A hybrid extreme learning machine model with harris hawks optimisation algorithm: an optimised model for product demand forecasting applications

Accurate and real-time product demand forecasting is the need of the hour in the world of supply chain management. Predicting future product demand from historical sales data is a highly non-linear problem, subject to various external and environmental factors. In this work, we propose an optimised forecasting model - an extreme learning machine (ELM) model coupled with the Harris Hawks optimisation (HHO) algorithm to forecast product demand in an e-commerce company. ELM is preferred over traditional neural networks mainly due to its fast computational speed, which allows efficient demand forecasting in real-time. Our ELM-HHO model performed significantly better than ARIMA models that are commonly used in industries to forecast product demand. The performance of the proposed ELM-HHO model was also compared with traditional ELM, ELM auto-tuned using Bayesian Optimisation (ELM-BO), Gated Recurrent Unit (GRU) based recurrent neural network and Long Short Term Memory (LSTM) recurrent neural network models. Different performance metrics, i.e., Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Percentage Error (MPE) were used for the comparison of the selected models. Horizon forecasting at 3 days and 7 days ahead was also performed using the proposed approach. The results revealed that the proposed approach is superior to traditional product demand forecasting models in terms of prediction accuracy and it can be applied in real-time to predict future product demand based on the previous week’s sales data. In particular, considering RMSE of forecasting, the proposed ELM-HHO model performed 62.73% better than the statistical ARIMA(7,1,0) model, 40.73% better than the neural network based GRU model, 34.05% better than the neural network based LSTM model, 27.16% better than the traditional non-optimised ELM model with 100 hidden nodes and 11.63% better than the ELM-BO model in forecasting product demand for future 3 months. The novelty of the proposed approach lies in the way the fast computational speed of ELMs has been combined with the accuracy gained by tuning hyperparameters using HHO. An increased number of hyperparameters has been optimised in our methodology compared to available models. The majority of approaches to improve the accuracy of ELM so far have only focused on tuning the weights and the biases of the hidden layer. In our hybrid model, we tune the number of hidden nodes, the number of input time lags and even the type of activation function used in the hidden layer in addition to tuning the weights and the biases. This has resulted in a significant increase in accuracy over previous methods. Our work presents an original way of performing product demand forecasting in real-time in industry with highly accurate results which are much better than pre-existing demand forecasting models.

     

HISYCOL a hybrid computational intelligence system for combined machine learning: the case of air pollution modeling in Athens

The analysis of air quality and the continuous monitoring of air pollution levels are important subjects of the environmental science and research. This problem actually has real impact in the human health and quality of life. The determination of the conditions which favor high concentration of pollutants and most of all the timely forecast of such cases is really crucial, as it facilitates the imposition of specific protection and prevention actions by civil protection. This research paper discusses an innovative threefold intelligent hybrid system of combined machine learning algorithms HISYCOL (henceforth). First, it deals with the correlation of the conditions under which high pollutants concentrations emerge. On the other hand, it proposes and presents an ensemble system using combination of machine learning algorithms capable of forecasting the values of air pollutants. What is really important and gives this modeling effort a hybrid nature is the fact that it uses clustered datasets. Moreover, this approach improves the accuracy of existing forecasting models by using unsupervised machine learning to cluster the data vectors and trace hidden knowledge. Finally, it employs a Mamdani fuzzy inference system for each air pollutant in order to forecast even more effectively its concentrations.     

A novel technique based on the improved firefly algorithm coupled with extreme learning machine (ELM-IFF) for predicting the thermal conductivity of soil

Engineering with Computers - Thermal conductivity is a specific thermal property of soil which controls the exchange of thermal energy. If predicted accurately, the thermal conductivity of soil has...     

A comparison of time series and machine learning models for inflation forecasting: empirical evidence from the USA

This study compares time series and machine learning models for inflation forecasting. Empirical evidence from the USA between 1984 and 2014 suggests that out of sixteen conditions (four different inflation indicators and four different horizons), machine learning models provide more accurate forecasting results in seven conditions and the time series models are better in nine conditions. Moreover, multivariate models give better results in fourteen conditions, and univariate models are better only in two conditions. This study shows that machine learning model prevails against time series models for the core personal consumption expenditure (core-PCE) inflation forecasting, and the time series model (ARDL) is better for the core consumer price (core-CPI) index inflation forecasting in all horizons.

     

A multiple multilayer perceptron neural network with an adaptive learning algorithm for thyroid disease diagnosis in the internet of medical things

The Journal of Supercomputing - Medical information systems such as Internet of Medical Things (IoMT) are gained special attention over recent years. X-ray and MRI images are important sources of...     

AK-SYSi: an improved adaptive Kriging model for system reliability analysis with multiple failure modes by a refined U learning function

Due to multiple implicit limit state functions needed to be surrogated, adaptive Kriging model for system reliability analysis with multiple failure modes meets a big challenge in accuracy and efficiency. In order to improve the accuracy of adaptive Kriging meta-model in system reliability analysis, this paper mainly proposes an improved AK-SYS by using a refined U learning function. The improved AK-SYS updates the Kriging meta-model from the most easily identifiable failure mode among the multiple failure modes, and this strategy can avoid identifying the minimum mode or the maximum mode by the initial and the in-process Kriging meta-models and eliminate the corresponding inaccuracy propagating to the final result. By analyzing three case studies, the effectiveness and the accuracy of the proposed refined U learning function are verified.

     

A classification method using a hybrid genetic algorithm combined with an adaptive procedure for the pool of ellipsoids

This paper presents a hybrid classification method that utilizes genetic algorithms (GAs) and adaptive operations of ellipsoidal regions for multidimensional pattern classification problems with continuous features. The classification method fits a finite number of the ellipsoidal regions to data pattern by using hybrid GAs, the combination of local improvement procedures and GAs. The local improvement method adaptively expands, rotates, shrinks, and/or moves the ellipsoids while each ellipsoid is separately handled with a fitness value assigned during the GA operations. A set of significant features for the ellipsoids are automatically determined in the hybrid GA procedure by introducing “don’t care” bits to encode the chromosomes. The performance of the method is evaluated on well-known data sets and a real field classification problem originated from a deflection yoke production line. The evaluation results show that the proposed method can exert superior performance to other classification methods such as k nearest neighbor, decision trees, or neural networks. Ki K. Lee received the B.S. degree from Han Yang University, Seoul, Korea in 1994, and the M.S. and Ph.D. degrees in industrial engineering from Korea Advanced Institute Science and Technology (KAIST), Daejeon, Korea in 1996 and 2005, respectively. From 2001 to 2004, he was a senior research engineer in telecommunication systems laboratory of LG Electronics Inc. Since 2005, he has been an assistant professor in the School of Management at Inje University, Kimhae, Korea. His research interests include intelligent decision support systems, soft computing, and pattern recognition. Wan C. Yoon received the B.S. degree from Seoul National University, Korea in 1977, the M.S. degree from KAIST, Korea in 1979, and the Ph.D. degree in industrial and systems engineering from Georgia Institute of Technology in 1987. He is professor of the Department of Industrial Engineering at KAIST, Korea. His research interests include application of artificial intelligence, human decision-making and aiding, information systems, and joint intelligent systems. Dong H. Baek received the B.S. degree from Han Yang University, Seoul, Korea in 1992, and the M.S. and Ph.D. degrees in industrial engineering from Korea Advanced Institute Science and Technology (KAIST), Daejeon, Korea in 1994 and 1999, respectively. He is an assistant professor in management information systems at department of business administration, Hanyang University, Korea. His research interests include management information systems, system engineering, and machine learning.     

A robust adaptive controller for an anaerobic digester with saturated input: Guarantees for the boundedness and convergence properties

In this work an adaptive controller for an anaerobic digester is developed taking into account the input constraints. The following assumptions are considered: (i) the biomass and chemical oxygen demand concentrations are unknown, (ii) the model parameters are unknown and vary but they are bounded, and (iii) the upper or lower bounds of model parameters are unknown. The Lyapunov-like function method is used to derive the controller. A state observer is employed to handle the saturation of the control input, and updated parameters are used to handle the unknown bounds of the plant parameters. Some features of the control design are: (i) discontinuous signals are avoided, (ii) the boundedness of the updated parameters is ensured despite input saturation, in order to avoid parameter drifting, and (iii) the convergence of the observer error to a residual set of user-defined size is ensured despite input saturation.     

A technique for monitoring SO2 in combustion exhausts: Use of a non-Nernstian sensing element in combination with an upstream catalytic filter

Detection of sulfur dioxide (SO₂) at high temperature (600–750 °C) in the presence of some interferents found in combustion exhausts (NO₂, NO, CO₂, CO, and hydrocarbon (C₃H₆)) is described. The detection scheme involves use of a catalytic filter in front of a non-Nernstian (mixed-potential) sensing element. The catalytic filter was a Ni:Cr powder bed operating at 850 °C, and the sensing elements were pairs of platinum (Pt) and oxide (Ba-promoted copper chromite ((Ba,Cu)_xCr_yO_z) or Sr-modified lanthanum ferrite (LSF)) electrodes on yttria-stabilized zirconia. The Ni:Cr powder bed was capable of reducing the sensing element response to NO₂, NO, CO, and C₃H₆, but the presence of NO₂ or NO (“NO_x”, at 100 ppm by volume) still interfered with the SO₂ response of the Pt–(Ba,Cu)_xCr_yO_z sensing element at 600 °C, causing approximately a 7 mV (20%) reduction in the response to 120 ppm SO₂ and a response equivalent to about 20 ppm SO₂ in the absence of SO₂. The Pt–LSF sensing element, operated at 750 °C, did not suffer from this NO_x interference but at the cost of a reduced SO₂ response magnitude (120 ppm SO₂ yielded 10 mV, in contrast to 30 mV for the Pt-(Ba,Cu)_xCr_yO_z sensing element). The powder bed and Pt–LSF sensing element were operated continuously over approximately 350 h, and the response to SO₂ drifted downward by about 7%, with most of this change occurring during the initial 100 h of operation.     

A system for self-diagnosis of an autonomous mobile robot using an internal state sensory system: fault detection and coping with the internal condition

Considering that intelligent robotic systems work in a real environment, it is important that they themselves have the ability to determine their own internal conditions. Therefore, we consider it necessary to pay some attention to the diagnosis of such intelligent systems and to construct a system for the self-diagnosis of an autonomous mobile robot. Autonomous mobile systems must have a self-contained diagnostic system and therefore there are restrictions to building such a system on a mobile robot. In this paper, we describe an internal state sensory system and a method for diagnosing conditions in an autonomous mobile robot. The prototype of our internal sensory system consists of voltage sensors, current sensors and encoders. We show experimental results of the diagnosis using an omnidirectional mobile robot and the developed system. Also, we propose a method that is able to cope with the internal condition using internal sensory information. We focus on the functional units in a single robot system and also examine a method in which the faulty condition is categorized into three levels. The measures taken to cope with the faulty condition are set for each level to enable the robot to continue to execute the task. We show experimental results using an omnidirectional mobile robot with a self-diagnosis system and our proposed method.