Hybrid Intelligent Systems

Ant-based clustering and sorting is a nature-inspired heuristic for generalclustering tasks. It has been applied variously, from problems arising in commerce, tocircuit design, to text-mining, all with some promise. However, although early resultswere broadly encouraging, there has been very limited analytical evaluation of thealgorithm. Toward this end, we first propose a scheme that enables unbiased interpretationof the clustering solutions obtained, and then use this to conduct a full evaluationof the algorithm. Our analysis uses three sets ...

The quadratic assignment problem (QAP) is a very difficult and practically relevant combinatorial optimization problem which has attracted much research effort Local search (LS) moves can be quickly evaluated on the QAP, and hence favoured methods tend to be hybrids of global optimization schemes and LS. Here we introduce the multiobjective QAP (mQAP) where m> 2 distinct QAPs must be minimized simultaneuously over the same permutation space, and hence we require a set of solutions approximating the Pareto front ...

This paper presents a novel hybrid fuzzy logic approach for the classification of thyroid disease. Hybrid fuzzy logic approaches have brought many benefits to the medical data classification problems such as reasoning on uncertain or incomplete data. The machine learning algorithms had been used with the fuzzy expert systems to define the fuzzy rule base. The optimization techniques had been used in the fuzzy expert systems for optimizing the fuzzy membership functions and fuzzy rules. Enhancing the machine learning algorithms and optimization techniques that are integrated with the fuzzy logic method can improve the overall performance of the fuzzy expert system. To deal with the curse of dimensionality problem and to enhance the integration of machine learning algorithm and fuzzy logic method, this paper presents an incremental learning based parallel fuzzy reasoning system (IL-PFRS) for medical diagnosis. In this research work, the decision tree classifier is used to extract the features from dataset. IL-PFRS is applied to classify the thyroid disease which is serious disease that needs attention and earlier detection. The thyroid disease dataset obtained from the UCI machine learning repository is used in this research work where the IL-PFRS showed the classification accuracy of 99% when testing using this dataset.

Rough Non-deterministic Information Analysis (RNIA) is a rough set-based data analysis framework for Nondeterministic Information Systems (NISs). RNIA-related algorithms and software tools developed so far for rule generation provide good characteristics of NISs and can be successfully applied to decision making based on non-deterministic data. In this paper, we extend RNIA by introducing stability factor that enables to evaluate rules in a more flexible way and by developing a question-answering functionality that enables decision makers to analyze data gathered in NISs in case there are no pre-extracted rules that may address specified conditions.

A framework of new unified neural and neuro-fuzzy approaches for integrating implicit and explicit knowledge in neuro-symbolic systems is proposed. In the developed hybrid system, training data set is used for building neuro-fuzzy modules, and represents ...

This paper presents the application of evolutionary multi-objective optimization (EMO) to the improvement of a face detection system. The face detection system is based on the boosted cascade system, and analyzes image positions on different scales in a three-stepprocedure. Based on threshold settings, the algorithm decides whether to continue with the test on a finer scale at the current position. Thus, the thresholds for all scales and stages have a major influence on the performance of the system, and become the subject of the evolutionary optimization according to three objectives: low false positive rate, high detection rate and low processing time. The used EMO is the extension of the Standard Genetic Algorithm to the EMO case by using Fuzzy Pareto Dominance as a meta-heuristic. The application of this EMO to the face detection system is explored and discussed using images from a standard face detection benchmark dataset. From the runtime analysis of the EMO it can be concluded that the algorithm reliably approaches the Pareto set of the problem.

The integration of machine learning (ML) in healthcare decision support systems (DSS) enhances diagnostics and treatment recommendations. However, conventional ML models often lack interpretability and rely on centralized data, raising privacy concerns under HIPAA and GDPR. This paper proposes a privacypreserving and interpretable ML architecture using federated learning (FL), differential privacy (DP), secure multiparty computation (SMC), and homomorphic encryption (HE). The approach enables collaborative training across distributed hospital systems without exposing patient data, while employing Random Forest for interpretable predictions with feature importance visualization. Natural Language Processing (NLP) enhances unstructured data analysis. Experiments on synthetic healthcare datasets demonstrate high accuracy, robust privacy, and interpretable outputs, offering a secure, scalable, and trustworthy AI solution for clinical decision-making.

This paper proposes Internet of Things (IoT) analytics and machine learning based on open-source software for environmental data collected from the monitored sites such as industrial and high-tech zones. The IoT platform needs to meet the functional requirements such as data collection and storage data for a long time, device management, real-time monitored parameters, security, and data analysis. We present the design method of an IoT platform with functions of data collection and storage, real-time data streaming, and how to apply Recurrent Neural Network (RNN) to predictive analysis of environmental parameters. We also implement data pipeline to serve machine learning model training as well as prediction. Initial prediction results for the ambient temperature parameter based on machine learning models and built-in IoT platforms can continue to be developed for many other environmental parameters.

Several semantic based user profile approaches have been in- troduced in the literature to learn the users' interests for per- sonalized search. However, many of them are ill-suited to cope with a domain of information that evolves and user in- terests that may change over time. In this paper, we propose a novel dual representation of a user's semantic profile to deal with this problem: (1) a lower-level semantic representation, consisting of an accumulated gathering of user activities over a long period of time, that uses a standard machine learning algorithm to detect user convergence, (2) a higher-level se- mantic representation that detects shifts in the user activities- once this shift is detected, the higher-level semantic represen- tation automatically updates the user profiles and reinitialize the system. Our experimental results demonstrate the feasi- bility of this approach.

In this paper, we focus on Collaborative Filtering to provide recommendations to users that fit their profiles. We employed two methods: (1) K-Nearest Neighbors classifier, and (2) a fast implementation of Collaborative Filtering approach: "user-to-user fast XOR bit operation". Both techniques serve the same objective, which is modifying the user's ontology profile (semantic profile). Technically, Collaborative Filtering extends the user's ontology profile based on the interests of a community of similar users. Also, we describe the implementation of the recommender system on a real platform, known as HyperMany-Media 1 at Western Kentucky University 2 . Finally, we evaluate the system based on Top-n-Recall and Top-n-Precision. The results show an improvement in Recall and Precsion using Collaborative Filtering.

In this paper, we present an approach that uses cluster analysis techniques to extend the ontology of an E-learning domain. This approach is significantly different from any current information retrieval systems, it uses a global ontology model that represents the whole Elearning domain combined with clusters' centroids vocabularies (terms) to extend the core ontology model. The most important advantage of clustering from the personalization perspective is that the clusters are later used as automatically constructed labels for each user profile. Hence, depending on the document collection and its evolution, both the user profiles and their underlying ontology labels are allowed to change or evolve accordingly. Our proposed approach has been implemented on the HyperMany-Media

There is little consensus on what artificial intelligence (AI) systems may or may not embrace. Although this may point to multiplicity of interpretations and backgrounds, a lack of conceptual clarity could thwart the development of common ground around the concept among researchers, practitioners and users of AI and pave the way for misinterpretation and abuse of the concept. This article argues that one of the effective ways to delineate the concept of AI is to compare and contrast it with human intelligence. In doing so, the article broaches the unique capabilities of humans and AI in relation to one another (human and machine tacit knowledge), as well as two types of AI systems: one that goes beyond human intelligence and one that is necessarily and inherently tied to it. It finally highlights how humans and AI can augment their capabilities and intelligence through synergistic human–AI interactions (i.e., human-augmented AI and augmented human intelligence), resulting in hybrid ...

Industri konstruksi di Indonesia masih sering mengalami masalah seperti proyek yang terlambat selesai dan biaya yang membengkak. Salah satu penyebab utamanya adalah perencanaan proyek yang kurang matang, terutama dalam mengatur jadwal, anggaran, dan sumber daya. Penelitian ini bertujuan untuk mengetahui seberapa besar pengaruh perencanaan proyek terhadap kinerja waktu dan biaya dalam proyek konstruksi gedung. Metode yang dipakai adalah studi kasus dengan mengumpulkan data lewat dokumen proyek, wawancara dengan manajer dan pekerja proyek, serta observasi langsung di lapangan. Data yang dianalisis meliputi jadwal, anggaran, serta realisasi waktu dan biaya proyek. Hasil penelitian diharapkan menunjukkan bahwa perencanaan yang baik bisa membantu proyek selesai tepat waktu dan sesuai anggaran. Dengan hasil ini, diharapkan pelaku proyek dapat memperbaiki cara perencanaan supaya proyek lebih lancar dan hasilnya maksimal. Kata kunci: perencanaan proyek, kinerja waktu, biaya konstruksi, efisiensi proyek

Since December 2019, we have detected the appearance of a new virus called COVID-19, which has spread, throughout the world. Everyone today, has given major importance to this new virus. Although we have little knowledge of the disease, doctors and specialists make decisions every day that have a significant impact on public health. There are many and various open data in this context, which are scattered and distributed. For this, we need to capitalize all the information in a data warehouse. For that, in this paper, we propose an approach to create a data warehouse from open data specifically from COVID-19 data. We start with the identification of the relevant sources from the various open data. Then, we collect the pertinent data. After that, we identify the multidimensional concepts used to design the data warehouse schema related to COVID-19 data. Finally, we transform our data warehouse to logical model and create our NoSQL data warehouse with Talend Open Studio for Big Data (TOS_BD).

Introduction. One of the central tasks of education is the development of students' abilities for research activities,
which is a key tool for gaining a subjective understanding of the surrounding reality, the formation of critical thinking,
and a scientific worldview. The solution to this problem in the context of large-scale digitalization of the educational
sphere can be achieved through the use of automated learning platforms with an intelligent component. The
purpose of this study is to develop the technological foundations for the functioning of a neural network for modeling
a personalized educational process in the context of using an intelligent learning system.
Materials and methods. The key idea of the study is the possibility of intelligent management of research
activities through the use of neural network functionality, which ensures adaptability and correction of the process
of mastering the material depending on the learning style of the student, the level of training, and the degree of
development of independent work skills.
Results. The structure of the generalized hybrid neural network is characterized, as a result of the functioning
of which personalized parameters of the research potential of students are formed. The structure of the matrix of
parameters intended for the input layers of the neural network is described. A procedure for forming clusters of input
parameters of the generalized neural network is proposed. A series of computational experiments is performed, and
an interpretation of the obtained results is given.
Conclusion. The study makes a certain contribution to the development of technology for organizing research
activities of students using intelligent control. It is aimed at identifying the potential of neural networks for solving
problems of modeling individual educational trajectories and monitoring educational process indicators.

Keterlambatan dalam proyek konstruksi merupakan permasalahan yang sering terjadi dan berdampak serius terhadap pencapaian tujuan proyek, baik dari segi waktu, biaya, maupun mutu. Penelitian ini bertujuan untuk mengidentifikasi dan menganalisis faktor-faktor utama yang menyebabkan keterlambatan dalam pelaksanaan proyek konstruksi. Dengan menggunakan pendekatan kuantitatif deskriptif, data diperoleh melalui penyebaran kuesioner kepada pelaku proyek seperti kontraktor, konsultan, dan pemilik proyek. Analisis dilakukan untuk mengevaluasi tingkat kontribusi masing-masing faktor terhadap keterlambatan, serta mengidentifikasi faktor yang paling dominan. Hasil penelitian menunjukkan bahwa faktor manajerial, seperti kurangnya perencanaan yang matang dan lemahnya koordinasi antar pihak, merupakan penyebab utama keterlambatan. Selain itu, faktor teknis, keuangan, dan kondisi eksternal seperti cuaca juga turut memberikan kontribusi signifikan. Dampak keterlambatan proyek tidak hanya menyebabkan pembengkakan biaya, tetapi juga mengganggu reputasi kontraktor dan menurunkan kepuasan pemilik proyek. Penelitian ini merekomendasikan perlunya penguatan manajemen waktu proyek, perbaikan dalam sistem komunikasi antar stakeholder, serta peningkatan pengawasan terhadap pelaksanaan proyek sebagai strategi untuk meminimalkan keterlambatan di masa mendatang. Temuan ini diharapkan dapat menjadi bahan evaluasi dan referensi dalam perencanaan serta pelaksanaan proyek konstruksi yang lebih efisien dan tepat waktu.

Computational intelligence (CI) techniques have positively impacted the petroleum reservoir characterization and modeling landscape. However, studies have showed that each CI technique has its strengths and weaknesses. Some of the techniques have the ability to handle datasets of high dimensionality and fast in execution, while others are limited in their ability to handle uncertainties, difficult to learn, and could not deal with datasets of high or low dimensionality. The ''no free lunch'' theorem also gives credence to this problem as it postulates that no technique or method can be applicable to all problems in all situations. A technique that worked well on a problem may not perform well in another problem domain just as a technique that was written off on one problem may be promising with another. There was the need for robust techniques that will make the best use of the strengths to overcome the weaknesses while producing the best results. The machine learning concepts of hybrid intelligent system (HIS) have been proposed to partly overcome this problem. In this review paper, the impact of HIS on the petroleum reservoir characterization process is enumerated, analyzed, and extensively discussed. It was concluded that HIS has huge potentials in the improvement of petroleum reservoir property predictions resulting in improved exploration, more efficient exploitation, increased production, and more effective management of energy resources. Lastly, a number of yet-to-be-explored hybrid possibilities were recommended.

Data clustering is an approach for automatically finding classes, concepts, or groups of patterns. It also aims at representing large datasets by a few number of prototypes or clusters. It brings simplicity in modelling data and plays an important role in the process of knowledge discovery and data mining. Data mining tasks require fast and accurate partitioning of huge datasets, which may come with a variety of attributes or features. This imposes computational requirements on the clustering techniques. Swarm Intelligence (SI) has emerged that meets these requirements and has successfully been applied to a number of real world clustering problems. This paper looks into the use of Particle Swarm Optimization for cluster analysis. The effectiveness of Fuzzy C-means clustering provides enhanced performance and maintains more diversity in the swarm and allows the particles to be robust to trace the changing environment. Data structure identifying from the large scale data has become a ...

Homeostatic sleep regulation is essential for optimizing the amount and timing of sleep, but the underlying mechanism remains unclear. Optogenetic activation of locus coeruleus noradrenergic neurons immediately increased sleep propensity following transient wakefulness. Fiber photometry showed that repeated optogenetic or sensory stimulation caused rapid declines of locus coeruleus calcium activity and noradrenaline release. This suggests that functional fatigue of noradrenergic neurons, which reduces their wake-promoting capacity, contributes to sleep pressure.

Logika fuzzy merupakan salah satu pendekatan dalam kecerdasan buatan yang digunakan untuk mengelola data yang bersifat tidak pasti dan ambigu dalam proses pengambilan keputusan. Logika fuzzy tidak mengikat nilai kebenaran pada kategori absolut seperti "benar" atau "salah", melainkan memetakan nilai tersebut dalam rentang kontinu yang memungkinkan gradasi tingkat kepastian. Pendekatan ini merepresentasikan cara manusia berpikir, di mana proses penilaian informasi dilakukan secara bertahap dan fleksibel, terutama saat harus menghadapi data yang tidak sepenuhnya jelas atau bersifat samar. Penelitian ini menguraikan konsep fundamental dari logika fuzzy, menjelaskan struktur sistem inferensinya, serta mengeksplorasi potensi pemanfaatannya dalam merancang sistem cerdas. Untuk menunjukkan implementasinya, penelitian ini mengembangkan model awal sistem pendukung keputusan yang didasarkan pada prinsip logika fuzzy. Hasil pengujian menunjukkan bahwa logika fuzzy memiliki kemampuan adaptasi yang tinggi dan dapat berfungsi secara efektif dalam situasi yang penuh ketidakpastian, seperti pada aplikasi kontrol suhu dan sistem prediktif.

Proyek konstruksi merupakan kegiatan kompleks yang memiliki tingkat ketidakpastian tinggi, baik dari segi waktu, biaya, maupun mutu. Risiko yang tidak dikelola dengan baik dapat menyebabkan keterlambatan, pembengkakan anggaran, hingga kegagalan proyek secara keseluruhan. Sistem manajemen risiko konvensional seringkali tidak mampu menangkap secara akurat ketidakpastian dan subjektivitas dalam proses penilaian risiko. Oleh karena itu, penelitian ini mengembangkan sistem cerdas berbasis logika fuzzy untuk membantu proses identifikasi, evaluasi, dan mitigasi risiko dalam proyek konstruksi. Metode yang digunakan mencakup integrasi Fuzzy Analytical Hierarchy Process (Fuzzy AHP) untuk penentuan bobot risiko, serta Fuzzy Failure Mode and Effects Analysis (Fuzzy FMEA) untuk menghitung tingkat prioritas risiko berdasarkan tiga parameter utama: severity, occurrence, dan detection. Studi kasus dilakukan pada proyek pembangunan jembatan di lingkungan perkotaan untuk menguji keefektifan sistem. Hasil penelitian menunjukkan bahwa sistem cerdas ini mampu mengolah data yang bersifat tidak pasti dan linguistik, serta memberikan rekomendasi mitigasi risiko yang lebih akurat dan adaptif dibandingkan metode tradisional. Sistem ini dapat menjadi alat bantu pengambilan keputusan yang efektif bagi para manajer proyek dalam merancang strategi pengendalian risiko secara proaktif dan terukur 12345678910 .

In recent years, multispectral image fusion methods are viewed as an effective tool to analyze multiband remote sensing images. In this paper a novel hybrid multispectral image fusion method using combine framework of wavelet transform and fuzzy logic is proposed. The proposed method provides novel tradeoff solution between the spectral and spatial fidelity and preserves more detail spectral and spatial information. New hybrid image fusion rules are also proposed. Proposed method is applied on registered Panchromatic and Multispectral images and simulation results are compared with standard image fusion parameters. The simulation results of proposed method also compared with five different standard Pan sharpening methods available in literature. It has been observed from simulation results that proposed algorithm preserves better spatial and spectral information and better visual quality compared to earlier reported methods.

ABSTRAK Pada era kecerdasan buatan modern, sistem dituntut mampu beradaptasi terhadap kompleksitas dan ketidakpastian lingkungan nyata. Penelitian ini memperkenalkan kerangka kerja inovatif yang mengombinasikan logika fuzzy dengan reinforcement learning untuk membentuk sistem cerdas hibrida yang responsif dan efisien. Pendekatan modular digunakan agar agen mampu belajar dan menyesuaikan aturan fuzzy berdasarkan umpan balik dari lingkungan. Eksperimen menunjukkan peningkatan akurasi dan kemampuan adaptif pada berbagai kondisi dinamis. Model ini memiliki potensi aplikasi dalam bidang robotika, kendaraan otonom, serta sistem rekomendasi berbasis konteks.

The style of writing or calligraphy applied in ancient manuscripts gives useful information to paleographers. The information helps paleographer to identify date, writer, number of writers, place of origin, and the originality of manuscripts. This information is known as features. The features from characters, tangent value, dominant background and also Grey-Level Co-occurrence Matrix (GLCM) have been used in this field of research. A novel technique was proposed for digital Jawi Paleography. Jawi is the original Malay writing based on Arabic characters. The technique proposed models triangles on images and extracts features from them. The features are used for classification. In this paper, new features for the Triangle Model are proposed. Also, the implementation of four zones is reported. The number of features has been extended from 12 to 45. For validation of proposed algorithm, 60,000:20,000 training and testing data from Hoda digit dataset has been prepared, selected randomly for 10 rounds of testing. For further verification, two Supervised Machine Learning (SML) and three Unsupervised Machine Learning (UML) algorithms were experimented. These experiments were conducted using a new Arabic calligraphy dataset that was set up from 1,225 Arabic letters taken from calligraphy books. From the data, SML experiments were conducted with the ratio of 807:408 for training and testing. Whereas for the UML, three classifiers were tested on 30 images of Arabic calligraphy dataset. Results from the tests prove that the Triangle Model technique can successfully be used in digital paleography of Jawi characters.

Calligraphy classification of the ancient manuscripts gives useful information to paleographers. Researches on digital paleography using calligraphy are done on the manuscripts to identify unidentified place of origin, number of writers, and the date of ancient manuscripts. Information that are used are features from characters, tangent value and features known as Grey-Level Co-occurrence Matrix (GLCM). For Digital Jawi Paleography, a novel technique is proposed based on the triangle. This technique defines three important coordinates in the image of each character and translates it into triangle geometry form. The features are extracted from the triangle to represent the Jawi (Arabic writing in Malay language) characters. Experiments have been conducted using seven Unsupervised Machine Learning (UML) algorithms and one Supervised Machine Learning (SML). This stage focuses on the accuracy of Arabic calligraphy classification. Hence, the model and test data are Arabic calligraphy letters taken from calligraphy books. The number of model is 711 for the UML and 1019 for the SML. Twelve features are extracted from the formed triangles used.

Effective identification of lung cancer at an initial stage is an important and crucial aspect for effective treatment and increase in survival rate. Lung cancer can be diagnosed with the help of MRI, CT scan, PET or X-ray. But CT scan images help in diagnosing the cancer at an early stage and include more detail than conventional X-ray images. CT scan images from database LIDC-TCIA are considered for research purpose. Several segmentation methods have been used to detect lung cancer at an early stage. Thresholding and Marker Controlled Watershed algorithm provides lower accuracy. To improve accuracy and determine the stage of cancer, hybrid method of image segmentation has been adopted. The system comprises of preprocessing, segmentation, feature extraction and classification steps. Classification is done using Support Vector Machine (SVM) to determine the severity of disease, i.e., in which stage the cancer is present. MATLAB R2010a has been used for simulation to detect lung canc...

Automatic captioning of Images has been explored extensively in the past 10 to 15 years. It is one of the elementary problems in Computer Vision and Natural Language Processing and has vast array of applications in the real world. In this survey, we aim to study different approaches used for the generation of image captions in a chronological manner starting from the basic template based caption generation model to using Neural Networks combined with external world knowledge. We review existing models in detail, highlighting the involved methodologies and improvements in the same that have occurred in time. We gave an overview to the standard image datasets and the evaluation measures developed to discern the quality of generated image captions. Apart from the basic benchmarks we also note speed and accuracy improvements in all the different approaches. Finally, we investigate further possibilities in automatic image caption generation.

Automatic captioning of Images has been explored extensively in the past 10 to 15 years. It is one of the elementary problems in Computer Vision and Natural Language Processing and has vast array of applications in the real world. In this survey, we aim to study different approaches used for the generation of image captions in a chronological manner starting from the basic template based caption generation model to using Neural Networks combined with external world knowledge. We review existing models in detail, highlighting the involved methodologies and improvements in the same that have occurred in time. We gave an overview to the standard image datasets and the evaluation measures developed to discern the quality of generated image captions. Apart from the basic benchmarks we also note speed and accuracy improvements in all the different approaches. Finally, we investigate further possibilities in automatic image caption generation.

Takagi-Sugeno-Kang fuzzy model to assist with real estate appraisals is described and optimized using evolutionary algorithms. Two approaches were compared in the paper. The first one consisted in learning the rule base and the second one in combining learning the rule base and tuning the membership functions in one process. Moreover two model variants with three and five triangular and trapezoidal membership functions describing each input variable were tested. Several TSK fuzzy models comprising different number of input variables were evaluated using the MATLAB. The evolutionary algorithms were based on Pittsburgh approach with the real coded chromosomes of constant length comprising whole rule base or both the rule base and all parameters of all membership functions. The experiments were conducted using training and testing sets prepared on the basis of actual 150 sales transactions made in one of Polish cities and located in a residential section. The results obtained were not decisive and further research in this area is needed. The real estate appraisals has become a large research area with considerable literature. Many professional journals such as "Appraisal Journal", "Real Estate Appraiser", "The Appraisal Review and Mortgage Underwriting Journal", "The Journal of Real Estate Research", "Journal of Property Valuation and Investment,", and "International Real Estate Review" specialize on the topic and practice of appraisal methods. Traditionally, three models have dominated the valuation of real estate: the sales comparison approach, the cost approach and the income capitalization approach [1]. More recently, hedonic pricing (multiple regression analysis) have been used to automate the comparison approach [2]. However, both groups of these methods have been criticized. The first group uses subjective judgments, whereas MRA has produced problems that result from the inclusion of outliers. Real data have several sources of error or imprecision generating difficulties to construct precision mass appraisal models. Automated valuation methodologies (AVM) using artificial methods have been offered as a solution for both problems . Automated valuation methodologies undergo many development during the last years. Mass appraisal modelling tries to replicate market behaviour. AVM usually demand patterns for groups of properties. For this reason, they refer to large groups rather than single property. The multiple regression analysis (MRA) remains the most reliable automated valuation method [2], which was successfully applied, among other things, in constructing price indices in Geneva, Switzerland, determining rental values in Bordeaux, France, explaining the market in Tel Aviv, Israel. However, MRA has two known problems. First, the procedure requires, that the appraiser selects the best comparables. Second, it is significantly influenced by the presence of outliers. An interesting direction for research has been the inclusion of the neural networks (NN) inside the AVM models [4], but several criticisms have been raised . The nature of the NN is informal, there is no clear function between the input and the output values. The algorithm learns by training. Inspired in the human brain, they save knowledge in weighted connections. The connections have an initial sum of the weighted inputs and an activation function which gave the output. The most widely used NN is based on multi-layer perceptron with a back propagation scheme of learning. A major drawback on NN is that knowledge is stored only in the weights with no direct significance to the valuation process. One of the most interesting problem in this area is the extraction of fuzzy rules from the trained NN. Some have argued that NN are better than MRA if the data set is large and if the right parameters are found. The mean absolute error resulted from NN model was lower (from 3,9 to 6.9%) than the mean absolute error from the regression model (from 7.5 to 11.3%) [1], [3]. However, several authors arrived at the same conclusion how outcomes vary with different NN models. Results from show that NN models give inconsistent results and long run times, which lead to reject this technique from mass appraisal. Analysis of the current directions in research shows that the most prominent types of AVM are fuzzy systems and genetic fuzzy rule-based systems . Fuzzy models have emerged as an effective tool, when the data are both quantitative and qualitative. They could be applied

Lost circulation is the most common problem encountered while drilling oil wells. This paper describes a distributed fuzzy expert system, called Smart-Drill, aimed in helping petroleum engineers to diagnose and solve lost circulation problems. To represent and manipulate perception-based evaluations of uncertainties of facts and rules, the expert system uses an uncertainty model with qualitative scales of plausibility values and multiset-based fuzzy algebra of strict monotonic operations. Its realization in inference procedures permits taking into account the change of plausibility of premises in expert systems rules. Original tools like CAPNET Expert System Shell, Knowledge Acquisition Tool and WITSML Converter implementing the proposed model were used for the development of the Smart-Drill. Overall, the system architecture is discussed and implementation details are provided. Both desktop and Web-based implementations permit petroleum engineers benefit from the system working out in the field. The system is currently at field testing phase in PEMEX, Mexican Oil Company.

Interpretation of medical images is often difficult and time consuming, even for experienced physicians. The aid of image analysis and machine learning can make this process easier. The medical service has been enriched with a lot of new techniques for diagnostic imaging during the last decades. In recent years the image processing mechanisms are used widely in several medical areas for improving earlier detection and treatment stages, in which the time factor is very important to discover the disease in the patient as possible as fast, especially in various cancer tumors such as the lung cancer, breast cancer. Lung cancer images passed basic three stages to achieve more quality and accuracy in our experimental results : firstly image enhancement stage which is low pre-processing image techniques: Gabor filter using a Gaussian rule in which produced the best resultant enhanced images, then auto-enhancement method then FFT(Fast Fourier Transform) respectively. In the image segmentati...

Microarray technology can measure the expression levels of thousands of genes in an experiment. This fact makes the use of computational methods in cancer research absolutely essential. One of the possible applications is in the use of Artificial Intelligence techniques. Several of these techniques have been used to analyze expression arrays, but there is a growing need for new and effective solutions. This paper presents a Case-based reasoning (CBR) system for automatic classification of leukemia patients from microarray data. The system incorporates novel algorithms for data mining that allow filtering, classification, and knowledge extraction. The system has been tested and the results obtained are presented in this paper.

This paper proposes two evolutionary approaches as procedures to solve the Synchronized and Integrated Two-Level Lot-Sizing and Scheduling Problem (SITLSP). This problem can be found in some industrial settings, mainly soft drink companies, where the production process involves two interdependent levels with decisions concerning raw material storage and soft drink bottling. The first approach to solve the SITLSP is a Multi-Population Genetic Algorithm (GA) with a hierarchical ternary tree structure for populations. The second approach is a Memetic Algorithm (MA) that extends the GA approach through the inclusion of a local search procedure. The computational study reported reveals that those methods are an effective alternative to solve real-world instances of the SITLSP.

1School of Information Dalian Maritime University No. 1, Linghai Road, Dalian 116026, PR China teesiv@dlmu.edu.cn ∗ Corresponding author: lhb@dlmu.edu.cn 2School of Computer Dalian University of Technology No. 2, Linggong Road, Ganjingzi District, Dalian 116023, PR ...

XCS is a learning classifier system that uses genetic algorithms to evolve a population of classifiers online. When applied to classification problems described by continuous attributes, XCS has demonstrated to be able to evolve classification models-represented as a set of independent interval-based rules-that are, at least, as accurate as those created by some of the most competitive machine learning techniques such as C4.5. Despite these successful results, analyses of how the different genetic operators affect the rule evolution for the interval-based rule representation are lacking. This paper focuses on this issue and conducts a systematic experimental analysis of the effect of the different genetic operators. The observations and conclusions drawn from the analysis are used as a tool for designing new operators that enable the system to extract models that are more accurate than those obtained by the original XCS scheme. More specifically, the system is provided with a new discovery component based on evolution strategies, and a new crossover operator is designed for both the original discovery component and the new one based on evolution strategies. In all these cases, the behavior of the new operators are carefully analyzed and compared with the ones provided by original XCS. The overall analysis enables us to supply important insights into the behavior of different operators and to improve the learning of interval-based rules in real-world domains on average.

Recently, feature maps have been applied to various problem domains. The success of some of these applications critically depends on whether feature maps are topologically ordered. Several different approaches have been proposed to improve the conventional self-organizing feature map (SOM) algorithm. However, these approaches do not guarantee that a topologically-ordered feature map can be formed at the end of a simulation. Therefore, the trial-and-error procedure still dominates the procedure of forming feature maps. In this paper, we propose a healing mechanism to repair feature maps that are not well topologically ordered. The healed map is then further finetuned by the conventional SOM algorithm with a small learning rate and a small-sized neighborhood set so as to improve the accuracy of the map. Two data sets were tested to illustrate the performance of the proposed method.

This paper introduces a novel method for defect detection in homogeneous flat surface products. The coefficient of variation is used as a homogeneity measure for approximate defect localization and features extracted from the Log -Gabor filter bank response are used to accurately localize and detect the defect while reducing the complexity of Gabor based inspection approaches. The scanning window size and threshold parameter are the two major factors that affect the system performance. An adaptive technique is proposed for selecting the size of the scanning window and automating the selection of the threshold level. Compared to the Log-Gabor filters, the proposed combination resulted in speeding up the defect detection process by about ten times. The experimental results show that the proposed system gives promising results and is applicable for defect detection in homogeneous surfaces like paper, steel plates, ceramic tiles and foils.

The problem of failure diagnosis has received a considerable attention in the domain of reliability engineering, process control and computer science. The increasing stringent requirement of quality of a product needs considerable attention in the performance and reliability of the manufacturing system. In general, the feedback control algorithm for a process designed to handle small perturbation that may arise under normal operating condition but can not accommodate any abnormal behavior due to fault. Thus the automated maintenance or early detection of worn equipment is becoming a critical issue. This justifies the need of development of effective methodology in the area of fault aware controller. In this paper we proposed a novel Algorithm and it have been tested and implemented for making Highly reliable system like Automated Cricket Ball Stitching Machine. Considering this need the present paper proposes the work on the development methodology of fault aware controller using embedded processor with reference to an early needle failure detection of a leather stitching machine.

In this paper, we present two new procedures for feature selection using a data quality measure. The first procedure is a filter method and the second is a hybrid method that combines the former method with a sequential forward selection (SFS), which is a wrapper method. Three classifiers; LDA, KNN and RPART, are used along with the wrapper method. Comparisons with the RELIEF and the usual SFS method are carried out on twelve well-known Machine Learning datasets. The experimental results show that our filter method outperforms the RELIEF, regarding both the misclassification error rate and the running time. Our hybrid method is faster than the SFS and it gives misclassification error rates quite similar to those given by the SFS.

The objective was to determine the optimal operating conditions for an artificial neural network (ANN) to estimate outcomes. The simulations involved using the 51 inputs while changing the desired output variable. indicates the minimum number of sample patterns an ANN requires for minimally acceptable outcome estimation, and establishes the limitation of the ANN as a useful tool.

Lost circulation is the most common problem encountered while drilling oil wells. This paper describes a distributed fuzzy expert system, called Smart-Drill, aimed in helping petroleum engineers to diagnose and solve lost circulation problems. To represent and manipulate perception-based evaluations of uncertainties of facts and rules, the expert system uses an uncertainty model with qualitative scales of plausibility values and multiset-based fuzzy algebra of strict monotonic operations. Its realization in inference procedures permits taking into account the change of plausibility of premises in expert systems rules. Original tools like CAPNET Expert System Shell, Knowledge Acquisition Tool and WITSML Converter implementing the proposed model were used for the development of the Smart-Drill. Overall, the system architecture is discussed and implementation details are provided. Both desktop and Web-based implementations permit petroleum engineers benefit from the system working out in the field. The system is currently at field testing phase in PEMEX, Mexican Oil Company.

SQL Injection attacks on web applications have become one of the most important information security concerns over the past few years. This paper presents a hybrid approach based on the Adaptive Intelligent Intrusion Detector Agent (AIIDA-SQL) for the detection of those attacks. The AIIDA-SQL agent incorporates a Case-Based Reasoning (CBR) engine which is equipped with learning and adaptation capabilities for the classification of SQL queries and detection of malicious user requests. To carry out the tasks of attack classification and detection, the agent incorporates advanced algorithms in the reasoning cycle stages. Concretely, an innovative classification model based on a mixture of an Artificial Neuronal Network together with a Support Vector Machine is applied in the reuse stage of the CBR cycle. This strategy enables to classify the received SQL queries in a reliable way. Finally, a projection neural technique is incorporated, which notably eases the revision stage carried out by human experts in the case of suspicious queries. The experimental results obtained on a real-traffic case study show that AIIDA-SQL performs remarkably well in practice.

This work presents a new hybrid architecture applied to autonomous mo- bile robot control - HyCAR (Hybrid Control for Autonomous Robots). This archi- tecture provides a robust control for robots as they become able to operate and adapt themselves to different environments and conditions. We designed this new hybrid control architecture, integrating the two main techniques used in robotic control

While software development productivity has grown rapidly, the weight values assigned to count standard Function Point (FP) created at IBM twenty-five years ago have never been updated. This obsolescence raises critical questions about the validity of the weight values; it also creates other problems such as ambiguous classification, crisp boundary, as well as subjective and locally defined weight values. All of these challenges reveal the need to calibrate FP in order to reflect both the specific software application context and the trend of today's software development techniques more accurately. We have created a FP calibration model that incorporates the learning ability of neural networks as well as the capability of capturing human knowledge using fuzzy logic. The empirical validation using ISBSG Data Repository (release 8) shows an average improvement of 22% in the accuracy of software effort estimations with the new calibration.

Function Point (FP) is a useful software metric that was first proposed 25 years ago, since then, it has steadily evolved into a functional size metric consolidated in the well-accepted Standardized International Function Point Users Group (IFPUG) Counting Practices Manual -version 4.2. While software development industry has grown rapidly, the weight values assigned to count standard FP still remain same, which raise critical questions about the validity of the weight values. In this paper, we discuss the concepts of calibrating Function Point, whose aims are to estimate a more accurate software size that fits for specific software application, to reflect software industry trend, and to improve the cost estimation of software projects. A FP calibration model called Neuro-Fuzzy Function Point Calibration Model (NFFPCM) that integrates the learning ability from neural network and the ability to capture human knowledge from fuzzy logic is proposed. The empirical validation using International Software Benchmarking Standards Group (ISBSG) data repository release 8 shows a 22% accuracy improvement of mean magnitude relative error (MMRE) in software effort estimation after calibration.

Abstract: The collection of wild larvae seed as a source of raw material is a major sub industry of shellfish aquaculture. To predict when, where and in what quantities wild seed will be available, it is necessary to track the appearance and growth of planktonic larvae. One of the most difficult groups to identify, particularly at the species level are the Bivalvia. This difficulty arises from the fact that fundamentally all bivalve larvae have a similar shape and colour. Identification based on gross morphological appearance is limited by the time- ...

Hybrid intelligent systems have emerged as a powerful approach to addressing the challenges of pattern recognition in dynamic environments. This paper presents a hybrid system that integrates neural networks, fuzzy logic, and evolutionary algorithms to improve the accuracy, adaptability, and robustness of pattern recognition models. Neural networks are employed for feature extraction, fuzzy logic is utilized to handle uncertainty, and evolutionary algorithms optimize the system's parameters over time. The proposed system was tested on synthetic and real-world datasets, including applications in financial market prediction and autonomous systems. The results demonstrated significant improvements in accuracy and adaptability compared to traditional models, with the hybrid system achieving up to 93% accuracy in dynamic classification tasks. Despite its effectiveness, challenges such as computational complexity and scalability remain. Future work will focus on optimizing the system for large-scale applications and enhancing transparency through explainable AI techniques. The findings offer a promising solution for complex pattern recognition tasks in rapidly changing environments.

Early requirements analysis (ERA) is quite significant for building agent-based systems. Goaloriented requirements analysis is promising for the agent-oriented early requirements analysis. In general, either visual modeling or formal specifications is used for the ERA. This way cannot capture requirements precisely and completely. In this paper, we present an integrative modeling framework for agent-oriented early requirements analysis; this framework implements goal-oriented requirement analysis. The integrative modeling combines visual modeling and formal modeling together. Extended i* framework is used for building visual models; formal specifications complement the visual modeling to define and refine requirements. Both visual and formal models are outlined through a practical agent-based system F-TRADE 1. The integrative modelling seems to model early requirements comprehensively and concretely, and benefit refinement and conflict management in building agent systems.

This paper examines the performance of a new Hidden Markov Model (HMM) structure used as the core of an Internet traffic classsifier and compares the results against other models present in the literature. Traffic modeling and classification find importance in many areas such as bandwidth management, traffic analysis, prediction and engineering, network planning, Quality of Service provisioning and anomalous traffic detection. The new HMM structure, which takes into account the packet payload size (PS) and the inter-packet times (IPT) sequences, is obtained by concatenation of a first part which is framed with a HMM profile with another part whose structure is that of a fully-connected HMM. The first part captures the specific properties of the initial protocol packets while the second part captures the statistical properties of the whole sequence present in the flow. Models generated are found to increase the accurate in classifying different traffic classes in the analysed dataset. The average accuracy obtained by the classifier is 62.5% having seen only five packets, 80.0% after examining 13 packets and 95.5% after seeing the unidirectional entire flow.

We have developed an approach to identification and tracking of currently unfolding news stories extracted from the news articles published on the Web. Our approach employs a set of agents to retrieve those articles from the Web that might refer to some developing news story. The set of agents is inspired by social insects, in particular by a bee colony. Bees identify popular terms, referred to as story words, relevant to the ongoing news stories and use them in foraging articles. This allows for a dynamic approach that reflects the changes in article space as new stories unfold and new articles are added. Subsequently a graph representation of the article space is constructed that contains retrieved articles and identified story words interconnected by edges according to relationships of relevance identified between elements of the graph. Stories are then extracted from the constructed graph by using Louvain method, commonly used to identify communities within modular graphs. Using this approach we have been able to identify news stories in a stream of articles retrieved from the Web with precision of 75.56%, with best precision generally achieved for recent news stories described by popular story words. Further we developed ways of visualization of multiple stories represented by sets of articles ordered in time. We propose two new metaphors both employing an exponential timeline. Both galactic streams and concurrent streams are highly suitable for visualizing multiple developing stories.