuai Li, Haonan Feng, Yueying Jiang, Yang Yang, Zhiguo Wang

“…The LISTA block, which evolves from the traditional iterative shrinkage thresholding algorithm (ISTA), is optimized for extracting sparse features more effectively. Furthermore, we create a synthetic dataset featuring complex frequency-modulated signals to train ULISTANet. …”
Get full text

Opportunities and Limitations of Wrist-Worn Devices for Dyskinesia Detection in Parkinson’s Disease by Alexander Johannes Wiederhold, Qi Rui Zhu, Sören Spiegel, Adrin Dadkhah, Monika Pötter-Nerger, Claudia Langebrake, Frank Ückert, Christopher Gundler

“…Dimensionality reduction in accelerometer-based movement data positively impacts performance, and models trained with semantically obtained features avoid overfitting. …”
Get full text

Detection of fasting blood sugar using a microwave sensor and convolutional neural network by Mohammad Amir Sattari, Mohsen Hayati

“…To interpret the complex, non-linear features of the sensor response, a convolutional neural network (CNN) was developed and trained using the entire dataset. …”
Get full text

Unobtrusive Nighttime Movement Monitoring to Support Nursing Home Continence Care: Algorithm Development and Validation Study by Hannelore Strauven, Chunzhuo Wang, Hans Hallez, Vero Vanden Abeele, Bart Vanrumste

“…Each window was labeled with 1 of the 4 chosen activity classes: in bed, agitation, turn, and out of bed. A total of 1416 features were selected and analyzed with an XGBoost algorithm. …”
Get full text

Nowcasting reported covid-19 hospitalizations using de-identified, aggregated medical insurance claims data. by Xueda Shen, Aaron Rumack, Bryan Wilder, Ryan J Tibshirani

“…We propose, implement, and evaluate a method for nowcasting the daily number of new COVID-19 hospitalizations, at the level of individual US states, based on de-identified, aggregated medical insurance claims data. …”
Get full text

Lyophilization and Sensory Analysis of Traditional Artisan Turkish Cheeses by Ebru Yıldırım, Celal Can Yalçıner, İlkay Yılmaz

“…Following the drying process, the sensory properties of the cheeses were evaluated by 10 trained panelists based on attributes, such as color, odor, texture, crispness, aroma, mouthfeel, and overall acceptability. …”
Get full text

Representation Learning of Multi-Spectral Earth Observation Time Series and Evaluation for Crop Type Classification by Andrea González-Ramírez, Clement Atzberger, Deni Torres-Roman, Josué López

“…Here, we propose a conceptually and computationally simple representation learning (RL) approach based on autoencoders (AEs) to generate discriminative features for crop type classification. …”
Get full text

Prediction of breast cancer Invasive Disease Events using transfer learning on clinical data as image-form. by Annarita Fanizzi, Samantha Bove, Maria Colomba Comes, Erika Francesca Di Benedetto, Agnese Latorre, Francesco Giotta, Annalisa Nardone, Alessandro Rizzo, Clara Soranno, Alfredo Zito, Raffaella Massafra

“…After transforming each patient, represented by a vector of clinical information, to an image form, we extracted low-level quantitative imaging features by means of a pre-trained Convolutional Neural Network, namely, AlexNET. …”
Get full text

Synergistic image and point cloud processing of UAV data for urban flood modeling: point cloud smart thinning and curb mapping by P. A. P. Zamboni, H. Hendrickx, D. Sprute, H. Flatt, M. I. Rushdi, F. Brodrecht, A. Eltner

“…Curb candidate points were proposed using geometric characteristics of the point cloud, including normal values, linearity, and verticality. Our rule-based method effectively mapped even subtle curb features, providing a rapid, cost-effective solution for large-area curb mapping. …”
Get full text

Translation of computed tomography images to T2-Weighted magnetic resonance images of lumbar spine using generative adversarial networks on sagittal images by Kwang Hyeon Kim, Eun-Chong Lee, Yeo Dong Yoon, Dong-Won Shin, Hae-Won Koo, Byung-Jou Lee

“…In qualitative evaluation, the similarity score for anatomical features (e.g., disc signal, paraspinal muscles, facet joints) averaged over 80%. …”
Get full text

Harmonizer: A Universal Signal Tokenization Framework for Multimodal Large Language Models by Amin Amiri, Alireza Ghaffarnia, Nafiseh Ghaffar Nia, Dalei Wu, Yu Liang

“…Harmonizer employs a unified approach to convert diverse, non-linguistic signals into discrete tokens via its FusionQuantizer architecture, built on FluxFormer, to efficiently capture essential signal features while minimizing complexity. We enhance features through STFT-based spectral decomposition, Hilbert transform analytic signal extraction, and SCLAHE spectrogram contrast optimization, and train using a composite loss function to produce reliable embeddings and construct a robust vector vocabulary. …”
Get full text