Results 241 to 250 of about 4,165 (288)

Enhanced stock market forecasting using dandelion optimization-driven 3D-CNN-GRU classification. [PDF]

Sci Rep
Jagadesh BN, RajaSekhar Reddy NV, Udayaraju P, Damera VK, Vatambeti R, Jagadeesh MS, Koteswararao C.   +6 more
europepmc   +1 more source

A Privacy‐Preserving System for Confidential Carpooling Services Using Homomorphic Encryption

Advanced Intelligent Systems, EarlyView.
This research presents a homomorphic encryption‐based solution to enhance privacy in carpooling without compromising functionality. Rigorous experiments confirm its robustness, accuracy, and efficiency in securely matching users while preserving confidentiality.
David Palma, Pier Luca Montessoro, Mirko Loghi, Daniele Casagrande   +3 more
wiley   +1 more source

A dual-path convolutional neural network combined with an attention-based bidirectional long short-term memory network for stock price prediction. [PDF]

PLoS One
Zhao G, Cheng Y, Yang J, Ouyang J.
europepmc   +1 more source

Device Specifications for Neural Network Training with Analog Resistive Cross‐Point Arrays Using Tiki‐Taka Algorithms

Advanced Intelligent Systems, EarlyView.
This study investigates the device specifications required for neural network training using analog resistive cross‐point arrays with the training algorithms. By demonstrating the robustness against non‐ideal update characteristics with these algorithms, it quantitatively shows how hardware‐aware training can relax device specifications.
Jinho Byun, Seungkun Kim, Doyoon Kim, Jimin Lee, Wonjae Ji, Seyoung Kim   +5 more
wiley   +1 more source

Energy‐Efficient Hardware Implementation of Spiking‐Restricted Boltzmann Machines Using Pseudo‐Synaptic Sampling

Advanced Intelligent Systems, EarlyView.
In this article, an energy‐efficient hardware implementation of spiking‐restricted Boltzmann machines using the pseudo‐synaptic sampling (PS2) method is presented. In the PS2 method, superior area and energy efficiency over previous approaches, such as the random walk method, are demonstrated, achieving a 94.94% reduction in power consumption during on‐
Hyunwoo Kim, Suyeon Jang, Uicheol Shin, Masatoshi Ishii, Atsuya Okazaki, Megumi Ito, Akiyo Nomura, Kohji Hosokawa, Sungmin Lee, Matthew BrightSky, Sangbum Kim   +10 more
wiley   +1 more source

Enhancing renewable energy certificate transactions through reinforcement learning and smart contracts integration. [PDF]

Sci Rep
He Q, Wang J, Shi R, He Y, Wu M.
europepmc   +1 more source

A Novel Mixed Convolution Transformer Model for the Fast and Accurate Diagnosis of Glioma Subtypes

Advanced Intelligent Systems, EarlyView.
The mixed convolutional transformer model represents a novel approach for the accurate and rapid diagnosis of glioma subtypes. This model employs advanced, complex layers and functions, establishing its uniqueness and enhancing its ability to deliver precise outcomes in glioma subtype detection.
S. M. Nuruzzaman Nobel, S. M. Masfequier Rahman Swapno, Md Babul Islam, AKM Azad, Salem A. Alyami, Md Alamin, Pietro Liò, Mohammad Ali Moni   +7 more
wiley   +1 more source

Deep Learning Methods in Soft Robotics: Architectures and Applications

Advanced Intelligent Systems, EarlyView.
Soft robotics has seen intense research over the past two decades and offers a promising approach for future robotic applications. However, standard industrial methods may be challenging to apply to soft robots. Recent advances in deep learning provide powerful tools to analyze and design complex soft machines that can operate in unstructured ...
Tomáš Čakurda, Monika Trojanová, Pavlo Pomin, Alexander Hošovský   +3 more
wiley   +1 more source

Herding towards pygmalion: Examining the cultural dimension of market and bank based systems. [PDF]

Heliyon
Saltik Ö, Rehman WU, Kaymaz T, Degirmen S.   +3 more
europepmc   +1 more source

Design Strategies of Capacitor‐Based Synaptic Cell for High‐Efficiency Analog Neural Network Training

Advanced Intelligent Systems, EarlyView.
This work explores the three‐transistors‐one‐capacitor synaptic cell design for analog in‐memory computing, focusing on improving performance and scalability in deep neural network (DNN) training. By optimizing transistor characteristics and proposing a novel cell design, challenges such as large cell areas and retention issues are addressed.
Byoungwoo Lee, Wonjae Ji, Hyejin Kim, Seungmin Han, Geonwoong Park, Pyeongkang Hur, Gilsu Jeon, Hyung‐Min Lee, Yoonyoung Chung, Junwoo Son, Yong‐Young Noh, Seyoung Kim   +11 more
wiley   +1 more source