Results 91 to 100 of about 95,777 (258)

IoT Based Sign Language Detection and Voice Conversion with Image Processing [PDF]

ITM Web of Conferences
The paper introduces an IoT-enabled system for real-time sign language recognition and voice conversion to improve communication for people with hearing or speech impairments.
Marathe Ashutosh, Kalaskar Prathmesh, Kathoke Yash, Joshi Tejas, Khandare Amartya, Kadu Anish   +5 more
doaj   +1 more source

Predicting Parameters Affecting Building Energy Consumption Using Machine Learning Models

Energy Science &Engineering, EarlyView.
This framework integrates long‐term weather forecasting with building energy simulation to predict energy demand. The CNN–LSTM model achieved the highest accuracy (R2 ≈ 0.95), supporting smart HVAC control with ~ 15% energy savings. ABSTRACT The rapid growth of population and the construction industry have led to an increase in energy demand and an ...
Bassam Musheer Kareem, Abdolsalam Ebrahimpour, Jafar Ghafouri, Roghayyeh Motallebzadeh   +3 more
wiley   +1 more source

Ultrafast in‐memory computing and highly efficient deep neural networks driven by phase‐change memory materials with partially amorphous state transitions

InfoScience, EarlyView.
This work addresses challenges including the nonlinear weight‐conductance update and the trade‐off between increasing melting uniformity and reducing solid‐to‐liquid transition time. It utilizes all four melting states to create an integrated framework for attaining in‐memory computing and deep neural network applications. The framework achieves a near‐
Kian‐Guan Lim, Shao‐Xiang Go, Qiang Wang, Dong‐Gwan Kim, Chan‐Hwi Baek, Qishen Wang, Tae Hoon Lee, Desmond K. Loke   +7 more
wiley   +1 more source

Hybrid deep-learning model to recognise emotional responses of users towards architectural design alternatives

Journal of Asian Architecture and Building Engineering, 2019
In architectural planning and initial designing process, it is critical for architects to recognise users’ emotional responses toward design alternatives.
Sunwoo Chang, Hanjong Jun
doaj   +1 more source

Artificial intelligence strategies for predicting kinase inhibitor resistance: A comprehensive review of methods, challenges, and future perspectives

Journal of Intelligent Medicine, EarlyView.
Abstract Kinase inhibitors are essential in targeted cancer therapy, yet resistance often emerges through secondary mutations, activation of compensatory signaling pathways, or drug‐efflux mechanisms. Artificial intelligence (AI) provides a workflow‐based strategy rather than a list of unrelated tools for predicting and addressing kinase‐inhibitor ...
Faris Hassan, Mohanad Ali Deifallah, Alaa Zaghloul, Rania Elgohary   +3 more
wiley   +1 more source

Cardiac MR Fingerprinting at 0.55T Using a Deep Image Prior for Joint T1, T2, and M0 Mapping

Journal of Magnetic Resonance Imaging, EarlyView.
ABSTRACT Background 0.55T systems offer unique advantages and may support expanded access to cardiac MRI. Purpose To assess the feasibility of 0.55T cardiac MR Fingerprinting (MRF), leveraging a deep image prior reconstruction to mitigate noise. Study Type Phantom and prospective in vivo assessment.
Zhongnan Liu, Zexuan Liu, Imran Rashid, Mauricio Stanzione Galizia, Christopher Scoma, William Truesdell, Prachi Agarwal, Nicole Seiberlich, Liyue Shen, Jesse Hamilton   +9 more
wiley   +1 more source

Machine Learning for Predictive Modeling in Nanomedicine‐Based Cancer Drug Delivery

Med Research, EarlyView.
The integration of AI/ML into nanomedicine offers a transformative approach to therapeutic design and optimization. Unlike conventional empirical methods, AI/ML models (such as classification, regression, and neural networks) enable the analysis of complex clinical and formulation datasets to predict optimal nanoparticle characteristics and therapeutic
Rohan Chand Sahu, Sanchit Arora, Dinesh Kumar, Ashish Kumar Agrawal   +3 more
wiley   +1 more source

Automated Indonesian Plate Recognition: YOLOv8 Detection and TensorFlow-CNN Character Classification

Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
The precise identification and reading of Indonesian vehicle number plates are important in many areas, including the enforcement of law, collection of charges, management of parking areas, and safety measures. This study integrates the implementation of
Windu Gata, Dwiza Riana, Muhammad Haris, Maria Irmina Prasetiyowati, Dika Putri Metalica   +4 more
doaj   +1 more source

Jointly Learned 3D Non‐Cartesian Sampling With Wave Encoding and Reconstruction for Neurovascular Phase Contrast MRI

Magnetic Resonance in Medicine, EarlyView.
ABSTRACT Purpose To develop accelerated 3D phase contrast (PC) MRI using jointly learned wave encoding and reconstruction. Methods Pseudo‐fully sampled neurovascular 4D flow data (N = 40) and a simulation framework were used to learn phase encoding locations, wave readout parameters, and model‐based reconstruction network (MoDL) for a rapid 3D PC scan (
Chenwei Tang, Brock W. Jolicoeur, James Rice, Caroline A. Doctor, Zaynab S. Yardim, Leonardo A. Rivera‐Rivera, Laura B. Eisenmenger, Kevin M. Johnson   +7 more
wiley   +1 more source

Spectral Representation of Neurochemicals With Phase, Frequency Offset, and Lineshape Invariance: Application to JPRESS for In Vivo Concentration and T2 Mapping by Deep Learning

Magnetic Resonance in Medicine, EarlyView.
ABSTRACT Purpose Using artificial intelligence neural networks to generate a representation that maps the input directly to neurochemical concentrations and metabolite‐level average transverse relaxation times (T2). Methods The proposed model used time‐domain JPRESS data as input and was trained to be invariant to phase shifts, frequency offsets, and ...
Yan Zhang, Jun Shen
wiley   +1 more source