Search

The increase in the usage of internet and social media has enabled people exchange views, opinions and thoughts as never before. This exchange of data has paved the way for sentiment analysis. The basic task of sentiment analysis is to classify the data into positive, negative and neutral. In this paper an effective MapReduce-Based Hybrid NBC-TFIDF (Naive Bayes Classifier -Term Frequency Inverse Document Frequency) algorithm is proposed to mine people sentiment. A Map Reduce-Based Hybrid NBC is employed to classify the data based on the polarity score of each sentence in social media data. The polarity score is calculated using the emotion corpus and the Diabetic corpus is created using food Glycemic Index and physical activity index. This study analyses the correlation of food habits, physical activity and diabetic risk factors among Indian population using social network data. Around two million data has been identified for the study and the study is restricted to India. The experimental result shows that MapReduce-Based Hybrid NBC–TFIDF performs efficiently in multimode cluster. The results reveal that no individual factor is associated with diabetic risk and also a group of common factors contribute to diabetes mellitus. It is found that 60% of the social media data had positive polarity about the food items that are high in Glycemic Index which is the main root cause for type – 2 Diabetes. This Big-Data analysis reveals that the young generations of India are unaware of risk factors of Diabetes mellitus. [ABSTRACT FROM AUTHOR]

Autoregressive Integrated Moving Average (ARIMA) and seasonal ARIMA (SARIMA) models are common techniques that are widely used in analysing and forecasting stationary and seasonal time series data. The three essential steps involved to construct ARIMA are identification, estimation, and checking the validity of the model. The most critical step followed in constructing the ARIMA model is model identification. However, overcoming the difficult local optima problem for both ARIMA and SARIMA is still challenging as there is no appropriate method to solve it. In this paper, the proposed parallel GA-SARIMA model is used to solve the problem of local optima, where the genetic algorithm (GA) is used at the initial stage to identify the order and estimation of the parameters for SARIMA. The National Climate Data Centre (NCDC) time series dataset is used for testing the efficiency of the final parallel GA-SARIMA model to forecast the mean temperature of India from 2000 to 2017. The GA algorithm is successfully implemented to solve the optimization problems by introducing better solutions suitable for SARIMA models. The results of the study showed that the implementation of the combined approach of parallel GA and SARIMA enhances the prediction accuracy of the model. The parallel GA-SARIMA method is particularly robust, faster and performs better than sequential SARIMA models in terms of running time and cost function values. [ABSTRACT FROM AUTHOR]

Thermal Power plant (TPP) is biggest source of power in India. About 65% of electricity is generated by using thermal power plant. The equipment of TPP runs for 24x7 days through the year. The fault of TPP equipment needs to identify at early stage before the breakdown of system or unit. The maintenance functions of TPP should be optimized carefully by selecting suitable maintenance strategy at least cost. Identification and confirmation of fault in TPP equipment is very important step for decision making. It helps to optimize the maintenance activity. This paper proposes an algorithm for use of co-ordinated condition monitoring approach for identification and confirmation of fault. The objective of this study is to improve the availability and heath of critical equipment of Dahanu Thermal Power Station (DTPS) located in western region of India. [ABSTRACT FROM AUTHOR]

Cricket is an extremely popular game. More than a million cricketers play cricket daily in India alone and aspire to become professional cricketers. Cricket Talent identification and enhancement is a challenging problem due to lack of quality coaches, meagre infrastructural facilities, and poor linkages of coaching academies & cricket authorities. In India, the problem is even tougher as the majority of the population resides in villages. Many of talented players do not get timely recognition of cricket boards’ authorities thus amounting to waste of talent. Many keep on pursuing cricket despite of being non-talented. Due to lack of application of appropriate scientific methods the selection process is also criticized as biased by many. In this paper, we present a web based system viz. Cricket Talent Identification, Enhancement and Selection (C-TIES) for addressing the above issues. C-TIES utilize a cricket talent knowledgebase of experts’ opinions aggregated by applying OWA Aggregation Operator and Relative Fuzzy Linguistic Quantifier (RFLQ). The C-TIES system classifies the cricket talent level of an enthusiast into five different classes by applying Normalized Adequacy Coefficient (NAC). The Talent Enhancement and Talent Selection subsystems also uses appropriate algorithms based on OWA, RFLQ and NAC to respectively enable identification of weaknesses in a player and select most talented n-players from a larger group of players. Thus, system reduces the time for identifying weaknesses and also provides a relatively better unbiased selection method for short listing players. The system has been developed using Struts 2.0, Hibernate, J2EE, Ajax, MySql are used. [ABSTRACT FROM AUTHOR]

Prediction of Indian monsoon is a challenging task due to complex dynamics and variability over the years. Skills of statistical predictors that perform well in a set of years are not as good for others. In this paper, we attempt to identify a set of predictors that have high skills for a cluster of years. A co-clustering algorithm, which extracts groups of years, paired with good predictor sets for those years, is used for this purpose. Weighted ensemble of these predictors are used in final prediction. Results on past 65 years data show that the approach is competitive with state of art techniques. [ABSTRACT FROM AUTHOR]

Abstract: Increasing demand of bandwidth in communication satellites has forced satellite links to be designed in Ku bands and above. But at these frequencies, rain and other tropospheric elements result in large attenuation. To mitigate the tropospheric attenuation of microwave satellite signals above 10GHz using any standard Fade Mitigation Technique (FMT), it is essential to have a priori knowledge about the level of attenuation. Hence, short-term rain attenuation prediction models play a key role in maintaining the link in which necessary compensation can be applied depending on the early information of attenuation. This paper presents a method of attenuation prediction using Adaptive Artificial Neural Network. Here In situ Learning Algorithm (ILA) has been used to enable the system to track the non-stationary nature of the attenuation. To validate this, Ku Band data, collected at three different sites in India have been used for the purpose of prediction. The performance of the algorithm is determined through the estimation of prediction accuracy by comparing the predicted values with the measured data. Results obtained using the mentioned technique shows considerably good accuracy even up to 20s of prediction interval with acceptable ratio between the under and over predictions. The prediction performance is evaluated for different prediction intervals. Furthermore the present model is also compared with the persistence model and the relative performance is quantified. [Copyright &y& Elsevier]

Abstract: In this paper, the parameter-wise optimization training process is implemented to achieve an optimal configuration of focused time lagged recurrent neural network (FTLRNN) models by embedding the gamma, laguarre, and multi-channel tapped delay line memory structure. The aim is to examine the prediction ability of the proposed models in order to predict one-day-ahead electric power load simultaneously as usual to oppose 1–24h forecast in sequel with a special emphasis on seasonal changes over a year. An improved delta-bar-delta algorithm is used to accelerate the training of neural networks and to improve the stability of the convergence. Experimental results indicate that the FTLRNN with time delay neural network (TDNN) clearly outperformed the gamma and laguarre based short-term memory structure in various performance metrics such as mean square error (MSE), normalized MSE, correlation coefficient (r) and mean absolute percentage error (MAPE) during evaluation process. Empirical results show that the proposed dynamic NN model consistently performs well on daily, weekly, and monthly average basis in terms of prediction accuracy. It is noticed from the literature review that an optimally configured FTLRNN with multi-channel tapped delay line memory structure is not currently available to solve short-term electrical power load prediction. The proposed method gives acceptable errors in all seasons, months and on daily basis. The average prediction error on three weeks is obtained as low as 1.67%. [ABSTRACT FROM AUTHOR]

The crop growth and crop yield in agriculture depend upon many factors such as weather conditions, soil type, and application of fertilizers. The crop net return can be increased by deciding suitable crops for a particular land depending upon its weather conditions. The application of an appropriate amount of fertilizers also promotes crop growth and yield. On the other hand, the use of fertilizers needs to be minimized to reduce the capital cost as well as to prevent its harmful effect on soil and the environment. This paper models the problem of increasing net crop benefit and reducing the application of fertilizers as multi-objective optimization functions. A hybrid CSA-PSO optimization algorithm is proposed for solving multi-objective problems by combining crow search algorithm (CSA) and particle swarm optimization (PSO). The performance of the proposed algorithm is evaluated against CEC 2009 benchmark functions. This algorithm is implemented for crop pattern optimization in India's Telangana state, which depicts the proposed algorithm's feasibility and effectiveness. • A multi-objective crop model is designed to maximize crop net return. • A new hybrid multi-objective optimization algorithm CSA-PSO is introduced. • The flight length is defined randomly to increase the exploration of the CSA-PSO. • The CSA-PSO is implemented for crop planning in Telangana, India. [ABSTRACT FROM AUTHOR]

Accurately forecasting energy demand can better predict future changes in energy demand. This study is aimed to develop more accurate clean energy prediction model from two perspectives of the modeling mechanisms and improvements on the model structure. For this purpose, a novel Riccati–Bernoulli differential equation is established through social practice theory, supply–demand relationship, and the preference of consumption in the energy economy. Considering the limited information in observation data, this differential equation is then transformed into a grey Riccati–Bernoulli model (GRBM(1,1)) according to the differential information principle. With the response function solved on the basis of polynomial equation theory and the power exponent optimized combining the modified flower pollination algorithm, the main process of GRBM(1,1) can be summarized. The four validation examples are provided for confirming the effectiveness and reliability of the new model by comparing with other existing models. Finally, the proposed model is employed to estimate and forecast the clean energy consumption in China and India. The results show that the proposed model demonstrates better estimation in all cases and efficiency in short-term clean energy consumption forecasting. Therefore, by using this optimum model, China's preference coefficient in total energy consumption is 0.7103, lower than that of India (0.8799), and China's preference coefficient in clean energy consumption is 0.9665, higher than that of Indian (0.7155), which means China has less interest to increase total energy consumption but more interest in popularizing the clean energy. • This paper proposed a novel grey Riccati–Bernoulli model for energy consumption prediction. • A specific solution algorithm for this Riccati–Bernoulli equation is discussed in this research. • We compared the proposed novel grey model with other 12 exiting prediction models. • The novel model also reveals China's effort in popularizing the use of clean energy. [ABSTRACT FROM AUTHOR]

• Develop an Optimal Resource Selection Framework on Internet-of-Things (ORSF-IoT). • It supports optimal resource selection through the proposed algorithms, namely, Resource Discovery and Improved Firefly Algorithms. • Propose an Iterative Agglomerative Fuzzy K-Means (IAFKM) Clustering Algorithm for selection of best resources by indexing and ranking them on the basis of matched resources. • The framework provides optimal solution for selecting the parametric value having exceeded limit as the brightest firefly in less time. • It helps in providing timely alarms to the system for corrective measurements and enhances system performancesignificantly. The fundamental requirement for communication and computation across distinct application areas on Internet-of-Things is the resource discovery that demands appropriate reasoning for the optimal selection. With exponential growth of resources and their produced huge amount of heterogeneous data, various activities with respect to foraging and sense-making loops face challenges due to interoperability. Hence, interoperability emerges as a major bottleneck for the requirement. Therefore, to eliminate the challenge, the paper has proposed an "Optimal Resource Selection Framework for Internet-of-Things" that deals with the interoperability and ease the resource discovery and selection. The framework facilitates formation of semantic knowledge base as Shared Virtual Composite Ontology for capturing dynamic IoT heterogeneous data. Moreover, it supports optimal resource selection through the proposed algorithms, namely , Resource discovery Algorithm and Improved Firefly Algorithm. Both algorithms target coordination and optimization with Shared Ontology, respectively. The feasibility of the framework is checked against data collected from Sutlej river, Ludhiana, Punjab, India. The proposed framework is evaluated using benchmark functions with respect to metrics such as mean, standard deviation, processing and execution time. The obtained results are compared with the existing Nature-Inspired algorithms to confirm the efficiency of the proposed framework. [ABSTRACT FROM AUTHOR]

In this article, a new optimization technique known as Kho-Kho optimization (KKO) algorithm is presented. This proposed technique is a population based meta-heuristic method which is inspired from the strategies used by players in a well known tag-team game played in India, i.e. Kho-Kho. The performance and superiority of the proposed method with respect to other existing methods is evaluated using twenty nine benchmark functions and real-time optimization problems related to power system i.e. combined emission economic dispatch and combined heat and power economic dispatch problem. • This paper presents a new Kho-Kho optimization algorithm (KKO). • KKO is inspired by a well-known tag-team game played in India known as Kho-Kho. • KKO mimics the strategies used by a chasing team to catch the runners of a running team. • Twenty-nine benchmark functions are used to test the performance of the proposed algorithm. • Further, KKO is used to solve real-time optimization problems of power system. [ABSTRACT FROM AUTHOR]