Results 91 to 100 of about 12,316 (267)

Explainable AI‐Driven Optimization of Electrode Activation Reduces Power Consumption While Preserving Object Recognition in Retinal Prostheses

Advanced Intelligent Systems, EarlyView.
Explainable artificial intelligence (XAI) guides selective electrode activation in retinal prostheses by emphasizing visually informative regions. XAI‐assisted phosphene generation maintains object recognition performance while significantly reducing stimulation power.
Sein Kim, Hamin Shim, Maesoon Im
wiley   +1 more source

Improved Long Short-Term Memory-Based Fixed-Time Fault-Tolerant Control for Unmanned Marine Vehicles with Signal Quantization

Journal of Marine Science and Engineering
This paper presents a fixed-time fault-tolerant control strategy based on an improved long short-term memory network for dynamic positioning of unmanned marine vehicles subject to signal quantization, disturbances, and input saturation.
Xin Yang, Li-Ying Hao, Jia-Bin Wang, Gege Dong, Tieshan Li   +4 more
doaj   +1 more source

Electroencephalogram‐Driven Recognition of Parkinson's Disease Through a Mycelium‐Inspired Memristive Reservoir Computing Circuit

Advanced Intelligent Systems, EarlyView.
This work presents a bio‐inspired computing framework for Parkinson's disease analog recognition using electroencephalogram signals. Temporally encoded EEG features stimulate a mycelium‐inspired memristive reservoir, where disease‐related patterns emerge through physical spatiotemporal dynamics.
Ioannis K. Chatzipaschalis, Ioannis Tompris, Pantelis Fraidakis, Iosif‐Angelos Fyrigos, Antonio Rubio, Georgios Ch. Sirakoulis   +5 more
wiley   +1 more source

Resource‐Aware Contrastive Scattering Meta‐Learning for Efficient Few‐Shot Acoustic Anomaly Detection

Advanced Intelligent Systems, EarlyView.
This paper introduces a resource‐aware Contrastive Scattering Meta‐Learning (CSML) framework for acoustic anomaly detection. By leveraging training‐free wavelet scattering and metric‐based meta‐learning, the model achieves competitive performance with only 50 K learnable parameters—a 98% reduction compared to state‐of‐the‐art frameworks—enabling ...
Rami Zewail, Bassem Mokhtar
wiley   +1 more source

Gesture Recognition of Filipino Sign Language Using Convolutional and Long Short-Term Memory Deep Neural Networks

Knowledge
In response to the recent formalization of Filipino Sign Language (FSL) and the lack of comprehensive studies, this paper introduces a real-time FSL gesture recognition system.
Karl Jensen Cayme, Vince Andrei Retutal, Miguel Edwin Salubre, Philip Virgil Astillo, Luis Gerardo Cañete, Gaurav Choudhary   +5 more
doaj   +1 more source

Trainable Bitwise Soft Quantization for Input Feature Compression

CoRR
Accepted to CPAL ...
Karsten Schrödter, Jan Stenkamp, Nina Herrmann, Fabian Gieseke   +3 more
openaire   +2 more sources

Visual and Visual‐Inertial SLAM Based on Enhanced Deep Learning Features and Motion Smoothness Constraints

Advanced Intelligent Systems, EarlyView.
A visual and visual‐inertial simultaneous localization and mapping (SLAM) algorithm, leveraging enhanced deep learning features and motion smoothness constraints, is proposed in this research work. This method retains the advantages of geometry‐based SLAM methods while effectively utilizing the powerful representational capabilities of data‐driven ...
Maosheng Jiang, Lei Ma, Muhua Zhang, Kai Shen   +3 more
wiley   +1 more source

A Neuromorphic Simulation Framework for Indium‐Gallium‐Zinc‐Oxide Charge‐Trap Synaptic Transistors: From Device Modeling to System Simulation

Advanced Intelligent Systems, EarlyView.
This work presents a comprehensive framework bridging device fabrication, modeling, and system‐level simulation for an indium‐gallium‐zinc‐oxide (IGZO) charge‐trap synaptic transistor‐based neuromorphic system. By developing a precise SPICE model derived from fabricated IGZO synaptic transistors, the study incorporates parasitic RC loads into array ...
Yumin Yun, Junhyeong Park, Sunyeol Bae, Chae‐Hwan Park, Dong Hyeon Lee, Soo‐Yeon Lee   +5 more
wiley   +1 more source

Neuromorphic Denoising with Fully Analog Memristive In‐Memory Computing

Advanced Intelligent Systems, EarlyView.
This article borrows the concepts of episodic memory in human brains to experimentally implement a memristor‐based neuromorphic denoising process. A homogeneous memristor processing unit is experimentally demonstrated for both temporal storage and neural network computation, imitating the synapses in the human brain.
Daijing Shi, Teng Zhang, Yuqi Li, Yaoyu Tao, Bonan Yan, Yuchao Yang   +5 more
wiley   +1 more source

Adaptive Sliding Mode Control for Unmanned Surface Vehicle Trajectory Tracking Based on Event-Driven and Control Input Quantization

Actuators
This primary study aims to optimize network resource utilization efficiency in marine control systems. A novel event-triggering condition is proposed to significantly reduce communication traffic, where the error norm is squared while the input norm ...
Zhihui Li, Mengyuan Li, Xinrui Jing, Changfu Yuan, Kai Wang   +4 more
doaj   +1 more source