Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)最新文献

In this transformative study, machine learning (ML) and t-distributed stochastic neighbor embedding (t-SNE) are employed to interpret intricate patterns in colorimetric images of cold atmospheric plasma (CAP)-treated water. The focus is on CAP's therapeutic potential, particularly its ability to generate reactive oxygen and nitrogen species (RONS) that play a crucial role in antimicrobial activity. RGB, HSV, LAB, YCrCb, and grayscale color spaces are extracted from the colorimetric expression of oxidative stress induced by RONS, and these features are used for unsupervised ML, employing density-based spatial clustering of applications with noise (DBSCAN). The DBSCAN model's performance is evaluated using homogeneity, completeness, and adjusted rand index with a predictive data distribution graph. The best results are achieved with 3,3′,5,5′-tetramethylbenzidine–potassium iodide colorimetric assay solution immediately after plasma treatment, with values of 0.894, 0.996, and 0.826. t-SNE is further conducted for the best-case scenario to evaluate the clustering efficacy and find the best combination of features to better present the results. Correspondingly, t-SNE enhances clustering efficacy and adeptly handles challenging points. The approach pioneers dynamic and comprehensive solutions, showcasing ML's precision and t-SNE's transformative visualization. Through this innovative fusion, complex relationships are unraveled, marking a paradigm shift in biomedical analytical methodologies.

Additive manufacturing technologies increasingly revolutionize current production techniques for object manufacturing. Particularly, fused deposition modeling (FDM) strongly impacts production processes by enabling the cost-effective and efficient creation of structures with complex designs and innovative geometries. The use of conductive filaments in FDM printing is paving the way for the advancement of entirely printed sensors and circuits, although this domain is still in its early stages. In this article, the design and production of bilayer deformable pressure sensors fabricated using conductive thermoplastic polyurethane are investigated. The potential to vary the mechanical and electrical characteristics of FDM-printed components by adjusting printing parameters is explored. The influence of different levels of material infill (20%, 50%, and 100%) and different contact geometries between layers (domes, pyramids, and cylinders) is studied. Electromechanical tests are carried out to characterize the sensor, applying pressures up to 22 kPa. The 3D-printed pressure sensors demonstrate tunable mechanical and electrical sensitivities at different infill values, with the highest value of −6.3 kPa⁻¹ achieved by using a pyramid layer at 100% infill. Sensor outputs registered during cyclic tests show reproducible responses with a wide range of sensitivity, paving the way for applicability in recording both static and periodic pressure changes.

Dynamic and agile locomotion in legged robots enables them to overcome obstacles and navigate complex and unstructured terrain. However, the leg mechanisms and actuators needed for versatile locomotion are much more challenging to manufacture and integrate in sub-gram scale robots. Herein, Picotaur, a 15.4 mg hexapedal robot with legs that enable various locomotion tasks such as turning, climbing 3D-printed stairs, and pushing loads for the first time at these size scales, is presented. 3D printing with two-photon polymerization enables the manufacture of electrostatically driven 2 degrees of freedom legs on a robot body made from a flexible printed circuit board. Based on simple control inputs, Picotaur can achieve alternating tripod gaits, reaching speeds up to 57 mm (7.2 body lengths) per second, as well as pronking gaits to tackle a wider variety of terrain. This approach to manufacturing and controlling legged robots at smaller scales provides a path forward toward robots that can be used for practical applications ranging from inspection to exploration and rival the performance of insects at similar size scales.

Mole-Inspired Robot for Planetary Exploration

This cover image (referring to article 2300392 by Tao Zhang, Kunyang Wang, Kun Xu, and co-workers) shows a mole-inspired robot burrowing inside the lunar regolith to create a small cave for in-situ detection or instrument placement in extraterrestrial subterranean exploration. The mole-inspired robot (child robot) connects to a rover (mother robot) with a cable for communication, power supply, and retraction. The rover first creates a cave entrance to fix the mole-inspired robot, and then the robot can burrow into the cave with low power consumption and high energy efficiency.

Cable-Crawling Robots

In article number 2300828, Bo Li, Guimin Chen, and co-workers report a centimeter-scaled cable-crawling robot for thin cables by utilizing multilayered dielectric elastomer actuators. The miniaturized robot (2.1 g, 43 mm long) can quickly crawl on extremely thin cables with different orientations, transport objects, and locomote across the water–air interface. Benefit from the excellent locomotion performance, the robot can be applied to perform inspection and maintenance tasks along pre-built cables inside some equipment with narrow, confined internal spaces, such as airplane wings. This novel centimeter-scaled robot offers a potential platform solution for operating in hazardous or difficult-to-access spaces.

Soft Robotic Morphing Wing for Unmanned Underwater Vehicles

Soft robots for underwater exploration are a powerful tool to assess ecological health and survey deep-sea environments autonomously. This cover illustrates an unmanned underwater vehicle featuring soft, hydraulically actuated wings deployed in the subsurface ocean of Enceladus. The incorporated soft wings have been designed to be pressure agnostic, impact resilient, and highly efficient, to enable autonomous surveying of large volumes. For further details, see article number 2300702 by Fabian Wiesemüller, Mirko Kovač, and co-workers.

Studying the behavior of electroactive cells, such as firing dynamics and chemical secretion, is crucial for developing human disease models and therapeutics. Following the recent advances in cell culture technology, traditional monolayers are optimized to resemble more 3D, organ-like structures. The biological and electrochemical complexity of these structures requires devices with adaptive shapes and novel features, such as precise electrophysiological mapping and stimulation in the case of brain- and heart-derived tissues. However, conventional organ-on-chip platforms often fall short, as they do not recreate the native environment of the cells and lack the functional interfaces necessary for long-term monitoring. Origami-on-a-chip platforms offer a solution for this problem, as they can flexibly adapt to the structure of the desired biological sample and can be integrated with functional components enabled by chosen materials. In this review, the evolution of origami-on-a-chip biointerfaces is discussed, emphasizing folding stimuli, materials, and critical findings. In the prospects, microfluidic integration, functional tissue engineering scaffolds, and multi-organoid networks are included, allowing patient-specific diagnoses and therapies through computational and in vitro disease modeling.

Surveillance cameras produce vast amounts of video data, posing a challenge for analysts due to the infrequent occurrence of unusual events. To address this, intelligent surveillance systems leverage AI and computer vision to automatically detect anomalies. This study proposes an innovative method combining 3D convolutions and long short-term memory (LSTM) modules to capture spatiotemporal features in video data. Notably, a structured coarse-level feature fusion mechanism enhances generalization and mitigates the issue of vanishing gradients. Unlike traditional convolutional neural networks, the approach employs depth-wise feature stacking, reducing computational complexity and enhancing the architecture. Additionally, it integrates microautoencoder blocks for downsampling, eliminates the computational load of ConvLSTM2D layers, and employs frequent feature concatenation blocks during upsampling to preserve temporal information. Integrating a Conv-LSTM module at the down- and upsampling stages enhances the model's ability to capture short- and long-term temporal features, resulting in a 42-layer network while maintaining robust performance. Experimental results demonstrate significant reductions in false alarms and improved accuracy compared to contemporary methods, with enhancements of 2.7%, 0.6%, and 3.4% on the UCSDPed1, UCSDPed2, and Avenue datasets, respectively.

Image preprocessing models are usually employed as the preceding operations of high-level vision tasks to improve the performance. The adversarial attack technology makes both these models face severe challenges. Prior research is focused solely on attacking single object detection models, without considering the impact of the preprocessing models (multifocus image fusion) on adversarial perturbations within the object detection system. Multifocus image fusion models work in conjunction with the object detection models to enhance the quality of the images and improve the capability of object detection system. Herein, the problem of attacking object detection system that utilizes multifocus image fusion as its preprocessing models is addressed. To retain the attack capabilities of adversarial samples against as many perturbations as possible, new attack method called adaptive retention attack (ARA) is proposed. Additionally, adversarial perturbations concentration mechanism and image selection mechanism, which, respectively, enhance the transferability and attack capability of ARA-generated adversarial samples. Extensive experiments have demonstrated the feasibility of the ARA. The results confirm that the ARA method can successfully bypass multifocus image fusion models to attack the object detection model.

Modular robots have unique advantages in handling faults and improving their robustness due to their self-reconfiguration capacity and homogeneous interchangeability. When locked joint failure occurs in modular robots, the distribution of the failed modules will affect the manipulation capacity of the robot. In this article, a novel self-reconfiguration method that utilizes only the remaining resources available to mitigate the damage caused by module joint failures is proposed. The key node configuration is searched by the particle swarm optimization (PSO) algorithm, and then the collision-free reconfiguration path is planned by the rapidly exploring random trees (RRT) algorithm. The proposed method not only handles single-module lockup failure but can also be expanded to multi-module lockup failures, fully improving the fault tolerance of the modular robot. The method is deployed on the hardware, and the feasibility of the algorithm is verified by self-reconfiguration experiments containing faulty modules.