A Novel Multi-task Tensor Correlation Neural Network for Facial Attribute Prediction

A geometry-enhanced graph neural network for learning the smoothness of glassy dynamics from static structure

Modeling the dynamics of glassy systems has been challenging in physics for several decades. Recent studies have shown the efficacy of Graph Neural Networks (GNNs) in capturing particle dynamics from the graph structure of glassy systems. However, current GNN methods do not take the dynamic patterns established by neighboring particles explicitly into account. In contrast to these approaches, this paper introduces a novel dynamical parameter termed "smoothness" based on the theory of graph signal processing, which explores the dynamic patterns from a graph perspective. Present graph-based approaches encode structural features without considering smoothness constraints, leading to a weakened correlation between structure and dynamics, particularly on short timescales. To address this limitation, we propose a Geometry-enhanced Graph Neural Network (Geo-GNN) to learn the smoothness of dynamics. Results demonstrate that our method outperforms state-of-the-art baselines in predicting glassy dynamics. Ablation studies validate the effectiveness of each proposed component in capturing smoothness within dynamics. These findings contribute to a deeper understanding of the interplay between glassy dynamics and static structure.

Newton Algorithm Based DELM for Enhancing Offline Tamil Handwritten Character Recognition

Numerous research based on offline Tamil recognition deals only with few Tamil characters since it becomes extremely complicated in distinguishing small variations in large handwritten document. The writer’s complexity affects the overall formation of the characters. Such types of complexities are due to discontinuation of structures, unnecessary over loops, variation in shapes as well as irregular curves. This complex issue results in enhanced error value rate. Therefore, to conquer such issues, this paper proposes a novel approach to enhance the offline Tamil handwritten character recognition by utilizing four principal steps: pre-processing, segmentation, feature extraction and classification. For optimal segmentation of Tamil characters, this paper utilizes the Tsallis entropy approach-based atom search (TEAS) optimization algorithm. Then a Newton algorithm based deep convolution extreme learning (DELM) approach is utilized for the extraction and classification of input images. Finally, experiments are carried out for numerous Tamil handwritten recognition-based approaches. The proposed Tamil character recognition utilizes the datasets of isolated Tamil handwritten characters established by HP lab India to evaluate the efficiency of the system.

Building Unmanned Store Identification Systems Using YOLOv4 and Siamese Network

Labor is the most expensive in retail stores. In order to increase the profit of retail stores, unmanned stores could be a solution for reducing labor cost. Deep learning is a good way for recognition, classification, and so on; in particular, it has high accuracy and can be implemented in real time. Based on deep learning, in this paper, we use multiple deep learning models to solve the problems often encountered in unmanned stores. Instead of using multiple different sensors, only five cameras are used as sensors to build a high-accuracy, low-cost unmanned store; for the full use of space, we then propose a method for calculating stacked goods, so that the space can be effectively used. For checkout, without a checking counter, we use a Siamese network combined with the deep learning model to directly identify products instantly purchased. As for protecting the store from theft, a new architecture was proposed, which can detect possible theft from any angle of the store and prevent unnecessary financial losses in unmanned stores. As all the customers’ buying records are identified and recorded in the server, it can be used to identify the popularity of the product. In particular, it can reduce the stock of unpopular products and reduce inventory.

Ultra-Sensitive Biosensor with Simultaneous Detection (of Cancer and Diabetes) and Analysis of Deformation Effects on Dielectric Rods in Optical Microstructure

This study proposes a refractive index sensor for the simultaneous detection of cancer and diabetes based on photonic crystals (PhC). The proposed PhC composed of silicon rods in the air bed arranged in a hexagonal lattice forms the fundamental structure. Two tubes are used to place the cancerous or diabetic samples for measurement. The sensor’s transmission characteristics are simulated and analyzed by solving Maxwell’s electromagnetic equations using the finite-difference time-domain approach for samples being studied. Therefore, diabetes and cancer are detected according to the changes in the refractive index of the samples using the laser source centered at 1550 nm. Considering the findings, the sensor’s geometry changes to adjust the suggested sensitivity and quality factor of structure. According to the results, transmission power ranges between 91 and 100% based on the sample. Moreover, sensitivity ranges from 1294 to 3080 nm/RIU and the maximum Figure of Mertie is nearly FOM = 1550.11 ± 150.11 RIU−1 with the detection in range 31 × 10−6 RIU. In addition, the small area (61.56 μm2) of biosensor results in its appropriateness for different uses in compact photonic integrated circuits. Next, we changed the shape of the dielectric rods and investigated their effects on the sensitivity parameter. The sensitivity and figure of merit after changes in the shape of dielectric rods and nanocavities are at best S = 20,393 nm/RIU and FOM = 9104.017 ± 606.93 RIU−1, receptively. In addition, the resolution detection range is 203.93 × 10−6 RIU.

High-Sensitivity Biosensor Based on Glass Resonance PhC Cavities for Detection of Blood Component and Glucose Concentration in Human Urine

In this work, a novel structure of an all-optical biosensor based on glass resonance cavities with high detection accuracy and sensitivity in two-dimensional photon crystal is designed and simulated. The free spectral range in which the structure performs well is about FSR = 630 nm. This sensor measures the concentration of glucose in human urine. Analyses to determine the glucose concentration in urine for a normal range (0~15 mg/dL) and urine despite glucose concentrations of 0.625, 1.25, 2.5, 5 and 10 g/dL in the wavelength range 1.326404~1.326426 μm have been conducted. The detection range is RIU = 0.2 × 10−7. The average bandwidth of the output resonance wavelengths is 0.34 nm in the lowest case. In the worst case, the percentage of optical signal power transmission is 77% with an amplitude of 1.303241 and, in the best case, 100% with an amplitude of 1.326404. The overall dimensions of the biosensor are 102.6 µm2 and the sensitivity is equal to S = 1360.02 nm/RIU and the important parameter of the Figure of Merit (FOM) for the proposed biosensor structure is equal to FOM = 1320.23 RIU−1.

Computational fluid dynamic simulations to improve heat transfer in shell tube heat exchangers

Improving the thermal efficiency of shell-tube heat exchangers is essential in industries related to these heat exchangers. Installing heat transfer boosters on the side of the converter tube is one of the most appropriate ways to enhance heat transfer and increase the efficiency of this equipment. In this article, spring turbulence is studied using the computational fluid dynamics tool. The displacement heat transfer coefficient and the friction coefficient were selected as the primary target parameters, and the effect of using spring tabulators on them was investigated. The ratio of torsion step length to turbulence pipe length, wire diameter to pipe diameter ratio, and flow regime was studied as the main simulation variables, and the simulation results were compared with a simple pipe. The effect of water-acting fluid, R22, and copper Nanofluid on tubes containing turbidity was compared and investigated. This study showed that due to the pressure drop, the pipe with a torsional pitch to pipe length ratio of 0.17, a turbulent diameter to pipe diameter ratio of 0.15, and a Reynolds number of 50,000 with fluid R22 has the best performance for heat transfer.

Tribological characterization of graphene oxide by laser ablation as a grease additive

In this work, the structural and tribological behavior of graphene oxide samples as a grease addi-tive was studied. By Nd:YAG laser ablation system and using graphite target at two laser energy of 0.3 W and 0.6 W, graphene oxide (GO) samples were successfully prepared. GO samples were characterized using Raman spectroscopy, field emission scanning electron microscopy (FESEM), Fourier transform infrared spectroscopy (FTIR) and energy dispersive X-ray spectroscopy (EDAX). Also, tribological behaviors of the lubricating grease, with and without the graphene oxide in grease, by the pin-on disc tribometer were determined. The Raman spectroscopy measurements showed D and G bound, which confirmed the successful synthesis of the graphene oxide sample and also the I D/I G, decreased by increasing laser power due to decreasing disorder in graphene oxide structure. FESEM images show that by ablating carbon atoms from graphite target in water, particles assemble to form a GO micro-cluster due to thermodynamically agglomeration with average size of about 3–4 µm, which the size of them depends on the laser pulse energy. Based on FTIR and EDAX analysis, GO sample which prepared at lower laser energy possessed the highest content of oxygen and oxygen functional groups. In addition, the results of tribological behavior showed that the friction-reducing ability and antiwear property of the grease can be improved effectively with the addition of GO. However, it is revealed that the small size GO has a better lubricating performance and therefore cluster size appears to play a role in the degree of wear protection due to its impact on the physical and chemical properties. The results of this study indicate that the GO sample prepared at lower laser energy (0.3 W) has a smaller size and the higher the oxygen content therefore provide better friction-reducing and anti-wear effect. Also, additive of graphene oxide in lubricating grease decreases coefficient of friction as well as wear. Based on our results, the application of GO as an additive in grease leads to increased performance of the lubricated kinematic machine.

Forecasting Daily Electricity Price by Hybrid Model of Fractional Wavelet Transform, Feature Selection, Support Vector Machine and Optimization Algorithm

This paper proposes a novel hybrid forecasting model with three main parts to accurately forecast daily electricity prices. In the first part, where data are divided into high- and low-frequency data using the fractional wavelet transform, the best data with the highest relevancy are selected, using a feature selection algorithm. The second part is based on a nonlinear support vector network and auto-regressive integrated moving average (ARIMA) method for better training the previous values of electricity prices. The third part optimally adjusts the proposed support vector machine parameters with an error-base objective function, using the improved grey wolf and particle swarm optimization. The proposed method is applied to forecast electricity markets, and the results obtained are analyzed with the help of the criteria based on the forecast errors. The results demonstrate the high accuracy in the MAPE index of forecasting the electricity price, which is about 91% as compared to other forecasting methods.

The Economic Evaluation of Methanol and Propylene Production from Natural Gas at Petrochemical Industries in Iran

This investigation scrutinizes the economic features and potential of propylene and methanol production from natural gas in Iran because greenhouse gas emissions released by natural gas-based production processes are lower than coal-based ones. Considering the advantage of Iran’s access to natural gas, this study evaluates and compares the economic value of different plans to complete the value chain of propylene production from natural gas and methanol in the form of four units based on three price scenarios, namely, optimistic, realistic, and pessimistic, using the COMFAR III software. Iran has been ranked as the second most prosperous country globally based on its natural gas reserves. Methanol and propylene production processes via natural gas will lower the release of greenhouse gas. This, increasing the investment and accelerating the development of methanol and propylene production units driven by natural gas will lead the world to a low emission future compared to coal-based plants. The economic evaluation and sensitivity analysis results revealed that the conversion of methanol to propylene is more attractive for investment than the sale of crude methanol. The development of methanol to propylene units is more economical than constructing a new gas to propylene unit because of the lower investment costs.

Day-ahead electricity price forecasting using WPT, VMI, LSSVM-based self adaptive fuzzy kernel and modified HBMO algorithm

Due to focal liberality in electricity market projection, researchers try to suggest powerful and successful price forecasting algorithms. Since, the accurate information of future makes best way for market participants so as to increases their profit using bidding strategies, here suggests an algorithm for electricity price anticipation. To cover this goal, separate an algorithm into three steps, namely; pre-processing, learning and tuning. The pre-processing part consists of Wavelet Packet Transform (WPT) to analyze price signal to high and low frequency subseries and Variational Mutual Information (VMI) to select valuable input data in order to helps the learning part and decreases the computation burden. Owing to the learning part, a new Least squares support vector machine based self-adaptive fuzzy kernel (LSSVM-SFK) is proposed to extract best map pattern from input data. A new modified HBMO is introduced to optimally set LSSVM-SFK variables such as bias, weight, etc. To improve the performances of HBMO, two modifications are proposed that has high stability in HBMO. Suggested forecasting algorithm is examined on electricity markets that has acceptable efficiency than other models.