DDC-Chat: Achieving accurate distracted driver classification through instruction tuning of visual language model by Chupei Liao, Kuoyi Lin

“…Due to the computational intensity of inference, DDC-Chat is optimized for deployment on remote servers, with data streamed from in-vehicle monitoring systems for real-time analysis.…”
Get full text

Optimization Strategies for Electric Vehicles: A Review of Evolutionary, Swarm, and Hybrid Algorithms by Kumar A. Vijay, Manohar V. Joshi

“…These techniques are evaluated against key metrics, including solution quality, convergence speed, computational cost, and robustness, illustrating how advancements over time have more effectively tackled the challenges associated with optimizing electric vehicle (EV) operation scenarios. …”
Get full text

Automation Applications in Integrated Animal Production System by Emre Aydemir, İnci Bilge

“…In this way, it is possible to evaluate all records of animal production in digital environment. …”
Get full text

Spiral cutoff-flow of quantum quartic oscillator by M. Girguś, S.D. Głazek

“…The matrices are obtained by evaluating matrix elements of the Hamiltonian between the associated harmonic-oscillator eigenstates and by correcting the computed matrices to compensate for their limited dimension, using the Wilsonian renormalization-group procedure. …”
Get full text

A survey on multi-agent reinforcement learning and its application by Zepeng Ning, Lihua Xie

“…We also address critical operational aspects, such as hyperparameter tuning and computational complexity, which are pivotal in practical implementations of MARL. …”
Get full text

Energy-Efficient Battery Thermal Management in Electric Vehicles Using Artificial-Neural-Network-Based Model Predictive Control by Kiheon Nam, Changsun Ahn

“…The proposed controller was evaluated using a simulation environment against a conventional rule-based controller under varying ambient temperatures. …”
Get full text

Stereo Direct Sparse Visual–Inertial Odometry with Efficient Second-Order Minimization by Chenhui Fu, Jiangang Lu

“…The proposed system is evaluated on the KITTI visual odometry benchmark and the EuRoC dataset. …”
Get full text

Quantifying Biodiversity in the Absence of Taxonomic Data: A Study of Thailand’s Economic Development Zones by Nikorn Mahawan, Wanpen Charoentrakulpeeti

“…By developing methods to evaluate biodiversity via alternative data, it is now possible to quantify the ecological carrying capacity in areas where taxonomic data are lacking. …”
Get full text

Design and Simulation of a Four-Legged Mobile Robot for Autonomous Navigation on a Spacecraft Hull by Motaz Hassan, Kayla Dremann, Ashton Orosa, Emily Metzger, Nathan Doty, Julia Patek, Siamak Farhad, Ajay Mahajan

“…The robot demonstrated the ability to follow the computed optimal path with a positional deviation of less than 0.5% by the third trial. …”
Get full text

RELIABILITY OF REAL TIME JUDGING SYSTEM by Maja Bučar Pajek, Warwick Forbes, Jernej Pajek, Bojan Leskošek, Ivan Čuk

“…The computer assisted system with a keyboard interface was used to record and display deductions from individual judges in real time. …”
Get full text

Formulating the in-plane frictional resistances and collapse mechanisms for multi-storey masonry block walls by L.U. Argiento, A. Maione, C. Casapulla

“…The key aspect of the proposed approach is the introduction of a criterion to evaluate the contribution of the actual frictional resistances depending on the inclination angle of the crack line. …”
Get full text

Use of 3-D Models for Surgical Planning of a Malunion in a Dog by Norihiro Muroi, Kiyohisa Fujii, Masakazu Shimada, Nobuo Kanno, Yasuji Harada, Yasushi Hara

“…Subsequently, a computed tomography image produced a bone replica using 3-D printing. …”
Get full text

Standard Deviation of Fiber-Coupling Efficiency for Free-Space Optical Communication Through Atmospheric Turbulence by Woohyeon Moon, Hoon Kim

“…Next, a new formula for the second moment of coupled optical power is developed by introducing the spatial filter to the fourth-order coherence function. The computer simulation is carried out to evaluate the accuracy of the formulas. …”
Get full text

A Pictorial Review of CT Angiography Imaging Features of Aortic Dissection and Its Complications: Role of Emergency Teleradiology by Reddy Muni Harika, Rao Pallavi, Kalyanpur Arjun

“…The clinical outcome is determined by the type and extent of dissection, and its associated complications. Thus, knowledge of computed tomography (CT) angiography imaging features of aortic dissection and its complications, coupled with a process for immediate interpretation such as teleradiology, is essential for early diagnosis and treatment. …”
Get full text

Synthetic data distillation enables the extraction of clinical information at scale by Elizabeth Geena Woo, Michael C. Burkhart, Emily Alsentzer, Brett K. Beaulieu-Jones

“…Abstract Large-language models (LLMs) show promise for clinical note information extraction, but deployment challenges include high computational costs and privacy concerns. We used synthetic data distillation to fine-tune smaller, open-source LLMs to achieve performance comparable to larger models while enabling local hardware deployment or reduced cloud costs. …”
Get full text

GaLAM: Two-Stage Outlier Detection Algorithm by Xiaojun Lu, Zhe Yan, Ziyun Fan

“…Image matching aims to establish correspondences between images and estimate relative transformations, serving as a critical component in many geometric computer vision tasks. However, due to the limitations of descriptors and the presence of moving objects in the target region, results from nearest-neighbor matching often include numerous outliers. …”
Get full text

UCM-NetV2: An efficient and accurate deep learning model for skin lesion segmentation by Chunyu Yuan, Dongfang Zhao, Sos S. Agaian

“…Evaluations on the ISIC2017 and ISIC2018 datasets demonstrate that UCM-NetV2 outperforms existing methods in accuracy and com- putational efficiency, achieving up to 67 times faster inference speeds than U-Net and requiring less than 0.04 GFLOPs. …”
Get full text

Efficiency of adaptive filter with envelope tracking algorithm when receiving signals with multi-position PSK against the background of non-fluctuation interferences by G. V. Kulikov, Trung Tien Do

“…Two types of such interference are considered – harmonic and relayed. Using computer simulation, the optimal filter parameters (adaptation coefficient and its length) are determined; the effect of the filter on the noise immunity of the quadrature signal receiver with multi-position phase shift keying for various combinations of interference and their intensity is estimated. …”
Get full text

Unmanned aerial vehicle field sampling and antenna pattern reconstruction using Bayesian compressed sensing by Sayeh Mirzaei, Alireza Gholipour

“…The reconstruction error of different CS implementations is computed and superiority of Bayesian CS is illustrated.…”
Get full text

Robust Synthetic Data Generation for Sequential Financial Models Using Hybrid Variational Autoencoder–Markov Chain Monte Carlo Architectures by Francesco Bruni Prenestino, Enrico Barbierato, Alice Gatti

“…These findings position the proposed framework as a computationally efficient and structurally simple alternative to Generative Adversarial Network (GAN)-based methods, suitable for real-world applications in data-driven financial modelling.…”
Get full text