Artificial Machines Research Articles

Exploiting Visual Features in Financial Time Series Prediction

The possibility to enhance prediction accuracy for foreign exchange rates was investigated in two ways: first applying an outside the box approach to modeling price graphs by exploiting their visual properties, and secondly employing the most efficient methods to detect patterns to classify the direction of movement. The approach that exploits the visual properties of price graphs which make use of density regions along with high and low values describing the shape; hence, the authors propose the name ‘Finance Vision.' The data used in the predictive model consists of 1-hour past price values of 4 different currency pairs, between 2003 and 2016. Prediction performances of state-of-the-art methods; Extreme Gradient Boosting, Artificial Neural Network and Support Vector Machines are compared over the same data with the same sets of features. Results show that density based visual features contribute considerably to prediction performance.

Neural networks support vector machine for mass appraisal of properties

PurposeThe paper introduced the use of a hybrid system of neural networks support vector machines (NNSVMs) consisting of artificial neural networks (ANNs) and support vector machines (SVMs) to price single-family properties.Design/methodology/approachThe mechanism of the hybrid system is such that its output is given by the SVMs which utilise the results of the ANNs as their input. The results are compared to other property pricing modelling techniques including the standalone ANNs, SVMs, geographically weighted regression (GWR), spatial error model (SEM), spatial lag model (SLM) and the ordinary least squares (OLS). The techniques were applied to a dataset of 3,225 properties sold during the period, January 2012 to May 2014 in Cape Town, South Africa.FindingsThe results demonstrate that the hybrid system performed better than ANNs, SVMs and the OLS. However, in comparison to the spatial models (GWR, SEM and SLM) the hybrid system performed abysmally under with SEM favoured as the best pricing technique.Originality/valueThe findings extend the debate in the body of knowledge that the results of the OLS can significantly be improved through the use of spatial models that correct bias estimates and vary prices across the different property locations. Additionally, utilising the result of the hybrid system is thus affected by the black-box nature of the ANNs and SVMs limiting its use to purposes of checks on estimates predicted by the regression-based models.

Aspectos críticos da expansão das possibilidades de recursos tecnológicos na investigação criminal: a inteligência artificial no âmbito do sistema de controle e de punição

O presente artigo tem como objetivo principal analisar criticamente as potenciais influências negativas da utilização de novas tecnologias no sistema de controle e de punição. Dada a quantidade de ferramentas atualmente gestadas, tanto pelos governos quanto pela iniciativa privada, optamos por uma análise do tipo panorâmica, propondo inicialmente uma espécie de cenário possível da dinâmica do processo de investigação. O problema central com o qual nos preocupamos é a expansão da intervenção estatal e privada nas liberdades individuais, o que se reflete na restrição de garantias processuais, atingindo diretamente a dignidade da pessoa humana, mesmo que se argumente a necessidade de uma paridade entre acusação e defesa. Partindo-se de uma pontual revisão bibliográfica sobre a utilização de máquinas com inteligência artificial na investigação, articulando literatura situada entre a tecnologia e o direito, com base principal no método hipotético dedutivo, concluímos não pela necessidade de expandir, mas de limitar, em praticamente todos os aspectos, a utilização de máquinas com inteligência artificial e a disseminação de potenciais investigadores criminais.

Fish freshness categorization from eyes and gills color features using multi-class artificial neural network and support vector machines

Developing new techniques to determine fish freshness and quality can enhance nutritional value of the overall household food basket. In this research, digital image analysis was utilized to assess the freshness of rainbow trout fish by tracing the color attributes of its eyes and gills. The image data were collected from left and right eyes and gills in a 10-day ice-storage duration, and color components were extracted in RGB, HSV, and L*a*b* color spaces. Analysis of variance revealed that the RGB components of both eyes and gills had a significant change towards getting brighter during the ice-storage. Feature extraction was fulfilled from the color spaces, and then artificial neural networks (ANNs) and support vector machines (SVMs) were applied for classification of the ice-storage durations. The overall accuracies of the developed models demonstrated that the ANN somewhat outperformed the SVM for both the extracted features from the eyes and gills. Moreover, the gills’ features could describe the variance in the storage durations more efficiently than those extracted from the eyes. Finally, it was concluded that the applied colorimetric system along with the developing models could be employed as a successful non-destructive approach for evaluation of fish freshness.

English

One of the major advancements in information technology (IT) is the use of IT tools to perform accounting functions and processes. In this paper, we provide discussions on how IT has affected the accountancy profession. We argued that the traditional duty of accountants is the preparation of financial statements, and consequently, several tasks are carried out throughout that function. In the pre-IT era, accountants were faced with delays in transaction processing and reporting, continuous errors and misstatements, and difficulty in storing large data on papers. However, following the emergence of sophisticated IT tools, accountants in the IT era are now able to prepare and present financial statements more timely and accurately. The availability of the internet has also increased access to financial reports by external users. This paper further argues that in light of the continuous advancements in IT, future accountants and accounting processes are likely to; be cloud-based, communicate with and through Artificial Intelligence machines; invest in Big Data and cyber-security, and explore the potentials of Virtual Reality and Augmented Reality in meeting users’ information needs. Hence, accountants and accountancy firms are advised to embrace new IT skills and tools, and keep up with technological trends.   Key words: Accountant, information technology, accountant, information technology, cloud computing, artificial intelligence and the big data.

An Intelligent Method for Detecting the Rate of Poverty Level with Reference to Tuberculosis

This paper represents the factors, which is important for the prediction of the population living below the poverty level as defined by world health organization through reverse engineering. The objective of this research work is to analyze how the tuberculosis detection rate can help us to predict the people living below the poverty line. The feed-forward artificial neural network and Support vector machines used for comparison. The Authors provide physical reasons behind the startling results that we obtained. This work used data collected by the World Health Organization. The data collected consisted of 202 observations of 358 variables and out of these vast numbers of variables; we selected only six variables of interest to build the model. After removing the not available rows, we get only 75 observations out of which we use only 57 observations to build our model. Although the error was a bit high, still with only these few observations both artificial neural networks and support vector machines yielded similar results, confirming our hypothesis. This paper also compares two well-known algorithms for variable importance and finally provides a solution to the problem of poverty by fuzzy cognitive maps. Various concepts related to the economy have been used to develop this model and results are astounding, based on the results solution to the present-day problems has been proposed.

Organismic materials for beyond von Neumann machines

The elementary basis of intelligence in organisms with a central nervous system includes neurons and synapses and their complex interconnections forming neural circuits. In non-neural organisms such as slime mold with gel-like media, viscosity modulation enables adaptation to changing environments. At a larger scale, collective intelligence emerges via social interactions and feedback in animal colonies. Learning and memory are therefore multi-scale features that evolve as a result of constant interactions with the environment. There is growing interest in emulating such features of intelligence in computing machines and autonomous systems. Materials that can respond to their environment in a manner similar to organisms (referred to as “organismic materials”) therefore may be of interest as hardware components in artificial intelligence machines. In this brief review, we present a class of semiconductors called correlated oxides as candidates for learning machines. The term “correlated” refers to the fact that electrons in such lattices strongly interact and the ground state is not what is predicted by classical band theory. Such materials can undergo insulator–metal transitions at near ambient conditions under external stimuli such as thermal or electrical fields, strain, and chemical doping. Depending on the mechanism driving the transition, intermediate states can be metastable with different volatilities, and the time scales of phase change can be controlled over many orders of magnitude. The change in electronic properties can be sharp or gradual, leading to digital or analog behavior. These properties enable the realization of artificial neurons and synapses and emulate the associative and non-associative learning characteristics found in various organisms. We examine microscopic properties concerning electronic and structural transitions leading to collective behavior and theoretical treatments of the ground state and dynamical response, showcasing VO2 as a model system. Next, we briefly review algorithms designed from the plasticity demonstrated by phase changing systems. We conclude the brief review with suggestions for future research toward realizing non-von Neumann machines.

Fuzzy Techniques for Artificial Snow Cover Optimization in the Ski Areas. Case Study: Obârșia Lotrului (Southern Carpathians, Romania)

This paper focuses on the environmental conflicts induced by insufficient continuous snow cover on the ski areas in Romania. The case study aims envisions the area of Southern Carpathians, Latoriței Mountains, belonging to the group of Parâng Mountains. The area chosen to develop and improve the artificial snow system was conducted for in the proposed ski area, Obârşia Lotrului. This fulfilled a necessary condition (geomorphological and climatic) for the development of the ski domain. The methodology focuses on two main stages phases. In the first stage phase, based on the GIS, the areas that have shown problems in terms of continuity of the snow layer and its thickness were identified, while the second phase, there is a supposed optimization based on Fuzzy logic for the installation of artificial snow. The corresponding thickness of snow for a longer period of time can lead to a higher socio-economic efficiency, as well as the increase of the use duration of the respective ski area, and also a prevention mechanism to environmental conflicts that may arise. The proposed study supports civil society by optimizing artificial snow machines through a positive impact on water resources allocated to a ski area in order to maintain a continuous snow cover.

Development of advanced artificial intelligence models for daily rainfall prediction

Abstract In this study, the main objective is to develop and compare several advanced Artificial Intelligent (AI) models namely Adaptive Network based Fuzzy Inference System optimized with Particle Swarm Optimization (PSOANFIS), Artificial Neural Networks (ANN) and Support Vector Machines (SVM) for the prediction of daily rainfall in Hoa Binh province, Vietnam. For this, meteorological variable parameters such as maximum temperature, minimum temperature, wind speed, relative humidity and solar radiation were collected and used as input parameters and daily rainfall as an output parameter in the models. Validation of the developed models was achieved using various quality assessment criteria such as correlation coefficient (R) and Mean Absolute Error (MAE), Skill Score (SS), Probability of Detection (POD), Critical Success Index (CSI), and False Alarm Ratio (FAR). The results showed that all the AI models provided reasonable predictions of daily rainfall but the SVM was found to be the best method for predicting rainfall. This method was also found to be the most robust and efficient prediction model while taking into account of input variability using the Monte Carlo approach. This AI based study would be helpful in quick and accurate prediction of daily rainfall.

Chatter Prediction in High Speed Machining of Titanium Alloy (Ti-6Al-4V) using Machine Learning Techniques

Titanium alloys have been extensively utilized in the aerospace and biomedical industries because of higher corrosion resistance and their good strength to weight ratio. In spite of several advantages, titanium alloys are difficult to machine because of their poor thermal conductivity and high chemical reactivity. Identification of suitable machining conditions is the key to get the good surface finish. Chatter during machining brings adverse effects in surface quality, dimensional accuracy and in tool life. The objective of this work is to identify chatter free machining conditions for machining titanium alloys and to predict the chatter occurrence with the help of machine leaning algorithms. During machining of titanium alloy, the vibration signals are captured for various machining conditions using accelerometer. From the raw signal statistical features are extracted and decision tree algorithm is used in selecting the dominant features. By monitoring the dominant features, chatter occurrences are predicted using Decision Tree (DT), Artificial Neural Network (ANN) and Support Vector Machines (SVM).

Statistical Global Modeling of β−-Decay Halflives Systematics Using Multilayer Feedforward Neural Networks and Support Vector Machines

In this work, the beta-decay halflives problem is dealt as a nonlinear optimiza- tion problem, which is resolved in the statistical framework of Machine Learning (LM). Continuing past similar approaches, we have constructed sophisticated Artificial Neural Networks (ANNs) and Support Vector Regression Machines (SV Ms) for each class with even-odd character in Z and N to global model the systemat- ics of nuclei that decay 100% by the β−-mode in their ground states. The arising large-scale lifetime calculations generated by both types of machines are discussed and compared with each other, with the available experimental data, with previous results obtained with neural networks, as well as with estimates coming from tradi- tional global nuclear models. Particular attention is paid on the estimates for exotic and halo nuclei and we focus to those nuclides that are involved in the r-process nucleosynthesis. It is found that statistical models based on LM can at least match or even surpass the predictive performance of the best conventional models of β-decay systematics and can complement the latter.

Prediction of significant wave height; comparison between nested grid numerical model, and machine learning models of artificial neural networks, extreme learning and support vector machines

Estimation of wave height is essential for several coastal engineering applications. This study advances a nested grid numerical model and compare its efficiency with three machine learning (ML) methods of artificial neural networks (ANN), extreme learning machines (ELM) and support vector regression (SVR) for wave height modeling. The models are trained by surface wind data. The results demonstrate that all the models generally provide sound predictions. Due to the high level of variability in the bathymetry of the study area, implementation of the nested grid with different Whitecapping coefficient is a suitable approach to improve the efficiency of the numerical models. Performance on the ML models do not differ remarkably even though the ELM model slightly outperforms the other models.

Employing Lethal Autonomous Weapon Systems

The ethics of warfare and military leadership must pay attention to the rapidly increasing use of artificial intelligence and machines. Who is responsible for the decisions made by a machine? Do machines make decisions? May they make them? These issues are of particular interest in the context of Lethal Autonomous Weapon Systems (LAWS). Are they autonomous or just automated? Do they violate the international humanitarian law which requires that humans must always be responsible for the use of lethal force and for the assessment that civilian casualties are proportionate to the military goals? The article analyses relevant documents, opinions, government positions, and commentaries using the methods of applied ethics. The main conceptual finding is that the definition of autonomy depends on what the one presenting it seeks to support. Those who want to use lethal autonomous weapon systems call them by another name, say, automated instead of autonomous. They impose standards on autonomy that machines do not meet, such as moral agency. Those who wish to ban the use of lethal autonomous weapon systems define them much less broadly and do not require them to do much more than to be a self-standing part of the causal chain.The article’s argument is that the question of responsibility is most naturally perceived by abandoning the most controversial philosophical considerations and simply stating that an individual or a group of people is always responsible for the creation of the equipment they produce and use. This does not mean that those who press the button, or their immediate superiors, are to blame. They are doing their jobs in a system. The ones responsible can probably be found in higher military leadership, in political decision-makers who dictate their goals, and, at least in democracies, in the citizens who have chosen their political decision-makers.

Characterization of kerogen content and activation energy of decomposition using machine learning technologies in combination with numerical simulations of formation heating

Reliable estimation of organic matter characteristics is essential in source and reservoir rocks evaluation. Their measurement is generally based on well logging and experiments after core sampling. In this study, we present a different approach from these methods to evaluate the characteristics of organic matter, which is based on the numerical simulations in combination with machine learning technologies.Formation heating processes of organic-rich shales and in-situ pyrolysis of kerogen are numerically simulated, where the time-series data of heater temperature are monitored. Here, we consider the whole organic matter composed with kerogen. The monitored heater temperature data are used as an input of inverse modeling by Artificial Neural Network (ANN) and Support Vector Machines (SVM) to figure out the characteristics of kerogen. Heater temperature acts as an indicator of type and maturity of kerogen, since it is affected by the bulk thermal conductivity of formation, which is a function of dynamically changing rock-and-pore composition by kerogen decomposition.We simulate the processes of electrical heating of 300 different formations, containing either one of Type 1, 2, or 3 kerogen with various amounts and activation energies. ANN method is employed to generate a data-driven model to estimate the unknown kerogen content and activation energy using heater temperature as an input data. SVM method, which categorizes dataset into the multiple classes by using hyperplanes, is applied to classify the dataset of heater temperature into different types of kerogens. Developed ANN and SVM models show great performances in the inversion and classification.The suggested characterization method provides a simple tool of estimating reactivity and type of kerogens. It will be used as a proxy for the inverse modeling of geochemical characterization of organic matter coupled with forward numerical simulations, by reducing the number of simulation runs required in the traditional inverse modeling.

The prediction of quality characteristics of cotton/elastane core yarn using artificial neural networks and support vector machines

Core yarn is a type of yarn that has a filament fiber in the center with a different fiber wrapped around it. This type of yarn is of growing importance in the textile industry. It is important to predict the quality characteristics of a core yarn before production to prevent the faulty production of fabrics. Therefore, the development of predictive models is a necessity in the textile industry. In this study, artificial neural network (ANN) and support vector machine (SVM) models are proposed to predict the quality characteristics of cotton/elastane core yarn, using fiber quality and spinning parameters. Principal component analysis and analysis of variance techniques are also used to reduce input dimensions, since high dimensional data may reduce a model’s potential for success in prediction. The prediction models are trained and tested using the data obtained from a textile production plant. The results of all the models are compared with each other on test data. Mean absolute percentage error (MAPE), mean absolute error (MAE) and correlation coefficient (R) are used to assess the prediction power of the models. Although on most of the tests SVM models fared slightly better than ANN models, both models provide accurate predictions for most of the yarn quality characteristics. The results show that the best models have over 90% success rate in MAPE and R. In particular, the Coefficient of Variance of mass (CVm) along the yarn, hairiness and Reisskilometer quality characteristics of the cotton/elastane core yarn are predicted with 91%, 93% and 95% accuracy, respectively.

Nanoscale Inorganic Motors Driven by Light: Principles, Realizations, and Opportunities.

The prospect of self-propelled artificial machines small enough to navigate within biological matter has fascinated and inspired researchers and the public alike since the dawn of nanotechnology. Despite many obstacles toward the realization of such devices, impressive progress on the development of its basic building block, the nanomotor, has been made over the past decade. Here, we review this emerging area with a focus on inorganic nanomotors driven or activated by light. We outline the distinct challenges and opportunities that differentiate nanomotors from micromotors based on a discussion of how stochastic forces influence the active motion of small particles. We introduce the relevant light-matter interactions and discuss how these can be utilized to classify nanomotors into three broad classes: nanomotors driven by optical momentum transfer, photothermal heating, and photocatalysis, respectively. On the basis of this classification, we then summarize and discuss the diverse body of nanomotor literature. We finally give a brief outlook on future challenges and possibilities in this rapidly evolving research area.

Relocating Acoustic Emission in Rocks with Unknown Velocity Structure with Machine Learning

Inversion of hypocenters is the first and most fundamental step in the study of seismic activities. It requires solving the nonlinear relation between the travel time and hypocenter locations, which is heavily dependent on the knowledge of the medium properties, most importantly the velocity structure. In this study, we prove that machine learning (ML) methods including artificial neural networks (ANNs) and support vector machines (SVMs) can relocate hypocenters without a priori knowledge of the velocity structure. We train ML models with acoustic emissions (AEs) created by breaking pencil leads at known locations on a laboratory fault, using the relative P-wave arrival time as the input and AE source locations as the output. The resultant ML models can accurately relocate AEs on the fault surface. With carefully chosen training strategies, the ANN model achieved better accuracy than the SVM model. This study suggests that ML methods can provide effective and accurate approaches for relocating seismic events in a medium with unknown velocity structures.

Investigating the identification of atypical sugarcane using NIR analysis of online mill data

In any given season thousands of tonnes of sugarcane with atypically low quality can pass undocumented through Australian sugarcane mills. Sugarcane with atypically low quality can negatively impact mill processes and throw off grower payment calculations. Mill laboratory operators often observe a small subset (1–5%) of cane consignments that have an unusually low juice Pol (Pij; a measure of sucrose content) relative to juice brix (Bij; a measure of dissolved sugars), that can indicate deteriorated or contaminated cane. Many mills only test a small subset of cane in the laboratory, with the majority of consignments analysed using fast near infrared (NIR) spectroscopic techniques. This means the true extent of ‘atypical’ consignments cannot be identified. To address this limitation, this paper compares five modelling approaches: Linear discriminant analysis (LDA), partial least squares discriminant analysis (PLS-DA), random forest (RF), Artificial Neural Networks (ANN) and Support Vector Machines (SVM). Model performance was reported as the correct classification rate (CCR) of typical and atypical samples based on independent test sets. The best performance was achieved by PLS-DA (CCRatypical = 88.65% and CCRtypical = 88.75%), while ANN had the lowest performance (CCRatypical = 85.27% and CCRtypical = 83.66%). The methodology used in this paper could be used to identify atypical consignments allowing mills to track occurrences to farms and if necessary develop process control operations for atypical cane. Furthermore, the use of a relatively simple modelling technique such as PLS-DA means model updates can be made efficiently and with confidence as PLS is already well established within the industry.

Room-temperature fabricated artificial synapse modulated by ultrathin SiOx buffer layer

In this work, a LiCoO2 (LCO)-based artificial synapse was fabricated at room temperature. Under continuous pulses stimuli, the device exhibited remarkable biological behaviors such as potentiating, depressing, forgetting, relearning, short-term plasticity (STP) and long-term plasticity, which were similar to the switching process in human brain. Switching process in LCO-based artificial synapse was controlled by the transport of Li ions between LCO film and ultrathin SiOx buffer layer, the latter was formed in LCO/Si interface during the fabrication process. This work provides a feasible way to realize low-temperature processed nerve synapse for neural network and artificial intelligence machines.

A predictive analytics framework for identifying patients at risk of developing multiple medical complications caused by chronic diseases.

Chronic diseases often cause several medical complications. This paper aims to predict multiple complications among patients with a chronic disease. The literature uses single-task learning algorithms to predict complications independently and assumes no correlation among complications of chronic diseases. We propose two methods (independent prediction of complications with single-task learning and concurrent prediction of complications with multi-task learning) and show that medical complications of chronic diseases can be correlated. We use a case study and compare the performance of these two methods by predicting complications of hypertrophic cardiomyopathy on 106 predictors in 1078 electronic medical records from April 2009-April 2017, inclusive. The methods are implemented using logistic regression, artificial neural networks, decision trees, and support vector machines. The results show multi-task learning with logistic regression improves the performance of predictions in terms of both discrimination and calibration.