Uncertainty-Aware Multimodal Trajectory Prediction via a Single Inference from a Single Model.

In the domain of autonomous driving, trajectory prediction plays a pivotal role in ensuring the safety and reliability of autonomous systems, especially when navigating complex environments. Unfortunately, trajectory prediction suffers from uncertainty problems due to the randomness inherent in the driving environment, but uncertainty quantification in trajectory prediction is not widely addressed, and most studies rely on deep ensembles methods. This study presents a novel uncertainty-aware multimodal trajectory prediction (UAMTP) model that quantifies aleatoric and epistemic uncertainties through a single forward inference.

Finding deceivers in social context with large language models and how to find them: the case of the Mafia game.

Lies are ubiquitous and often happen in social interactions. However, socially conducted deceptions make it hard to get data since people are unlikely to self-report their intentional deception behaviors, especially malicious ones. Social deduction games, a type of social game where deception is a key gameplay mechanic, can be a good alternative to studying social deceptions.

Sub--benziporphyrin: a subcarbaporphyrinoid and its B complex with an unprecedented planar tridentate 14π-aromatic network.

Sub--benziporphyrins were synthesized by Pd-catalyzed cross-coupling of ,'-diboryl--benzitripyrrane with 9,10-bis(1,1-dibromomethylenyl)anthracene. Reaction of sub--benziporphyrin with PhBCl and triethylamine gave its B-phenyl complex as a tetracoordinate nonaromatic B complex. In contrast, the reaction with BBr and triethylamine furnished a neutral B porphyrinoid with a planar and triangular coordination as the first example, in which the -phenylene unit was partially reduced, allowing for the global 14π-aromatic circuit.

Stiffness-tunable velvet worm-inspired soft adhesive robot.

Considering the characteristics and operating environment of remotely controlled miniature soft robots, achieving delicate adhesion control over various target surfaces is a substantial challenge. In particular, the ability to delicately grasp wrinkled and soft biological and nonbiological surfaces with low preload without causing damage is essential. The proposed adhesive robotic system, inspired by the secretions from a velvet worm, uses a structured magnetorheological material that exhibits precise adhesion control with stability and repeatability by the rapid stiffness change controlled by an external magnetic field.

Modified Si Oxidation Behavior by Ultrathin Ni Catalyst Enabling Oxidant-Less Metal-Assisted Chemical Etching.

Metal-assisted chemical etching (MACE), a wet-based anisotropic etching process for semiconductors, has emerged as an alternative to plasma-based etching. However, using noble metal catalysts in MACE limits the implementation of complementary metal-oxide-semiconductor (CMOS) processes. This study explores Si etching using an ultrathin Ni catalyst as a novel approach for MACE.

GAIT-CKD (Gait Analysis using Artificial Intelligence for digital Therapeutics of patients with Chronic Kidney Disease): design and methods.

Background: Digital therapeutics are emerging as treatments for diseases and disabilities. In chronic kidney disease (CKD), gait is a potential biomarker for health status and intervention effectiveness. This study aims to analyze gait characteristics in CKD patients, providing baseline data for digital therapeutics development.

Innovative Use of Carbon Nanofibers/Praseodymium Cobaltite for Targeted Detection of Hematologic Sulfamethazine.

Antibiotics are essential for treating illnesses, but abuse has resulted in serious consequences. Rapid and precise detection of antibiotic residues, such as sulfamethazine (SFZ), in water and biological samples is critical for public health and environmental safety. To address this challenge, we have introduced a pioneering electrochemical sensor incorporating a nanocomposite of perovskite-structured praseodymium cobaltite (PrCoO) integrated with carbon nanofibers (CNFs) on a glassy carbon electrode (GCE|CNF/PrCoO).

Feasibility of Simultaneous Anodal Transcranial Direct Current Stimulation During Gait Training in Chronic Stroke Patients: A Randomized Double-Blind Pilot Clinical Trial.

Background: Transcranial direct current stimulation (tDCS) is a therapeutic tool for improving post-stroke gait disturbances, with ongoing research focusing on specific protocols for its application. We evaluated the feasibility of a rehabilitation protocol that combines tDCS with conventional gait training.

Methods: This was a randomized, double-blind, single-center pilot clinical trial.

Sculpting the Electronic Nano-Terrain on a Perovskite Film for Efficient Charge Transport.

Nanopatterned halide perovskites have emerged to improve the performance of optoelectronic devices by controlling the crystallographic and optical properties via morphological modification. However, the correlation between the photophysical property and morphology transformation in nanopatterned perovskite films remains elusive, which hinders the rational design of nanopatterned halide perovskites for optoelectronic devices. In this study, we employed nanoimprinting lithography on a perovskite film to exert a precise control over grain growth and manipulate electronic structures at the level of individual grains.

Individual and collective manipulation of multifunctional bimodal droplets in three dimensions.

Spatiotemporally controllable droplet manipulation is vital across numerous applications, particularly in miniature droplet robots known for their exceptional deformability. Despite notable advancements, current droplet control methods are predominantly limited to two-dimensional (2D) deformation and motion of an individual droplet, with minimal exploration of 3D manipulation and collective droplet behaviors. Here, we introduce a bimodal actuation strategy, merging magnetic and optical fields, for remote and programmable 3D guidance of individual ferrofluidic droplets and droplet collectives.

Thermal Dehydrogenation Impact on Positive Bias Stability of Amorphous InSnZnO Thin-Film Transistors.

Recently, the growing demand for amorphous oxide semiconductor thin-film transistors (AOS TFTs) with high mobility and good stability to implement ultrahigh-resolution displays has made tracking the role of hydrogen in oxide semiconductor films increasingly important. Hydrogen is an essential element that contributes significantly to the field effect mobility and bias stability characteristics of AOS TFTs. However, because hydrogen is the lightest atom and has high reactivity to metal and oxide materials, elucidating its impact on AOS thin films has been challenging.

Artificial Intelligence-Based Diagnostic Support System for Patent Ductus Arteriosus in Premature Infants.

: Patent ductus arteriosus (PDA) is a prevalent congenital heart defect in premature infants, associated with significant morbidity and mortality. Accurate and timely diagnosis of PDA is crucial, given the vulnerability of this population. : We introduce an artificial intelligence (AI)-based PDA diagnostic support system designed to assist medical professionals in diagnosing PDA in premature infants.

MultiSenseBadminton: Wearable Sensor-Based Biomechanical Dataset for Evaluation of Badminton Performance.

The sports industry is witnessing an increasing trend of utilizing multiple synchronized sensors for player data collection, enabling personalized training systems with multi-perspective real-time feedback. Badminton could benefit from these various sensors, but there is a scarcity of comprehensive badminton action datasets for analysis and training feedback. Addressing this gap, this paper introduces a multi-sensor badminton dataset for forehand clear and backhand drive strokes, based on interviews with coaches for optimal usability.

A Janus carbaporphyrin pseudo-dimer.

Carbaporphyrin dimers, investigated for their distinctive electronic structures and exceptional properties, have predominantly consisted of systems containing identical subunits. This study addresses the associated knowledge gap by focusing on asymmetric carbaporphyrin dimers with Janus-like characteristics. The synthesis of a Janus-type carbaporphyrin pseudo-dimer 5 is presented.

Metalla-Carbaporphyrinoids Consisting of an Acyclic N-Confused Tetrapyrrole Analogue Served as Stable Near-Infrared-II Dyes.

We present herein the synthesis of novel pseudo-metalla-carbaporphyrinoid species (1M: M=Pd and Pt) achieved through the inner coordination of palladium(II) and platinum(II) with an acyclic N-confused tetrapyrrin analogue. Despite their tetrapyrrole frameworks being small, akin to well-known porphyrins, these species exhibit an unusually narrow HOMO-LUMO gap, resulting in an unprecedentedly low-energy absorption in the second near-infrared (NIR-II) region. Density functional theory (DFT) calculations revealed unique d-p-conjugated electronic structures involving the metal d-ligand p hybridized molecular orbitals of 1M.

Engagnition: A multi-dimensional dataset for engagement recognition of children with autism spectrum disorder.

Engagement plays a key role in improving the cognitive and motor development of children with autism spectrum disorder (ASD). Sensing and recognizing their engagement is crucial before sustaining and improving the engagement. Engaging technologies involving interactive and multi-sensory stimuli have improved engagement and alleviated hyperactive and stereotyped behaviors.

Adapting low-dose CT denoisers for texture preservation using zero-shot local noise-level matching.

Background: On enhancing the image quality of low-dose computed tomography (LDCT), various denoising methods have achieved meaningful improvements. However, they commonly produce over-smoothed results; the denoised images tend to be more blurred than the normal-dose targets (NDCTs). Furthermore, many recent denoising methods employ deep learning(DL)-based models, which require a vast amount of CT images (or image pairs).

Magnetic particle image scanner based on asymmetric core-filled electromagnetic actuator.

Monitoring the distribution of magnetic nanoparticles (MNPs) in the vascular system is an important task for the advancement of precision therapeutics and drug delivery. Despite active targeting using active motilities, it is required to visualize the position and concentration of carriers that reach the target, to promote the development of this technology. In this work, a feasibility study is presented on a tomographic scanner that allows monitoring of the injected carriers quantitatively in a relatively short interval.

Partitioning surface wave propagation on reconfigurable porous plane.

This paper introduces a novel reconfigurable technique for partitioning the propagation of surface waves by utilizing a T-shaped structure and pathways established through the introduction of fluid metal or metal pins into evenly spaced cylindrical cavities within a porous surface wave platform. Notably, the co-printing of metal and dielectric materials via 3D printing is employed, resulting in an expedited fabrication process. Extensive 3D electromagnetic simulations and experimental investigations validate the proposed approach's efficacy in achieving surface wave division while minimizing interference.

Rewritable Photoluminescence and Structural Color Display for Dual-Responsive Optical Encryption.

Optical encryption using coloration and photoluminescent (PL) materials can provide highly secure data protection with direct and intuitive identification of encrypted information. Encryption capable of independently controlling wavelength-tunable coloration as well as variable light intensity PL is not adequately demonstrated yet. Herein, a rewritable PL and structural color (SC) display suitable for dual-responsive optical encryption developed with a stimuli-responsive SC of a block copolymer (BCP) photonic crystal (PC) with alternating in-plane lamellae, of which a variety of 3D and 2D perovskite nanocrystals is preferentially self-assembled with characteristic PL, is presented.