PiCoCo: Pixelwise Contrast and Consistency Learning for Semisupervised Building Footprint Segmentation by Jian Kang, Zhirui Wang, Ruoxin Zhu, Xian Sun, Ruben Fernandez-Beltran, Antonio Plaza

“…Most state-of-the-art methods based on CNNs are focused on the design of network architectures for improving the predictions of building footprints with full annotations, while few works have been done on building footprint segmentation with limited annotations. …”
Get full text

Presentation Attack Detection on Limited-Resource Devices Using Deep Neural Classifiers Trained on Consistent Spectrogram Fragments by Kacper Kubicki, Paweł Kapusta, Krzysztof Ślot

“…We propose a novel approach to convolutional phoneme classifier training, which ensures high phoneme recognition accuracy even for significantly simplified network architectures, thus enabling efficient utterance verification on resource-limited hardware, such as mobile phones or embedded devices. …”
Get full text

A Low Complexity Persistent Reconnaissance Algorithm for FANET by Yuan Guo, Hongying Tang, Ronghua Qin

“…Researchers have proposed various network architectures and routing protocols to address the network connectivity problems associated with the high mobility of UAVs, and have achieved considerable results in a flying ad hoc network (FANET). …”
Get full text

Artificial intelligence in remote sensing geomorphology—a critical study by Urs Mall, Daniel Kloskowski, Philip Laserstein, Philip Laserstein

“…Our research makes the case that despite the increasing ease with which deep learning methods can be applied to existing data sets, a more thorough and critical assessment of the AI results is required to ensure that future network architectures can produce the reliable geomorphological maps that these methods are capable of delivering.…”
Get full text

Bayesian Inference and Dynamic Neural Feedback Promote the Clinical Application of Intelligent Congenital Heart Disease Diagnosis by Weimin Tan, Yinyin Cao, Xiaojing Ma, Ganghui Ru, Jichun Li, Jing Zhang, Yan Gao, Jialun Yang, Guoying Huang, Bo Yan, Jian Li

“…We demonstrate on various neural network architectures how the reliability obtained by Bayesian inference interprets and quantifies the significant performance difference between internal and external test sets of neural networks, and how the devised feedback cell helps the neural networks to maintain high accuracy and reliability, despite the input being corrupted by noise or when using an external test set.…”
Get full text

A Novel Base-Station Selection Strategy for Cellular Vehicle-to-Everything (C-V2X) Communications by Qiaozhi Hua, Keping Yu, Zheng Wen, Takuro Sato

“…Currently, a macro-femtocell network is used as the new C-V2X networking architecture. However, there are two unresolved problems for C-V2X in macro-femtocell networks. …”
Get full text

Networked health care: Rethinking value creation in learning health care systems by Øystein D. Fjeldstad, Julie K. Johnson, Peter A. Margolis, Michael Seid, Pär Höglund, Paul B. Batalden

“…This paper proposes a networked architecture that can mobilize and integrate the resources of health care professionals, interested patients, family, and other community members in the delivery and improvement of health care systems. …”
Get full text

Tomato Disease Recognition Using a Compact Convolutional Neural Network by Emre Ozbilge, Mehtap Kose Ulukok, Onsen Toygar, Ebru Ozbilge

“…The results show that the proposed network performs better than pre-trained knowledge transferred deep network models, and that there is no need to constitute very large, complicated network architectures to achieve superior tomato disease identification performance. …”
Get full text

LEET: stock market forecast with long-term emotional change enhanced temporal model by Honglin Liao, Jiacheng Huang, Yong Tang

“…The experimental results obtained from a genuine dataset demonstrate that this method is superior to the majority of deep learning network architectures when it comes to predicting stock prices.…”
Get full text

Outdoor Plant Segmentation With Deep Learning for High-Throughput Field Phenotyping on a Diverse Wheat Dataset by Radek Zenkl, Radu Timofte, Norbert Kirchgessner, Lukas Roth, Andreas Hund, Luc Van Gool, Achim Walter, Helge Aasen

“…Increasing the amount of publicly available data with high human agreement on annotations and further development of deep neural network architectures will provide high potential for robust field-based plant segmentation in the near future. …”
Get full text

Local Descriptor Learning for Change Detection in Synthetic Aperture Radar Images via Convolutional Neural Networks by Huihui Dong, Wenping Ma, Yue Wu, Maoguo Gong, Licheng Jiao

“…Considering that change detection task takes image pairs as an input, we first explore multiple neural network architectures, which are specifically adapted to the change detection task. …”
Get full text

Detection of Patients with Congenital and Often Concealed Long-QT Syndrome by Novel Deep Learning Models by Florian Doldi, Lucas Plagwitz, Lea Philine Hoffmann, Benjamin Rath, Gerrit Frommeyer, Florian Reinke, Patrick Leitz, Antonius Büscher, Fatih Güner, Tobias Brix, Felix Konrad Wegner, Kevin Willy, Yvonne Hanel, Sven Dittmann, Wilhelm Haverkamp, Eric Schulze-Bahr, Julian Varghese, Lars Eckardt

“…Objective: Identification of congenital and often concealed LQTS by utilizing novel deep learning network architectures, which are specifically designed for multichannel time series and therefore particularly suitable for ECG data. …”
Get full text

An Investigation of Preprocessing Filters and Deep Learning Methods for Vessel Type Classification With Underwater Acoustic Data by Lucas C. F. Domingos, Paulo E. Santos, Phillip S. M. Skelton, Russell S. A. Brinkworth, Karl Sammut

“…Various combinations of deep convolutional neural network architectures, and preprocessing filter layers, were evaluated using a new dataset based on a subset of the extensive open-source Ocean Networks Canada hydrophone data. …”
Get full text

A Novel Method for the Classification of Butterfly Species Using Pre-Trained CNN Models by Fathimathul Rajeena P. P., Rasha Orban, Kogilavani Shanmuga Vadivel, Malliga Subramanian, Suresh Muthusamy, Diaa Salam Abd Elminaam, Ayman Nabil, Laith Abulaigh, Mohsen Ahmadi, Mona A. S. Ali

“…This research work utilizes transfer learning based on various convolutional neural network architectures such as VGG16, VGG19, MobileNet, Xception, ResNet50, and InceptionV3 to classify the butterfly species into various categories. …”
Get full text

DeepRare: Generic Unsupervised Visual Attention Models by Phutphalla Kong, Matei Mancas, Bernard Gosselin, Kimtho Po

“…Finally, <b>DR21</b> (4) is tested with several network architectures such as VGG16 (V16), VGG19 (V19), and MobileNetV2 (MN2), and (5) it provides explanation and transparency on which parts of the image are the most surprising at different levels despite the use of a DNN-based feature extractor.…”
Get full text

HFNet: A CNN Architecture Co-designed for Neuromorphic Hardware With a Crossbar Array of Synapses by Roshan Gopalakrishnan, Yansong Chua, Pengfei Sun, Ashish Jith Sreejith Kumar, Ashish Jith Sreejith Kumar, Arindam Basu

“…The hardware-software co-optimization of neural network architectures is a field of research that emerged with the advent of commercial neuromorphic chips, such as the IBM TrueNorth and Intel Loihi. …”
Get full text

Learning-in-the-Fog (LiFo): Deep Learning Meets Fog Computing for the Minimum-Energy Distributed Early-Exit of Inference in Delay-Critical IoT Realms by Enzo Baccarelli, Michele Scarpiniti, Alireza Momenzadeh, Sima Sarv Ahrabi

“…Interestingly enough, the designed algorithm is capable to self-detect (typically, unpredictable) environmental changes and quickly self-react them by properly re-configuring the available computing and networking resources; and, (iii) we design the main building blocks and related virtualized functionalities of an Information Centric-based networking architecture, which enables the LiFo platform to perform the aggregation of spatially-distributed IoT sensed data. …”
Get full text

Determination of Neural Network Parameters for Path Loss Prediction in Very High Frequency Wireless Channel by Segun I. Popoola, Abigail Jefia, Aderemi A. Atayero, Ogbeide Kingsley, Nasir Faruk, Olasunkanmi F. Oseni, Robert O. Abolade

“…Different neural network architectures were trained with varying kinds of input parameters, number of hidden neurons, activation functions, and learning algorithms to accurately predict corresponding path loss values. …”
Get full text

Deep Learning-Based Gender Classification by Training With Fake Data by Mohamed Oulad-Kaddour, Hamid Haddadou, Cristina Conde Vilda, Daniel Palacios-Alonso, Karima Benatchba, Enrique Cabello

“…Four classifiers based on popular convolutional neural network architectures were implemented. In the test phase, we used faces of real identities extracted from well-known experimental databases such as Face Recognition Technology (FERET), Faculdade de Engenharia Industrial (FEI) faces, Face Recognition and Artificial Vision (FRAV) and Labeled Faces in the Wild (LFW). …”
Get full text

A unified view on weakly correlated recurrent networks by Dmytro eGrytskyy, Dmytro eGrytskyy, Tom eTetzlaff, Tom eTetzlaff, Markus eDiesmann, Markus eDiesmann, Markus eDiesmann, Moritz eHelias, Moritz eHelias

“…The derived averages are exact for fixed out-degree network architectures and approximate for fixed in-degree. …”
Get full text