Hybrid Artificial Intelligence Systems Research Articles

Unleashing the Power of Artificial Intelligence in Real Estate Valuation: Opportunities and Challenges Ahead

The convergence of real estate valuation and artificial intelligence (AI) represents a transformative frontier in the real estate industry. This paper explores the strategic importance of real estate valuation and the integration of AI technologies, shedding light on their multifaceted contributions to decision-making, value enhancement, and market insights. Through a comprehensive review of literature, theoretical frameworks, and industry insights, the study examines the potential of AI-driven valuation models, predictive analytics, and Explainable AI (XAI) techniques in revolutionizing traditional valuation practices. Key areas of future research, including data integration, ethical considerations, and the development of hybrid AI systems, are identified to advance the field and address emerging challenges. By leveraging AI technologies responsibly, stakeholders can unlock new opportunities for efficiency, accuracy, and transparency in real estate valuation, ultimately shaping a more resilient and sustainable future for the industry.

Conceptual Foundations of Information Modeling Technology in Urban Planning

Introduction. For the management of complex urban planning systems, the problems of choosing alternatives and finding effective solutions under conditions of risk and uncertainty in the interaction of many exogenous and endogenous factors are of great theoretical and practical importance. A special place in decision-making is occupied by an integrated approach that allows, based on artificial intelligence models, expert assessment, analytical and computational models, modeling methods and a number of other models and methods, to successfully apply various approaches to decision support, to provide a deeper and more comprehensive account of various factors. , their relationship, act in conditions of semistructured or unstructured information about the control object. In this regard, the problem of creating integrated intelligent decision support systems based on the theory and principles of hybrid artificial intelligence systems, mathematical modeling methods, system analysis, synthesis of control actions, etc. is relevant.The purpose of this article is to clarify the conceptual foundations of information modeling technology in urban planning.Materials and methods. To achieve this goal, the article used methods of problem analysis, synthsis, scientific approaches to solving the stated problem, classification of hybrid models used in information modeling in urban planning. The materials of the article are the works of scientists on the stated issues.Research results. The article points out that the possibilities of modeling in urban planning are associated with the development of hybrid models, which are models that are built using various methods. The author determined that a hybrid intelligent system is a combination of: analytical models, expert systems, artificial neural networks, fuzzy systems, genetic algorithms, simulation statistical models. The main task in the development of hybrid systems is to best combine different forms of representation and methods of knowledge processing in the decision-making process in the field of urban planning.Discussion and conclusion. The article substantiates the importance of introducing hybrid models for studying the functioning and forecasting the development of urban infrastructure. Approaches to the creation of intelligent information systems for decision support in urban planning based on a combination of analytical methods and models, such as simulation modeling, computational calculations, optimization calculations with soft computing models, such as fuzzy systems, neural networks, genetic solutions of complex weakly structured or unstructured tasks. The creation of such systems will increase the level of managerial decision-making in urban planning, better assess the quality of the housing policy being pursued.

Detection of Monkeypox Disease from Human Skin Images with a Hybrid Deep Learning Model.

Monkeypox, a virus transmitted from animals to humans, is a DNA virus with two distinct genetic lineages in central and eastern Africa. In addition to zootonic transmission through direct contact with the body fluids and blood of infected animals, monkeypox can also be transmitted from person to person through skin lesions and respiratory secretions of an infected person. Various lesions occur on the skin of infected individuals. This study has developed a hybrid artificial intelligence system to detect monkeypox in skin images. An open source image dataset was used for skin images. This dataset has a multi-class structure consisting of chickenpox, measles, monkeypox and normal classes. The data distribution of the classes in the original dataset is unbalanced. Various data augmentation and data preprocessing operations were applied to overcome this imbalance. After these operations, CSPDarkNet, InceptionV4, MnasNet, MobileNetV3, RepVGG, SE-ResNet and Xception, which are state-of-the-art deep learning models, were used for monkeypox detection. In order to improve the classification results obtained in these models, a unique hybrid deep learning model specific to this study was created by using the two highest-performing deep learning models and the long short-term memory (LSTM) model together. In this hybrid artificial intelligence system developed and proposed for monkeypox detection, test accuracy was 87% and Cohen's kappa score was 0.8222.

Ant colony optimisation and fuzzy system for prediction of computational data of fluid flow in a bubble column reactor

ABSTRACT Computational data of a complex problem could be mapped and solved by artificial intelligence (AI) for postprocessing purposes and numerical time-saving. A fuzzy adaptive network as a hybrid AI system has already been used for CFD data machine learning. However, no investigation has been done for the ant colony optimisation (ACO) performance evaluation compared to the adaptive network. As a state-of-the-art method, the ACO and fuzzy system are combined and tuned to estimate the flow in a reactor. The liquid-phase velocity in the y-direction is predicted using a combination of fuzzy system and ACO in a large domain. The findings further indicate that, in addition to the CFD dataset and Navier-Stokes’s equations, employing an ant colony optimisation structure as a training technique may give an accurate approximation of two-phase flow. Furthermore, for numerical methods, a continuous link between input and output datasets may be a significant data source for the AI mechanism to train the physical process, incredibly bubbly flow. The ant colony optimisation shows a more accurate prediction than the adaptive network. As far as authors know, there are no such investigations to develop a new AI algorithm and performance analysis for fluid dynamics problems.

Harpia: A hybrid system for agricultural UAV missions

The present paper introduces Harpia, a hybrid artificial intelligent planning system for UAVs. Harpia aims to execute tasks for agricultural applications with minimum human intervention. The mission's execution is on-board, running under the Robotic Operating System and executing re-planning for tasks and path planning with obstacle avoidance. The re-planning can happen after mission changes in real-time or unpredictable UAV behavior. It combines Planning Domain Definition Language for task planning, Bayesian Network to evaluate mission execution, and K-Nearest Neighbors algorithm to select a path planner. Thus, Harpia's novelty focuses on robustness for autonomously planning and re-planning the sequence of tasks and trajectories to regions of interest. The main contributions include an autonomous system architecture for planning missions with minimum human intervention, no boundary by specific tasks, and computationally simple for operating within non-convex scenarios. The computational tests report results for 21 simulated scenarios, where Harpia handled all situations properly, e.g., making decisions about task re-planning with 97.57% accuracy based on battery health and choosing the better path-planning for each case with at least 95% of accuracy.

A review on proliferation of artificial intelligence in wind energy forecasting and instrumentation management.

Energy is the source of economic growth, and energy consumption indicates the country's state of development. Energy engineering is a relatively new technical discipline. It is increasinglyconsidered as a significant step in meeting carbon reduction targets, which can produce a variety of appealing outcomes that are useful to humanity's evolution. Many countries have adopted national policies to decrease pollution by reducing fossil fuel use and increasing renewable energy usage by alleviating climate change (wind and solar, etc.). The ever-growing need for renewable sources has led to economic and technological problems, such as wind energy, essential for effective grid control, and the design of a wind project. Precise estimates offer network operators and power system designers vital information for the generation of an appropriate wind turbine and controlling demand and supply power. This work provides an in-depth study of the proliferation of artificial intelligence (AI) in the prediction of wind energy generation. The devices employed to calculate wind speed are examined and discussed, with a focus on studies recently published. This review's findings show that AI is being employed in power wind energy measurement and forecasts. When compared to individual systems, the hybrid AI system gives more accurate findings. The discussion also found that correct handling and calibration of the anemometer can increase predicting accuracy. This conclusion suggests that increasing the accuracy of wind forecasting can be accomplished by lowering equipment errors that measure the meteorological parameter and mitigate carbon emission.

Retracted] Classification and Analysis of College Students’ Skills Using Hybrid AI Models

Each individual diversifies in the population with certain characteristics. Thus, diversity is a scientifically proven and widely accepted phenomenon when the human being is a concern. One of the areas where the diversity of human beings is mostly paid attention to is called the learning process, since different forms of responses could be observed. For example, each student perceives, assimilates, and uniquely processes the information when being transmitted to him, which confirms the inherited diversity. In this regard, educational systems are required to deal effectively with students and to apply the principles of personalized learning, which is pertinent to learning processes that meet the individual needs and interests of learners. By doing so, taking into account their unique characteristics, talents, skills, inclinations, and desires are satisfied. This manuscript presents an innovative model to classify college students’ skills. A hybrid artificial intelligence (AI) system that fully automates the process of personalized training is proposed based on individual skills by taking into account the priority of personalized and fully customized learning systems. The process specifically utilizes the Rasch statistical analysis model and an innovative fuzzy Bayesian network. Higher‐level reasoning is generated for the automated and personalized learning process in which college students are automatically classified into a certain category based on their skills.

Creating an ATC knowledge graph in support of the artificial situational awareness system

Automation has been recognized as a possible solution for increasing air traffic controller workload trends. This paper presents a methodology for creating an air traffic control knowledge graph, which is used as part of a hybrid artificial intelligence system for air traffic control operations. The system combines machine learning and symbolic reasoning with the purpose of achieving artificial situational awareness in a narrow domain of en-route air traffic control operations. This approach allows the use of user-defined knowledge alongside existing knowledge repositories. The novel knowledge graph development methodology is universal for any area of air traffic management which relies on the aeronautical information exchange models. In this paper we also present the open-source tools which were developed to make this approach possible and system performance evaluations. Future work should address achieving real-time operation and additional task automation, accompanied by appropriate ontology and graph expansion.

Акторная модель построения нейро-нечетких систем

Development of actors-based model of neuro-fuzzy systems is considered. Different ways of distributed asynchronous artificial intelligent systems. Actor model, which is based on an interaction of separate and independent units, allows creating of hybrid intelligent calculating systems. Properties of actors and the specifics of their communication give a number of ways for providing system’s self-diagnostics and self-organization. The comparison of efficiency of distributed neuro-fuzzy system, based on actors model, and a monolith system, created as one unit, is provided. Time of processing a specific number of datasets was performed on both if these types of systems for this purpose. Memory distribution and calculating units’ interaction of distributed hybrid artificial intelligence systems were estimated.

IoT Application of Transfer Learning in Hybrid Artificial Intelligence Systems for Acute Lymphoblastic Leukemia Classification.

Acute lymphoblastic leukemia is the most common cancer in children, and its diagnosis mainly includes microscopic blood tests of the bone marrow. Therefore, there is a need for a correct classification of white blood cells. The approach developed in this article is based on an optimized and small IoT-friendly neural network architecture. The application of learning transfer in hybrid artificial intelligence systems is offered. The hybrid system consisted of a MobileNet v2 encoder pre-trained on the ImageNet dataset and machine learning algorithms performing the role of the head. These were the XGBoost, Random Forest, and Decision Tree algorithms. In this work, the average accuracy was over 90%, reaching 97.4%. This work proves that using hybrid artificial intelligence systems for tasks with a low computational complexity of the processing units demonstrates a high classification accuracy. The methods used in this study, confirmed by the promising results, can be an effective tool in diagnosing other blood diseases, facilitating the work of a network of medical institutions to carry out the correct treatment schedule.

Artificial Intelligence Hybrid System for Enhancing Retinal Diseases Classification Using Automated Deep Features Extracted from OCT Images

After the advent of 2D eye imaging technology, Optical Coherence Tomography (OCT) became one of the most effective and commonly used imaging techniques for non-invasive retinal eye disease evaluation. Blindness is primarily diagnosed using OCT with one of the following two eye diseases categories: diabetic macular edema (DME) or age-related macular degeneration (AMD). The classification of eye retina diseases using OCT images recently became a challenge with the development of machine teaching and profound learning techniques. In this paper, a hybrid artificial intelligence system for multiclass classification of eye retina diseases using automated deep features extracted using Advanced OCT Network (AOCTNet) CNN architecture from OCT images especially spectral domain (SD-OCT) images have been proposed. The proposed methodology mainly can be used to classify retinal diseases into normal and four abnormal classes (AMD, choroidal neovascularization (CNV), DME, and Drusen) retinal disease. The proposed system constructed using eight types of machine learning algorithms, all of which achieved high performance overall. This methodology is a potentially powerful computer aided diagnostic (CAD) tool for the use of SD-OCT imaging for retinal diseases.

The Duality of Data and Knowledge Across the Three Waves of AI

We discuss how over the last 30 to 50 years, Artificial Intelligence (AI) systems that focused only on data have been handicapped, and how knowledge has been critical in developing smarter, intelligent, and more effective systems. In fact, the vast progress in AI can be viewed in terms of the three waves of AI as identified by DARPA. During the first wave, handcrafted knowledge has been at the center-piece, while during the second wave, the data-driven approaches supplanted knowledge. Now we see a strong role and resurgence of knowledge fueling major breakthroughs in the third wave of AI underpinning future intelligent systems as they attempt human-like decision making, and seek to become trusted assistants and companions for humans. We find a wider availability of knowledge created from diverse sources, using manual to automated means both by repurposing as well as by extraction. Using knowledge with statistical learning is becoming increasingly indispensable to help make AI systems more transparent and auditable. We will draw a parallel with the role of knowledge and experience in human intelligence based on cognitive science, and discuss emerging neuro-symbolic or hybrid AI systems in which knowledge is the critical enabler for combining capabilities of the data-intensive statistical AI systems with those of symbolic AI systems, resulting in more capable AI systems that support more human-like intelligence.

The Concept of the Cognitive Cycle in tasks of General Artificial Intelligence

One of the main problems underlying research programs in the field of general artificial intelligence is the problem of the insufficiency of particular approaches and mathematical models. The paper proposes the concept of creating a hybrid artificial intelligence system for solving practical problems of extracting the meaning of a text that implements the principles of the hermeneutical circle. The concept offers a syncretic-sequential combination of connectionist, symbolic approaches, as well as methods of cluster analysis. The concept is based on the idea of creating hybrid, primarily human-machine systems.

Subspecialty-Level Deep Gray Matter Differential Diagnoses with Deep Learning and Bayesian Networks on Clinical Brain MRI: A Pilot Study.

To develop and validate a system that could perform automated diagnosis of common and rare neurologic diseases involving deep gray matter on clinical brain MRI studies. In this retrospective study, multimodal brain MRI scans from 212 patients (mean age, 55 years ± 17 [standard deviation]; 113 women) with 35 neurologic diseases and normal brain MRI scans obtained between January 2008 and January 2018 were included (110 patients in the training set, 102 patients in the test set). MRI scans from 178 patients (mean age, 48 years ± 17; 106 women) were used to supplement training of the neural networks. Three-dimensional convolutional neural networks and atlas-based image processing were used for extraction of 11 imaging features. Expert-derived Bayesian networks incorporating domain knowledge were used for differential diagnosis generation. The performance of the artificial intelligence (AI) system was assessed by comparing diagnostic accuracy with that of radiologists of varying levels of specialization by using the generalized estimating equation with robust variance estimator for the top three differential diagnoses (T3DDx) and the correct top diagnosis (TDx), as well as with receiver operating characteristic analyses. In the held-out test set, the imaging pipeline detected 11 key features on brain MRI scans with 89% accuracy (sensitivity, 81%; specificity, 95%) relative to academic neuroradiologists. The Bayesian network, integrating imaging features with clinical information, had an accuracy of 85% for T3DDx and 64% for TDx, which was better than that of radiology residents (n = 4; 56% for T3DDx, 36% for TDx; P < .001 for both) and general radiologists (n = 2; 53% for T3DDx, 31% for TDx; P < .001 for both). The accuracy of the Bayesian network was better than that of neuroradiology fellows (n = 2) for T3DDx (72%; P = .003) but not for TDx (59%; P = .19) and was not different from that of academic neuroradiologists (n = 2; 84% T3DDx, 65% TDx; P > .09 for both). A hybrid AI system was developed that simultaneously provides a quantitative assessment of disease burden, explainable intermediate imaging features, and a probabilistic differential diagnosis that performed at the level of academic neuroradiologists. This type of approach has the potential to improve clinical decision making for common and rare diseases.Supplemental material is available for this article.© RSNA, 2020.

Analysing the intermeshed patterns of road transportation and macroeconomic indicators through neural and clustering techniques

As is widely acknowledged, the transportation of goods by road can, in one way or another, be linked to a range of macroeconomic indicators. A hybrid artificial intelligence system is proposed in this paper to analyse the interaction between transportation patterns and the economy. The temporal patterns of road transportation and macroeconomic trends are studied, by combining the use of both (supervised and unsupervised) neural networks and clustering techniques. The proposed system is validated, by establishing links between road transportation data from Spain and macroeconomic trends over 6 years (2011–2017). The results reveal an interesting inner structure of the data, through data visualizations of intermeshed relations between road transportation patterns and macroeconomic indicators. The same data structure was also visible in the output of the clustering techniques. Furthermore, a number of high-quality predictions were advanced by processing the road transportation data as time series, and forecasting the future values of the main series. These results demonstrated the validity of the proposed linkage between road transportation data and macroeconomic indicators.

Special issue HAIS 2015: Recent advancements in hybrid artificial intelligence systems and its application to real-world problems

Special issue HAIS 2015: Recent advancements in hybrid artificial intelligence systems and its application to real-world problems

Special issue HAIS 2014: Recent advancements in hybrid artificial intelligence systems and its application to real-world problems

Special issue HAIS 2014: Recent advancements in hybrid artificial intelligence systems and its application to real-world problems

Hybrid Artificial Intelligence System for the Design of Highly-Automated Production Systems

Abstract The automated design of production systems is a young field of research which has not been widely explored by industry nor research in recent decades. Currently, the effort spent in production system design is increasing significantly in automotive industry due to the number of product variants and product complexity. Intelligent methods can support engineers in repetitive tasks and give them more opportunity to focus on work which requires their core competencies. This paper presents a novel artificial intelligence methodology that automatically generates initial production system configurations based on real industrial scenarios in the automotive field of body-in-white production. The hybrid methodology reacts flexibly against data sets of different content and has been implemented in a software prototype.

Prediction of permanent deformation in asphalt pavements using a novel symbiotic organisms search–least squares support vector regression

The prediction of asphalt performance can be very important in terms of increasing service life and performance while saving energy and money. In this study, a new hybrid artificial intelligence (AI) system, SOS–LSSVR, has been proposed to predict the permanent deformation potential of asphalt pavement mixtures. SOS–LSSVR utilizes the symbiotic organisms search (SOS) and the least squares support vector regression (LSSVR), which are seen as a complementary system. The prediction model can be established from all input and output data pairs for LSSVR, while SOS optimizes the system’s tuning parameters. To avoid sampling bias and to partition the dataset into testing and training, a cross-validation technique was chosen. The results can be compared to those of previous studies and other predictive methods. Through the use of four error indicators, SOS–LSSVR accuracy was verified in predicting the permanent deformation behavior of an asphalt mixture. The present study demonstrates that the proposed AI system is a valuable decision-making tool for road designers. Additionally, the success of SOS–LSSVR in building an accurate prediction model suggests that the proposed self-optimized prediction framework has found an underlying pattern in the current database and thus can potentially be implemented in various disciplines.

A Hybrid Artificial Intelligent System for Age Estimation Based on Length of Left Hand Bone

A Hybrid Artificial Intelligent System for Age Estimation Based on Length of Left Hand Bone