This is the author’s accepted version of the following publication: Armaghani, D., Momeni, E., Abad, S., Khandelwal, M. (2015) Feasibility of ANFISmodel for prediction of groundvibrationsresultingfromquarryblasting. Environmental Earth Sciences, 74(4), 2845-2860.
Efficiency of the unit operations of quarrying viz. loading, transporting and crushing is the maximum with optimum rock fragmentation. Maximum efficiency minimizes the cost of production. Therefore optimum rock fragmentation is always one of the objectives in any production blasting. Rock fragmentation is said to be optimum if the rock needs no further treatment after the blast. A lot of research has already been conducted on the various aspects of the fragmentation with the sole objective of improving the same [1-2, 4-7, 17, 21-22, 24- 31, 34-35, 38, 43,45-49, 51, 61-62, 65-71, 74-75, 78]. It is reported that more than 20 factors affect the blast results . These factors can be grouped in four different categories: rock geotechnical parameters such as density, hardness, compressibility; explosive parameters such as density, velocity of detonation; technical parameters such as delay interval, primer strength and location and geometrical parameters such as burden, spacing, and stemming . A number of empirical models are available to estimate post-blast rock fragmentation resultingfrom a blast [9-11, 39, 42, 64]. Concept of ANN has been applied to model various aspects of blast-induced groundvibrations [32, 37, 55, 76], air overpressure , fly rock [54,57,79], back break [15, 20, 36, 56, 73], powder factor [32-33, 44], estimation of blast geometry [13, 52, 59,77], estimation of an appropriate type of explosive , estimation of fragmentation [3, 15-16, 40-41, 50, 53, 58, 63, 80-81] etc. A critical analysis of the models indicates that the modeling using ANN is beneficial in rock blasting
Blasting is routinely carried out at various resource extraction sites, even in urban areas. As a consequence of this, residents around urban quarry sites are affected by ground vibration induced by blasting on a regular basis. In this study, a prediction and visualization system for groundvibrations is devel- oped for the purpose of reducing the adverse psychological effects of blasting. The system consists of predicting ground vibration using an Artificial Neural Network (ANN) and visualizing it on an online map using Web-GIS. A pre- diction model using ANN that learned the optimum weight by taking 50 sets of data indicated a regression value of 0.859 and a Mean Square Error (MSE) of 0.0228. Compared with previous researches, these values are not bad re- sults. Peak Particle Velocity (PPV) was used as a metric to measure ground vibration intensity. A color contour is generated using GIS tools based on the PPV value of each prediction point. The system is completed by overlaying the contour onto a basic map in a website. The basic map shows the sur- rounding area through the use of Google Maps data. This system can be used by anyone with access to the internet and a browser, requiring no special software or hardware. In addition, mining operations can utilize the data to modify blasting design and planning to minimize ground vibration. In con- clusion, this system has the potential to alleviate the worries of surrounding residents caused by groundvibrationsfromblasting due to the fact that they can personally check the predicted vibration around their locale. Further- more, since this data will be publicly available on the internet, it is also possi- ble that this system can contribute to research in other fields.
advanced analytical  and semi-analytical  models have recently been proposed, particularly for predicting vibrationsfrom underground lines , however there is an increasing trend for the utilisation of numerical techniques. In particular, time domain and frequency domain finite element method (FEM) (, , , , , ) approaches have been widely developed. A shortcoming of the FEM is that it becomes computationally expensive for large domains and requires the use of an absorbing boundary to truncate the modelling space . To reduce run- times, the computational domain has been reduced to 2.5 dimensions by assuming that the track is invariant in the direction of train passage (, ). Although this considerably reduces
Ground borne vibration is not a common environmental problem unlikely to airborne noise. It is an unusual for vibration from sources such as buses and trucks to be perceptible, even in location near to major roads. Some of the common sources of ground borne vibration are trains, buses on rough roads and construction activities. The vibrations on the road will be generated on the ground and transmitted the vibration waves which propagate through the various soil and rock strata to the foundation of any adjacent buildings, then throughout the remainder of the building structures. The maximum vibration amplitude of the floors and walls of the building normally will be at the resonance frequencies of various components of the building. Apart from that, Hunaidi  implied that a ground borne vibration is highly dependent on the direction, position and frequency. Although vibration is possibly not really significant, it should not be overlooked as a minor problem in contributing to the structural damage and also the effect on sensitive equipment, such as those accommodate in hospital operating theatres, scientific research laboratories, etc.
final output is obtained by summing of all incoming signals. The training algorithm, namely ANFIS, was developed by Jang . Basically, ANFIS takes the initial fuzzy model and tunes it by means of a hybrid technique combining gradient descent back-propagation and mean least-squares optimization algorithms (see Fig. 4). At each epoch, an error measure, usually defined as the sum of the squared difference between actual and desired output, is reduced. Training stops when either the predefined epoch number or error rate is obtained. The gradient descent algorithm is mainly
at different microphones were examined using Eq. (6) to ob- tain experimental decay rates. Notably, the theoretical decay rates of low-frequency sounds are very low, indicating that a drop in sound pressure in the atmosphere is caused mostly by geometrical spreading. Theoretically speaking, the exper- imental decay rates should approach the theoretical values – and thus come very close to zero. However, the measured sound pressures exceed the expected values, so most of the values of α are negative. The value of α deviates only slightly from zero except when the data were obtained on a rainy day (experiments No. 1 and No. 2). The following factors may be responsible for this deviation: (1) wind turbulence; (2) the fact that the microphones are mounted about 80 cm above the ground, and the rugged river bed may scatter and reflect sound waves, effectively changing the sound pressure near the microphone; and (3) experimental error. Regarding the smaller attenuation measured on the rainy day, more studies should be carried out to investigate the effect of rain on sound propagation in the atmosphere.
Mechanical Engineering Department, N.I.T Rourkela Page 16 are must widely studied hybrid system now a days, as due to the advantages of two very important modelling technique i.e. NN  and Fuzzy logic . Malki et.al.  adopted adaptive neuro fuzzy relationships to model the UH-60A Black Hawk pilot floor vertical vibration. They have considered 200 data of UH-60A helicopter flight envelop for training and testing purpose. They conducted the study in two parts i.e. the first part involves level flight conditions and the second part involves the entire (200 points) database including maneuver condition. They concluded from their study that neuro fuzzy model can successfully predict the pilot vibration. LI ke et.al.  applied ANFIS to solve the forecast problem of microwave effect by adopting microwave parameters and its threshold as variable. Then they develop an ANFISmodel to study its forecasting ability. By comparing the output of ANFIS with training and testing data, they concluded with good forecasting ability, small error and low data requirement are found with ANFIS. Srinivasan et.al.  applied ANFIS based on PD plus I controller to the dynamic model of 6-DOF robot manipulator (PUMA Robot). Numerical simulation using the dynamic model of 6-DOF robot arm shows the effectiveness of the approach in trajectory tracking problems. Comparative evaluation with respect to PID, fuzzy PD+I controls are presented to validate the controller design. They concluded that a satisfactory tracking precision could be achieved using ANFIS based PD+I controller combination than fuzzy PD+I only or conventional PID only. Roohollah Noori et.al , predicted daily carbon monoxide (CO) concentration in the atmosphere of Tehran by means of ANN and ANFIS models. In this study they used Forward selection (FS) and Gamma test (GT) methods, for selecting input variables for developing hybrid models with ANN and ANFIS. They concluded that Input selection improves prediction capability of both ANN and ANFIS models and it not only reduces the output error but reduces the time of calculation due to less input variable. U. Yüzgeç et.al., , investigates different modelling approaches and compares for drying of baker’s yeast in a fluidized bed dryer based on ANN and ANFIS. In this work they investigates four modelling concepts: modelling based on the mass and energy balance, modelling based on diffusion mechanism in the granule, modelling based on recurrent ANN and modelling based on ANFIS, to predict the dry matter of product, product temperature and product quality.
Car-following models are among the most important components of micro traffic flow simulation which is studied by transportation experts to evaluate new applications of intelligent transportation systems. Until now, several car- following models have been proposed. An obvious disadvantage of the former models is the great number of param- eters which are difficult to calibrate. In this paper, a car-following model was modeled and developed by combining an Adaptive Neuro-Fuzzy Inference System (ANFIS) and a Classification And Regression Tree (CART) to simulate and predict future behavior of each driver-vehicle-unit (DVU). In this model, the reaction time was instantaneously calcu- lated based on the time interval between acceleration and relative velocity by the proposed model and was considered as a new input. The results were compared with the fixed reaction time and the reaction time proposed by Ozaki. To evaluate the performance of the model, we compared the proposed model's output data with real conditions and it was found that the precision of the proposed model was significantly high with regard to the instantaneous reaction time. According the implemented simulation, the proposed model reached a good validity on the basis of proximity to a real situation of car-following.
Trevor Kitson made me realise that it was possible to be smart and funny, Mike Hardman for having the foresight to grab a box of tissues whenever I walked through his office door when I eventually became an internal student. Although Massey could bend the rules in those pre-studylink days a student loan required a minimum of seven papers…….but I only had one semester! So I physically couldn’t attend all my classes, I just grabbed the notes, sat the exams and came back the following year to do the lab work. I want to thank Mark Patchett for just being the best tonic one could ever need when things looked glum, Rosie Bradshaw for her kindness, and Kathryn Stowell, a newly minted lecturer when I was an internal student, has encouraged me ever since. Lesley Collins for allowing a complete unknown to contribute to her book, Austen Ganley from Albany for helping to prepare me for Vienna when Palmerston North was just too far away and lastly Andrew Sutherland-Smith and David Penny who have stoically listened to my troubles academic and personal once a week for six years. In retrospect I do not know how they coped and without them I surely would have quit. I also thank David for organising payment of my fees, and Massey for paying the bill. It is an extraordinarily lonely thing to attempt a PhD without the camaraderie and the vicarious learning opportunities of watching fellow students give presentations etc. I want to especially thank Bruce White from the library for his help and patience and Tim White for helping me navigate computer-speak.
at initial period (closer distance) than that observed at far off distances i.e., attenuation of vibration magnitude will be faster at closer distance than that observed at far off distances. At closer distance, interference of blast waves is influenced by enhanced charge length/concentration, ratio between total charge and charge per delay and delay timing between two initiations made in same or different holes of a blasting round. Interference of blast waves from different holes result into constructive or destruct- tive interference i.e., magnification or reduction in resul- tant magnitude. Constructive interference causes ampli- fication in magnitude and sustains for longer duration. Destructive interference, on the other hand, results into low magnitude and sustains for lesser time duration. For far off distances, magnitude of vibration measured is the resultant impact of interference of blast waves generated from different delays of a blasting round. Attenuation characteristics in this zone are also very slow. At such distances, wave transmitted from different holes of a blasting round adds to the less energy contained waves during the path of transmission to quantify duration and magnitude of vibration. The waves at such distances take longer time to pass through any element of construction (civil or rock) or particle of medium coming in its path and generates poor stress and strain rate.
In the second plot there were 10 Carabidae belonging to the 8 species trapped – Abax parallelus, Amara equestris, Cylindera germanica, Harpalus aﬃ nis, Harpalus rubripes, Molops piceus, Ophonus rupicola, Poecilus cupreus. In the third area there were only 2 pieces recorded – Harpalus aﬃ nis and Poecilus cupreus both belonging to the indication group E. The fourth plot (third quarry terrace) was again not inhabited by Carabid beetles, only two specimens were found there – eurytopic Pseudoophonus ruﬁ pes and Harpalus aﬃ nis. In the last examined terrace the abundance was slightly higher. In total 7 specimens belonging to 7 species were trapped here. Due to their low abundance, all species were evaluated as eudominant. Numbers of species at individual sites are summarized in Tab. I. Species dominance and aﬃ liation to bioindication groups are shown in Tab. II.
ABSTRACT: Stock Market is the market for security where organized trading of Stocks takes place either through exchange or over the counter in electrical or physical form. It plays an important role in canalizing capital from the investors to the business houses. As the stock prices get fluctuated every second it becomes very difficult to predict the stock price. Many have tried predicting the stock market, but very few have succeeded. It becomes difficult to guess or predict what would be stock price next second.We are implementing the prediction models of Artificial Neural Network (ANN) to predict the future stock price. The accuracy of models while predicting the stock price is tested with the real price which will be helpful for shareholder to predict the stock price of stocks.
and most economic scheme (EGCP01) that is partly re- sponsible for a lower score than the other two schemes in the prediction of SLWC. While the Thompson and the Morrison schemes employ explicit advection of each hy- drometeor category, the EGCP01 scheme only advects total condensate and uses local storage arrays to diagnose the relative contribution to each hydrometeor class. In one of the cases this difference plays a particularly large role as the EGCP01 fails to predict the measured amount of supercooled cloud water, and instead diagnoses all the condensate in terms of cloud ice and snow. This is opposite to the other two schemes that predict a pure supercooled liquid cloud more in accordance with the measurements. By using the droplet size distribution and droplet con- centration that is assumed in the microphysics schemes together with the predicted SLWC we are able to predict the droplet size in terms of MVD. The results suggest that a droplet concentration that is typical of a continental site provides an MVD that in the mean corresponds well with the measurements. The study also suggests that explicit prediction of the variation of MVD from case to case requires a prediction of the variation in droplet con- centration for cloud water. This is a limitation of all the three microphysics schemes tested here, which only pre- dict one moment of cloud liquid water (mass mixing ratio). For practical application of the model, this will introduce an uncertainty in the predicted icing intensity for single icing events. However, since there is no bias in MVD when using the proper droplet concentration, a fixed number concentration may be adequate for clima- tological studies of in-cloud icing. It is a subject for future experiments to test whether full two-moment schemes are able to explicitly predict the variation in droplet con- centration, for improvement of explicit prediction of icing intensity.
The evolutionary history of the vault MVP should help identify possible past functions and illuminate current thoughts on function. The big picture questions are these: are vaults an- cestral, having been retained in some species, but fallen into disrepair or lost beyond all recognition in others, or alterna- tively have they been comprised parts that had other functions and have come together in a fairly remote eukaryote and vaults formed thereafter? If we could be conﬁdent which spe- cies have functional vaults, and which do not appear to have need for them, or possibly maintain the MVP monomer for another purpose, we should be able to clarify their role. We can suggest that this exquisite example of form, with no known fundamental function, was in LECA and as putative MVP has also been reported in bacterial genomes (H6L4P8 provisional annotation MVP) could conceivably have been pre- sent in the last universal common ancestor LUCA. It seems unlikely that vaults would be present in some very diverse groups (such as kinetoplasts, alveolates, amoebozoa, and metazoans) but not be present in others. Finding a link be- tween species that do not appear to have a need to maintain the vault and whether vtRNA is associated with it might illu- minate an underlying basic function. Equipped with a personal computer, an internet connection, and a means of viewing pdb ﬁles, anyone can extend sequence homology analysis to investigation in three dimensions, and we suggest that in silico analysis should routinely be used to check for presumptive structure relationships between potentially ancestrally related proteins. However, that is the work for the future. In all these studies, we require the power from tertiary and quaternary studies to combine with the power of purely sequence-based
Abstract- In the present paper ANFIS based model for trip generation is formed for calculating volume of trip generation in Meerut. This model demonstrates the relationship which is not linear between dependent variables and the independent variables assigned to this model. Forecasting of trips generation is entirely based on demonstrated ANFISmodel. Error produced during machine learning phase of this model is very low. The traditional transportation method is based on simple trends extrapolations which are linear in nature.
A device that couples two commercially reliable items, the ice maker and the ejector nozzle, forms the basis of a continuous ice blast machine. This device contains fractured chips, receives sufficient fluidizing air form one end to balance the suction demand of the ejector on other end to create an induced fluidized flow of the ice chips from source to nozzle. When balanced this process operates indefinitely in a steady-state mode giving the ice blast process unmatched long reliability as an industrial process. Figure 7 shows the process of making ice chips, transporting them to the nozzle and ejecting them towards a target.
As a part of assessment test for the void upper air observation over the south-eastern part of Korea Peninsula to the weather forecasting, automatic radiosonde equipment has been oper- ated at the Changwon Weather Station since 2012. The ra- diosonde is Vaisala RS-92 GPS with known accuracy of bet- ter than 0.5 K (Nash et al., 2011; Miloshevich et al., 2009). As the radiosondes have been launched for the experimen- tal purpose, the temporal resolution is variable (from 3 to 12 h), and the observation period is also variable. For exam- ple, during the year 2012, there were two intensive obser- vation periods, one from 25 to 29 June and another from 24 to 29 August. During these periods, radiosondes were launched eight times a day, but this number was reduced to twice a day during the other observation period. Radiosonde data are available dating back to June 2012, and the number of radiosonde data used for the current study is 117. These limited number of available radiosonde data are compared with two different sets of the NWP data, one from hourly KLAPS (Korea Local-area Analysis and Prediction System; NIMR, 2012; Lee et al., 2010) analysis data and another from the 6-hourly ECMWF (European Centre for Medium-range Weather Forecasts) analysis data (Richardson et al., 2013) with the spatial resolution of 0.25 ◦ . The NWP data are lin- early interpolated to the RPG radiometer site using the sur- rounding four grid points. For the vertical grid points, the NWP profiles are vertically interpolated to match the ra- diometer retrieval altitudes at below 10 km, while the original grid points are used for the above 10 km.
Abstract—One of the main issues for a robotic passer is to detect the onset of a handover, in order to avoid the object from being released when the human partner is not ready or if some impact occurs. This paper presents the methodology for a robotic passer, that is potentially able to estimate the interaction forces by the receiver on the object, thus to achieve fluent and safe handovers. The proposed system uses a vibrator that energizes the object and an accelerometer that monitors vibration propagation through the object during the handover. We focused on the machine-learning technique to classify between four states during object handover. A neural network was trained for these four states and tested online. In experimental trials an accuracy of 85.2% and 93.9% were obtained respectively for four classes and two classes of actions by a neural network classifier.
This study applied the Adaptive Neuro-Fuzzy Inference System (ANFIS) to design a recognition model of personalized rehabilitation. In the model, the user may take a wearable sensor and follow the assigned joint-relax exercise to measure the motions of the upper limbs. The sensor that is embedded with the chips of accelerometer, gyroscope, and inclinometer produced the sample datasets due to the exercise schedule of physiotherapy assignment. All motion samples were labeled by arbitrary numbers, which can be identified to the specific motion, for the data training process. A Fuzzy Inference System (FIS) was initially designed by the steps of data pre-processing, featuring, fuzzifying, and ruling Fuzzy logics according to the sample datasets. The FIS was then trained by the ANFIS for optimization by tuning parameters of the features. In testing, the accomplished FIS could recognize the motion features by the defuzzifier that infers the label corresponding to the motion. As a result, the average recognition rate was higher than 90% when the testing motions followed the sampling schedule of the physiotherapy assignment. The model can be applied in the ubiquitous healthcare measurement for health services. The professionals can assess whether the subject obeyed the assigned program or not based on detail motions of the exercise. This approach can be enabled on the trackable interface for the physiatrists to screen the motions of routine rehabilitation.