Статьи журнала - International Journal of Intelligent Systems and Applications
Все статьи: 1159
Статья научная
Healthcare is a fundamental human right. Vulnerable populations in healthcare refer to those who are at greater risk of suffering from health hazards due to various socio-economic factors, geographical barriers, and medical conditions. Mapping of this vulnerable population is a vital part of healthcare planning for any region. Very few such research regarding the distribution of healthcare service providers was carried out in the Nepali context previously. Thus, the results of vulnerability mapping can help with meaningful interventions for healthcare demands. This study focused on combining geo-analytics, unsupervised machine learning algorithms, and entropy methods for performing vulnerability mapping. K-means++ clustering algorithm was applied to household data of Ratnanagar municipality for the purpose of creating multiple clusters of households. An open-source routing machine was used to compute the distance to the nearest health service provider from each household in Ratnanagar municipality. The entropy method was used to evaluate the vulnerability measure of each cluster. Later, based on the population of different clusters in each ward and their respective vulnerability measures, each ward’s vulnerability measure was quantified. It can be observed that wards that are farther away from the east-west highway have higher vulnerability indices. This study found that machine learning algorithms can be effectively used in combination with the weighting method for vulnerability mapping. Using an unsupervised machine learning algorithm made sure that dimensions of vulnerability are visible.
Бесплатно
Heart Beat Classification Using Particle Swarm Optimization
Статья научная
This paper proposes a novel system to classify three types of electrocardiogram beats, namely normal beats and two manifestations of heart arrhythmia. This system includes three main modules: a feature extraction module, a classifier module, and an optimization module. In the feature extraction module, a proper set combining the shape features and timing features is proposed as the efficient characteristic of the patterns. In the classifier module, a multi-class support vector machine (SVM)-based classifier is proposed. For the optimization module, a particle swarm optimization algorithm is proposed to search for the best value of the SVM parameters and upstream by looking for the best subset of features that feed the classifier. Simulation results show that the proposed algorithm has very high recognition accuracy. This high efficiency is achieved with only little features, which have been selected using particle swarm optimizer.
Бесплатно
Heart Disease Prediction Using Modified Version of LeNet-5 Model
Статья научная
Particularly compared to other diseases, heart disease (HD) claims the lives of the greatest number of people worldwide. Many priceless lives can be saved with the help of early and effective disease identification. Medical tests, an electrocardiogram (ECG) signal, heart sounds, computed tomography (CT) images, etc. can all be used to identify HD. Of all sorts, HD signal recognition from ECG signals is crucial. The ECG samples from the participants were taken into consideration as the necessary inputs for the HD detection model in this study. Many researchers analyzed the risk factors of heart disease and used machine learning or deep learning techniques for the early detection of heart patients. In this paper, we propose a modified version of the LeNet-5 model to be used as a transfer model for cardiovascular disease patients. The modified version is compared to the standard version using four evaluation metrics: accuracy, precision, recall, and F1-score. The achieved results indicated that when the LeNet-5 model was modified by increasing the number of used filters, this increased the model's ability to handle the ECGs dataset and extract the most important features from it. The results also showed that the modified version of the LeNet-5 model based on the ECGs image dataset improved accuracy by 9.14 percentage points compared to the standard LeNet-5 model.
Бесплатно
Heart Diseases Diagnosis Using Neural Networks Arbitration
Статья научная
There is an increase in death rate yearly as a result of heart diseases. One of the major factors that cause this increase is misdiagnoses on the part of medical doctors or ignorance on the part of the patient. Heart diseases can be described as any kind of disorder that affects the heart. In this research work, causes of heart diseases, the complications and the remedies for the diseases have been considered. An intelligent system which can diagnose heart diseases has been implemented. This system will prevent misdiagnosis which is the major error that may occur by medical doctors. The dataset of statlog heart disease has been used to carry out this experiment. The dataset comprises attributes of patients diagnosed for heart diseases. The diagnosis was used to confirm whether heart disease is present or absent in the patient. The datasets were obtained from the UCI Machine Learning. This dataset was divided into training, validation set and testing set, to be fed into the network. The intelligent system was modeled on feed forward multilayer perceptron, and support vector machine. The recognition rate obtained from these models were later compared to ascertain the best model for the intelligent system due to its significance in medical field. The results obtained are 85%, 87.5% for feedforward multilayer perceptron, and support vector machine respectively. From this experiment we discovered that support vector machine is the best network for the diagnosis of heart disease.
Бесплатно
Helicopter Control Using Fuzzy Logic and Narma-L2 Techniques
Статья научная
Helicopter instability is one of the most limitations that should be addressed in a nonlinear application. Accordingly, researchers are invited to design a robust and reliable controller to obtain a stable system and enhance its overall performance. The present study focuses on the use of the intelligent system in controlling the pitch and yaw angles. This lead to controlling the elevation and the direction of the helicopter. Further to the application of the Linear Quadratic Regulator (LQR) controller, this research implemented the Proportional Integral Derivative (PID), Fuzzy Logic Control (FLC), and Artificial Neural Network (ANN). The results show that FLC achieved a good controllability for both angles, particularly for the pitch angle in comparison to the nonlinear auto regressive moving average (NARMA-L2). Moreover, NARMA-L2 requires further improvement by using, for example, the swarm optimization method to provide better controllability. The PID controller, on the other hand, had a greater capability in controlling the yaw angle in comparison to the other controllers implemented. Accordingly, it is suggested that the integration of PID and FLC may lead to more optimal outcomes.
Бесплатно
Heuristic-based Approach for Dynamic Consolidation of Software Licenses in Cloud Data Centers
Статья научная
Since its emergence, cloud computing has continued to evolve thanks to its ability to present computing as consumable services paid by use, and the possibilities of resource scaling that it offers according to client’s needs. Models and appropriate schemes for resource scaling through consolidation service have been considerably investigated, mainly, at the infrastructure level to optimize costs and energy consumption. Consolidation efforts at the SaaS level remain very restrained mostly when proprietary software are in hand. In order to fill this gap and provide software licenses elastically regarding the economic and energy-aware considerations in the context of distributed cloud computing systems, this work deals with dynamic software consolidation in commercial cloud data centers 〖DS〗^3 C. Our solution is based on heuristic algorithms and allows reallocating software licenses at runtime by determining the optimal amount of resources required for their execution and freed unused machines. Simulation results showed the efficiency of our solution in terms of energy by 68.85% savings and costs by 80.01% savings. It allowed to free up to 75% physical machines and 76.5% virtual machines and proved its scalability in terms of average execution time while varying the number of software and the number of licenses alternately.
Бесплатно
Статья научная
Attention Deficit Hyperactive Disorder (ADHD) is a disruptive neurobehavioral disorder characterized by abnormal behavioral patterns in attention, perusing activity, acting impulsively and combined types. It is predominant among school going children and it is tricky to differentiate between an active and an ADHD child. Misdiagnosis and undiagnosed cases are very common. Behavior patterns are identified by the mentors in the academic environment who lack skills in screening those kids. Hence an unsupervised learning algorithm can cluster the behavioral patterns of children at school for diagnosis of ADHD. In this paper, we propose a hierarchical clustering algorithm to partition the dataset based on attribute dependency (HCAD). HCAD forms clusters of data based on the high dependent attributes and their equivalence relation. It is capable of handling large volumes of data with reasonably faster clustering than most of the existing algorithms. It can work on both labeled and unlabelled data sets. Experimental results reveal that this algorithm has higher accuracy in comparison to other algorithms. HCAD achieves 97% of cluster purity in diagnosing ADHD. Empirical analysis of application of HCAD on different data sets from UCI repository is provided.
Бесплатно
Статья научная
The Huge amount of Big Data is constantly arriving with the rapid development of business organizations and they are interested in extracting knowledgeable information from collected data. Frequent item mining of Big Data helps with business decision and to provide high quality service. The result of traditional frequent item set mining algorithm on Big Data is not an effective way which leads to high computation time. An Apache Hadoop MapReduce is the most popular data intensive distributed computing framework for large scale data applications such as data mining. In this paper, the author identifies the factors affecting on the performance of frequent item mining algorithm based on Hadoop MapReduce technology and proposed an approach for optimizing the performance of large scale frequent item set mining. The Experiments result shows the potential of the proposed approach. Performance is significantly optimized for large scale data mining in MapReduce technique. The author believes that it has a valuable contribution in the high performance computing of Big Data.
Бесплатно
Статья научная
Scheduling is the process of improving the performance of a parallel and distributed system. Parallel systems are part of distributed systems. Parallel systems refers to the concept of run parallel jobs that can be run simultaneously on several processors. Load balancing and scheduling are very important and complex problems in multiprocessor systems. So that problems are an NP-Complete problems. In this paper, we introduce a method based on genetic algorithms for scheduling and laod balancing in parallel heterogeneous multi-processor systems. The results of the simulations indicate Genetic algorithm for scheduling at in systems is better than LPT, SPT and FIFO. Simualation results indicate Genetic Algorithm reduce total response time and also it increase utilization.
Бесплатно
How do Machine Learning Algorithms Effectively Classify Toxic Comments? An Empirical Analysis
Статья научная
Toxic comments on social media platforms, news portals, and online forums are impolite, insulting, or unreasonable that usually make other users leave a conversation. Due to the significant number of comments, it is impractical to moderate them manually. Therefore, online service providers use the automatic detection of toxicity using Machine Learning (ML) algorithms. However, the model's toxicity identification performance relies on the best combination of classifier and feature extraction techniques. In this empirical study, we set up a comparison environment for toxic comment classification using 15 frequently used supervised ML classifiers with the four most prominent feature extraction schemes. We considered the publicly available Jigsaw dataset on toxic comments written by human users. We tested, analyzed and compared with every pair of investigated classifiers and finally reported a conclusion. We used the accuracy and area under the ROC curve as the evaluation metrics. We revealed that Logistic Regression and AdaBoost are the best toxic comment classifiers. The average accuracy of Logistic Regression and AdaBoost is 0.895 and 0.893, respectively, where both achieved the same area under the ROC curve score (i.e., 0.828). Therefore, the primary takeaway of this study is that the Logistic Regression and Adaboost leveraging BoW, TF-IDF, or Hashing features can perform sufficiently for toxic comment classification.
Бесплатно
Статья научная
Cloud computing has its characteristics along with some important issues that should be handled to improve the performance and increase the efficiency of the cloud platform. These issues are related to resources management, fault tolerance, and security. The purpose of this research is to handle the resource management problem, which is to allocate and schedule virtual machines of cloud computing in a way that help providers to reduce makespan time of tasks. In this paper, a hybrid algorithm for dynamic tasks scheduling over cloud's virtual machines is introduced. This hybrid algorithm merges the behaviors of three effective techniques from the swarm intelligence techniques that are used to find a near optimal solution to difficult combinatorial problems. It exploits the advantages of ant colony behavior, the behavior of particle swarm and honeybee foraging behavior. Experimental results reinforce the strength of the proposed hybrid algorithm. They also prove that the proposed hybrid algorithm is the best and outperformed ant colony optimization, particle swarm optimization, artificial bee colony and other known algorithms.
Бесплатно
Hybrid Approach to Pronominal Anaphora Resolution in English Newspaper Text
Статья научная
One of the challenges in natural language understanding is to determine which entities to be referred in the discourse and how they relate to each other. Anaphora resolution needs to be addressed in almost every application dealing with natural language such as language understanding and processing, dialogue system, system for machine translation, discourse modeling, information extraction. This paper represents a system that uses the combination of constraint-based and preferences-based architectures; each uses a different source of knowledge and proves effective on computational and theoretical basis, instead of using a monolithic architecture for anaphora resolution. This system identifies both inter-sentential and intra-sentential antecedents of “Third person pronoun anaphors” and “Pleonastic it”. This system uses Charniak Parser (parser05Aug16) as an associated tool, and it relays on the output generated by it. Salience measures derived from parse tree are used in order to find out accurate antecedents from the list of all potential antecedents. We have tested the system extensively on 'Reuters Newspaper corpus' and efficiency of the system is found to be 81.9%.
Бесплатно
Hybrid Black Hole Algorithm for Bi-Criteria Job Scheduling on Parallel Machines
Статья научная
Nature-inspired algorithms are recently being appreciated for solving complex optimization and engineering problems. Black hole algorithm is one of the recent nature-inspired algorithms that have obtained inspiration from black hole theory of universe. In this paper, four formulations of multi-objective black hole algorithm have been developed by using combination of weighted objectives, use of secondary storage for managing possible solutions and use of Genetic Algorithm (GA). These formulations are further applied for scheduling jobs on parallel machines while optimizing bi-criteria namely maximum tardiness and weighted flow time. It has been empirically verified that GA based multi-objective Black Hole algorithms leads to better results as compared to their counterparts. Also the use of combination of secondary storage and GA further improves the resulting job sequence. The proposed algorithms are further compared to some of the existing algorithms, and empirically found to be better. The results have been validated by numerical illustrations and statistical tests.
Бесплатно
Hybrid Clustering-Classification Neural Network in the Medical Diagnostics of the Reactive Arthritis
Статья научная
In the paper, the hybrid clustering-classification neural network is proposed. This network allows to increase a quality of information processing under the condition of overlapping classes due to the rational choice of learning rate parameter and introducing special procedure of fuzzy reasoning in the clustering-classification process, which occurs both with external learning signal ("supervised"), and without one ("unsupervised"). As similarity measure neighborhood function or membership one, cosine structures are used, which allow to provide a high flexibility due to self-learning-learning process and to provide some new useful properties. Many realized experiments have confirmed the efficiency of proposed hybrid clustering-classification neural network; also, this network was used for solving diagnostics task of reactive arthritis.
Бесплатно
Hybrid Deep Optimal Network for Recognizing Emotions Using Facial Expressions at Real Time
Статья научная
Recognition of emotions by utilizing facial expressions is the progression of determining the various human facial emotions to infer the mental condition of the person. This recognition structure has been employed in several fields but more commonly applied in medical arena to determine psychological health problems. In this research work, a new hybrid model is projected using deep learning to recognize and classify facial expressions into seven emotions. Primarily, the facial image data is obtained from the datasets and subjected to pre-processing using adaptive median filter (AMF). Then, the features are extracted and facial emotions are classified through the improved VGG16+Aquila_BiLSTM (iVABL) deep optimal network. The proposed iVABL model provides accuracy of 95.63%, 96.61% and 95.58% on KDEF, JAFFE and Facial Expression Research Group 2D Database (FERG-DB) which is higher when compared to DCNN, DBN, Inception-V3, R-152 and Convolutional Bi-LSTM models. The iVABL model also takes less time to recognize the emotion from the facial image compared to the existing models.
Бесплатно
Hybrid Flow Shop Scheduling Problem Using Artificial Immune System
Статья научная
Artificial immune system (AIS) is a new technique for solving combinatorial optimization problems. AIS are computational systems that explore, describe and apply different mechanisms inspired by biological immune system in order to solve problems in different domains. In this paper, we propose an algorithm based on the principle of clonal selection and affinity maturation mechanism in an immune response used to solve the Hybrid Flow Shop (FSH) scheduling problem. The parameters in this kind of algorithm play an important role in the quality of solutions in one hand and computer time (CPU) needed another hand. The experimental results have shown the influence of these parameters.
Бесплатно
Hybrid Intelligent Agent-Based Internal Analysis Architecture for CRM Strategy Planning
Статья научная
Nowadays attaining the general and comprehensive information about customers by means of traditional methods is difficult for CEO's because of the agility and complexity of organizations. So they spend a considerable time to gather and analyze the market data and consider it according to the organization's strategy. Presenting a useful architecture that capable to diagnose the organization's advantages and disadvantages, and identify the attainable competitive advantages are the main goals of this paper. The output of such architecture can be a general exhibition of company that prepares a clear and on time comprehensive view for CEO's.
Бесплатно
Hybrid Intelligent Routing in Wireless Mesh Networks: Soft Computing Based Approaches
Статья научная
Wireless Mesh Networks (WMNs) are the evolutionary self-organizing multi-hop wireless networks to promise last mile access. Due to the emergence of stochastically varying network environments, routing in WMNs is critically affected. In this paper, we first propose a fuzzy logic based hybrid performance metric comprising of link and node parameters. This Integrated Link Cost (ILC) is computed for each link based upon throughput, delay, jitter of the link and residual energy of the node and is used to compute shortest path between a given source-terminal node pair. Further to address the optimal routing path selection, two soft computing based approaches are proposed and analyzed along with a conventional approach. Extensive simulations are performed for various architectures of WMNs with varying network conditions. It was observed that the proposed approaches are far superior in dealing with dynamic nature of WMNs as compared to Adhoc On-demand Distance Vector (AODV) algorithm.
Бесплатно
Hybrid Method for the Navigation of Mobile Robot Using Fuzzy Logic and Spiking Neural Networks
Статья научная
The aim of this paper is to present a strategy describing a hybrid approach for the navigation of a mobile robot in a partially known environment. The main idea is to combine between fuzzy logic approach suitable for the navigation in an unknown environment and spiking neural networks approach for solving the problem of navigation in a known environment. In the literature, many approaches exist for the navigation purpose, for solving separately the problem in both situations. Our idea is based on the fact that we consider a mixed environment, and try to exploit the known environment parts for improving the path and time of navigation between the starting point and the target. The Simulation results, which are shown on two simulated scenarios, indicate that the hybridization improves the performance of robot navigation with regard to path length and the time of navigation.
Бесплатно
Hybrid Multi-Objective Particle Swarm Optimization for Flexible Job Shop Scheduling Problem
Статья научная
Hybrid algorithm based on Particle Swarm Optimization (PSO) and Simulated annealing (SA) is proposed, to solve Flexible Job Shop Scheduling with five objectives to be minimized simultaneously: makespan, maximal machine workload, total workload, machine idle time & total tardiness. Rescheduling strategy used to shuffle workload once the machine breakdown takes place in proposed algorithm. The hybrid algorithm combines the high global search efficiency of PSO with the powerful ability to avoid being trapped in local minimum of SA. A hybrid multi-objective PSO (MPSO) and SA algorithm is proposed to identify an approximation of the pareto front for Flexible job shop scheduling (FJSSP). Pareto front and crowding distance is used for identify the fitness of particle. MPSO is significant to global search and SA used to local search. The proposed MPSO algorithm is experimentally applied on two benchmark data set. The result shows that the proposed algorithm is better in term quality of non-dominated solution compared to the other algorithms in the literature.
Бесплатно
