The Experts below are selected from a list of 240 Experts worldwide ranked by ideXlab platform
Radu Timofte - One of the best experts on this subject based on the ideXlab platform.
-
learning discriminative Model prediction for tracking
International Conference on Computer Vision, 2019Co-Authors: Goutam Bhat, Martin Danelljan, Luc Van Gool, Radu TimofteAbstract:The current strive towards end-to-end trainable computer vision systems imposes major challenges for the task of visual tracking. In contrast to most other vision problems, tracking requires the learning of a robust target-specific appearance Model online, during the inference stage. To be end-to-end trainable, the online learning of the target Model thus needs to be embedded in the tracking architecture itself. Due to the imposed challenges, the popular Siamese paradigm simply predicts a target feature template, while ignoring the background appearance information during inference. Consequently, the Predicted Model possesses limited target-background discriminability. We develop an end-to-end tracking architecture, capable of fully exploiting both target and background appearance information for target Model prediction. Our architecture is derived from a discriminative learning loss by designing a dedicated optimization process that is capable of predicting a powerful Model in only a few iterations. Furthermore, our approach is able to learn key aspects of the discriminative loss itself. The proposed tracker sets a new state-of-the-art on 6 tracking benchmarks, achieving an EAO score of 0.440 on VOT2018, while running at over 40 FPS. The code and Models are available at https://github.com/visionml/pytracking.
Mohd Nordin Adlan - One of the best experts on this subject based on the ideXlab platform.
-
application of response surface methodology rsm for optimization of ammoniacal nitrogen removal from semi aerobic landfill leachate using ion exchange resin
Desalination, 2010Co-Authors: Mohammed J K Bashir, Hamidi Abdul Aziz, Mohd Suffian Yusoff, Mohd Nordin AdlanAbstract:Disposal of untreated landfill leachate can be a source of hazard to receiving waters. Hence, treatment of landfill leachate is considered environmentally essential. In this study, optimization of ammoniacal nitrogen (NH3–N) removal from Malaysian semi-aerobic landfill stabilized leachate using synthetic cation ion exchange resin was investigated. An ideal experimental design was carried out based on Central Composite Design (CCD) with response surface methodology (RSM). This RSM was used to evaluate the effects of process variables and their interaction towards the attainment of their optimum conditions. Equilibrium isotherms in this study were analyzed using the Langmuir and Freundlich. Kinetic data were obtained and analyzed using pseudo-first-order and pseudo-second-order equations. Based on statistical analysis, the NH3–N removal Model proved to be highly significant with very low probability values (< 0.0001). The optimum conditions obtained were 24.6 cm3 resin dosage, 6.00 min contact time, and 147.0 rpm shaking speed. This resulted in 94.2% removal of NH3–N as obtained from the Predicted Model, which fitted well with the laboratory results (i.e., 92%). The adsorption isotherm data were fitted well to the Langmuir isotherm, and the monolayer adsorption capacity was found as12.56 mg/g.
Jun Shen - One of the best experts on this subject based on the ideXlab platform.
-
performance prediction of hfc hc hfo and hcfo working fluids for high temperature water source heat pumps
Applied Thermal Engineering, 2020Co-Authors: Han Yan, Li Ding, Bowen Sheng, Xueqiang Dong, Yanxing Zhao, Quan Zhong, Wenchi Gong, Maoqiong Gong, Hao Guo, Jun ShenAbstract:Abstract High temperature water source heat pumps (HTWSHP) plays an increasingly important role in drying and building heating due to its remarkable energy-saving effect. However, traditional heat pump working fluids such as R134a are not applicable for HTWSHP and the research on alternative working fluids is limited by the complex process of working fluids screening. This paper is aimed to quickly and easily obtain the performance of a large amount of working fluids for screening. A new simple performance Predicted Model was proposed in a simple vapor compression cycle at condensation temperatures from 70 to 110 °C. By knowing only a working fluid’s critical temperature and pressure, the specific volumetric heating capacity (VHC) and coefficient of performance (COP) can be Predicted. Based on the Model, the performance prediction for the newer working fluids involving R1336mzz(Z) and R1224yd(Z) was conducted. The results produced by the Model were compared with the values calculated by Peng-Robinson equation of state (PR EoS) and the default, high-accuracy equations implemented in REFPROP 10.0. The Predicted values in this work show good agreement. Besides, the Model can also be applied varying compressor isentropic efficiencies from 60% to 80%, superheats from 0 to 10 °C and sub-coolings from 0 to 8 °C.
Gholamreza Abi - One of the best experts on this subject based on the ideXlab platform.
-
Optimization the Effects of Physicochemical Parameters on the Degradation of Cephalexin in Sono-Fenton Reactor by Using Box-Behnken Response Surface Methodology
Catalysis Letters, 2019Co-Authors: Tariq J. Al-musawi, Hossein Kamani, Edris Bazrafshan, Ayat Hossein Panahi, Marcela Fernandes Silva, Gholamreza AbiAbstract:This work aims to study the degradation process using Sono-Fenton reactor for the treating of pharmaceutical wastewater loaded with cephalexin. The degradation process was tested as a function of pH (3–11), concentration of degradation agent H_2O_2 (40–80 mg/L), metal catalyst agent Fe^2+ (4–12 mg/L), reaction time (up to 100 min), and initial cephalexin concentration (50–100 mg/L). The effects of these parameters were tested and optimized by using Box-Behnken response surface methodology (RSM). All the experiments were performed with exposure to ultrasonic irradiation of a frequency of 130 kHz. According to the ANOVA results with a confidence level of 95%, a high regression and fitting values were obtained between the experimental degradation data of cephalexin and the RSM Predicted Model. This finding suggests that RSM is an extremely significant and accurate methodology to Model the degradation process of cephalexin using Sono-Fenton reactor. Accordingly, the optimum degradation efficiency of 90% was obtained at conditions of pH 3, H_2O_2 concentration = 60 mg/L, Fe^2+ concentration = 8 mg/L, cephalexin concentration = 50 mg/L, and reaction time = 60 min. Thus, the current study demonstrated that the Sono-Fenton reactor can be used effectively as an advanced oxidation treatment unit for degradation of cephalexin under optimized environmental conditions. Graphical Abstract
N.m. Sachindra - One of the best experts on this subject based on the ideXlab platform.
-
Shrimp biowaste fermentation with Pediococcus acidolactici CFR2182: Optimization of fermentation conditions by response surface methodology and effect of optimized conditions on deproteination/demineralization and carotenoid recovery
Enzyme and Microbial Technology, 2007Co-Authors: Narayan Bhaskar, P. V. Suresh, P.z. Sakhare, N.m. SachindraAbstract:Abstract Fermentation of shrimp biowaste was conducted using different lactic acid bacteria (LAB) to select the efficient starter culture based on pH reduction and acid production. Pediococcus acidolactici CFR2182 was found to be the efficient ( P ≤ 0.05) among the five starter cultures tested. Fermentation conditions viz ., inoculum level (X1), sugar level (X2) and incubation time (X3) were optimized using response surface methodology (RSM) to obtain the desirable pH of 4.3 ± 0.1. The optimized conditions were found to be 5% (v/w) inoculum (with 8.28 log cfu ml −1 ), 15% (w/w) glucose and 72 h of incubation time at 37 ± 1 °C to attain a pH of 4.30. The usefulness of the Predicted Model was further validated by considering random combinations of the independent factors. The high correlation (with regression coefficient close to 1.0) between the Predicted and observed values during validation indicated the validity of the Model. The effect of fermentation, by P. acidolactici CFR2182, on the production of chitin (as indicated by deproteination and demineralization efficiency) and recovery of carotenoids was also studied. Deproteination of 97.9 ± 0.3% and demineralization of 72.5 ± 1.5% was achieved by fermentation of shrimp biowaste with P. acidolactici . The carotenoid recovery in fermented shrimp biowaste, as compared to the wet waste, varied between 72.4 and 78.5% during fermentation.
