Evolving spiking neural networks for personalised modelling, classification and prediction of spatio-temporal patterns with a case study on stroke

Kasabov, Nikola; Feigin, Valery L.; Hou, Zeng-Guang; Chen, Yixiong; Liang, Linda; Krishnamurthi, Rita; Othman, Muhaini; Parmar, Priya

doi:10.1016/j.neucom.2013.09.049

Cited by 131 publications

(78 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Five features were considered for obtaining the disease prediction using the three methods RS-RMC, PPM-VA and PE-SSTD respectively. From the figure, the value of disease prediction rate achieved using the proposed RS-RMC framework is higher when compared to two other existing techniques namely, PPM-VA [1] and PE-SSTD [2]. Besides we can also observe that by increasing the number of patients who provide their disease features, the disease prediction rate is increased using all the methods.…”

Section: Disease Prediction Ratementioning

confidence: 78%

“…The RS-RMC framework is simulated using MATLAB. The experimental work is compared against the existing Prevention and Potential Management of Ventricular Arrhythmias (PPM-VA) [1] and Prediction of Events using Spatio Spectro Temporal Data (PE-SSTD) [2] to identify the effectiveness of RS-RMC framework. The performance of the RS-RMC framework is measured in terms of disease prediction rate, execution time and false positive rate on effective disease diagnosis and class accuracy.…”

Section: Experimental Settingsmentioning

confidence: 99%

“…Prediction of Events using Spatio Spectro Temporal Data (PE-SSTD) [2] provided with a case study on stroke resulting in the accuracy of the disease being diagnosed. However, both the above methods lack the class accuracy of disease diagnosis with the increase in the feature.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multitude Classifier Using Rough Set Jelinek Mercer Naïve Bayes for Disease Diagnosis

Prema¹,

Maheswari²

2016

View full text Add to dashboard Cite

Classification model has received great attention in any domain of research and also a reliable tool for medical disease diagnosis. The domain of classification model is used in disease diagnosis, disease prediction, bio informatics, crime prediction and so on. However, an efficient disease diagnosis model was compromised the disease prediction. In this paper, a Rough Set Rule-based Multitude Classifier (RS-RMC) is developed to improve the disease prediction rate and enhance the class accuracy of disease being diagnosed. The RS-RMC involves two steps. Initially, a Rough Set model is used for Feature Selection aiming at minimizing the execution time for obtaining the disease feature set. A Multitude Classifier model is presented in second step for detection of heart disease and for efficient classification. The Naïve Bayes Classifier algorithm is designed for efficient identification of classes to measure the relationship between disease features and improving disease prediction rate. Experimental analysis shows that RS-RMC is used to reduce the execution time for extracting the disease feature with minimum false positive rate compared to the state-ofthe-art works.

show abstract

Section: Disease Prediction Ratementioning

confidence: 78%

Section: Experimental Settingsmentioning

confidence: 99%

See 1 more Smart Citation

Multitude Classifier Using Rough Set Jelinek Mercer Naïve Bayes for Disease Diagnosis

Prema¹,

Maheswari²

2016

View full text Add to dashboard Cite

show abstract

“…Thus, mHealth technology is an alternative for cost effective health support. The review of this study also discover that mHealth researchers and publishers have focused more on individual prevention diseases (Table 1) such as selfmanagement for diabetes [14,15], gout [16], chronic obstructive pulmonary disease [17], bipolar disorders [18] and bowel disease [19], stroke [20,21] heart disease [22] and flu [23]. Article [23] presented HHeal, an app which integrates flu risk information and flu preventive behaviors, which provide a personal flu risk bar that arises when a user is near someone with flu-like symptoms and drops when the user finishes one of the suggested flu-preventive behaviors.…”

Section: Trends Of Mhealth Appsmentioning

confidence: 84%

A Survey on Trend, Opportunities and Challenges of mHealth Apps

Jusoh

2017

Int. J. Interact. Mob. Technol.

View full text Add to dashboard Cite

Abstract-Advancement of mobile technologies such as smartphones and PC tablets has given a great impact on healthcare systems. The mobile technology offers innovative approaches to addressing complex health concerns. Many mobile health applications (mHealth apps) are currently available on marketplaces. These apps are designed to facilitate various health issues and problems, and are intended to be used outside clinics. However, very little research has been conducted to address trend, opportunities, and challenging issues of the apps. The purpose of this study is to investigate the current state of mHealth. A literature survey was conducted. Major findings of this study include, smartphones will be the major platform for mHealth apps, the number of published software is much higher than published scientific research, current mHealth apps lacking in grounded based theory and evaluation, and security and usability issues are still vulnerable. The findings suggest that involvement of all healthcare stakeholders is critical to the success of mHealth apps.Keywords-mHealth apps; mobile computing; smartphoness IntroductionMobile technology has changed and will continue to change the life of millions of people around the globe. It is a technology which allows a computing device not to be connected to any fixed physical link. Examples of mobile computing devices are smartphones, laptops, tablets, e-book readers, cameras, and so on; the most powerful and attractive one is smartphones. It incorporates all aspects of computing application and wireless communications.Nearly 85% of the world population will have access to 3G wireless coverage, with the half of the population living in areas with 4G networks in year 2017 [1]. The growth of smartphones has far-reaching implications for eHealth [2]. The word eHealth was defined in [3] as "a relation to health services delivery such as healthcare, health system, health sector or health industry which suggests that eHealth refer more to services and systems rather than to the health of people". Smartphones have become a common device in healthcare settings; leading to rapid growth in the development of mHealth apps [4].

show abstract

“…The learning of ESNN has many good advantages as it can be applied incrementally, is adaptive and theoretically 'lifelong'. Therefore, the system can learn any new pattern via creating new output neurons, connecting them to the input neurons and merging with the similar ones [25][26][27]. This model stands on two principles: possibility of establishment of new classes and the merging of the similarities.…”

mentioning

confidence: 99%

Memetic Harmony Search Algorithm Based on Multi-objective Differ-ential Evolution of Evolving Spiking Neural Networks

Saleh¹,

Shamsuddin²

2015

Int J Swarm Intel Evol Comput

View full text Add to dashboard Cite

Spiking neural network (SNN) plays an essential role in classification problems. Although there are many models of SNN, Evolving Spiking Neural Network (ESNN) is widely used in many recent research works. Evolutionary algorithms, mainly differential evolution (DE) have been used for enhancing ESNN algorithm. However, many realworld optimization problems include several contradictory objectives. Rather than single optimization, Multi-Objective Optimization (MOO) can be utilized as a set of optimal solutions to solve these problems. In this paper, Harmony Search (HS) and memetic approach was used to improve the performance of MOO with ESNN. Consequently, Memetic Harmony Search Multi-Objective Differential Evolution with Evolving Spiking Neural Network (MEHSMODE-ESNN) was applied to improve ESNN structure and accuracy rates. Standard data sets from the UCI machine learning are used for evaluating the performance of this enhanced multi objective hybrid model. The experimental results have proved that the Memetic Harmony Search Multi-Objective Differential Evolution with Evolving Spiking Neural Network (MEHSMODE-ESNN) gives better results in terms of accuracy and network structure. Unlike previous study mentioned earlier in Jin [14] and other single objective studies [18,19], this paper deals with an improved multi objective method to obtain simple and accurate ESNN. The proposed method evolves toward optimal values defined by several objectives with model accuracy and ESNN's structure to improve performance for classification problems. The remaining parts of this paper are organized as follows: Methods including: Evolving Spiking Neural Network, Multi Objective Differential Evolution are presented in section 2. In addition, section 3 clarifies the proposed method Memetic Harmony Search Multi-Objective Differential Evolution with Evolving Spiking Neural Network (MEHSMODE-ESNN) used in this paper, Experimental design is discussed in section 4, section 5 explains in detail the results and discussion, and finally, section 6 concludes the paper with future works. MethodsThis section reviews the vital foundation of evolving spiking neural network (ESNN) and discusses the evolutionary algorithms that have been utilized for enhancement. In the first part, an introduction of ESNN, neuron coding, learning method and ESNN design, and its algorithm is presented. The second part focuses on the algorithms which are used for improvement of ESNN. The concepts and methods of multi objective optimization (MOO) are highlighted. After that, the literature focuses on the working of differential evolution, harmony search (HS) algorithm and memetic approach which is used to improve and enhance the performance of classification . Evolving spiking neural network (ESNN)Currently, several enhancements of SNN have been proposed. Wysoski improved one of these new models known as Evolving Spiking Neural Network (ESNN) [20]. Generally, ESNN used the principles of evolving connectionist systems (ECOS) where neurons are created incrementall...

show abstract

Evolving spiking neural networks for personalised modelling, classification and prediction of spatio-temporal patterns with a case study on stroke

Cited by 131 publications

References 33 publications

Multitude Classifier Using Rough Set Jelinek Mercer Naïve Bayes for Disease Diagnosis

Multitude Classifier Using Rough Set Jelinek Mercer Naïve Bayes for Disease Diagnosis

A Survey on Trend, Opportunities and Challenges of mHealth Apps

Memetic Harmony Search Algorithm Based on Multi-objective Differ-ential Evolution of Evolving Spiking Neural Networks

Contact Info

Product

Resources

About

Evolving spiking neural networks for personalised modelling, classification and prediction of spatio-temporal patterns with a case study on stroke

Cited by 131 publications

References 33 publications

Multitude Classifier Using Rough Set Jelinek Mercer Na&#239;ve Bayes for Disease Diagnosis

Multitude Classifier Using Rough Set Jelinek Mercer Na&#239;ve Bayes for Disease Diagnosis

A Survey on Trend, Opportunities and Challenges of mHealth Apps

Memetic Harmony Search Algorithm Based on Multi-objective Differ-ential Evolution of Evolving Spiking Neural Networks

Contact Info

Product

Resources

About

Multitude Classifier Using Rough Set Jelinek Mercer Naïve Bayes for Disease Diagnosis

Multitude Classifier Using Rough Set Jelinek Mercer Naïve Bayes for Disease Diagnosis