Daily electric vehicle charging dataset for training reinforcement learning algorithms.

Reinforcement learning algorithms are increasingly utilized across diverse domains within power systems. One notable challenge in training and deploying these algorithms is the acquisition of large, realistic datasets. It is imperative that these algorithms are trained on extensive, realistic datasets over numerous iterations to ensure optimal performance in real-world scenarios. In pursuit of this goal, we curated a comprehensive dataset capturing electric vehicle (EV) charging details over a span of 29,600 days within a designated parking facility. This dataset encompasses necessary information such as connection times, charging durations, and energy consumption of individual EVs. The methodology involved employing conditional tabular generative adversarial networks (CTGAN) to craft a pool of synthetic dataset from a smaller initial dataset collected from an EV charging facility located on the Caltech campus. Subsequently, multiple post-processing techniques were implemented to extract data from this pool, ensuring compliance with the charging station's capacity constraint while maintaining a realistic daily EV demand profile derived from historical data. Using kernel density estimation (KDE), the distributional characteristics of the historical data, especially concerning the timing of EV connections, were faithfully replicated. The developed dataset is specifically useful in training offline reinforcement learning algorithms.

Synthesis, antileishmanial activity and molecular modeling of new 1-aryl/alkyl-3-benzoyl/cyclopropanoyl thiourea derivatives.

Due to the lack of effective vaccine(s) against leishmania and also pharmacokinetics issues of current drugs, it is necessary to discover new antileishmanial agents. Within this particular study, a series of novel 1-aryl/alkyl-3-benzoyl/cyclopropanoyl thiourea derivatives were synthesized (yields 69-84%) and evaluated as antileishmanial compounds (1-11). Synthetic derivatives were subjected to in vitro antileishmanial assessment against Leishmania major promastigotes by colorimetric MTT assay. Compounds 3 (IC50 38.54 µg/mL), 5 (IC50 84.75 µg/mL) and 10 (IC50 70.31 µg/mL) exhibited higher activities after 48 h but were less potent than amphotericin B (IC50 0.19 µg/mL). Antileishmanial activities indicated priority of 5-methyl-4-phenyl thiazole over furyl methyl substituents and 4-phenyl thiazole on thiourea nitrogen. N-myristoyltransferase (NMT) was selected as a validated L. major target for molecular docking studies. In silico results indicated the contribution of hydrophobic, π-stacking and H-bond interactions in binding to target. Most of the synthesized derivatives had lower binding affinities to human NMT (hNMT) than leishmanial enzyme. Docking conformations of top-ranked selective binders (compounds 3 and 5) were subjected to 50 ns MD simulations inside L. major HMT (LmNMT) active site. MD trajectories were used to extract RMSD, RMSF, Rg and durability of intramolecular/intermolecular H-bonds of the complex. It was observed that compound 3 escaped from LmNMT binding site during simulation period and no stable complex could be envisaged. Unlike 3, compound 5 attained stable binding conformation with converged stability parameters. Although mechanistic details for antileishmanial effects of synthesized derivatives are to be explored, current results may be implicated in further structure-guided approach toward potent antileishmanial agents.

Selective Microwave Zeroth-Order Resonator Sensor Aided by Machine Learning.

Microwave sensors are principally sensitive to effective permittivity, and hence not selective to a specific material under test (MUT). In this work, a highly compact microwave planar sensor based on zeroth-order resonance is designed to operate at three distant frequencies of 3.5, 4.3, and 5 GHz, with the size of only λg-min/8 per resonator. This resonator is deployed to characterize liquid mixtures with one desired MUT (here water) combined with an interfering material (e.g., methanol, ethanol, or acetone) with various concentrations (0%:10%:100%). To achieve a sensor with selectivity to water, a convolutional neural network (CNN) is used to recognize different concentrations of water regardless of the host medium. To obtain a high accuracy of this classification, Style-GAN is utilized to generate a reliable sensor response for concentrations between water and the host medium (methanol, ethanol, and acetone). A high accuracy of 90.7% is achieved using CNN for selectively discriminating water concentrations.