An Efficient and Low-Complexity Transformer-Based Deep Learning Framework for High-Dynamic-Range Image Reconstruction by Josue Lopez-Cabrejos, Thuanne Paixão, Ana Beatriz Alvarez, Diodomiro Baldomero Luque

“…In this context, various architectures with different approaches exist, such as convolutional neural networks, diffusion networks, generative adversarial networks, and Transformer-based architectures, with the latter offering the best quality but at a high computational cost. …”
Get full text

A Non-Contact AI-Based Approach to Multi-Failure Detection in Avionic Systems by Chengxin Liu, Michele Ferlauto, Haiwen Yuan

“…The proposed method combines a self-attention mechanism with an adaptive graph convolutional neural network to enhance diagnostic precision. …”
Get full text

A Rolling-Bearing-Fault Diagnosis Method Based on a Dual Multi-Scale Mechanism Applicable to Noisy-Variable Operating Conditions by Jing Kang, Taiyong Wang, Ye Wei, Usman Haladu Garba, Ying Tian

“…Ultimately, the signal that has been denoised is utilized as input for the DWMFCNN model to recognize different kinds of rolling-bearing faults. Results from the experiments show that the suggested approach shows an improved denoising performance and a greater adaptability to changing working conditions.…”
Get full text

Investigating the accuracy of neural networks for blood pressure prediction in the ICU by Charles J. Gillan, Bartosz Gorecki

“…The physiological state of an ICU patient is therefore quite different to a hyper or hypotensive patient outside hospital, suggesting that predicting blood pressure in this environment is more challenging The work investigates whether building neural network architectures with multivariate input data is capable of predicting blood pressures in this environment. …”
Get full text

Evaluation of YOLO Efficiency in Automatic Orange Detection in Multi-Exposure Images by M. R. Oviedo Espinosa, L. R. Porto, V. S. W. Orlando, A. M. G. Tommaselli, A. P. Dal Poz, N. N. Imai

“…In this sense, this paper focus on the detection of oranges in multispectral images, with different spectral bands and exposures, using a convolutional neural network (CNN) known as YOU ONLY LOOK ONCE (YOLO). …”
Get full text

Deep-Learning Techniques Applied for State-Variables Estimation of Two-Mass System by Grzegorz Kaczmarczyk, Radoslaw Stanislawski, Marcin Kaminski

“…The design stages and the overall concept in this case are completely different than with the applications of classical observers (e.g., the Luenberger, the Kalman filter) often used for similar objects. …”
Get full text

HyperKon: A Self-Supervised Contrastive Network for Hyperspectral Image Analysis by Daniel La’ah Ayuba, Jean-Yves Guillemaut, Belen Marti-Cardona, Oscar Mendez

“…We also perform a thorough ablation study on different kinds of layers, showing their performance in understanding hyperspectral layers. …”
Get full text

Experimentally validated inverse design of FeNiCrCoCu MPEAs and unlocking key insights with explainable AI by Fangxi Wang, Allana G. Iwanicki, Abhishek T. Sose, Lucas A. Pressley, Tyrel M. McQueen, Sanket A. Deshmukh

“…This computational workflow, along with the fundamental insights gained, can be readily expanded and applied to the design of MPEAs with different elemental compositions, as well as to materials beyond MPEAs.…”
Get full text

Enhancing Remote Sensing Image Quality through Data Fusion and Synthetic Aperture Radar (SAR): A Comparative Analysis of CNN, Lightweight ConvNet, and VGG16 Models by Desynike Puspa Anggreyni, Indriatmoko, Aniati Murni Arymurthy, Andie Setiyoko

“…The method involves using Synthetic Aperture Radar (SAR) to combine adjacent satellite images from different viewpoints, thereby improving image coverage. …”
Get full text

Altitude aware trajectory prediction methods for non towered terminal airspace by Haipeng Zhu, Qiang Tong, Jinqing Hu, Xiulei Liu, Shoulu Hou

“…The model independently extracts altitude features using temporal convolutional networks(TCN), it then incorporates a channel attention fusion mechanism to dynamically fuse altitude features into the trajectory representation across different channels. …”
Get full text

A selective CutMix approach improves generalizability of deep learning-based grading and risk assessment of prostate cancer by Sushant Patkar, Stephanie Harmon, Isabell Sesterhenn, Rosina Lis, Maria Merino, Denise Young, G. Thomas Brown, Kimberly M. Greenfield, John D. McGeeney, Sally Elsamanoudi, Shyh-Han Tan, Cara Schafer, Jiji Jiang, Gyorgy Petrovics, Albert Dobi, Francisco J. Rentas, Peter A. Pinto, Gregory T. Chesnut, Peter Choyke, Baris Turkbey, Joel T. Moncur

“…This strategy resulted in improved model generalizability in the test set compared with three different control experiments when evaluated on both needle biopsy slides and whole-mount prostate slides from different centers. …”
Get full text

STYLISTIC MEANS OF IMPLEMENTING THE IDEA OF THE WORLD’S IRIDESCENCE IN PH.K. DICK’S “UBIK” IN THE CONTEXT OF TRANSLATION TRANSFORMATIONS by Svitlana F. Aleksenko, Larysa I. Taranenko

“…The idea of the world’s iridescence in the novel is brought about by the literary work’s fluctuating plot convolutions stemming from seemingly incoherent planes of different sections of the novel: a mosaic of the primary diegesis together with several hypo-diegeses comes across as a kind of an ontic hazy maze building up to an overall effect of the world’s fluidity and oscillation. …”
Get full text

Fully invertible hyperbolic neural networks for segmenting large-scale surface and sub-surface data by Bas Peters, Eldad Haber, Keegan Lensink

“…We address the explosion of the number of convolutional kernels by combining fully invertible networks with layers that contain the convolutional kernels in a compressed form directly. …”
Get full text

A novel method based on the SCNGO‐ICEEMDAN and MCNN‐BiLSTM model for fault diagnosis of motor bearings for more electric aircraft by Dongsheng Yuan, Feng Liu, Zhonggang Yin, Yanqing Zhang, Yanping Zhang, Peien Luo

“…Then, a multi‐scale convolutional neural network (MCNN) is used to extract the time–frequency domain features of the de‐noised signal and perform information fusion. …”
Get full text

TSNetIQ: High-Resolution DOA Estimation of UAVs Using Microphone Arrays by Kequan Zhu, Tian Jin, Shitong Xie, Zixuan Liu, Jinlong Sun

“…Experiments are conducted to evaluate the proposed method under different signal-to-noise ratios (SNRs), sampling frequencies, and array configurations. …”
Get full text

Space Precession Target Classification Based on Radar High-Resolution Range Profiles by Yizhe Wang, Cunqian Feng, Yongshun Zhang, Sisan He

“…This paper presents two methods for classifying different types of space precession targets from the HRRPs. …”
Get full text

Digital Twin Network-Based 6G Self-Evolution by Yuhong Huang, Mancong Kang, Yanhong Zhu, Na Li, Guangyi Liu, Qixing Wang

“…Specifically, the proposed architecture introduces a key concept called “future shots” that gives accurate network predictions under different time scales of self-evolution strategies for various network elements. …”
Get full text

CNN Based Automatic Speech Recognition: A Comparative Study by Hilal Ilgaz, Beyza Akkoyun, Özlem Alpay, M. Ali Akcayol

“…The data set consists of one-second voice commands that have been converted into a spectrogram and used to train different artificial neural network (ANN) models. Various variants of CNN are used in deep learning applications. …”
Get full text

Sound Quality Prediction Method of Dual-Phase Hy-Vo Chain Transmission System Based on MFCC-CNN and Fuzzy Generation by Jiabao LI, Lichi AN, Yabing CHENG, Haoxiang WANG

“…To understand the impact of the MFCC order and the frame number on prediction accuracy, MFCC feature maps of different specifications are analyzed. The dataset is expanded threefold using fuzzy generation with an appropriate membership degree. …”
Get full text

Integrating Viewing Direction and Image Features for Robust Multi-View Multi-Object 3D Pedestrian Tracking by R. Ali, M. Mehltretter, C. Heipke

“…However, many of these developments do not address the critical challenge of generalization across different camera constellations, i.e., having camera constellations that differ between training and testing, limiting their effectiveness in real-world applications. …”
Get full text