EdgeCompress: coupling multi-dimensional model compression and dynamic inference for EdgeAI by Kong, Hao, Liu, Di, Huai, Shuo, Luo, Xiangzhong, Subramaniam, Ravi, Makaya, Christian, Lin, Qian, Liu, Weichen

“…Dynamic image cropping and compound shrinking together constitute a multi-dimensional CNN compression framework, which is able to comprehensively reduce the computational redundancy in both input images and neural network architectures, thereby improving the inference efficiency of CNNs. …”
Get full text

Facial macro expression analysis by Lim, Jie Xian

“…The methodology employed involves the integration of advanced neural network architectures, including Convolutional Neural Networks (CNNs) to process and analyze facial expressions from static images. …”
Get full text

Artificial intelligence (AI) processing for enhancing an intelligent sensor - I by Ng, Jessie Wei Jie

“…Nevertheless, prevailing solutions have predominantly relied on singular network architectures to capture the inverse scattering process, yielding less than optimal recovery outcomes. …”
Get full text

Application of deep learning algorithm for synthetic aperture radar automatic target recognition by Zhao, Yuxuan

“…Focusing on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset, the study provides an exhaustive comparison between two state-of-the-art convolutional neural network architectures: the You Only Look Once (YOLO) versions 5 and 8. …”
Get full text

Towards SDN-Enabled Big Data Platform for Social TV Analytics by Hu, Han, Wen, Yonggang, Gao, Yue, Chua, Tat-Seng, Li, Xuelong

“…Such a platform presents tremendous challenges in networking architecture for our big data platform. We propose to build a cloud-centric platform with SDN support, providing on-demand virtual machines and reconfigurable networks. …”
Get full text
Get full text

Highly stable 3D porous heterostructures with hierarchically-coordinated octahedral transition metals for enhanced performance supercapacitors by Hong, J, Lee, Y, Ahn, D, Pak, S, Lee, J, Jang, A, Lee, S, Hou, B, Cho, Y, Morris, S, Shin, H, Cha, S, Sohn, J, Kim, J

“…The superior pseudo-capacitive energy storage characteristics are strongly attributed to the interconnected 3D nanoporous network architectures of the TTMOs along with the secondary layered nanosheets that provide 1) the enlarged surface area with the high conductivity, 2) the facile and multi-access ion paths, and 3) the favorable structural stability. …”

Synthesis, structure and properties of three 1D d10 metal–organic coordination polymers with 5-amino-2,4,6-triiodoisophthalic acid by Zhang, L., Wei, Y., Zhong, Y.Q., Chang, Y., Meng, Q.H., Ng, S.W., Zhang, K.L.

“…Extended 3D supramolecular network architectures are further constructed through the weak secondary interactions: aromatic stacking, halogen bonding and hydrogen bonding. …”

CNN architectures for road surface wetness classification from acoustic signals by Bahrami, Siavash, Doraisamy, Shyamala, Azman, Azreen, Nasharuddin, Nurul Amelina, Yue, Shigang

“…Experimentation and comparative performance evaluations against several neural networks architectures were performed. Recorded acoustic signals were segmented into equal frames and thirteen MFCCs were extracted for each frame to train the CNNs. …”
Get full text

Voice verification using i-vectors and neural networks with limited training data by Mamyrbayev, Orken Zh., Othman, Mohamed, Akhmediyarova, A. T., Kydyrbekova, Aizada S., Mekebayev, Nurbapa O.

“…This poses unique challenges in developing DNN-based voice identification systems, since optimized external interfaces and network architectures can no longer be used. We propose to use the training i-Vectors to train the initial DNN to identify the voice. …”
Get full text

Principles and Labs for Deep Learning / by Huang, Shih-Chia, author 651354, Le, Trung-Hieu, author 651355, ScienceDirect (Online service) 7722

Get full text

Att-TasNet: Attending to Encodings in Time-Domain Audio Speech Separation of Noisy, Reverberant Speech Mixtures by William Ravenscroft, Stefan Goetze, Thomas Hain

“…Time-domain audio speech separation networks (TasNets) are among the most commonly used network architectures for this task. TasNet models have demonstrated strong performance on typical speech separation baselines where speech is not contaminated with noise. …”
Get full text

HISTOPATHOLOGY IMAGE CLASSIFICATION USING HYBRID PARALLEL STRUCTURED DEEP-CNN MODELS by Kevin Joy DSOUZA, Zahid Ahmed ANSARI

“…Further, the proposed models are parallelized using the TensorFlow-GPU framework to accelerate the training of these deep CNN (Convolution Neural Networks) architectures. This study uses the transfer learning technique during training and early stopping criteria are used to avoid overfitting during the training phase. these models use LSTM parallel layer imposed in the model to experiment with four considered architectures such as MobileNet, VGG16, and ResNet with 101 and 152 layers. …”
Get full text

Automatic feature selection for performing Unit 2 of vault in wheel gymnastics. by Eiji Kitajima, Takashi Sato, Koji Kurata, Ryota Miyata

“…We implemented this automation using recurrent all-pairs field transforms (RAFT) and XMem, i.e., deep network architectures respectively for optical flow estimation and video object segmentation. …”
Get full text

Investigations on the Optimal Estimation of Speech Envelopes for the Two-Stage Speech Enhancement by Yanjue Song, Nilesh Madhu

“…Next, we investigate low-complexity neural network architectures to map degraded envelopes to the optimal codebook entry in practical systems. …”
Get full text

Artificial neural network models for prediction of intestinal permeability of oligopeptides by Kim Min-Kook, Kang Sang-Kee, Choi Kihang, Shin Jae-Min, Rhee Hokyoung, Jung Dong, Kim Minkyoung, Kim Junhyoung, Jung Eunkyoung, Yun Cheol-Heui, Choi Yun-Jaie, Choi Seung-Hoon

“…Both binary and VHSE (principal components score Vectors of Hydrophobic, Steric and Electronic properties) descriptors produced statistically significant training models; the models with simple neural network architectures showed slightly greater predictive power than those with complex ones. …”
Get full text

EnsembleSplice: ensemble deep learning model for splice site prediction by Victor Akpokiro, Trevor Martin, Oluwatosin Oluwadare

“…Within this research purview, efficient and accurate splice site detection is highly desirable, and a variety of computational models have been developed toward this end. Neural network architectures have recently been shown to outperform classical machine learning approaches for the task of splice site prediction. …”
Get full text

Convolutional Neural Networks Hyperparameter Tunning for Classifying Firearms on Images by Isaac Cardoza, Juan P. García-Vázquez, Arnoldo Díaz-Ramírez, Verónica Quintero-Rosas

“…In this work, we evaluated the performance variation using two benchmarks Convolutional Neural Networks architectures: AlexNet and Inception V3. We obtained a maximum accuracy of 94.11% when using the Inception V3 network and transfer learning. …”
Get full text

Model selection, adaptation, and combination for transfer learning in wind and photovoltaic power forecasts by Jens Schreiber, Bernhard Sick

“…In particular, none of the related work examines different model selection and adaptation strategies for neural network architectures. Also, none of the current studies investigates the influence of available training samples and considers seasonality in the evaluation. …”
Get full text

Mesoscopic model for filament orientation in growing actin networks: the role of obstacle geometry by Julian Weichsel, Ulrich S Schwarz

“…Our results suggest that two fundamentally different network architectures compete with each other in growing actin networks, irrespective of obstacle geometry, and clarify how simulated and electron tomography data have to be analyzed for non-flat obstacle geometries.…”
Get full text

Prediction of Hydrodynamic Parameters of the State of the Bottomhole Zone of Wells Using Machine Learning Methods by Andrey V. Soromotin, Dmitriy A. Martyushev, Alexander A. Melekhin

“…The article presents the results of testing various neural network architectures: the number of layers and neurons in layers with the choice of the best one. …”
Get full text