Recovery of Incomplete IoT Sensed Data using High-Performance Extended-Input Neural-Like Structure

Izonin, Ivan; Tkachenko, Roman; Kryvinska, Natalia; Zub, Khrystyna; Mishchuk, Oleksandra; Lisovych, Taras

doi:10.1016/j.procs.2019.11.054

Cited by 25 publications

(13 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The imputation method group contains two types of methods that are related to the use of some models, namely, non-model or model-based approaches. In terms of the number of values that result from the use of imputation methods, there are approaches based on single imputation methods and multiple imputation methods [6]. Single-fill algorithms give a single complete set of data, where each space is replaced by a value.…”

Section: Methods Of Imputation (Restoration Filling)mentioning

confidence: 99%

A New Approach for Missing Data Imputation in Big Data Interface

Wang

Shakhovska

Sachenko

et al. 2020

ITC

View full text Add to dashboard Cite

The three-stage approach for missing data imputation in Big data interface is proposed in the paper. The first stage includes designing the Big data model in the task of missing data recovery, which enables to process the structured and semistructured data. The next stage is developing the method of missing data recovery based on functional dependencies and association rules. The estimating the algorithm complexity for missing data recovery is provided at the last stage. The proposed method of missing data recovery creates additional data values using a based domain and functional dependencies and adds these values in available training data. The performing the analysis of data different types is possible too. The correctness of the imputed values is verified on the classifier built on the original dataset. The proposed method performs in 12% better than the EM and RF methods for 30% missing data and enables the parallel execution in distributed databases. The acceleration for m=41 attributes is larger in 12.5 times for 20 servers (processors) comparing with the non-parallel modeю

show abstract

Section: Methods Of Imputation (Restoration Filling)mentioning

confidence: 99%

A New Approach for Missing Data Imputation in Big Data Interface

Wang

Shakhovska

Sachenko

et al. 2020

ITC

View full text Add to dashboard Cite

show abstract

“…Taking into account the noise interference and data loss that may occur in the process of sensor signals transmission, the model for loss data recovery can also be considered when designing the algorithm. In this case, multiple structures such as SNN, RNN, GRNN, LSTM and SGTM can be combined with A-optimal-based CNN [60][61][62][63][64][65][66].…”

Section: Future Workmentioning

confidence: 99%

Signals classification based on IA-optimal CNN

Zhang

et al. 2021

Neural Comput & Applic

View full text Add to dashboard Cite

The versatility of the existing A-optimal-based CNN for solving multiple types of signals classification problems has not been verified by different signals datasets. Moreover, the existing A-optimal-based CNN uses a simplified approximate function as the optimization objective function instead of precise analytical function, which affects the signals classification accuracy to a certain extent. In this paper, a classification method called IA-optimal CNN is proposed. To improve the stability of the classifier, the trace of the covariance matrix of the weights of the fully connected layer is used as the optimization objective function, and the parameter optimization model is established without any simplification of the optimization objective function. In addition, to avoid the difficulty of not being able to obtain the analytical expression formula of the partial derivative of the inverse matrix with regard to the networks parameters, a novel dual function is introduced to transform the optimization problem into an equivalent binary function optimization problem. Furthermore, based on the above analytical solution results, the parameters are updated using the alternate iterative optimization method and the accurate weight update formula is deduced in detail. Five signals datasets are used to test the universality of the IAoptimal CNN in signals classification fields. The performance of IA-optimal CNN is showed, and the experimental results are compared with the existing A-optimal-based classification algorithm. Lastly, the following conclusion is proved theoretically: For the A-optimal-based CNN, the trace of the covariance matrix will continue to decrease and approach a convergence value in the iterative process, but it is impossible for the networks to strictly reach the A-optimal state.

show abstract

“…Під час розроблення більшості систем "розумного" будинку, наступним етапом після налаштування процесу збирання та зберігання отриманих від сенсорів даних є процес розробки алгоритму логіки роботи системи [4]. Розвиток індустрії розроблення "розумних" будинків привів даний етап від розробки функцій опрацювання наперед визначених ситуацій, що виникають у будинку до розробки логіки з застосуванням алгоритмів штучного навчання для реагування системою на події, що не передбачаються розробниками системи завчасно, а покладаючись на вірність автоматизованого прийняття рішень системою.…”

Section: ʟˈˊ˖ˎ˟˕˃˕ˋ ˇˑ˔ˎ˪ˇˉˈːːˢ ˕˃ ˫˘ ˑ˄ˆˑ˅ˑ˓ˈːːˢunclassified

Selection of the Optimal Structure of Hidden Layers of the Artificial Neural Network for Energy Efficiency Analysis

Kazarian¹,

Teslyuk²,

Kazymyra³

2021

UJIT

View full text Add to dashboard Cite

A method for optimal structure selection of hidden layers of the artificial neural network (ANN) is proposed. Its main idea is the practical application of several internal structures of ANN and further calculation of the error of each hidden layer structure using identical data sets for ANN training. The method is based on the alternate comparison of the expected result values and the actual results of the feedforward artificial neural networks with a different number of inner layers and a different number of neurons on each layer. The method afforces searching the optimal internal structure of ANN for usage in the development of "smart" house systems and for calculation of the optimal energy consumption level in accordance with current conditions, such as room temperature, presence of people, and time of the day. The usage of the presented method allows to reduce the time spent on choosing the effective structure of the artificial neural network at the initial stages of research and to pay more attention to the relationship between the input and output data, as well as to such important parameters of the ANN learning process, as a number of training iterations, minimal training error, etc. The software has been developed that allows to carry out the processes of training, testing, and obtaining the output results of the algorithm of the artificial neural network, such as the expected value of power consumption and operating time of each individual appliance. The disadvantage of the approach used in finding the optimal internal structure of the artificial neural network is that each subsequent structure is created on the basis of the most efficient of the previously created structures without analyzing other structures that showed worse results with fewer hidden layers. It was found that to improve the solution of this problem it is necessary to create a mechanism which will be based on the analysis of input data, output data, will analyze the internal relationships between parameters and will optimize the network structure at each stage using certain logical rules according to the results obtained in the previous step. It is established that this problem is a nonlinear programming problem that can be solved in the further development of this study.

show abstract

Recovery of Incomplete IoT Sensed Data using High-Performance Extended-Input Neural-Like Structure

Cited by 25 publications

References 11 publications

A New Approach for Missing Data Imputation in Big Data Interface

A New Approach for Missing Data Imputation in Big Data Interface

Signals classification based on IA-optimal CNN

Selection of the Optimal Structure of Hidden Layers of the Artificial Neural Network for Energy Efficiency Analysis

Contact Info

Product

Resources

About