https://eartharxiv.org/repository/object/149/download/296/

A comprehensive review of deep learning applications in hydrology and water resources

Agriculture and livestock play a vital role in social and economic stability. Food safety and transparency in the food supply chain are a significant concern for many people. Internet of Things (IoT) and blockchain are gaining attention due to their success in versatile applications. They generate a large amount of data that can be optimized and used efficiently by advanced deep learning (ADL) techniques. The importance of such innovations from the viewpoint of supply chain management is significant in different processes such as for broadened visibility, provenance, digitalization, disintermediation, and smart contracts. This article takes the secure IoT-blockchain data of Industry 4.0 in the food sector as a research object. Using ADL techniques, we propose a hybrid model based on recurrent neural networks (RNN). Therefore, we used long short-term memory (LSTM) and gated recurrent units (GRU) as a prediction model and genetic algorithm (GA) optimization jointly to optimize the parameters of the hybrid model. We select the optimal training parameters by GA and finally cascade LSTM with GRU. We evaluated the performance of the proposed system for a different number of users. This paper aims to help supply chain practitioners to take advantage of the state-of-the-art technologies; it will also help the industry to make policies according to the predictions of ADL.

https://www.mdpi.com/1424-8220/20/10/2990/pdf

IoT-Blockchain Enabled Optimized Provenance System for Food Industry 4.0 Using Advanced Deep Learning

Prediction of rainfall is one of the major concerns in the domain of meteorology. Several techniques have been formerly proposed to predict rainfall based on statistical analysis, machine learning and deep learning techniques. Prediction of time series data in meteorology can assist in decision-making processes carried out by organizations responsible for the prevention of disasters. This paper presents Intensified Long Short-Term Memory (Intensified LSTM) based Recurrent Neural Network (RNN) to predict rainfall. The neural network is trained and tested using a standard dataset of rainfall. The trained network will produce predicted attribute of rainfall. The parameters considered for the evaluation of the performance and the efficiency of the proposed rainfall prediction model are Root Mean Square Error (RMSE), accuracy, number of epochs, loss, and learning rate of the network. The results obtained are compared with Holt–Winters, Extreme Learning Machine (ELM), Autoregressive Integrated Moving Average (ARIMA), Recurrent Neural Network and Long Short-Term Memory models in order to exemplify the improvement in the ability to predict rainfall.

Prediction of Rainfall Using Intensified LSTM Based Recurrent Neural Network with Weighted Linear Units

Biometric systems are used for the verification and identification of individuals using their physiological or behavioral features. These features can be categorized into unimodal and multimodal systems, in which the former have several deficiencies that reduce the accuracy of the system, such as noisy data, inter-class similarity, intra-class variation, spoofing, and non-universality. However, multimodal biometric sensing and processing systems, which make use of the detection and processing of two or more behavioral or physiological traits, have proved to improve the success rate of identification and verification significantly. This paper provides a detailed survey of the various unimodal and multimodal biometric sensing types providing their strengths and weaknesses. It discusses the stages involved in the biometric system recognition process and further discusses multimodal systems in terms of their architecture, mode of operation, and algorithms used to develop the systems. It also touches on levels and methods of fusion involved in biometric systems and gives researchers in this area a better understanding of multimodal biometric sensing and processing systems and research trends in this area. It furthermore gives room for research on how to find solutions to issues on various unimodal biometric systems.

Unimodal and Multimodal Biometric Sensing Systems: A Review

Though naive Bayes text classifiers are widely used because of its simplicity, the techniques for improving performances of these classifiers have been rarely studied. In this paper, we propose and evaluate some general and effective techniques for improving performance of the naive Bayes text classifier. We suggest document model based parameter estimation and document length normalization to alleviate the problems in the traditional multinomial approach for text classification. In addition, Mutual-Information-weighted naive Bayes text classifier is proposed to increase the effect of highly informative words. Our techniques are evaluated on the Reuters21578 and 20 Newsgroups collections, and significant improvements are obtained over the existing multinomial naive Bayes approach.

Effective methods for improving naive Bayes text classifiers

Over years, natural calamities like drought have taken a huge toll on human life and resources. As the prediction methods increase, the effects of natural calamities can be reduced to an extent by preplanning and providing warnings to the people. Metrological drought indices like standardized precipitation index and standardized precipitation evapotranspiration index are used to identify drought and its severity level. By forecasting these indices, the occurrences of drought are predicted using the prediction models which help the society to take preventive measures due to the effect of drought. Many research works on prediction majorly focused on statistical methods such as Holt–Winters and ARIMA, but these methods lack accuracy to provide long-term forecasts. However, with advances in the area of machine learning especially artificial neural networks and deep neural networks, there seems to be a method to predict drought in the long term with a good accuracy. Long short-term memory is used in recurrent neural network to predict the drought indices which handle the real-time nonlinear data well and good that can help authorities better prepare and mitigate natural disasters. In this paper, we compare the 1-, 6- and 12-month prediction of the ARIMA statistical model with LSTM using multivariate input in hopes of bettering said performance.

Drought prediction based on SPI and SPEI with varying timescales using LSTM recurrent neural network

Recently, sleep disorder is taken as a serious issue in people living. Normally people cerebrum passes through variety of static physiological steps or changes for the duration of sleep. Biomedical signal such as EEG, ECG, EOG and EMG setup and signals used to recognize sleep disorders. This work proposes better technique that can be designed to discriminate the stages of sleep which can help physicians to do an analysis and examination of related sleep disorders. In order to identify a modification inside brain, EEG signal partitioned with 5 frequency bands: delta, theta, alpha, beta and gamma. After signal acquisition, Band pass filter is applied to discriminate the input EEG signal of Fpz–Cz electrodes into frequency bands. Statistical specific features are extracted from distinctiveness impression of EEG signal. Then classification is required for classifying the sleep stages automatically with fuzzy kernel support vector machine and simple recurrent network (SRN). In SRN, statistical features were extracted and allocate 30 s period to 5 possible levels in sleep; wakefulness, Non Rapid Eye Movement Sleep Stage 1 (NREMSS 1), NREMSS 2, NREMSS 3 and NREMSS 4, Rapid Eye Movement Sleep Stage (REMSS). These signal acquired from sleep-EDF repository from PhysioBank (PB) used to validate our proposed scheme. Simple recurrent network classification performance rate is found as 90.2% than that of other new classifiers such as feed forward neural network (FNN) and probabilistic neural network (PNN) next it was compared and results are experimented in proposed work.

Support vector machine and simple recurrent network based automatic sleep stage classification of fuzzy kernel

Decision making needs more support to gain momentum with increasing trend in big data analytics. Conventionally, descriptive and predictive analytics supported the decision making, however, the outcomes of the resultant analytics is of a potentially lower one. Hence, to improve the decision making support in big data analytics, a newer technique is adopted, namely prescriptive analytics, which offers an improved advancement in predicting the probable consequences and its outcome. Best outcome is achieved using optimization techniques in prescriptive analytics that identifies the uncertainties in making the decisions better. Since optimization improves the effectiveness of prescriptive analytics w.r.t varied applications. In order to address the prescriptive analytics technique over various application and to improve the effectiveness of research over prescriptive analytics, in this paper a survey on the applications of prescriptive analytics over big data analytics is addressed. Further, the key issues in prescriptive analytics and comparisons between several applications are as of prescriptive analytics is discussed in terms of the respective techniques and evaluation over it are discussed.

A survey on various applications of prescriptive analytics

Multimodal systems integrate multiple sources of human information to ensure high level security. Multimodal biometric systems increase the recognition rate of the biometric systems either by reducing the false acceptance rate (FAR) or false rejection rate (FRR). Multiple biometric traits can be combined at feature level. Feature level fusion increases the reliability of the system by preventing the biometric template from modification. In the proposed system, feature level fusion is employed to fuse the feature vectors of iris and ear extracted by Principal Component Analysis technique, which also reduces the dimension of the feature vectors. Finally matching is performed by comparing the test fused feature vectors with all training images using distance measure. This system is developed to study and analyze, whether the performance of multimodal biometric system is improved over unimodal biometric system by attaining 93% success rate when fusion is inclined.

/pdf/feature-level-fusion-in-multimodal-biometric-authentication-22uwsckb3q.pdf

S. Poornima

Papers

Prediction of Rainfall Using Intensified LSTM Based Recurrent Neural Network with Weighted Linear Units

Drought prediction based on SPI and SPEI with varying timescales using LSTM recurrent neural network

Support vector machine and simple recurrent network based automatic sleep stage classification of fuzzy kernel

A survey on various applications of prescriptive analytics

Feature Level Fusion in Multimodal Biometric Authentication System