Search

The global interest in market prediction has driven the adoption of advanced technologies beyond traditional statistical models. This paper explores the use of machine learning and deep learning techniques for stock market forecasting. We propose a comprehensive approach that includes efficient feature selection, data preprocessing, and classification methodologies. The wavelet transform method is employed for data cleaning and noise reduction. Feature selection is optimized using the Dandelion Optimization Algorithm (DOA), identifying the most relevant input features. A novel hybrid model, 3D-CNN-GRU, integrating a 3D convolutional neural network with a gated recurrent unit, is developed for stock market data analysis. Hyperparameter tuning is facilitated by the Blood Coagulation Algorithm (BCA), enhancing model performance. Our methodology achieves a remarkable prediction accuracy of 99.14%, demonstrating robustness and efficacy in stock market forecasting applications. While our model shows significant promise, it is limited by the scope of the dataset, which includes only the Nifty 50 index. Broader implications of this work suggest that incorporating additional datasets and exploring different market scenarios could further validate and enhance the model's applicability. Future research could focus on implementing this approach in varied financial contexts to ensure robustness and generalizability. [ABSTRACT FROM AUTHOR]

Due to the distinctive optical, mechanical and electrical characteristics, silicon nanowire (SilNW), one of the one dimensional nanostructures, has become a potential sensing nanomaterial. SilNWs have drawn interest in high-sensitive sensor fabrication, primarily because of their large surface-volume ratios, which significantly enhanced the detection limit to femtomolar concentrations and also provided high sensitivity. Due to its high charge sensitivity, SilNW FET-based sensors had been employed extensively for sensing various chemical as well as biological species. In this work, the sensing performance and applications of different SilNW biosensors, gas sensors, chemical and metal ion sensors were studied. In this study, we have also elaborated the most current developments as well as the sensing performance of various SilNW-based Covid-19 sensors. [ABSTRACT FROM AUTHOR]

The present numerical analysis focused on the low-GWP refrigerants during condensation inside a smooth and dimple tube. The low global warming potential refrigerants considered for the present numerical analysis are hydrocarbon includes propane (R290) and propylene (R1270), hydrofluoroolefin includes 2,3,3,3-tetrafluoropropene (R1234yf) and 1,3,3,3-tetrafluoropropene (R1234ze(E)), hydrofluorocarbon 1,1-difluoroethane (R152a), and an azeotropic mixture R430A (R152a 76 % + R600a 24 % by mass). The working conditions are mass velocity ranges between 50 and 200 kg/ m 2 s, dryness fraction of 0.5 and 0.75, heat flux of 5 kW/ m 2 , and temperature of saturation of 30, 40, and 50 ∘ C. The effect of saturation temperature, mass velocity and dryness fraction were investigated along the smooth and dimpled tubes. The VOF model is used to solve the mathematical formulations and the evaporation/condensation rate is determined by using Lee's model. The simulated void fractions were reduced by 2.18 % for R134a, 3.93 % for R290, 3.31 % for R1234yf, 2.55 % for R1234ze(E), 3.52 % for R1270, 2.42 % for R430A, and 1.37 % for R152a by increasing the saturation temperature from 30 to 50 ∘ C at a quality of 50 % inside a smooth tube. And, the two-phase friction factor was reduced by 5.38 % and 2.42 % with R1234yf at a dryness fraction of 0.5 and saturation temperature of 40 ∘ C for smooth and dimple tubes. Also, the pressure drops were increased by increasing the mass flux and decreasing the saturation temperature along the smooth and dimpled tube. [ABSTRACT FROM AUTHOR]

Chest X-Ray (CXR) images provide most anatomical details and the abnormalities on a 2D plane. Therefore, a 2D view of the 3D anatomy is sometimes sufficient for the initial diagnosis. However, close to fourteen commonly occurring diseases are sometimes difficult to identify by visually inspecting the images. Therefore, there is a drift toward developing computer-aided assistive systems to help radiologists. This paper proposes a deep learning model for the classification and localization of chest diseases by using image-level annotations. The model consists of a modified Resnet50 backbone for extracting feature corpus from the images, a classifier, and a pixel correlation module (PCM). During PCM training, the network is a weight-shared siamese architecture where the first branch applies the affine transform to the image before feeding to the network, while the second applies the same transform to the network output. The method was evaluated on CXR from the clinical center in the ratio of 70:20 for training and testing. The model was developed and tested using the cloud computing platform Google Colaboratory (NVidia Tesla P100 GPU, 16 GB of RAM). A radiologist subjectively validated the results. Our model trained with the configurations mentioned in this paper outperformed benchmark results. [ABSTRACT FROM AUTHOR]

The international community limits the usage of higher global warming potential (GWP) refrigerants like R134a in refrigeration and air-conditioning systems. In view of this, the present study focuses on the low-GWP alternatives to R134a during condensation inside a smooth and dimpled tube. The refrigerants considered for this study are propane (R290), 2,3,3,3-tetrafluoropropene (R1234yf), and 1,3,3,3-tetrafluoropropene (R1234ze). The geometric specifications of smooth and dimple tubes are 8.38 mm ID with 1.5 m length. The operating conditions are saturation temperature of 40°C, mass flux ranging between 50 and 200 kg m−2 s−1, and dryness fraction of 0.5 and 0.75. The flow field was assumed to be transient, three-dimensional and turbulent while the VOF model was used to solve the governing equations. The effect of mass flux and dryness fraction was studied with R134a and its alternatives. The simulated void fraction values are compared with experimental values and empirical correlations. In this study, the total pressure drop was reduced by 15 and 20% with smooth tube and 11 and 16.7% with dimpled tube by using R1234yf at the quality of 0.5 and 0.75. However, it was increased with R290 and R1234ze. The power consumption was reduced by using R1234yf as a substitute to R134a and the thermophysical properties are quite similar. [ABSTRACT FROM AUTHOR]

In this study, the numerical simulations for multiphase fluid flow inside a smooth and dimpled tube were investigated at low mass velocities during the condensation of R-134a to determine the pressure drop. The numerical analysis was conducted at a dryness fraction of 0.5, temperature of saturation of 30–50°C, and mass fluxes range between 50 and 200 kg m−2 s−1. The impact of mass flux on the pressure drops had been studied along the smooth and dimpled tube. The smooth and dimpled tubes were designed with an inside and outside diameter of 8.38 and 9.54 mm, respectively. The specifications of the dimpled tube were o = 1 mm, p = 5.08 mm, z = 4.99 mm, and e = 0.5 mm. The Volume of Fluid (VOF) flow model was utilized in this study and the flow field was assumed to be three-dimensional, transient and turbulent. With an increase in mass flux for both smooth and dimple tubes, total pressure drop and frictional pressure drop increases. The numerically simulated two-phase friction factor was compared with the well-known correlations of the dimple tube. Also, the numerically simulated pressure drop for the dimple tube was more compared with the plain tube and the pressure drop decreases with an increase in temperature of saturation. [ABSTRACT FROM AUTHOR]

In the present investigation, the evolution of texture and microstructure during incremental sheet forming was investigated. Hot-rolled sheets of commercially pure titanium were subjected to single-point incremental forming to obtain truncated pyramid geometries. It was observed from texture measurements that there was splitting of basal poles along the transverse direction. Moreover, a significant number of twins was observed in the deformed microstructure with the fraction of extension twins being highest compared to other variants. The crossing of deformation twins, formation of twin lamellar structure and formation of secondary extension twins within primary contraction twins were additionally observed. The state of deformation in the pyramid walls was analyzed via finite element method which in turn was used as input for carrying out crystallographic texture simulations via visco-plastic self-consistent simulations. It was observed that the state of deformation in the wall regions is plain strain compression plus through-thickness shear. [ABSTRACT FROM AUTHOR]

A number of new isoxazole coupled pyrimido[4,5-c]isoquinolines has been synthesized in good to excellent yields by the one pot method. The Cu(I)-catalyzed cycloaddition reaction between the terminal alkyne 4 and various aldehydes has led to nitrile oxides. The in vitro study of antitumor activity of the products has indicated three of those to be potent anticancer (MCF-7) agents with IC50 values close to that of the standard drug. Molecular docking studies have also been conducted to complement the experimental results. [ABSTRACT FROM AUTHOR]

Incremental Sheet Forming (ISF) is a dieless forming process and has capability to form complex 3D geometries. Double Sided Incremental Forming (DSIF) is the most flexible variant of ISF as it uses two tools, one on either side of the sheet (one tool forms the sheet and other acts as support). However, forming the components with acceptable accuracy is one of the challenges as it depends on many factors such as sheet and tool(s) deflections as well as machine tool errors. If these deflections/deviations are not compensated in tool path, accuracy of the component gets affected and support tool may lose contact or squeeze the sheet while forming components. In the present work, grid-based method is used to measure the machine tool error at discrete points of the work envelope. To enhance the accuracy and support tool contact condition, machine tool errors are compensated in tool path along with tool and sheet deflection compensations developed earlier. To demonstrate the effectiveness of developed methodology on the accuracy, components having different geometric characteristics as well as opening sizes are formed with and without compensating for machine tool errors in tool path. Results indicate that deviation in symmetry within the same contour reduced from 850 μm to less than 40 μm. In addition, support tool has maintained contact throughout support surface with maximum force of 50 N when machine tool errors are compensated. [ABSTRACT FROM AUTHOR]

This study deals with the evolution of crystallographic texture during secondary processing of aluminium-lithium alloy AA2195 sheets and its effect on the single-point incremental forming (SPIF) process. Significantly different textures were generated in AA2195 alloy sheets by the unidirectional rolling (UDR) and multi-step cross-rolling (MSCR) processes followed by subsequent annealing. The differently textured sheets were then subjected to the SPIF process. For UDR processed sheets, the texture was the strong copper type (Cu-type), whereas in MSCR processed sheets, the texture comprised weak fibres. The UDR samples with strong texture experienced cracking during incremental forming, whereas the MSCR samples could be formed without any cracks. Detailed analyses of the microstructure and texture were performed at various locations on the incrementally formed part to understand the deformation micromechanism at specific locations on the formed component. [ABSTRACT FROM AUTHOR]