Machine Intelligence Technologies Research Articles

CartoMark: a benchmark dataset for map pattern recognition and map content retrieval with machine intelligence

Maps are fundamental medium to visualize and represent the real word in a simple and philosophical way. The emergence of the big data tide has made a proportion of maps generated from multiple sources, significantly enriching the dimensions and perspectives for understanding the characteristics of the real world. However, a majority of these map datasets remain undiscovered, unacquired and ineffectively used, which arises from the lack of numerous well-labelled benchmark datasets, which are of significance to implement the deep learning techniques into identifying complicated map content. To address this issue, we develop a large-scale benchmark dataset involving well-labelled datasets to employ the state-of-the-art machine intelligence technologies for map text annotation recognition, map scene classification, map super-resolution reconstruction, and map style transferring. Furthermore, these well-labelled datasets would facilitate map feature detection, map pattern recognition and map content retrieval. We hope our efforts would provide well-labelled data resources for advancing the ability to recognize and discover valuable map content.

Digital tools of strategic management in agrarian business

Introduction. The paper examines trends in the definition and application of digital technologies in the system of strategic management of agrarian business entities. Considered the content of digitalization of the economy and its role for the activity of modern agricultural companies of Ukraine. The purpose of the paper is to characterize the state of the current level and determine the potential of using digital tools of strategic management by subjects of the agrarian business environment based on the results of the study of theoretical aspects, methodological justifications and practical foundations of implementation. Results. Digital transformation facilitates significant progress in human analysis and thinking. Thanks to large-scale cloud bases and the calculations carried out on their basis, humanity has the opportunity to create and use innovative technologies based on more reliable, highly intelligent and fast technologies. A significant number of progressive business models have appeared, which provide for differentiated management based on data arrays and artificial intelligence. Machine intelligence technologies ensure the quality of decision-making, increase the efficiency of both internal and external processes of the company, and also improve the customer experience. At the same time, the most important factor of ensuring competitive advantages is achieved - the speed of development. Conclusion. The most promising digitalization tools that will allow to significantly increase the efficiency of management are: automation of financial and investment planning processes, use of programs to ensure users' access to financial data in real time, expansion of operations analytics to speed up the decision-making process, application of large-volume processing technologies data for related business processes. Digitization of the strategic management of an agricultural company allows to change not only the management of its material part of production, but also to transform the contour of regulation and control of activities as a whole, since the ability to obtain valuable information from highly productive digital information exchanges appears.

Digital Twin-enabled Industrial Internet of Things, Immersive Metaverse and Machine Intelligence Technologies, and Event Modeling and Forecasting Tools in Simulated 3D Extended Reality Environments

Digital Twin-enabled Industrial Internet of Things, Immersive Metaverse and Machine Intelligence Technologies, and Event Modeling and Forecasting Tools in Simulated 3D Extended Reality Environments

Using Recurrent Neural Networks for Predicting Type-2 Diabetes from Genomic and Tabular Data.

The development of genomic technology for smart diagnosis and therapies for various diseases has lately been the most demanding area for computer-aided diagnostic and treatment research. Exponential breakthroughs in artificial intelligence and machine intelligence technologies could pave the way for identifying challenges afflicting the healthcare industry. Genomics is paving the way for predicting future illnesses, including cancer, Alzheimer's disease, and diabetes. Machine learning advancements have expedited the pace of biomedical informatics research and inspired new branches of computational biology. Furthermore, knowing gene relationships has resulted in developing more accurate models that can effectively detect patterns in vast volumes of data, making classification models important in various domains. Recurrent Neural Network models have a memory that allows them to quickly remember knowledge from previous cycles and process genetic data. The present work focuses on type 2 diabetes prediction using gene sequences derived from genomic DNA fragments through automated feature selection and feature extraction procedures for matching gene patterns with training data. The suggested model was tested using tabular data to predict type 2 diabetes based on several parameters. The performance of neural networks incorporating Recurrent Neural Network (RNN) components, Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU) was tested in this research. The model's efficiency is assessed using the evaluation metrics such as Sensitivity, Specificity, Accuracy, F1-Score, and Mathews Correlation Coefficient (MCC). The suggested technique predicted future illnesses with fair Accuracy. Furthermore, our research showed that the suggested model could be used in real-world scenarios and that input risk variables from an end-user Android application could be kept and evaluated on a secure remote server.

Internet of Things-based smart vehicles design of bio-inspired algorithms using artificial intelligence charging system

Abstract Artificial intelligence (AI) is a machine intelligence technology with vast potential for a smart industrial revolution. This study aims to create new electric-powered transportation such as bicycles, motorbikes, and other vehicles. The combination of high-speed, resiliency, and low-latency connection, as well as AI and Internet of Things (IoT) technologies, will enable the transformation to fully autonomous vehicles. This electric motorcycle tracks its speed, location, and other data using IoT logic. A smart charging system has also been developed to keep them ready to use effectively. The proposed research also reduces the damage to the environment efficiently.

An entropy minimization based multilevel colour thresholding technique for analysis of breast thermograms using equilibrium slime mould algorithm

Breast cancer is one of the leading causes of death in women due to the abnormal growth of cells known as a tumour. Thermography is an imaging technique used to capture infrared radiation and generate a thermogram. The major advantages of thermography are contactless, radiation-free, painless, and real-time screening. The thermogram is used further in a pathological investigation. However, in the modern-day, machine intelligence technologies are used for the analysis of breast thermograms, which assist the expert in decision making. The machine intelligence technique requires a thresholding image during the preprocessing stage, which warrants an efficient thresholding method. Here, we investigate the multilevel thresholding objective function to minimize the information regarding the entropic dependence on various classes. A new Equilibrium Slime Mould Algorithm (ESMA) is proposed for colour image thresholding, an improvement of the Slime Mould Algorithm (SMA), by integrating the equilibrium practice in updating the slime mould positions from an equilibrium pool concept of Equilibrium Optimizer (EO). The ESMA performance is compared with well know optimization algorithms and ranked one based on Friedman’s mean rank, when evaluated using 53 test problems. Further, the ESMA is used for the development of an entropy minimization based multilevel colour thresholding method for the analysis of breast thermograms. It is applied in two sets of experiments using grey components and the RGB components of breast thermograms. The encouraging results on the thermogram image analysis are presented. Even more interesting results are seen while evaluating our proposal in terms of different metrics—the peak signal to noise ratio (PSNR), the feature similarity (FSIM), and the structure similarity (SSIM). Statistical a nalysis provided reveals the suitability of the technique for the analysis of breast thermograms. The method may assist the medical practitioners, as an additional tool. The ESMA may be useful for solving different optimization problems in the world of engineering.

Application of machine intelligence technology in the detection of vaccines and medicines for SARS-CoV-2.

Researchers have found many similarities between the 2003 severe acute respiratory syndrome (SARS) virus and SARS-CoV-19 through existing data that reveal the SARS's cause. Artificial intelligence (AI) learning models can be created to predict drug structures that can be used to treat COVID-19. Despite the effectively demonstrated repurposed drugs, more repurposed drugs should be recognized. Furthermore, technological advancements have been helpful in the battle against COVID-19. Machine intelligence technology can support this procedure by rapidly determining adequate and effective drugs against COVID-19 and by overcoming any barrier between a large number of repurposed drugs, laboratory/clinical testing, and final drug authorization. This paper reviews the proposed vaccines and medicines for SARS-CoV-2 and the current application of AI in drug repurposing for COVID-19 treatment.

Quality consistency analysis for complex assembly process based on Bayesian networks

In recent years, assembly process has been rapidly pushing the envelope in building complex, optimized products, by taking advantage of big data mining and machine intelligence technologies. Along with such developments, it has become increasingly necessary to strictly control quality consistency level of the assembly activities. However, due to the difficulty of modelling, quality consistency improvement of complex assembly process has always been a challenge for academia and industry. This paper attempts to describe the assembly process by using Bayesian networks and to provide an effective data-based scheme for improving quality consistency. First of all, considering the nonlinear and coupling characteristics, we introduce the maximum information coefficient and network deconvolution method to detect the direct associations in the assembly process and get an undirected graph. Secondly, in order to obtain a complete Bayesian network, we derive the directions of edges based on the independence between causal variable distribution and function mechanism. Thus, the key influence factors on quality consistency and the latent causal mechanism can be analyzed. This data-based scheme is applied to power consistency analysis of a real diesel engine production line, where the effectiveness is further demonstrated from real industrial data. As a result, this study provides theoretical support and technical guarantee for the improvement of assembly process, quality control, product quality and enterprise benefit.

A practical guide to intelligent image-activated cell sorting.

Intelligent image-activated cell sorting (iIACS) is a machine-intelligence technology that performs real-time intelligent image-based sorting of single cells with high throughput. iIACS extends beyond the capabilities of fluorescence-activated cell sorting (FACS) from fluorescence intensity profiles of cells to multidimensional images, thereby enabling high-content sorting of cells or cell clusters with unique spatial chemical and morphological traits. Therefore, iIACS serves as an integral part of holistic single-cell analysis by enabling direct links between population-level analysis (flow cytometry), cell-level analysis (microscopy), and gene-level analysis (sequencing). Specifically, iIACS is based on a seamless integration of high-throughput cell microscopy (e.g., multicolor fluorescence imaging, bright-field imaging), cell focusing, cell sorting, and deep learning on a hybrid software-hardware data management infrastructure, enabling real-time automated operation for data acquisition, data processing, intelligent decision making, and actuation. Here, we provide a practical guide to iIACS that describes how to design, build, characterize, and use an iIACS machine. The guide includes the consideration of several important design parameters, such as throughput, sensitivity, dynamic range, image quality, sort purity, and sort yield; the development and integration of optical, microfluidic, electrical, computational, and mechanical components; and the characterization and practical usage of the integrated system. Assuming that all components are readily available, a team of several researchers experienced in optics, electronics, digital signal processing, microfluidics, mechatronics, and flow cytometry can complete this protocol in ~3 months.

Intelligent Cell Search Engine

A fundamental challenge of biology is to understand the vast heterogeneity of cells, particularly how cellular composition, structure, and morphology are linked to cellular physiology. Unfortunately, conventional technologies are limited in uncovering these relations. We present a real-time machine intelligence technology based on a radically new architecture that realizes real-time image-based intelligent cell search and sorting at an unprecedented rate. The technology integrates high-throughput cell imaging, cell focusing, and cell sorting on a hybrid software-hardware data management infrastructure, enabling real-time automated operation for data acquisition, data processing, decision making, and actuation. Specifically, we use it to demonstrate real-time sorting of microalgal and blood cells based on intracellular protein localization and cell-cell interaction from large heterogeneous populations for studying photosynthesis and atherothrombosis, respectively. Our technology is highly versatile and expected to enable machine-based scientific discovery in biological, pharmaceutical, and medical sciences.

Fusion of Gaussian Process Kernel Regressors for Fault Prediction in Intelligent Energy Systems

Integration of energy systems with machine intelligence technologies advances the new generation of intelligent energy systems. One feature of intelligent energy systems is their ability to predict a future fault state (prognosis), and thus support control actions. This paper introduces a prognostic framework based on concepts originating from the machine learning universe and proceeds to assess the performance of the prognostics algorithms with statistical methods aiming to formulate a linear predictor whose coefficients are the solution of a multi-objective optimization problem. Prediction is achieved through independent Gaussian process kernel regressors put together as terms of a linear forecaster. In this novel framework the available data is used to train the regression models whose degradation predictions cover a predetermined time period and have the form of a predictive distribution whose mean and variance values are computed for future moments. Thus, given the observed data points one may search for the most probable values of other quantities of interest, or the values at different points from those measured. The feasibility of the cascading prognostics methodology is demonstrated via a turbine blade degradation example. This implementation is characterized by advantages that include the utilization of an optimization process that simultaneously determines the lowest possible values in a set of different statistical measures and the employment of a set of kernels for modeling various data features and capturing the system dynamics.

Automatic Role Recognition in Multiparty Conversations: An Approach Based on Turn Organization, Prosody, and Conditional Random Fields

Roles are a key aspect of social interactions, as they contribute to the overall predictability of social behavior (a necessary requirement to deal effectively with the people around us), and they result in stable, possibly machine-detectable behavioral patterns (a key condition for the application of machine intelligence technologies). This paper proposes an approach for the automatic recognition of roles in conversational broadcast data, in particular, news and talk shows. The approach makes use of behavioral evidence extracted from speaker turns and applies conditional random fields to infer the roles played by different individuals. The experiments are performed over a large amount of broadcast material (around 50 h), and the results show an accuracy higher than 85%.