Search

Machine learning (ML) is a fast-growing field that has vast applications in different areas and sintering has had no exemption from that. In this paper, the application of ML methods in sintering of the various materials has been reviewed. Based on our review, it was used to optimize the sintering process and improve the characteristics of the final product. For instance, a supervised learning algorithm was used to predict the temperature and time based on the raw material properties and the desired properties of the final product in sintering. Among all ML methods, k-nearest neighbor (k-NN), random forest (RF), support vector machine (SVM), regression analysis (RA), and artificial neural networks (ANN) had great applications in the sintering field. There are a limited number of papers that used deep learning in sintering. In conclusion, ML methods can be used to optimize sintering process in energy, cost and time.

Objective Corticospinal tract (CST) injury may lead to motor disorders in children with Cerebral Palsy (CP). However, the precise underlying mechanisms are still ambiguous. We aimed to characterize the CST structure and function in children with CP and determine their contributions to balance and gait impairments. Method Twenty-six children with spastic CP participated. Transcranial magnetic stimulation (TMS) and diffusion tensor imaging (DTI) were utilized to characterize CST structure and function. Common clinical measures were used to assess gait speed, endurance and balance, and mobility. Results CST structure and function were significantly altered in children with CP. Different abnormal patterns of CST structure were identified as either abnormal appearance of brain hemispheres (Group-1) or semi-normal CST appearance (Group-2). We found significant correlations between the DTI parameters of the more affected CST and gait features only in Group-1. Conclusion CST structure and function are abnormal in children with CP and these abnormalities may contribute to balance and gait impairment in some children with CP. Significance Our findings may lead to the development of further investigations on the mechanisms underlying gait impairment in children with CP and on decision-making for more effective rehabilitation.

Hydrological modeling academic studies have focused on the response to human-caused land use changes. The effects of land use change on flood degree in the catchment basin of Ekbatan Dam were investigated in this study, which looked at changes that occurred in 1985, 2000, and 2015. A combination of remote sensing and the Hydrologic Engineering Center-Hydrologic Modeling System (HEC-HMS) was used to achieve this goal. First, Landsat satellite images and sensors from Thematic Mapper, Enhanced Thematic Mapper Plus (ETM +), and Operational Land Imager were used to create land use maps for the target years. The weighted curve numbers (CN), a parameter related to infiltration, were then calculated for land uses. The extracted CN value, along with physiographic parameters and rainfall-runoff data, was then imported into the HEC-HMS model to simulate the effect of land use changes on runoff volume. After calibration and validation of the model using five (5) flood events, the simulation results showed an increase in the discharge peak volume of 64.3, 67.3, and 70.5 (m3/s) during the years 1985, 2000, and 2015, respectively, which resulted in an increase in the runoff height in these years as well.

The present work aims to investigate the geometrical parameters of the graphite die on energy consumption needed for sintering of a ZrB2 sample. The Maxwell and electrical charge conservation equations are solved to obtain the electrical potential and current of the system. The governing equations are discretized by the Galerkin method and solved using the finite element method. The electric current distribution is obtained at each geometry and the temperature contours are obtained. The results showed that the height of die has a direct effect on power consumption. This can be attributed to the increased electric resistance and consequent increased Joule heating. On the other hand, increasing the die height resulted in more uniform temperature distribution through the sintered sample.

We aimed to characterize the impact of anti-gravity locomotion training on the structure and function of the corticospinal tract (CST) in cerebral palsy (CP). Fourteen CP children participated. Nine children were trained with an antigravity treadmill (Alter-G) and five children received occupational therapy (OT). Treatments were provided for 45 min each session, 3 sessions per week for 8 weeks. Diffusion tensor imaging (DTI) was used, and fractional anisotropy (FA), mean diffusivity (MD), radial (RD) and axial (AD) diffusivity was extracted to characterize the structure of the CST. Transcranial magnetic stimulation (TMS) was used and threshold, latency, and peak-peak amplitude of the MEP signal, elicited by the TMS, were used to quantify the function of the CST. Walking ability was evaluated by measuring gait speed, endurance, balance, and mobility. The evaluations were performed before and after the interventions. The results showed that FA improved in both sides of the brain for the AlterG group, but enhanced only in the less affected side of the OT group. MD, RD, and AD mostly improved in the more affected side of the AlterG group. The enhancement of the CST function was similar in both groups. Walking speed and endurance also enhanced in both groups, but the improvement was greater in the AlterG group. Our findings demonstrate that AlterG training can improve gait ability, and simultaneously result in brain neuroplasticity. The clinical implication is that AlterG training can be used as an effective rehabilitation approach to improve gait persistently.

Electromagnetic tracking (EMT) systems are often used to track the position and orientation of a navigation tool during navigated surgery operations. But, their sensitivity to field distortions originating from electromagnetic emitting devices or metallic objects present in the environment reduces measurement accuracy. The purpose of this study is to incorporate orientation information in correcting position data provided by EMT based on Hardy's Multi-Quadric method (HMQ). We implemented the HMQ algorithm in two ways: the basic form in which location data is used only and the modified form in which both the orientation and location data are incorporated into a normalized vector in the relevant formula. Comparing the corrected position data with their corresponding reference values, which are provided by the optical tracking system, it is observed that the mean global error is reduced approximately by half and the variance is decreased nearly to its one tenth.

In this study, isolated word recognition system has been investigated. The purpose of this research is to increase the performance of children's speech recognizer using vocal tract length normalization. The speech data that has been used to recognize phase, are correct and incorrect pronunciation of 47 words. This recognition system has been created to design a speech therapy software. Recognition of correct and wrong pronunciation and help children to improve it are the goals of this software. Four Baseline models have been Trained, one for children, one combined model (females and children) and two for Adults (by exploiting one Persian database). Children's model was trained with data that has been collected from 25 children. 13 children's vocabulary data were used to recognize phase. These experiments were implemented in HTK toolkit. Poor performance was improved using VTLN. Improvement of adult's model was more than children's model.