This work demonstrates the potential of machine learning (ML) method to predict catalytic activity of transition metal complex precatalyst toward ethylene polymerization. For this purpose, 294 ...complexes and 15 molecular descriptors were selected to build the artificial neural network (ANN) model. The catalytic activity can be well predicted by the obtained ANN model, which was further validated by external complexes. Boruta algorithm was employed to explicitly decipher the importance of descriptors, illustrating the conjugated bond structure, and bulky substitutions are favorable for catalytic activity. The present work indicates that ML could give useful guidance for the new design of homogenous polyolefin catalyst.
Machine learning method was applied to investigate the catalytic activity of 294 bis(imino)pyridine metal analogue complexes toward ethylene polymerization. By using 15 selected descriptors, the obtained neural network models exhibit good correlation and cross validation coefficient values, which were further validated by external complexes. The interpretation of descriptors indicates the important role of conjugated bond structure and bulky substitutions, providing guidance for the new design of homogenous polyolefin catalyst.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SBCE, SBMB, UL, UM, UPUK
Mobility patterns at region level can provide more macroscopic and intuitive knowledge on how people gather in or depart from the region. However, the analysis and prediction of regional mobility ...patterns have yet to be effectively addressed. In light of this, using smart card data (SCD) and points of interest (POI) data, a multi-step methodology which integrates the inner-restricted fuzzy C-means clustering, nonnegative tensor factorization and artificial neural network are proposed and implemented in this paper. It overcomes the difficulties in region division, pattern extraction, and prediction. The bus SCD and POI data in Beijing city are utilized for proving the usefulness of the methodology. The regional mobility patterns of bus travellers in Beijing city are extracted from the third-order tensors involving 1110 regions, 34 time slots, and 7 days of the week. The analyzed results show that the proposed methodology has a good performance on predicting the regional mobility patterns based on the regional properties. Furthermore, by considering both of the regional boarding and alighting patterns, the predictions of the regional aggregation pattern can also be achieved. These research achievements can not only provide a deep insight on the human mobility patterns at region level, but also support the evidence-based and forward-looking urban planning and intelligent transportation management.
This brief presents a wireless, low-power embedded system that recognizes hand gestures by decoding surface electromyography (EMG) signals. Ten hand gestures used on commercial trackpads, including ...pinch, stretch, swipe left, swipe right, scroll up, scroll down, single click, double click, pat, and ok, can be recognized in real time. Features from four differential EMG channels are extracted in multiple time windows. Unlike traditional data segmentation methods, an event-driven method is proposed, with the gesture event detected in the hardware. Feature extraction is triggered only when an event is detected, minimizing computation, memory, and system power. A time-delayed artificial neural network (ANN) is used to predict the gesture from the transient EMG features instead of traditional steady-state features. The ANN is implemented in the microcontroller with a processing time less than 0.2 ms. The detection results are sent wirelessly to a computer. The device weights 15.2 g. A 4.6 g battery supports up to 40 h continuous operation. To our knowledge, this brief shows the first real-time, embedded hand-gesture-recognition system using only transient EMG signals. Experiments with four subjects show that the device can achieve a recognition of ten gestures with an average accuracy of 94%.
In this project, the degradation of 4-Chloro phenol (4-CP) in aqueous environment by ultraviolet/persulphate (UV/PS) process was investigated in a batch photo-reactor. The full factorial design (FFD) ...and artificial neural networks (ANN) were used to investigate the influence of experimental variables comprising initial concentration of persulfate and 4-CP, and pH on the removal of 4-CP. The optimal conditions were achieved at 60 mM of persulphate(PS) and 0.5 mM of 4-CP and pH of 10. At this condition, the removal of 4-CP was 90.3% (experimental), and the predicted quantity by FFD and ANN approaches were 91.24 and 90.37%, respectively, and the removal of COD was 54.3% after 60 min of reaction. Also, the ANN model was better than FFD and the root mean square error (RMSE) of ANN was lower than FFD model (0.6017
AAN
˂ 0.6832
FFD
). The ANN needs larger sets of data and computational time. A high correlation coefficient (R
2
ANN
= 0.9987, R
2
FFD
= 0. 9983) was attained by an assessment between the results of experimental and model. The average percentage error for ANN and FFD were 0.188 and 0.545, respectively, representing the benefit of ANN in taking the nonlinear performance of the system.
Full text
Available for:
BFBNIB, GIS, IJS, KISLJ, NUK, PNG, UL, UM, UPUK
A mixed physically based/machine learning (ML) approach to measure tropospheric attenuation A in all-weather conditions by means of microwave radiometers (MWRs) is proposed. The key idea is to ...combine the advantages originating from the accurate radiometric A retrievals, provided by the well-established Cosmic background (CB) approach in clear-sky conditions, with the benefits coming from ML techniques. The latter aim at estimating A in rainy situations through a simplified approach able to overcome the issues posed by more complex techniques such as the standard solution of the radiative transfer equation or the Sun tracking (ST) microwave technique. To this aim, an artificial neural network (ANN) is devised to turn the antenna noise temperatures measured by a four-channel MWR (from Ka- to W-band) into tropospheric attenuation at the frequencies of the radiometric channels, namely 23.8, 31.4, 72.5, and 82.5 GHz. The network is properly trained and tested by taking advantage of the concurrent CB and ST measurements collected by the RpG radiometer deployed at Politecnico di Milano, Milan, Italy, under the ESA-funded WRAD project. The proposed approach to retrieve the tropospheric attenuation is intended to overcome the limits associated both with the ST technique (only measurements during the day, link elevation strictly bound to the Sun ecliptic) and to the CB one (unreliable measurements in rainy conditions).
There is a trend to use artificial neural networks (ANNs) as approximation models to implement explicit model-predictive control (EMPC) on hardware. However, the vanilla ANN-based EMPC scheme ...requires an overredundant ANN structure for achieving better fitting performance but at the expense of increasing the online implementation resources, such as computation time, memory cost, etc. This article proposes a light implementation scheme for ANN-based EMPC (LISABE). It shows much superior control performance than the vanilla scheme with reduced online computation time and memory resources under a combination of an optimized data generation process and an improved ANN structure. On the one hand, attention-based tree-search sampling is proposed to help enhance the ANN's fitting performance by optimizing the distribution of the offline laws of EMPC. On the other hand, by taking advantage of the bilaterally bounded property of the offline law distribution in power converter applications, a dual-rectified-linear-unit ANN is proposed as the approximation model for EMPC. It significantly improves the fitting performance with a reduced ANN structure. Simulations and experiments verify that the LISABE addresses the challenge of performing online computation of EMPC with a long prediction horizon using low-cost microprogrammed control units and can further save around 84% of online computation and memory for the current-mode boost converter and around 50% of online computation and memory for the voltage-mode buck converter compared with the vanilla ANN-based EMPC.
The present study intends to develop multi-layered feed-forward back-propagation algorithm based artificial neural network (FFBPNN) models to predict the synthesis gas (SG) compositions (H2, CH4, CO ...& CO2) and yields (mol/kg) for supercritical water gasification (SCWG) of food wastes. Such models are trained with Levenberg-Marquardt (L-M) algorithm, minimized using gradient descent approach and tested with real-time experimental datasets obtained from literature. Moreover, to determine an optimal form of the neural network for a typical non-catalytic SCWG process, a trial and error approach involving multiple combinations of transfer functions and neurons in the network layers is performed. The predicted values of SG compositions yield delivered by the FFBPNN models are in line with the experimental datasets converging to a mean squared error (MSE) value below 0.300 range and coefficient of determination (R2) above 98%. Best prediction accuracy is achieved for CO yield prediction characterized by a least MSE of 0.022 and highest train-test R2 of 0.9942–0.9939. The performance of the developed FFBPNN models can be arranged on the basis of MSE as (ann7)CO < (ann6)CH₄ < (ann5)H₂ < (ann8)CO₂ and on the basis of testing R2 as (ann7)CO > (ann6)CH₄ > (ann5)H₂ > (ann8)CO₂.
•Assessment of factors affecting synthesis gas compositions and yields for SCWG of food wastes.•Development of ANN-based generic models to predict the SG yields for SCWG of food wastes.•Comparison between experimental values and ANN-based model predicted values of SG yields.•Appreciable prediction of SG yields with MSE <0.300 and RMSE >98% range.•Illustration of ANN as an effective tool for prediction of yields individual SG compounds.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
The current investigation deals with how chemically activated carbon derived from industrial paper sludge (ACPS) performs on sorptive removal of enrofloxacin (ENF), an antibacterial drug from its ...water solution. Thermogravimetric (TGA) and proximate analysis of raw paper sludge (RPS) were conducted. ACPS was characterized with proximate analysis, XRD, FT-IR, SEM and BET. The influence of five operational parameters viz. adsorbate concentration (initial), dose of adsorbent, pH, temperature, and contact time on the adsorption of ENF onto ACPS has been conducted using batch experiments. The process of adsorption was optimized through ANN (artificial neural network) in addition to RSM (response surface methodology). The maximum percentage removal (95.85%) was achieved at initial ENF concentration 12 mg/g, adsorbent dose 1.2 g/L, contact duration of 18 h and temperature 20 °C. Kinetic data were best fitted into pseudo-second order kinetic model and adsorption equilibrium study indicates that the adsorption process follows Langmuir isotherm model. Adsorption capacity was noted to have a highest value of 44.44 mg/g. A study on thermodynamics of the adsorption process suggests that it exhibits spontaneity, being essentially exothermic. Cost analysis and reusability study confirm that adsorbent produced from industrial paper sludge is cost-effective and reusable. Therefore, ACPS as adsorbent has potency for removing ENF from aqueous solution.
Display omitted
•Adsorbent was developed from industrial paper sludge.•Above 95% removal of enrofloxacin was achieved.•Operational parameters were optimized using RSM and ANN.•72.45% removal of enrofloxacin was possible after four cycle of use of adsorbent.•The cost of preparation of adsorbent is INR 207.35 per kg.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
In this research paper, Giuseppe Peano and Cantor set fractals based miniaturized hybrid fractal antenna (GCHFA) is proposed that operates for biomedical applications. The proposed GCHFA is designed ...by merging Giuseppe Peano and Cantor set fractals that help in achieving better performance characteristics as well as miniaturization. Firefly algorithm (FA) has been employed to optimize the feed position of the designed antenna. The substrate material selected for the proposed GCHFA is low‐cost, commercially available FR4 epoxy whose thickness is 1.6 mm and relative permittivity is 4.4. A data set of 65 GCHFAs with different geometrical parameters is generated for the realization of two different bioinspired approaches. For the performance evaluation of fabricated prototype, vector network analyzer is used. The experimentally observed resonant frequencies are 2.4400 and 5.8115 GHz, and at these resonant frequencies, S (1,1) < −10 dB. The designed antenna is suitable for Industrial, Scientific, and Medical bands of biomedical applications. Moreover, the behavior of the proposed GCHFA is nearly omnidirectional. A comparative study of three different artificial neural networks (ANNs) is also done to evaluate the most suitable ANN type for the analysis of proposed GCHFA. The optimized, simulated, and experimental results depict that they are closely matched.
Full text
Available for:
FZAB, GIS, IJS, IZUM, KILJ, NLZOH, NUK, OILJ, PILJ, PNG, SAZU, SBCE, SBMB, UL, UM, UPUK
•Tillage aims to make the soil most favorable for the cultivation.•The increase of organic matter in surface with reduced tillage favors soil biomass.•Predictive capacities of MLR and ANN methods are ...assessed to estimate potato yield.•Yield was influenced by tillage, biomass, soil resistance and organic matter.•ANN model had greater potential to estimate yield from tillage and soil properties.
Tillage aims to prepare the soil with the adequate treatment to create the ideal and most favorable conditions for cultivation. To evaluate the effect of tillage systems on soil environment, it is mandatory to measure the modifications in physical, chemical and biological properties. In recent decades, artificial intelligence systems were used for developing predictive models to simplify, estimate and predict many farming processes. They are also employed to optimize performance and control risks. These systems have become true virtual helpers, and more so when integrated with predictive analytics. In the present study, the effects of tillage systems on soil properties and crop production and the predictive capabilities of multiple linear regressions (MLR) and artificial neural networks (ANN) are evaluated to estimate organic potato crop yield including soil microbial biomass (MB), soil resistance to penetration, soil organic matter (OM) and tillage system. Potato yield was found to be significantly impacted by tillage and soil properties. The results showed that MLR model estimated crop yield more accuracy than ANN model. Correlation coefficient and root mean squared (RMSE) were 0.97 and 0.077 between the measured and the estimated data by the ANN model, respectively. Generally, the ANN model showed greater potential in determining the relationship between potato yield, tillage and soil properties.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
You have reached the maximum number of search results that are displayed.
For better performance, the search offers a maximum of 1,000 results per query (or 50 pages if the option 10/page is selected).
Consider using result filters or changing the sort order to explore your results further.