Current Issue : April - June Volume : 2018 Issue Number : 2 Articles : 6 Articles
Among all diseases affecting rice production, rice blast disease has the greatest\nimpact. Thus, monitoring and precise prediction of the occurrence of this disease are important;\nearly prediction of the disease would be especially helpful for prevention. Here, we propose an\nartificial-intelligence-based model for rice blast disease prediction. Historical data on rice blast\noccurrence in representative areas of rice production in South Korea and historical climatic data are\nused to develop a region-specific model for three different regions: Cheolwon, Icheon and Milyang.\nA rice blast incidence is then predicted a year in advance using long-term memory networks (LSTMs).\nThe predictive performance of the proposed LSTM model is evaluated by varying the input variables\n(i.e., rice blast disease scores, air temperature, relative humidity and sunshine hours). The most\nwidely cultivated rice varieties are also selected and the prediction results for those varieties are\nanalyzed. Application of the LSTM model to the accumulated rice-blast disease score data confirms\nsuccessful prediction of rice blast incidence. In all regions, the predictions are most accurate when all\nfour input variables are combined. Rice blast fungus prediction using the proposed LSTM model is\nvariety-based; therefore, this model will be more helpful for rice breeders and rice blast researchers\nthan conventional rice blast prediction models....
Energy is vital for the sustainable development of China. Accurate forecasts of annual energy demand are essential to schedule\nenergy supply and provide valuable suggestions for developing related industries. In the existing literature on energy use prediction,\nthe artificial intelligence-based (AI-based) model has received considerable attention. However, few econometric and statistical\nevidences exist that can prove the reliability of the current AI-based model, an area that still needs to be addressed. In this study, a\nnew energy demand forecasting framework is presented at first. On the basis of historical annual data of electricity usage over the\nperiod of 1985ââ?¬â??2015, the coefficients of linear and quadratic forms of the AI-based model are optimized by combining an adaptive\ngenetic algorithm and a cointegration analysis shown as an example. Prediction results of the proposed model indicate that the\nannual growth rate of electricity demand in China will slow down. However, China will continue to demand about 13 trillion\nkilowatt hours in 2030 because of population growth, economic growth, and urbanization. In addition, the model has greater\naccuracy and reliability compared with other single optimization methods....
One of themain challenges in artificial intelligence or computational linguistics is understanding the meaning of a word or concept.\nWe argue that the connotation of the termââ?¬Å?understanding,ââ?¬Â or the meaning of the word ââ?¬Å?meaning,ââ?¬Â ismerely a wordmapping game\ndue to unavoidable circular definitions. These circular definitions arise when an individual defines a concept, the concepts in its\ndefinition, and so on, eventually forming a personalized network of concepts, which we call an iWordNet. Such an iWordNet serves\nas an external representation of an individualââ?¬â?¢s knowledge and state of mind at the time of the network construction. As a result,\nââ?¬Å?understandingââ?¬Â and knowledge can be regarded as a calculable statistical property of iWordNet topology. We will discuss the\nconstruction and analysis of the iWordNet, as well as the proposed ââ?¬Å?Path of Understandingââ?¬Â in an iWordNet that characterizes an\nindividualââ?¬â?¢s understanding of a complex concept such as a written passage. In our pilot study of 20 subjects we used a regression\nmodel to demonstrate that the topological properties of an individualââ?¬â?¢s iWordNet are related to his IQ score, a relationship that\nsuggests iWordNets as a potential new methodology to studying cognitive science and artificial intelligence....
Recent developments in artificial intelligence (AI) have led to a significant increase in\nthe use of AI technologies. Many experts are researching and developing AI technologies in their\nrespective fields, often submitting papers and patent applications as a result. In particular, owing\nto the characteristics of the patent system that is used to protect the exclusive rights to registered\ntechnology, patent documents contain detailed information on the developed technology. Therefore,\nin this study, we propose a statistical method for analyzing patent data on AI technology to improve\nour understanding of sustainable technology in the field of AI. We collect patent documents that\nare related to AI technology, and then analyze the patent data to identify sustainable AI technology.\nIn our analysis, we develop a statistical method that combines social network analysis and Bayesian\nmodeling. Based on the results of the proposed method, we provide a technological structure that\ncan be applied to understand the sustainability of AI technology. To show how the proposed method\ncan be applied to a practical problem, we apply the technological structure to a case study in order to\nanalyze sustainable AI technology....
Machine learning and artificial intelligence have strong roots on principles of neural\ncomputation. Some examples are the structure of the first perceptron, inspired in the\nretina, neuroprosthetics based on ganglion cell recordings or Hopfield networks. In\naddition, machine learning provides a powerful set of tools to analyze neural data,\nwhich has already proved its efficacy in so distant fields of research as speech\nrecognition, behavioral states classification, or LFP recordings. However, despite the\nhuge technological advances in neural data reduction of dimensionality, pattern selection,\nand clustering during the last years, there has not been a proportional development of\nthe analytical tools used for Timeââ?¬â??Frequency (Tââ?¬â??F) analysis in neuroscience. Bearing this\nin mind, we introduce the convenience of using non-linear, non-stationary tools, EMD\nalgorithms in particular, for the transformation of the oscillatory neural data (EEG, EMG,\nspike oscillationsââ?¬Â¦) into the Tââ?¬â??F domain prior to its analysis with machine learning tools.\nWe support that to achieve meaningful conclusions, the transformed data we analyze\nhas to be as faithful as possible to the original recording, so that the transformations\nforced into the data due to restrictions in the Tââ?¬â??F computation are not extended to\nthe results of the machine learning analysis. Moreover, bioinspired computation such\nas brainââ?¬â??machine interface may be enriched from a more precise definition of neuronal\ncoding where non-linearities of the neuronal dynamics are considered....
As the accuracy of the electricity load forecast is crucial in providing better cost-effective risk management plans, this\npaper proposes a Short-Term Electricity Load Forecast (STLF) model with a high forecasting accuracy. A cascaded forward BPN\nneuro-wavelet forecast model was adapted to perform the STLF. The model was composed of several neural networks whose\ndata were processed using a wavelet technique. The data used in the model was electricity load historical data. The historical\nelectricity load data was decomposed into several wavelet coefficients using the Discrete wavelet transform (DWT). The wavelet\ncoefficients were used to train the neural networks (NNs) and later, used as the inputs to the NNs for electricity load prediction.\nThe Levenberg-Marquardt (LM) algorithm was selected as the training algorithm for the NNs. To obtain the final forecast, the\noutputs from the NNs were recombined using the same wavelet technique....
Loading....