Results 71 to 80 of about 1,578 (183)

Interleaved Diffractive Networks for Information Transfer Through Random Diffusers

Laser &Photonics Reviews, EarlyView.
This work presents a cascaded diffractive optical network that enables information transfer through random, unknown diffusers using passive, interleaved structured layers that mitigate scattering without digital computation. A hybrid optical‐digital version further improves robustness and reconstruction fidelity under distortions, with both simulations
Yuhang Li, Yiyang Wu, Shiqi Chen, Xilin Yang, Aydogan Ozcan   +4 more
wiley   +1 more source

Deep Reinforcement Learning Based Autonomous Decision‐Making for Cooperative Uncrewed Aerial Vehicles: A Search and Rescue Real World Application

Journal of Field Robotics, EarlyView.
ABSTRACT This paper presents the first end‐to‐end framework that combines guidance, navigation, and centralized task allocation for multiple UAVs performing autonomous search‐and‐rescue (SAR) in GNSS‐denied indoor environments. A twin delayed deep deterministic policy gradient controller is trained with an artificial potential field (APF) reward that ...
Thomas Hickling, Maxwell Hogan, Abdulla Tammam, Nabil Aouf   +3 more
wiley   +1 more source

Detecting Plateau Zokor (Eospalax baileyi) Mounds in UAV Imagery of Alpine Meadows Using Deep Learning Algorithms

Remote Sensing in Ecology and Conservation, EarlyView.
We developed PZM‐YOLO to automatically detect plateau zokor mounds in UAV imagery of alpine meadows. The model achieved reliable detection of small and densely distributed mounds under complex backgrounds, outperforming the baseline YOLOv5s. This framework supports mound counting, mound position, rodent impact assessment, and grassland restoration ...
Yang Yang, Limin Hua, Lianguo Wang, Jiazhen Li, Rui Dong, Siwei Yang   +5 more
wiley   +1 more source

Practically Error‐Free Junctions Enable Solving Large Instances of Exact Cover Problems Using Network‐Based Biocomputation

Small, EarlyView.
Scaling nanofluidic channel geometries to sub‐200 nm is demonstrated to suppress junction guiding errors in network‐based biocomputing. The resulting increase in path fidelity enables experimental solution of Exact Cover instances with more than 33 million possible solutions, establishing a new benchmark for network‐based biocomputing. ABSTRACT Network‐
Eugene Christo V R, Christoph Robert Meinecke, Bert Nitzsche, Roman Lyttleton, Cordula Reuther, Danny Reuter, Heiner Linke, Till Korten, Stefan Diez   +8 more
wiley   +1 more source

Artificial intelligence empowers targeted protein degradation: Core technological innovations, multi‐scenario applications, and translational prospects

Smart Molecules, EarlyView.
AI is transforming TPD by improving the design, prediction, and optimization of degraders such as PROTACs, molecular glues, and LYTACs. This review summarizes key AI‐driven advances, highlights applications across drug discovery stages, and discusses remaining challenges and future directions for accelerating the development of therapies against ...
Shuanglin Qin, Rui Peng, Guangshuai Zhang, Si Yan, Jin Xiao, Zishu Liu, Ziyu Tan, Qingqing Xie, Shangjie Li, Wei Luo, Xiaohe Xiao   +10 more
wiley   +1 more source

Improving String Matching through Enhanced Hashing

Software: Practice and Experience, EarlyView.
ABSTRACT Background Hashing offers opportunities to tune string matching algorithms while enabling efficient data retrieval and pattern detection. Many of the best algorithms apply hashing. Objective We try to develop faster online algorithms for exact string matching.
Francesco Pio Marino, Jorma Tarhio
wiley   +1 more source

Evaluating the Energy Efficiency of Optimization Techniques in C, Python, and Java

Software: Practice and Experience, EarlyView.
ABSTRACT Background Software plays a critical role in modern society, but its energy consumption is a growing concern. This issue is especially evident in the Internet of Things (IoT), which involves billions of devices operating under strict energy constraints, most of which rely on C Programming Language (PL) because of its energy efficiency. Outside
Carlos Pulido, Félix García, Ma Ángeles Moraga, Miguel Baños‐González, Juan Antonio Rico‐Gallego, Javier Corral‐García   +5 more
wiley   +1 more source

Reverse engineering strut‐and‐tie models for assessing reinforced concrete structures

Structural Concrete, EarlyView.
Abstract Strut‐and‐tie models enable the design of reinforced concrete structures with static or geometrical discontinuities, providing interpretability and control over the load path. These models are valuable for designing discontinuity regions of new structures and for validating nonlinear finite‐element analysis results. However, developing a strut‐
Karin Yu, Walter Kaufmann
wiley   +1 more source

A Multi‐Sequence Adversarial Fusion U‐Net for Brain Tumor Image Segmentation

IEEJ Transactions on Electrical and Electronic Engineering, EarlyView.
In the field of brain tumor image segmentation, in order to avoid the impact of insufficient number of training samples, the method of fusing multi‐modal MRI information before segmentation is widely used. However, when fusing different modal features, existing methods only add fixed weights to the features of each modality, resulting in insufficient ...
Jie Wang, Jinglu Hu
wiley   +1 more source

Concatenated Constrained Coding: A New Approach to Efficient Constant-Weight Codes. [PDF]

Entropy (Basel)
Immink KS, Weber JH, Nguyen TT, Cai K.
europepmc   +1 more source