ECG heart beat classification method based on modified ABC algorithm

Electrocardiogram is the most commonly used tool for the diagnosis of cardiologic diseases. In order to help cardiologists to diagnose the arrhythmias automatically, new methods for automated, computer aided ECG analysis are being developed. In this paper, a Modified Artificial Bee Colony (MABC) algorithm for ECG heart beat classification is introduced. It is applied to ECG data set which is obtained from MITBIH database and the result of MABC is compared with seventeen other classifier's accuracy.In classification problem, some features have higher distinctiveness than others. In this study, in order to find higher distinctive features, a detailed analysis has been done on time domain features. By using the right features in MABC algorithm, high classification success rate (99.30%) is obtained. Other methods generally have high classification accuracy on examined data set, but they have relatively low or even poor sensitivities for some beat types. Different data sets, unbalanced sample numbers in different classes have effect on classification result. When a balanced data set is used, MABC provided the best result as 97.96% among all classifiers.Not only part of the records from examined MITBIH database, but also all data from selected records are used to be able to use developed algorithm on a real time system in the future by using additional software modules and making adaptation on a specific hardware.     

Safety-based availability assessment at design stage

The availability of a system or equipment is one of the crucial characteristics that measures the customer satisfaction and strongly influences his final choice decision between concurrent products. The aim of this work is to provide an approach to improve the products availability assessment by taking into account the safety criteria by considering the use situations at design stage. Our work focuses on the routine design of complex products. The availability is often simply estimated considering reliability and maintainability. Basically, the intrinsic availability is the probability that it is operating satisfactorily at any point in time when used under conditions stated by design specifications. The time considered includes operating time and active repair time. Thus, intrinsic availability excludes from consideration all other times in the product lifecycle such as: accident management time, storage time, administrative time or logistic time. But many studies show that the loss of availability performance is also due to accidents that occur in different unforeseeable utilization situations. This engenders stops of the system to ensure the users safety according to standards recommendations. In this purpose, we consider the structural product architecture and the different use cases that correspond to the operational states and downtimes due to stop events that may happen during the utilization like failures, maintenance tasks and accidents. Then, we propose a product behavioral analysis including the use cases to describe interactions between the product and users or maintenance operators. We use Markov chains to model the use cases corresponding to operating time (OT), maintenance time (MT) and preparing time after accidents (RT). Then these three parameters are considered to specify a generic approach to improve the availability assessment. Such an approach provides the traceability of the product behavior along its lifecycle. In this way, the main causes of stop can be identified and this may guide the designer for improving the availability of the product future versions. To validate our approach, an application is presented considering a printing line. The comparison of our simulation considering an industrial case study shows a good agreement about the influence of safety on the availability.     

Correlation between crystallization kinetics and melt phase behavior of crystalline-amorphous block copolymer/homopolymer blends

We show that the phase behavior of the strongly segregated blend consisting of a crystalline-amorphous diblock copolymer (C-b-A) and an amorphous homopolymer (h-A), which depends on the degree of wetting of A blocks by h-A, can be probed by the crystallization kinetics of the C block. A lamellae-forming poly(ethylene oxide)-block-polybutadiene (PEO-b-PB) was blended with PB homopolymers (h-PB) of different molecular weights to yield the blends exhibiting ‘wet brush’, ‘partially dry brush’, and ‘dry brush’ phase behavior in the melt state. The crystallization rate of the PEO blocks upon subsequent cooling, as manifested by the freezing (crystallization) temperature (T_f), was highly sensitive to the morphology and spatial connectivity of the microdomains governed by the degree of wetting of PB blocks. As the weight fraction of h-PB reached 0.48, for instance, T_f experienced an abrupt rise as the system entered from the wet-brush to the dry-brush regime, because the crystallization in the PEO cylindrical domains in the former required very large undercooling due to a homogeneous nucleation-controlled mechanism while the process could occur at the normal undercooling in the latter since PEO domains retained lamellar identity with extended spatial connectivity. Our results demonstrate that as long as the C block is present as the minor constituent the melt phase behavior of C-b-A/h-A blends can also be probed using a simple cooling experiment operated under differential scanning calorimetry (DSC).     

An efficient algorithm for incrementally mining frequent closed itemsets

The purpose of mining frequent itemsets is to identify the items in groups that always appear together and exceed the user-specified threshold of a transaction database. However, numerous frequent itemsets may exist in a transaction database, hindering decision making. Recently, the mining of frequent closed itemsets has become a major research issue because sets of frequent closed itemsets are condensed yet complete representations of frequent itemsets. Therefore, all frequent itemsets can be derived from a group of frequent closed itemsets. Nonetheless, the number of transactions in a transaction database can increase rapidly in a short time period, and a number of the transactions may be outdated. Thus, frequent closed itemsets may be changed with the addition of new transactions or the deletion of old transactions from the transaction database. Updating previously closed itemsets when transactions are added or removed from the transaction database is challenging. This study proposes an efficient algorithm for incrementally mining frequent closed itemsets without scanning the original database. The proposed algorithm updates closed itemsets by performing several operations on the previously closed itemsets and added/deleted transactions without searching the previously closed itemsets. The experimental results show that the proposed algorithm significantly outperforms previous methods, which require a substantial length of time to search previously closed itemsets.     

Synthesis of biodegradable poly(trans-4-hydroxy-N-benzyloxycarbonyl-l-proline)-block-poly(ε-caprolactone) copolymers and micellar characterizations

A series of novel types of diblock poly(trans-4-hydroxy-N-benzyloxycarbonyl-l-proline)-block-poly(ε-caprolactone) (PHpr10-b-PCL) copolymers were synthesized by ring-opening polymerization from macroinitiator poly(trans-4-hydroxy-N-benzyloxycarbonyl-l-proline) (PHpr10) and ε-caprolactone (ε-CL) in the presence of organocatalyst dl-lactic acid (dl-LA). The M_n of the copolymers increased from 3370 to 19,040 g mol⁻¹ with the molar ratio (10-100) of ε-CL to PHpr10. These products were characterized by differential scanning calorimetry (DSC), ¹H NMR, and gel permeation chromatography. According to DSC, the glass-transition temperature (T_g) of the diblock copolymers depend on the molar ratio of monomer/initiator that were added. The hydrolytic degradation behavior of PHpr-b-PCLs was evaluated from weight-loss measurements and the change of M_n and M_w/M_n. With higher PCL contents resulted in a slower weight loss, while having a higher molecular weight loss percentage. Their micellar characteristics in an aqueous phase were investigated by fluorescence spectroscopy, transmission electron microscopy (TEM), and dynamic light scattering (DLS). The block copolymers formed micelles in the aqueous phase with critical micelle concentrations (CMCs) in the range of 1.33-4.22 mg L⁻¹. The micelles exhibited a spindly shape and showed a narrow monodisperse size distribution. The obtained micelles have a relatively high drug-loading of about 26% when the feed weight ratio of amitriptyline hydrochloride (AM) to polymer was 1/1. An increase of molecular weight and hydrophobic components in copolymers produced a higher CMC value and greater loading efficiencies were observed.     

Optimal design of adaptive type-2 neuro-fuzzy systems: A review

Type-2 fuzzy logic systems have extensively been applied to various engineering problems, e.g. identification, prediction, control, pattern recognition, etc. in the past two decades, and the results were promising especially in the presence of significant uncertainties in the system. In the design of type-2 fuzzy logic systems, the early applications were realized in a way that both the antecedent and consequent parameters were chosen by the designer with perhaps some inputs from some experts. Since 2000s, a huge number of papers have been published which are based on the adaptation of the parameters of type-2 fuzzy logic systems using the training data either online or offline. Consequently, the major challenge was to design these systems in an optimal way in terms of their optimal structure and their corresponding optimal parameter update rules. In this review, the state of the art of the three major classes of optimization methods are investigated: derivative-based (computational approaches), derivative-free (heuristic methods) and hybrid methods which are the fusion of both the derivative-free and derivative-based methods.     

Solving the team orienteering problem using effective multi-start simulated annealing

The team orienteering problem (TOP) is known as an NP-complete problem. A set of locations is provided and a score is collected from the visit to each location. The objective is to maximize the total score given a fixed time limit for each available tour. Given the computational complexity of this problem, a multi-start simulated annealing (MSA) algorithm which combines a simulated annealing (SA) based meta-heuristic with a multi-start hill climbing strategy is proposed to solve TOP. To verify the developed MSA algorithm, computational experiments are performed on well-known benchmark problems involving numbers of locations ranging between 42 and 102. The experimental results demonstrate that the multi-start hill climbing strategy can significantly improve the performance of the traditional single-start SA. Meanwhile, the proposed MSA algorithm is highly effective compared to the state-of-the-art meta-heuristics on the same benchmark instances. The proposed MSA algorithm obtained 135 best solutions to the 157 benchmark problems, including five new best solutions. In terms of both solution quality and computational expense, this study successfully constructs a high-performance method for solving this challenging problem.     

On discovery of soft associations with “most” fuzzy quantifier for item promotion applications

In item promotion applications, there is a strong need for tools that can help to unlock the hidden profit within each individual customer’s transaction history. Discovering association patterns based on the data mining technique is helpful for this purpose. However, the conventional association mining approach, while generating “strong” association rules, cannot detect potential profit-building opportunities that can be exposed by “soft” association rules, which recommend items with looser but significant enough associations. This paper proposes a novel mining method that automatically detects hidden profit-building opportunities through discovering soft associations among items from historical transactions. Specifically, this paper proposes a relaxation method of association mining with a new support measurement, called soft support, that can be used for mining soft association patterns expressed with the “most” fuzzy quantifier. In addition, a novel measure for validating the soft-associated rules is proposed based on the estimated possibility of a conditioned quantified fuzzy event. The new measure is shown to be effective by comparison with several existing measures. A new association mining algorithm based on modification of the FT-Tree algorithm is proposed to accommodate this new support measure. Finally, the mining algorithm is applied to several data sets to investigate its effectiveness in finding soft patterns and content recommendation.     

A weighted string pattern matching-based passage ranking algorithm for video question answering

Video question answering aims to pinpoint answers in response to user’s specified questions. However, most question answering technologies involve in integrating rich specific external knowledge such as syntactic parsers, which are often unavailable for many languages. In this paper, we present a new string pattern matching-based passage ranking algorithm for extending traditional text Q/A toward videoQ/A. Users interact with our videoQ/A system through natural language questions whereas our system returns three sentence-length passages with corresponding video clips as answers. We collect 45 GB Discovery videos and 253 Chinese questions for evaluation. The experimental results showed that our method outperformed six top-performed ranking models. It is 7.39% better than the second best method (language model-based) in relatively MRR score and 6.12% in precision rate. Besides, we also show that the use of a trained Chinese word segmentation tool did decrease the overall videoQ/A performance where most ranking algorithms dropped at least 10% in relatively MRR, precision, and answer pattern recall rates.