Z-Score Experience Replay in Off-Policy Deep Reinforcement Learning.

Reinforcement learning, as a machine learning method that does not require pre-training data, seeks the optimal policy through the continuous interaction between an agent and its environment. It is an important approach to solving sequential decision-making problems. By combining it with deep learning, deep reinforcement learning possesses powerful perception and decision-making capabilities and has been widely applied to various domains to tackle complex decision problems.

The Degree of Cervical Intervertebral Disc Degeneration Is Associated With Denser Bone Quality of the Cervical Sub-endplate and Vertebral Body.

Objective: The relationship between cervical disc degeneration and bone quality of adjacent vertebral body remains controversial. This study aims to investigate the relationship between cervical disc degeneration and bone quality of the adjacent vertebral body and sub-endplate bone with a new MRI-based bone quality score in patients over 50 years with cervical spondylosis.

Methods: We retrospectively reviewed 479 cervical disc segments from 131 patients.

Spatial interpolation of global DEM using federated deep learning.

The digital elevation model (DEM) provides important data support for 3D terrain modeling. However, due to the complex and changeable terrain in the real world and the high cost of field measurement, it is extremely difficult to obtain continuous and high-density elevation data directly. Therefore, it is necessary to rely on spatial interpolation technology to restore the DEM overall picture in the original sampling area.

Investigating the Effects of AL049796.1 Silencing in Inhibiting High Glucose-Induced Colorectal Cancer Progression.

Patients with colorectal cancer (CRC) and diabetes share many risk factors. Despite a strong association between diabetes and CRC being widely studied and confirmed, further genetic research is needed. This study found higher AL049796.

Chinese undergraduates' mental health help-seeking behavior: the health belief model.

The detection rate of mental health problems among undergraduates has recently risen significantly. However, undergraduates underutilize mental health services; approximately a third only of undergraduates in need of treatment use school counseling resources. Based on a social psychological theoretical framework, the health belief model, factors of undergraduates' willingness to seek help when dealing with psychological problems were investigated.

High Thermal Performance Ultraviolet (368 nm) AlGaN-Based Flip-Chip LEDs with an Optimized Structure.

In this study, we have fabricated a 368 nm LED with an epitaxial Indium Tin Oxide (ITO) contact layer. We analyze the thermal performance of the flip-chip LED with a symmetric electrode and metal reflective layer, applying ANSYS to build a coupled electro-thermal finite element model (FEM) of the temperature distribution in the multiple quantum wells (MQWs). We compare our system with the traditional Au-bump flip-chip LED and a flip-chip LED with a Distributed Bragg Reflector (DBR) layer.

A Retrospective Study of the Effect of Spinopelvic Parameters on Fatty Infiltration in Paraspinal Muscles in Patients With Lumbar Spondylolisthesis.

Objective: The effect on fat infiltration (FI) of paraspinal muscles in degenerative lumbar spinal diseases has been demonstrated except for spinopelvic parameters. The present study is to identify the effect of spinopelvic parameters on FI of paraspinal muscle (PSM) and psoas major muscle (PMM) in patients with degenerative lumbar spondylolisthesis.

Methods: A single-center, retrospective cross-sectional study of 160 patients with degenerative lumbar spondylolisthesis (DLS) and lumbar stenosis (LSS) who had lateral full-spine x-ray and lumbar spine magnetic resonance imaging was conducted.

Autonomous Atmospheric Water Harvesting over a Wide RH Range Enabled by Super Hygroscopic Composite Aerogels.

Sorption-based atmospheric water harvesting (SAWH) offers a sustainable strategy to address the global freshwater shortage. However, obtaining sorbents with excellent performance over a wide relative humidity (RH) range and devices with fully autonomous water production remains challenging. Herein, magnesium chloride (MgCl) is innovatively converted into super hygroscopic magnesium complexes(MC), which can effectively solve the problems of salt deliquescence and agglomeration.

Generative AI-based Data Completeness Augmentation Algorithm for Data-driven Smart Healthcare.

In the decade, artificial intelligence has achieved great popularity and applications in medicine and healthcare. Various AI-based algorithms have shown astonishing performance. However, in various data-driven smart healthcare algorithms, the problem of incomplete dataset remains a huge challenge.

RAP Vol: Robust Adversary Populations With Volume Diversity Measure.

Deep reinforcement learning (DRL) algorithms have made remarkable achievements in various fields, but they are vulnerable to changes in environment dynamics. This vulnerability easily leads to poor generalization, low performance, and catastrophic failures in unseen environments, which severely hinders the application of DRL in real-world scenarios. The robustness via adversary populations (RAP) algorithm addresses this issue by introducing a population of adversaries that perturb the protagonist.

AUV Path Planning Considering Ocean Current Disturbance Based on Cloud Desktop Technology.

In the field of ocean energy detection, Autonomous Underwater Vehicles (AUVs) offer significant advantages in terms of manpower, resource, and energy efficiency. However, the unpredictable nature of the ocean environment, particularly the real-time changes in ocean currents, poses navigational risks for AUVs. Therefore, effective path planning in dynamic environments is crucial for AUVs to perform specific tasks.

Two-in-One Polymeric NO-Donor Prodrugs Mediate Precision and Synergistic Prostate Cancer Treatment.

Chemotherapy predominates in clinical treatment of prostate cancer (PCa), while irreversible resistance to chemotherapeutics and severe side effects hinder the therapeutic efficacy, especially in castration-resistant PCa (CRPC). Herein, a bombesin (BBN)-decorated two-in-one prodrug (T-NO/E-PMs) incorporating a polymeric nitric oxide (NO) donor and acetal-linked 17β-estradiol (E) in one backbone is developed, aiming to inhibit androgen receptor (AR) expression, reprogram the tumor microenvironment of CRPC, and enhance estradiol-mediated hypoxic CRPC therapy. Following efficient internalization mediated by BBN, T-NO/E-PMs releases estradiol and NO in response to the unique intracellular environments.

In Situ Grown Silver-Polymer Framework with Coordination Complexes for Functional Artificial Tissues.

Self-sensing actuators are critical to artificial robots with biomimetic proprio-/exteroception properties of biological neuromuscular systems. Existing add-on approaches, which physically blend heterogeneous sensor/actuator components, fall short of yielding satisfactory solutions, considering their suboptimal interfaces, poor adhesion, and electronic/mechanical property mismatches. Here, a single homogeneous material platform is reported by creating a silver-polymer framework (SPF), thus realizing the seamless sensing-actuation unification.

A Tiny Model for Fast and Precise Ship Detection via Feature Channel Pruning.

It is of great significance to accurately detect ships on the ocean. To obtain higher detection performance, many researchers use deep learning to identify ships from images instead of traditional detection methods. Nevertheless, the marine environment is relatively complex, making it quite difficult to determine features of ship targets.

Macromolecular NO-Donor Micelles for Targeted and Augmented Chemotherapy against Prostate Cancer.

Mitoxantrone (MTO) is clinically utilized for treating hormone-refractory prostate cancer (PCa), however, the therapeutic outcome is far from optimal due to the lack of proper drug carrier as well as the inherent MTO detoxification mechanisms of DNA lesion repair and anti-oxidation. Herein, a bombesin-installed nanoplatform combining the chemotherapeutic MTO and the chemotherapeutic sensitizer of nitric oxide (NO) is developed based on MTO-loaded macromolecular NO-donor-containing polymeric micelles (BN-NM ) for targeted NO-sensitized chemotherapy against PCa. BN-NM actively target and accumulates in PCa sites and are internalized into the tumor cells.

Self-Sustained Programmable Hygroelectronic Interfaces for Humidity-Regulated Hierarchical Information Encryption and Display.

The emerging moisture-driven energy generation (MEG) technology opens up new possibilities for humidity-responsive materials, devices, and interdisciplinary opportunities in fields like information security. However, such potential remains untapped. Here, an original MEG structure with a hygroionic energy-conversion route by selective coating of ionic hygroscopic hydrogels on a carbon black surface is reported.

A DBULSTM-Adaboost Model for Sea Surface Temperature Prediction.

Sea surface temperature (SST) is an important parameter to measure the energy and heat balance of sea surface. The change of sea surface temperature has an important impact on the marine ecosystem, marine climate and marine environment. Therefore, sea surface temperature prediction has become an significant research direction in the field of ocean.

Disc degeneration contributes to the denser bone in the subendplate but not in the vertebral body in patients with lumbar spinal stenosis or disc herniation.

Background Context: It is commonly believed that decreased bone quality would lead to endplate degeneration and arthritic changes in the facet joints, and thus accelerated disc degeneration (DD). However, some more detailed studies of vertebral bone structure have found that bone mineral density (BMD) in the vertebral body is increased rather than decreased in moderate or greater disc degeneration. The relationship between BMD and DD still needs further study.

Enriching Facial Anti-Spoofing Datasets via an Effective Face Swapping Framework.

In the era of rapid development of the Internet of things, deep learning, and communication technologies, social media has become an indispensable element. However, while enjoying the convenience brought by technological innovation, people are also facing the negative impact brought by them. Taking the users' portraits of multimedia systems as examples, with the maturity of deep facial forgery technologies, personal portraits are facing malicious tampering and forgery, which pose a potential threat to personal privacy security and social impact.

Exploration of Laser Marking Path and Algorithm Based on Intelligent Computing and Internet of Things.

Nowadays, laser processing technology is being used more and more in various fields, and the requirements for laser control procedures are getting higher and higher. This paper aims to study the path generation problem of laser marking technology in order to improve the efficiency of laser marking as well as the protection of the marking material. Therefore, we creatively propose two-path generation methods, namely, sawtooth parallel and contour parallel, and design the boundary curve offset algorithm and domain partition intersection algorithm for the computer simulation of the two marking paths, respectively.

The Intelligent Path Planning System of Agricultural Robot via Reinforcement Learning.

Agricultural robots are one of the important means to promote agricultural modernization and improve agricultural efficiency. With the development of artificial intelligence technology and the maturity of Internet of Things (IoT) technology, people put forward higher requirements for the intelligence of robots. Agricultural robots must have intelligent control functions in agricultural scenarios and be able to autonomously decide paths to complete agricultural tasks.