Artificial neural networks and multicriterion analysis for sustainable irrigation planning

The objective of the present paper is to select the best compromise irrigation planning strategy for the case study of Jayakwadi irrigation project, Maharashtra, India. Four-phase methodology is employed. In phase 1, separate linear programming (LP) models are formulated for the three objectives, namely. net economic benefits, agricultural production and labour employment. In phase 2, nondominated (compromise) irrigation planning strategies are generated using the constraint method of multiobjective optimisation. In phase 3, Kohonen neural networks (KNN) based classification algorithm is employed to sort nondominated irrigation planning strategies into smaller groups. In phase 4, multicriterion analysis (MCA) technique, namely, Compromise Programming is applied to rank strategies obtained from phase 3. It is concluded that the above integrated methodology is effective for modeling multiobjective irrigation planning problems and the present approach can be extended to situations where number of irrigation planning strategies are even large in number. (c) 2004 Elsevier Ltd. All rights reserved.

Voltage and Temperature Aware Statistical Leakage Analysis Framework Using Artificial Neural Networks

Artificial neural networks (ANNs) have shown great promise in modeling circuit parameters for computer aided design applications. Leakage currents, which depend on process parameters, supply voltage and temperature can be modeled accurately with ANNs. However, the complex nature of the ANN model, with the standard sigmoidal activation functions, does not allow analytical expressions for its mean and variance. We propose the use of a new activation function that allows us to derive an analytical expression for the mean and a semi-analytical expression for the variance of the ANN-based leakage model. To the best of our knowledge this is the first result in this direction. Our neural network model also includes the voltage and temperature as input parameters, thereby enabling voltage and temperature aware statistical leakage analysis (SLA). All existing SLA frameworks are closely tied to the exponential polynomial leakage model and hence fail to work with sophisticated ANN models. In this paper, we also set up an SLA framework that can efficiently work with these ANN models. Results show that the cumulative distribution function of leakage current of ISCAS'85 circuits can be predicted accurately with the error in mean and standard deviation, compared to Monte Carlo-based simulations, being less than 1% and 2% respectively across a range of voltage and temperature values.

Artificial database for character recognition research

This paper describes a technique for artificial generation of learning and test sample sets suitable for character recognition research. Sample sets of English (Latin), Malayalam, Kannada and Tamil characters are generated easily through their prototype specifications by the endpoint co-ordinates, nature of segments and connectivity.

Generating artificial chromosomes with probability control in genetic algorithm for machine scheduling problems

In this paper, a novel genetic algorithm is developed by generating artificial chromosomes with probability control to solve the machine scheduling problems. Generating artificial chromosomes for Genetic Algorithm (ACGA) is closely related to Evolutionary Algorithms Based on Probabilistic Models (EAPM). The artificial chromosomes are generated by a probability model that extracts the gene information from current population. ACGA is considered as a hybrid algorithm because both the conventional genetic operators and a probability model are integrated. The ACGA proposed in this paper, further employs the ``evaporation concept'' applied in Ant Colony Optimization (ACO) to solve the permutation flowshop problem. The ``evaporation concept'' is used to reduce the effect of past experience and to explore new alternative solutions. In this paper, we propose three different methods for the probability of evaporation. This probability of evaporation is applied as soon as a job is assigned to a position in the permutation flowshop problem. Experimental results show that our ACGA with the evaporation concept gives better performance than some algorithms in the literature.

Cascaded Cross Flow DBD-Adsorbent Technique for NOX Abatement in Diesel Engine Exhaust

In this paper, a different type of cross flow dielectric barrier discharge (DBD) reactor was designed and tested. Here the gas flow is perpendicular to the barrier discharge electrode. Discharge plasma was utilized to oxidize NO contained in the exhaust gas to NO2 and subsequent NO2 removal can be improved using an adsorbent system. A detailed study of DeNO(X) in a stationary diesel engine exhaust was carried out using pulsed electrical discharges/adsorbent processes. Activated alumina (Al2O3) and MS-13x were used as adsorbents at room temperature. The main emphasis is laid on the removal of NOX from the filtered diesel engine exhaust. In filtered exhaust environment, the cross flow reactor along with adsorbent exhibits a superior performance with regard to NOX removal when compared to that with axial flow of gas. In this paper we bring out a relative comparison of discharge plasma and plasma-adsorbent process at various gas flow rates, ranging from 2 l/min to 25 l/min. The discharge plasma-adsorbent assisted barrier discharge reactor has shown promising results in NOX removal at high flow rates.

Artificial commutation for inversion into a weak AC system in a multiterminal HVDC system

This paper deals with the application of artificial commutation for a normally rated inverter connecting a weak AC system in a multiterminal HVDC (MTDC) system. Artificial commutation is achieved using series capacitors. A modular digital simulation technique is developed to study the dynamic performance of the system. It is shown that by a proper selection of the value of the capacitor it is possible to limit the valve stresses and the DC harmonics to acceptable levels and achieve an improved performance during severe transient conditions. The determination of the value of the series capacitor is based on a parametric study.

Vibration Signature Analysis Using Artificial Neural Networks

Damage detection by measuring and analyzing vibration signals in a machine component is an established procedure in mechanical and aerospace engineering. This paper presents vibration signature analysis of steel bridge structures in a nonconventional way using artificial neural networks (ANN). Multilayer perceptrons have been adopted using the back-propagation algorithm for network training. The training patterns in terms of vibration signature are generated analytically for a moving load traveling on a trussed bridge structure at a constant speed to simulate the inspection vehicle. Using the finite-element technique, the moving forces are converted into stationary time-dependent force functions in order to generate vibration signals in the structure and the same is used to train the network. The performance of the trained networks is examined for their capability to detect damage from unknown signatures taken independently at one, three, and five nodes. It has been observed that the prediction using the trained network with single-node signature measurement at a suitability chosen location is even better than that of three-node and five-node measurement data.

Artificial intelligence approaches to network management: recent advances and a survey

With increased number of new services and users being added to the communication network, management of such networks becomes crucial to provide assured quality of service. Finding skilled managers is often a problem. To alleviate this problem and also to provide assistance to the available network managers, network management has to be automated. Many attempts have been made in this direction and it is a promising area of interest to researchers in both academia and industry. In this paper, a review of the management complexities in present day networks and artificial intelligence approaches to network management are presented. Published by Elsevier Science B.V.

Nitrogen and carbon flows through Belandur lake - Role of Bellandur lake as a natural wetland treating Bangalore wastewater

Much of the Bangalore sewage is treated in three streams namely Bellandur (K&C Valley),Vrishabhavati and Hebbal-Nagavara stream systems. Among these it is estimated that out of a total of about 500MLD of partially treated sewage is let into the Bellandur tank. We estimate that a total of about 77t N non-industrial anthropogenic nitrogen efflux (mainly urine and excreta) in Bangalore city. This is distributed between that handled by the three sewage streams, soak-pits and land deposition. About 17-24.5t N enters the Bellandur tank daily. This has been happening over few decades and our observations suggest that this approximately 380ha tank is functioning as a C and N removal system with reasonable efficiency. The ammoniacal and nitrate nitrogen content of the water at the discharge points were estimated and found that over 80% of the nitrogen influx and over 75% of the C influx is removed by this tank system. We observed that there are three nitrogen sinks namely bacterial, micro-algal and macrophytes. The micro-algal fraction is dominated by Microcystis and Euglenophyceae members and they appear to constitute a significant fraction. Water hyacinth represents the single largest representative of the macrophytes. This tank has been functioning in this manner for over three decades. We attempt to study this phenomenon from a material balance approach and show that it is functioning with a reasonable degree of satisfaction as a natural wetland. As the population served and concomitant influx into this wetland increases, there is a potential for the system to be overloaded and to collapse. Therefore a better understanding of its function and the need for maintenance is discussed in the paper.

Wetland flora of Uttara Kannada

Uttara Kannada with its luxuriant tropical climate coupled with heavy rainfall harbours a large number of seasonal wetlands, which are inhabited by diverse wetland plants. These wetland plants are of diverse habitats as they may be aquatic, semiaquatic or of moist soils. Different localities were selected throughout the district and studied for their species composition, diversity, richness across different habitats, families, etc. Many wetland plants were found to be endemic and endangered having many economical uses due to their medicinal properties, edibility, etc.

Volume Change behaviour in Calcitic Soil influenced with Sulphuric Acid using Artificial Neural Networks

This paper elucidates the methodology of applying artificial neural network model (ANNM) to predict the percent swell of calcitic soil in sulphuric acid solutions, a complex phenomenon involving many parameters. Swell data required for modelling is experimentally obtained using conventional oedometer tests under nominal surcharge. The phases in ANN include optimal design of architecture, operation and training of architecture. The designed optimal neural model (3-5-1) is a fully connected three layer feed forward network with symmetric sigmoid activation function and trained by the back propagation algorithm to minimize a quadratic error criterion.The used model requires parameters such as duration of interaction, calcite mineral content and acid concentration for prediction of swell. The observed strong correlation coefficient (R2 = 0.9979) between the values determined by the experiment and predicted using the developed model demonstrates that the network can provide answers to complex problems in geotechnical engineering.

Stress-Strain Prediction of Jointed Rocks using Artificial Neural Networks

The applicability of Artificial Neural Networks for predicting the stress-strain response of jointed rocks at varied confining pressures, strength properties and joint properties (frequency, orientation and strength of joints) has been studied in the present paper. The database is formed from the triaxial compression tests on different jointed rocks with different confining pressures and different joint properties reported by various researchers. This input data covers a wide range of rock strengths, varying from very soft to very hard. The network was trained using a 3 layered network with feed forward back propagation algorithm. About 85% of the data was used for training and remaining15% for testing the predicting capabilities of the network. Results from the analyses were very encouraging and demonstrated that the neural network approach is efficient in capturing the complex stress-strain behaviour of jointed rocks. A single neural network is demonstrated to be capable of predicting the stress-strain response of different rocks, whose intact strength vary from 11.32 MPa to 123 MPa and spacing of joints vary from 10 cm to 100 cm for confining pressures ranging from 0 to 13.8 MPa.