Search

The Rubik’s cube is a prototypical combinatorial puzzle that has a large state space with a single goal state. The goal state is unlikely to be retrieved using orders of randomly generated moves, posing unique challenges for machine learning. The proposed work is above to solve the Rubik’s cube with recursion and DeepCubeA, a deep reinforcement learning approach that learns how to solve increasingly difficult states in reverse from the goal state without any specific domain knowledge. DeepCubeA solves 100% of all test patterns, finding a shortest path to the goal state 60.3% of the time. Deep Cube A generalizes to other combinatorial puzzles andis able to solve the 15 puzzle, 24 puzzle, 35 puzzle, 48 puzzle, Lights Out and Sokoban, finding a shortest path in the majority of verifiable cases. These models were trained with 1 4 GPUs and 20 30 CPUs. This varies throughout training as the training is often stopped and started again to make room for other processes. Further our experimentation compares the results of Rubik’s cube solving among both recursion and DeepCubeA and also with the state of art models. Later, we intend to develop a new deep learning model with an application.

Tampering an image became more manageable due to the advent of photo editing software. So, it is essential to detect and correct the tampered locations. This article presents an image watermarking scheme that applies a modified version of 8 data bits and 4 redundant bits of Hamming code. It operates over a block of 3 pixels at a time. The 24 bits of the 3 pixels are rearranged and divided into 2 processing units, each comprising 12 bits. Out of 12 bits in a unit, 4 bits are used as redundant bits, and 8 bits are used as data bits. Watermark bits (WBs) are generated from data bits using a logistic map (LM) and stored in redundant bit positions. Experimental results reveal that this proposed technique maintains a fair balance for both capacity and distortion. The measured capacity is 2.67 bits per pixel (bpp) with a 39.21 decibels (dB) distortion. The estimated structural similarity (SSIM) is 0.9844, and the accuracy is 0.9999. Furthermore, it was also found that the proposed technique performs fairly well compared to existing techniques in capacity and distortion. [ABSTRACT FROM AUTHOR]

Background: Colorectal carcinoma is one of the leading causes of mortality worldwide. Although the current TNM staging helps in prognostic stratification, these cancers are known to show heterogeneous behavior within the same stage. A search for other prognostic histopathological factors has been in process. One such factor is tumor budding. Aims and Objectives: This study was aimed at enumerating tumor budding, stratifying it, and identifying correlation with other the clinicopathological factors. Materials and Methods: This was a retrospective study conducted in the Department of Pathology, Hassan Institute of Medical Sciences, Hassan. A total of 124 cases were studied. Archived blocks and slides were retrieved, reviewed, and assigned a tumor budding grade on H&E staining. Grade of tumor budding was correlated with various clinical and histopathological parameters for statistically significant association. Results: A total of 124 cases were studied which showed female preponderance (54.8%) in presentation and the most common age group being 61–70years (48%). Adenocarcinoma was the most common histological subtype (83.8%). Lymph node metastasis was observed in 52 cases (42%). The grade of tumor budding was low in 96 cases (77.5%), intermediate in 20 cases (16%), and high in 8 cases (6.5%). Statistically significant association was observed between grade of tumor budding and age, histological grade, lymphovascular invasion, and lymph node involvement. Conclusion: Tumor budding is an independent prognostic marker for adverse prognosis and predictor of lymph node metastasis. Enumerating tumor budding on routine H&E slide is an inexpensive method of providing additional prognostic factors for better patient management.

Activated carbon/CuFe2O4 composite was made using a hydrothermal process. X-ray diffraction (XRD), transmission electron microscopy (TEM), nitrogen adsorption isotherms, vibrating sample magnetometer (VSM), UV–visible diffuse reflectance spectra (DRS), and Fourier transform infrared (FT-IR) spectroscopy were used to characterise the CuFe2O4/AC composites that were synthesised using the previously mentioned method. Each phase’s existence is confirmed by XRD, and TEM revealed the spherically shaped nanoparticles. The Fe–O, Cu–O, and AC vibration modes in the composite are validated by the infrared spectra. Under 60 min of visible light irradiation, the 10%-CuFe2O4/AC composite, which has a bandgap of 2.19 eV and soft-ferromagnetic characteristics, demonstrated strong photocatalytic activity in decomposing MB (50 ppm, 30 mL) up to 99.5%. Through preservation of its high percentage of dye degradation, the 10%-CuFe2O4/AC composite may be used again. The results of the radical trapping experiments indicate that the primary active species involved in the photocatalytic degradation process are superoxide (O2−) and hydroxyl (OH*). Five cycles of the photocatalyst’s recyclability were investigated, and the results showed that the replicated catalysts showed very little rate variations. An effective photocatalyst for the breakdown of wastewater dye is CuFe2O4/AC. [ABSTRACT FROM AUTHOR]

Novel CoZnO2 and SnO2 doped CoZnO2 nanocomposites (NCs) were synthesized by the co‐precipitation method successfully and analyzed using UV‐Vis, FT‐IR, XRD and SEM analysis etc. The UV‐Vis studies confirmed the absorption values of CoZnO2 and SnO2 doped CoZnO2 at 359 and 365 nm respectively and the obtained FT‐IR peaks at 569 and 538 cm−1 revealed the presence of metal‐oxygen bonds successfully. The crystalline size was found to be 21.46 and 40.35 nm. In SEM analysis, CoZnO2 showed the densified un‐uniform particles whereas SnO2 doped CoZnO2 NCs seemed to be bunch of particles combined together. The synthesized NCs have proved the photocatalytic property by confirming the degradation efficiency of 72.22 and 82.22 % against methylene blue (MB) under sunlight irradiation as natural source at the time interval of 120 mins. It is revealed by the enhancement in the reduction of 4‐nitrophenol by changing the parameters and the efficiency percentage of 89.46 and 94.52 % at 18 and 16 mins respectively. The adsorption study was carried out by changing different concentrations of targeted pesticide like glyphosate and the percentage (%) efficiency was calculated to be 90.90, 83.53, 78.49 %, and 91.02, 88.23, 80.64 % for CoZnO2 and SnO2 doped CoZnO2 effectively. The high inhibition against DPPH was found to be 42.7 and 53.7 % at 500 μg mL−1 and the maximum zone of inhibition was found to be 22 mm against to 240 μg mL−1 of E. coli. Therefore, the current study proposed that the CoZnO2 and SnO2 doped CoZnO2 have good capability for bio‐chemical catalytic applications. [ABSTRACT FROM AUTHOR]