An Application of Inverse Reinforcement Learning to Estimate Interference in Drone Swarms

Despite the increasing applications, demands, and capabilities of drones, in practice they have only limited autonomy for accomplishing complex missions, resulting in slow and vulnerable operations and difficulty adapting to dynamic environments. To lessen these weaknesses, we present a computational framework for deducing the original intent of drone swarms by monitoring their movements. We focus on interference, a phenomenon that is not initially anticipated by drones but results in complicated operations due to its significant impact on performance and its challenging nature. We infer interference from predictability by first applying various machine learning methods, including deep learning, and then computing entropy to compare against interference. Our computational framework begins by building a set of computational models called double transition models from the drone movements and revealing reward distributions using inverse reinforcement learning. These reward distributions are then used to compute the entropy and interference across a variety of drone scenarios specified by combining multiple combat strategies and command styles. Our analysis confirmed that drone scenarios experienced more interference, higher performance, and higher entropy as they became more heterogeneous. However, the direction of interference (positive vs. negative) was more dependent on combinations of combat strategies and command styles than homogeneity.     

Coulomb forces impacts on nanomaterial transportation within porous tank with lid walls

Journal of Thermal Analysis and Calorimetry - Electrical sensor has been considered in the current attempt. Combination of buoyancy, electric and radiative forces has been included in the governing...     

Efficacy of incorporating PCMs into the commercial wall on the energy-saving annual thermal analysis

Journal of Thermal Analysis and Calorimetry - In this study, the efficacy of incorporating phase change material (PCM) into the building walls on the annual heat transfer reduction is examined....     

Review on the Use of Artificial Intelligence to Predict Fire Performance of Construction Materials and Their Flame Retardancy

The evaluation and interpretation of the behavior of construction materials under fire conditions have been complicated. Over the last few years, artificial intelligence (AI) has emerged as a reliable method to tackle this engineering problem. This review summarizes existing studies that applied AI to predict the fire performance of different construction materials (e.g., concrete, steel, timber, and composites). The prediction of the flame retardancy of some structural components such as beams, columns, slabs, and connections by utilizing AI-based models is also discussed. The end of this review offers insights on the advantages, existing challenges, and recommendations for the development of AI techniques used to evaluate the fire performance of construction materials and their flame retardancy. This review offers a comprehensive overview to researchers in the fields of fire engineering and material science, and it encourages them to explore and consider the use of AI in future research projects.     

Zymography for Picogram Detection of Lipase and Esterase Activities

Lipases and esterases are important catalysts with wide varieties of industrial applications. Although many methods have been established for detecting their activities, a simple and sensitive approach for picogram detection of lipolytic enzyme quantity is still highly desirable. Here we report a lipase detection assay which is 1000-fold more sensitive than previously reported methods. Our assay enables the detection of as low as 5 pg and 180 pg of lipolytic activity by direct spotting and zymography, respectively. Furthermore, we demonstrated that the detection sensitivity was adjustable by varying the buffering capacity, which allows for screening of both high and low abundance lipolytic enzymes. Coupled with liquid chromatography-mass spectrometry, our method provides a useful tool for sensitive detection and identification of lipolytic enzymes.     

Deficiency zero for random reaction networks under a stochastic block model framework

Journal of Mathematical Chemistry - Deficiency zero is an important network structure and has been the focus of many celebrated results within reaction network theory. In our previous paper...     

A single-camera technique for simultaneous measurement of large solid particles transported in rapid shallow channel flows

This paper describes a measurement technique that was successfully applied in a study of bed load transport of large spherical solid particles in a shallow and supercritical flow (Fr?=?2.59–3.17) down a steep slope. The experimental condition was characterized by the relatively large solid particle size compared to the flow depth (d _p /h?=?0.23–0.35), and compared to the tracer diameter (d _p /d _t ?≈?130). The technique incorporated particle image velocimetry and particle tracking velocimetry (PTV) to simultaneously measure the characteristics of the two phases. In order to detect true solid particles and to distinguish them from each other and the unwanted objects, a particle characterization (PCR) algorithm based on Hough transform was employed. The output from the PCR process was utilized for PTV, as well as to generate the corresponding tracer images for special needs. Validation tests have confirmed the pixel accuracy and high reliability of the combined technique. Experimental results obtained with the developed technique include flow velocities, particle velocities, and concentration. The analysis has shown that the particle concentration profile followed an exponential relationship of the form similar to that of Rouse’s profiles, despite the large d _p /h ratio. It also revealed the effect of phase interaction, as a low loading rate of light particles on the order of O(10^?3) could yield a noticeable slowdown in the streamwise fluid velocity.     

Synthesis of Jasminaldehyde by Solid-Liquid Phase Transfer Catalysis Without Solvent,Under Microwave Irradiation

α-n-amylcinnamaldehyde (jasminaldehyde) was obtained with 82 % yield by solid-liquid phase transfer catalysis without solvent within 3 days at room temperature. By use of domestic microwave irradiation, the same yield was obtained within 1 minute at a power of 600 W.     

Anomalous thermal hysteresis in the SmC* phase of 10FHBBBM7*, revealed by dielectric measurements

The SmC* phase of (R)-4-(1-methylheptyloxycarbonyl)phenyl 4'-(4-decyloxy-3-fluorobenzoyloxy)-benzoate, 10FHBBBM7*, shows an anomalous thermal hysteresis that is reflected in the values of the measured dielectric constant. When the cooling-heating cycle is repeated, a memory effect occurs. In this work, we present a detailed study and a tentative interpretation of this unusual effect.