SIMLR: Machine Learning inside the SIR Model for COVID-19 Forecasting

Accurate forecasts of the number of newly infected people during an epidemic are critical for making effective timely decisions. This paper addresses this challenge using the SIMLR model, which incorporates machine learning (ML) into the epidemiological SIR model. For each region, SIMLR tracks the changes in the policies implemented at the government level, which it uses to estimate the time-varying parameters of an SIR model for forecasting the number of new infections one to four weeks in advance. It also forecasts the probability of changes in those government policies at each of these future times, which is essential for the longer-range forecasts. We applied SIMLR to data from in Canada and the United States, and show that its mean average percentage error is as good as state-of-the-art forecasting models, with the added advantage of being an interpretable model. We expect that this approach will be useful not only for forecasting COVID-19 infections, but also in predicting the evolution of other infectious diseases.

Forecasting of Natural Gas Consumption in Poland Based on ARIMA-LSTM Hybrid Model

Natural gas is one of the main energy sources in Poland and accounts for about 15% of the primary energy consumed in the country. Poland covers only 1/5 of its demand from domestic deposits. The rest is imported from Russia, Germany, Norway, the Czech Republic, Ukraine, and Central Asia. An important issue concerning the market of energy resources is the question of the direct impact of the prices of energy resources on the income of exporting and importing countries. It should also be remembered that unexpected and large fluctuations are detrimental to both exporters and importers of primary fuels. The article analyzes natural gas deposits in Poland, raw material trade and proposes a model for forecasting the volume of its consumption, which takes into account historical consumption, prices of energy resources and assumptions of Poland’s energy policy until 2040. A hybrid model was built by combining ARIMA with LSTM artificial neural networks. The validity of the constructed model was assessed using ME, MAE, RMSE and MSE. The average percentage error is 2%, which means that the model largely represents the real gas consumption course. The obtained forecasts indicate an increase in consumption by 2040.

Modeling Energy Demand—A Systematic Literature Review

In this article, a systematic literature review of 419 articles on energy demand modeling, published between 2015 and 2020, is presented. This provides researchers with an exhaustive overview of the examined literature and classification of techniques for energy demand modeling. Unlike in existing literature reviews, in this comprehensive study all of the following aspects of energy demand models are analyzed: techniques, prediction accuracy, inputs, energy carrier, sector, temporal horizon, and spatial granularity. Readers benefit from easy access to a broad literature base and find decision support when choosing suitable data-model combinations for their projects. Results have been compiled in comprehensive figures and tables, providing a structured summary of the literature, and containing direct references to the analyzed articles. Drawbacks of techniques are discussed as well as countermeasures. The results show that among the articles, machine learning (ML) techniques are used the most, are mainly applied to short-term electricity forecasting on a regional level and rely on historic load as their main data source. Engineering-based models are less dependent on historic load data and cover appliance consumption on long temporal horizons. Metaheuristic and uncertainty techniques are often used in hybrid models. Statistical techniques are frequently used for energy demand modeling as well and often serve as benchmarks for other techniques. Among the articles, the accuracy measured by mean average percentage error (MAPE) proved to be on similar levels for all techniques. This review eases the reader into the subject matter by presenting the emphases that have been made in the current literature, suggesting future research directions, and providing the basis for quantitative testing of hypotheses regarding applicability and dominance of specific methods for sub-categories of demand modeling.

Prediksi Indeks Harga Saham Gabungan (IHSG) Menggunakan Algoritma Autoregressive Integrated Moving Average (ARIMA)

There are various types of investment in Indonesia, one of which is the Indeks Harga Saham Gabungan (IHSG) or in English it is called the Indonesia Composite Index, ICI, or IDX Composite. IHSG is an important parameter to consider when making an investment considering that IHSG is a joint stock. This study aims to predict the price of the IHSG with data mining techniques using an algorithm that can be used as a reference for investors when making an investment. ARIMA is a model for generating estimates from historical data. Data in this study were collected from the monthly IHSG from January 4, 2010 - November 26, 2019. Based on the correlation plot, two autocorrelations (lag 1, lag 32) were found to be significant. This model can predict with an average percentage error of 0.004 so that this prediction is considered good enough to predict the stock price of the IHSG.

Visual design intuition: predicting dynamic properties of beams from raw cross-section images

In this work we aim to mimic the human ability to acquire the intuition to estimate the performance of a design from visual inspection and experience alone. We study the ability of convolutional neural networks to predict static and dynamic properties of cantilever beams directly from their raw cross-section images. Using pixels as the only input, the resulting models learn to predict beam properties such as volume maximum deflection and eigenfrequencies with 4.54% and 1.43% mean average percentage error, respectively, compared with the finite-element analysis (FEA) approach. Training these models does not require prior knowledge of theory or relevant geometric properties, but rather relies solely on simulated or empirical data, thereby making predictions based on ‘experience’ as opposed to theoretical knowledge. Since this approach is over 1000 times faster than FEA, it can be adopted to create surrogate models that could speed up the preliminary optimization studies where numerous consecutive evaluations of similar geometries are required. We suggest that this modelling approach would aid in addressing challenging optimization problems involving complex structures and physical phenomena for which theoretical models are unavailable.

Day-Ahead Forecasting of Losses in the Distribution Network

Utility companies in the Nordics have to nominate how much electricity is expected to be lost in their power grid the next day. We present a commercially deployed machine learning system that automates this day-ahead nomination of the expected grid loss. It meets several practical constraints and issues related to, among other things, delayed, missing and incorrect data and a small data set. The system incorporates a total of 24 different models that performs forecasts for three sub-grids. Each day one model is selected for making the hourly day-ahead forecasts for each sub-grid. The deployed system reduced the mean average percentage error (MAPE) with 40% from 12.17 to 7.26 per hour from mid-July to mid-October, 2019. It is robust, flexible and reduces manual work. Recently, the system was deployed to forecast and nominate grid losses for two new grids belonging to a new customer. As the presented system is modular and adaptive, the integration was quick and needed minimal work. We have shared the grid loss data-set on Kaggle.

Development of a Virtual Flowmeter as an Enhanced Alternative for Field Production Monitoring

Flowrate is a valuable information for the oil and gas industry. High accuracy on flowrate estimation enhances production operations to control and manage the production. Recognized as a cost-efficient solution, the VFM (virtual flowmeter) is a mathematical-based technology designed to estimate the flowrates using available field instrumentation. The VFM approach developed in this work combines black-box simulations with mixed-integer linear programming (MILP) problem to obtain the flowrates dismissing the tuning process. The methodology included a set of multiphase flow correlations, and the MILP was developed to estimate the flowrate and designate the best fit model. We evaluated the proposed VFM against 649 well test data. The methodology presented 4.1% average percentage error (APE) for percentile 25% and 13.5% APE for percentile 50%. We developed a VFM technology to be used in scenarios with a lack of data, and we believe that our tuning-free method can contribute to the future of VFM technologies.

Estimation of Fruit Load in Australian Mango Orchards Using Machine Vision

The performance of a multi-view machine vision method was documented at an orchard level, relative to packhouse count. High repeatability was achieved in night-time imaging, with an absolute percentage error of 2% or less. Canopy architecture impacted performance, with reasonable estimates achieved on hedge, single leader and conventional systems (3.4, 5.0, and 8.2 average percentage error, respectively) while fruit load of trellised orchards was over-estimated (at 25.2 average percentage error). Yield estimations were made for multiple orchards via: (i) human count of fruit load on ~5% of trees (FARM), (ii) human count of 18 trees randomly selected within three NDVI stratifications (CAL), (iii) multi-view counts (MV-Raw) and (iv) multi-view corrected for occluded fruit using manual counts of CAL trees (MV-CAL). Across the nine orchards for which results for all methods were available, the FARM, CAL, MV-Raw and MV-CAL methods achieved an average percentage error on packhouse counts of 26, 13, 11 and 17%, with SD of 11, 8, 11 and 9%, respectively, in the 2019–2020 season. The absolute percentage error of the MV-Raw estimates was 10% or less in 15 of the 20 orchards assessed. Greater error in load estimation occurred in the 2020–2021 season due to the time-spread of flowering. Use cases for the tree level data on fruit load was explored in context of fruit load density maps to inform early harvesting and to interpret crop damage, and tree frequency distributions based on fruit load per tree.

Fish Feeder for Aquaculture with Fish Feed Remaining and Feed Out Monitoring System Based on IoT

Feeding fish is a process that affects fish yields. Undisciplined feeding of fish resulted in decreased quality and quantity of fish. The potential for this problem can be reduced by implementing an IoT-based technology. That technology needs to have a monitoring system for remaining feed and the success of feeding. This study using a proximity sensor and infrared distance sensor for the monitoring system for the fish feeder. The results obtained are that the infrared distance sensor can provide information about the remaining fish feed more accurately after being calibrated, the average percentage error of the total test is 5,1%. While the proximity infrared sensor can provide information on the success of throwing feed, from the total testing of the proximity sensor, the success rate of detecting throw feed is 100%. Both information can be monitored via the Blynk platform on the user’s smartphone.

Memristor-CMOS Hybrid Neuron Circuit with Nonideal-Effect Correction Related to Parasitic Resistance for Binary-Memristor-Crossbar Neural Networks

Voltages and currents in a memristor crossbar can be significantly affected due to nonideal effects such as parasitic source, line, and neuron resistance. These nonideal effects related to the parasitic resistance can cause the degradation of the neural network’s performance realized with the nonideal memristor crossbar. To avoid performance degradation due to the parasitic-resistance-related nonideal effects, adaptive training methods were proposed previously. However, the complicated training algorithm could add a heavy computational burden to the neural network hardware. Especially, the hardware and algorithmic burden can be more serious for edge intelligence applications such as Internet of Things (IoT) sensors. In this paper, a memristor-CMOS hybrid neuron circuit is proposed for compensating the parasitic-resistance-related nonideal effects during not the training phase but the inference one, where the complicated adaptive training is not needed. Moreover, unlike the previous linear correction method performed by the external hardware, the proposed correction circuit can be included in the memristor crossbar to minimize the power and hardware overheads for compensating the nonideal effects. The proposed correction circuit has been verified to be able to restore the degradation of source and output voltages in the nonideal crossbar. For the source voltage, the average percentage error of the uncompensated crossbar is as large as 36.7%. If the correction circuit is used, the percentage error in the source voltage can be reduced from 36.7% to 7.5%. For the output voltage, the average percentage error of the uncompensated crossbar is as large as 65.2%. The correction circuit can improve the percentage error in the output voltage from 65.2% to 8.6%. Almost the percentage error can be reduced to ~1/7 if the correction circuit is used. The nonideal memristor crossbar with the correction circuit has been tested for MNIST and CIFAR-10 datasets in this paper. For MNIST, the uncompensated and compensated crossbars indicate the recognition rate of 90.4% and 95.1%, respectively, compared to 95.5% of the ideal crossbar. For CIFAR-10, the nonideal crossbars without and with the nonideal-effect correction show the rate of 85.3% and 88.1%, respectively, compared to the ideal crossbar achieving the rate as large as 88.9%.