Review on Heart Sound Wavelet Neural Network Applications

Abstract

An investigation of Heart sound is an important technique for cardiovascular assessment that contains physiological and obsessional information of various components of the guts and collaborations between them. This paper expects to arrange a framework for dissecting heart sounds as well as programmed investigation and arrangement. With the elements separated by moving ridge decay and Normalized Average applied scientist Energy, a completely unique soft neural system strategy with structure learning is projected for the guts sound characterization. Explores completely different avenues concerning real info exhibited that our methodology will effectively prepare all the tried heart sounds not withstanding for those with past inconspicuous heart ailments.

Keywords

Heart sounds, Energy, Neural network

Introduction

Cardiac diagnostic procedure is wide utilized by physicians to gauge internal organ functions in patients and sight presence of abnormalities. It’s but a troublesome ability to amass. Nowadays signals made by the center don't seem to be solely detected employing a medical instrument however additionally discovered as phonocardiograms on monitor screen. Several pathological conditions that cause murmurs and aberrations of HSs manifest abundant earlier in phonocardiography than area unit mirrored by symptoms.

Processing of Heart Sound Signals

It describes the assorted stages concerned within the analysis of heart sounds and separate riffle rework as a most popular methodology for bio-signal process [1-5]. Therefore additionally, the gaps that also exist between up to date strategies analysis of heart sounds and applications of heart sounds applications for clinical diagnosing are reviewed. Plenty of progress has been created however crucial gaps still exist. There's a scarcity of accord in analysis outputs; inter-patient ability of signal process rule continues to be problematic [6-14]; the method of clinical validation of study techniques wasn't sufficiently rigorous in most of the reviewed literature; and in and of itself knowledge integrity and mensuration area unit still unsure, that most of the time diode to inaccurate interpretation of results [15-19]. The heart sound signal or PCG signal of a traditional heart is comprised of 2 distinct activities particularly the primary heart sound, S1 and also the second heart sound, S2. These correspond to the traditional heart sounds of lup and dup, severally. Within the case of AN abnormal heart, there can be many alternative signal activities between initial and second sounds [20-26].

Auscultation and phonocardiography not solely give necessary clinical data but are easy to use and price effective. PCG is also a superb tool for diagnostic procedure coaching and helps within the understanding of the hemodynamics of the heart. In developing countries, wherever some medical facilities are still thought of a luxury, this cost-effective approach of providing treatment would improve the lifetime of patients with controller pathologies [27-30].

Heart sounds of seventeen ancient and nineteen abnormal sound waves are divided pattern Empirical Mode Decomposition (EMD) supported kurtosis. S1, S2, pulse and heartbeat murmurs are divided. These segments are given to back propagation artificial neural network (ANN) [31-35]. altogether completely different neural networks used for S1, pulse murmurs and heartbeat murmurs then additive results of these network are used for characteristic heart valve diseases. Neural networks architectures are altogether completely different for S1, pulse and heartbeat murmurs [36-42].

Neural Network

For Statistical analysis and data modeling neural networks are often used [43-49]. Neural networks are typically used for the consequences includes couched in terms of classification, or forecasting.

A neural network is associate interconnected assembly of easy process components, units or nodes, whose practicality is loosely, supported the animal vegetative cell. The process ability of the network is hold on within the inter unit affiliation strengths, or weights, obtained by a method of adaptation to, or learning from, a group of training patterns [50-58].

Neural Networks are widely used in many applications

Applications of Neural Network

Following are the applications used in Neural Networks

1. Character Recognition

2. Image Compression

3. Stock Market Prediction

4. Traveling Salesman’s Problem

5. Medicine, Electronic Nose, Security, and Loan Applications

6. Miscellaneous Applications

Neural network simulations seem to be a recent development. However, this field was established before the appearance of computers, and has survived a minimum of one major blow and a number of other eras [59-66].

There are many important advances which are boosted by the utilization of cheap pc emulations. Following associate initial amount of enthusiasm, the sector survived an amount of frustration and dishonor [67-74]. Throughout this era once funding and skilled support was negligible, necessary advances were created by comparatively few researchers [75-87]. The printed book of Minsky and Papert, during which they summed up a general feeling of frustration (against neural networks) among researchers, and was therefore, accepted by most while not more analysis. Currently, the neural network field enjoys a betterment of interest and a corresponding increase in funding [88-99].

Conclusion

Neural networks are the area unit appropriate for predicting statistic principal attributable to learning solely from examples, with none has to be compelled to add extra data that may bring additional confusion than prediction impact. Neural networks area unit able to generalize and area unit immune to noise. On the opposite hand, it's typically attainable | impossible | uphill | inconceivable | unimaginable| insufferable | out of the question | unacceptable | impracticable | unattainable | unfeasible | impractical} to work out specifically what a neural network learned and it's additionally laborious to estimate possible prediction error.

References

1. Tikoo S and Malik N. Detection, Segmentation and Recognition of Face and its Features Using Neural Network. J Biosens Bioelectron. 2016;7:210.
2. Tamal M et al. Study Of Dairy Industry Wastewater Using Synthesised Hydroxyapatite Nanoparticles: Thermally Activated Nanoparticles, Treatment Efficiency, Isotherm, Thermodynamics, Kinetics Modelling And Optimization Using Artificial Neural Network Modelling. ICP. 2016.
3. Zribi M and Boujelbene Y. The Neural Networks with an Incremental Learning Algorithm Approach for Mass Classification in Breast Cancer. Biomedical Data Mining. 2016.
4. Werner FM and Coveñas R. Efficacy of the Deep-Brain Stimulation in Parkinsons Disease According to a Neural Network. J Cytol Histol. 2016.
5. Maduako ID, Yun Z, Patrick B (2016) Simulation and Prediction of Land Surface Temperature (LST) Dynamics within Ikom City in Nigeria Using Artificial Neural Network (ANN). J Remote Sensing & GIS 5: 158 doi: 10.4172/2469-4134.1000158
6. Abdulrazak YS et al. Memetic Harmony Search Algorithm Based on Multi-objective Differ-ential Evolution of Evolving Spiking Neural Networks. Int J Swarm Intel Evol Comput. 2016.
7. Duraid FA and Ali HK. Artificial Neural Networks Controller for Crude Oil Distillation Column of Baiji Refinery. J Chem Eng Process Technol. 2016;7:272.
8. Felix-Martin W and Rafael C. Additional Antidepressant Pharmacotherapies According to a Neural Network. Brain Disord Ther. 2016;5:203.
9. Raji CG and Vinod CSS. Artificial Neural Networks in Prediction of Patient Survival after Liver Transplantation. J Health Med Informat. 2016;7: 215.
10. Zhiqiang Y et al. Comparing RMB Exchange Rate Forecasting Accuracy based on Dynamic BP Neural Network Model and the ARMA Model. J Stock Forex Trad. 2016;5:161.
11. Felix-Martin W and Rafael C. Symptoms and Therapeutic Options of the Anti-NMDA Receptor Encephalitis According To a Neural Network. Anat Physiol. 2016;1:e136.
12. Viju R. A Neural Network Analysis of Treatment Quality and Efficiency of Hospitals. J Health Med Informat. 2015;6:209.
13. Kuldip P et al. A Short Review of Deep Learning Neural Networks in Protein Structure Prediction Problems. Adv Tech Biol Med. 2015;3:139.
14. Babita P. Online Signature Recognition Using Neural Network. J Elec Electron Syst 2014;4:155.
15. Babu AS and Reddy SK. Exchange Rate Forecasting using ARIMA, Neural Network and Fuzzy Neuron. J Stock Forex Trad. 2015;4:155.
16. Felix-Martin W and Rafael C. Treatment of Bipolar Disorder according to a Neural Network. J Cytol Histol. 2015;6:368.
17. Abou-Nassif GA. Predicting the Tensile and Air Permeability Properties of Woven Fabrics Using Artificial Neural Network and Linear Regression Models. J Textile Sci Eng. 2015;5:209.
18. Yusif MH et al. Inflation Forecasting in Ghana-Artificial Neural Network Model Approach. Int J Econ Manag Sci. 2015;4:274.
19. Taghipour M et al. Application of Artificial Neural Network for Modeling and Prediction of MTT Assay on Human Lung Epithelial Cancer Cell Lines. J Biosens Bioelectron. 2015;6:170.
20. Lohani AK and Krishan G. Groundwater Level Simulation Using Artificial Neural Network in Southeast, Punjab, India. J Geol Geophys. 2015;4:206.
21. García I and Prado-Prado F. State of Art: Review of Theoretical Study of GSK-3β and a New Neural Networks QSAR Studies for the Design of New Inhibitors Using 2D-Descriptors. Biochem Pharmacol (Los Angel). 2015;4:170.
22. Agatonovic-Kustrin S and David WM. The Use of Probabilistic Neural Network and UV Reflectance Spectroscopy as an Objective Cultured Pearl Quality Grading Method. Mod Chem Appl. 2015;3:152.
23. Lohani AK and Krishan G. Application of Artificial Neural Network for Groundwater Level Simulation in Amritsar and Gurdaspur Districts of Punjab, India. J Earth Sci Clim Change. 2015;6:274.
24. Balasubramonian M and Dharani S. Design and Implementation of SHE PWM in a Single Phase A.C.Chopper Using Generalized Hopfield Neural Network. IJIRSET.
25. Pushpa N et al. Speech Processing Of Tamil Language With Back Propagation Neural Network And Semi- Supervised Traning. IJIRCCE.
26. Murugan ASS and Muthurakesh D. Harmonics Impedance Measurement Using Neural Network. IJIRSET.
27. Rajalakshmi M. Recurrent Neural Network Identification: Comparative Study on Nonlinear Process. IJIRSET. 2014.
28. Dhongde VS et al. IRIS Recognition Using Neural Network. IJIRSET. 2014.
29. Lokhande SK and Dhongde VS. Fingerprint Identification System Based On Neural Network. IJIRSET.
30. Fayrouz D and Benyounes O. Neural Network Training By Gradient Descent Algorithms: Application on the Solar Cell. IJIRSET. 2014.
31. Sanjib KH. Artificial Neural Network and Efficiency Estimation in Rice Yield. IJIRSET. 2014.
32. Shilpi R and Falguni P. Predicting Reservoir Water Level Using Artificial Neural Network. IJIRSET. 2014.
33. Amaury de S et al. Modeling of Surface and Weather Effects Ozone Concentration Using Neural Networks in West Center of Brazil. J Climatol Weather Forecasting. 2015;3:123.
34. Mayankkumar BP and Sunil RY. Stock Price Prediction Using Artificial Neural Network. IJIRSET. 2014.
35. Baljit K and Vijay D. Neural Network Based New Algorithm for Noise Removal and Edge Detection: A Survey. IJIRSET. 2013.
36. Priyank J and Jayesh G. Online Signature Verification Using Energy, Angle and Directional Gradient Feature With Neural Network. IJIRSET. 2013.
37. Florence S et al. Predicting the Risk of Heart Attacks using Neural Network and Decision Tree. IJIRCCE. 2014.
38. Anicham S and Murukesh C. An Efficient Iris Recognition System Using Contourlet Transform and Neural Networks. IJIRSET. 2014.
39. Sanjivani B and Ranjan R. Parkinson Diagnosis using Neural Network: a Survey. IJIRSET. 2013.
40. Noori PSB and Devaki SR. Development of an Artificial Neural Network Model to Predict the Properties of Alpha and Near Alpha Titanium Alloys as a Function of Their Composition. IJIRSET. 2014.
41. Priyanka D and Parsai MP. A MATLAB based Face Recognition using PCA with Back Propagation Neural network. IJIRCCE. 2014.
42. Anu A and Paulchamy B. Detection of Breast Cancer Using Artificial Neural Networks. IJIRSET. 2014.
43. Nilesh P and Lalit B. Neural Networks Based Approach for Machining and Geometric Parameters optimization of a CNC End Milling. IJIRSET. 2014.
44. Nikhil C and Debbie F. Automatic Melanoma Detection Using Multi- Stage Neural Networks. IJIRSET. 2014.
45. Navneet K and Ramanpreet K. Channel Estimation Using DFT Based Automoly Classifying Neural Network. IJIRCCE. 2014.
46. Sudeshana P et al. Modeling of ambient for Rspm and Spm Pollutants through artifical neural network in sensitive area of ujjain city. ICP. 2014.
47. Priyanka Y et al. Modeling of ambient for sox and nox pollutants through artifical neural network in industrial area of ujjain city. ICP. 2014.
48. Parul C and Hardeep SR. Neural Network Based Static Sign Gesture Recognition System. IJIRCCE. 2014.
49. Ajay SR et al. Operation Sequencing in CAPP by using Artificial Neural Network. IJIRSET. 2013.
50. Nasira GM and Banumathi P. Automatic Defect Detection Algorithm for Woven Fabric using Artificial Neural Network Techniques. IJIRCCE. 2014.
51. Srinivas N et al. Identification of Cardiac Arrhythmia with respect to ECG Signal by Neural Networks and Genetic Programming. IJIRSET. 2013.
52. Dighe MS et al. Using Artificial Neural Network Classification and Invention of Intrusion in Network Intrusion Detection System. IJIRCCE. 2015.
53. Angel M and Preethy PT. Fuzzy Clustering For Speaker Identification – MFCC + Neural Network. IJAREEIE. 2014.
54. Ramesh BVS and Girija PN. Duration Modeling For Telugu Language with Recurrent Neural Network. IJIRCCE. 2015.
55. Rachana PB and Suvarna KG. Frequency Offset Compensation In OFDM System Using Neural Network. IJAREEIE. 2014.
56. Prerna K and Umesh D. A Novel Approach to Recognition of English Characters Using Artificial Neural Network. IJAREEIE. 2014.
57. Gauri B and Ranjana R. Support Vector Machine Neural Network Based Optimal Binary Classifier for Diabetic Retinopathy. A Social Collaboration Platform for Schools. 2015.
58. Aqhsa QS and Narayanan K. Detection of Tumor in MRI Images Using Artificial Neural Networks. IJAREEIE. 2014.
59. Hartaranjit S et al. A Novel Neural Network Based Edge Detector for Non-Synthetic and Medical Images. IJAREEIE. 2014.
60. Nageswara RK et al. Secondary Structure Prediction of proteins causing Diabetic Foot Ulcers using Artificial Neural Networks. IJIRCCE. 2013.
61. Gaetano L. Are Neural Networks Imitations of Mind?. J Comput Sci Syst Biol. 2015;8:124-126.
62. Devi S and Ayswarya N. Artificial Neural Network Approach for Load Forecasting in Demand Side Management. IJAREEIE. 2015.
63. Monirul IMd. A Novel Approach for Text-Independent Speaker Identification Using Artificial Neural Network. IJIRCCE. 2013.
64. Shanmugapriya K and Soniya M. AN ADAPTIVE NEURAL NETWORK CLASSIFIED BASED IMAGE FORGERY DETECTION. IJAREEIE. 2013.
65. Gurumoorthy K et al. Reduction of Harmonic Distortion by applying various PWM and Neural Network Techniques in Grid connected Photovoltaic Systems. IJAREEIE. 2013.
66. Dhanalakshmi N and Vijaya KK. Digital gas identification system using artificial neural networks. IJAREEIE. 2014.
67. Anjali R and Manju RM. Offline Signature Verification Based on SVM and Neural Network. IJAREEIE. 2013.
68. Emmy K and Filmy F. Enhancement of Power System Stability by Optimal Adaptive Under Frequency Load Shedding Using Artificial Neural Networks. IJAREEIE. 2013.
69. Binishiny K and Rajesh T. Fuzzy and Neural Network Based License- Plate Localization and Recognition. IJAREEIE. 2014.
70. Swetha GC and Sudarshana RHR. Voltage Stability Assessment in Power Network Using Artificial Neural Network. IJAREEIE. 2014.
71. Rashmi J and Bhawana G. Prediction of Global Solar Radiation Using Artificial Neural Network. IJAREEIE. 2013.
72. Shaik RK et al. Particle swarm optimization and neural network for frequency domain identification of servo system with friction force. IJAREEIE. 2013.
73. Kusuma G et al. Simulation of DTC IM Based on PI& Artificial Neural Network Technique. IJAREEIE. 2013.
74. Ramakrishnan M. Chaotic Neural Network Based Hashing Algorithm for Image Authentication. IJAREEIE. 2014.
75. Ritu T and Manoj N. Designing and Simulation of Dual Loop Speed Controller For Efficient Speed Control Of Permanent Magnet Synchronous Machine Using Neural Network. IJAREEIE. 2013.
76. Shashank M and Tripathi GS. Comparison of Various Neural Network Algorithms Used for Location Estimation in Wireless Communication. IJAREEIE. 2013.
77. Ramaa PVM Probabilistic Neural Network for Brain Tumor Classification. IJAREEIE. 2013.
78. Pankaj S et al. Design and Implementation of Cerebral Model Neural Network based Controller using VxWorksRTOS ported toMPC8260. IJAREEI. 2013. 
79. Alpaydm E. Neural models of incremental supervised and unsupervised learning. Ecole Polytechuique De Lausanne, Switzerland. 1990.
80. Barschdorff D et al. Phonocardiogram analysis of congenital and acquired heart diseases using artificial neural networks. Advances in Fuzzy Systems-Applications and Theory (3), Comparative approaches to medical reasoning, World Scientific Publishing Co. 1995;271-288.
81. Basak J et al. A connectionist model for category perception: theory and implementation. IEEE Transactions on Neural Networks. 1993;4:257-269.
82. Bently PM. Time-frequency analysis of native and prosthetic heart valve sounds. PhD Thesis, Electrical and Electronics Department, University of Edinburgh. 1996.
83. Berlich R et al. A comparison between the performance of feed forward neural networks and the supervised growing neural gas algorithm. 1996.
84. Berlich R and Kunze M. A comparison between the performance of feed forward neural networks and the supervised growing neural Gas algorithm. Nuclear Instruments and Methods in Physics Research A. 1997;389:274-277.
85. Jörg B and Gerald S. Dynamic cell structure learns perfectly topology preserving map, Neural Computation. 1995;7:845-865.
86. Burzevski V and Mohan CK. Hierarchical growing cell structures, In: ICNN96: Proceedings of the International Conference of the Neural Networks. 1996.
87. Carpenter GA and Grossberg S. ART2: self-organizing of stable category recognition codes for analog input patterns. Applied Optics. 1987;26:4919-4930.
88. Chin-Der W and Stelios CAT. A comparative study of self-organizing clustering algorithms dignet and ART2, Neural Networks. 1997;10:737-753.
89. Cohen A. Biomedical Signal Processing, Boca Raton-Florida: CRC Press Inc. 1997;75-79.
90. Ingrid D. Ten lectures on wavelets, Society for Industrial and Applied Mathematics, Philadelphia, PA, 1992.
91. Debjais F. Time-frequency analysis of heart murmurs. Part II: optimisation of time-frequency representations and performance evaluation. Medical & Biological Engineering & Computing. 1997;35:480-485.
92. Dokur Z et al. Classification of MR and CT images using genetic algorithms. In: 20th Annual International Conference of the IEEE-EMBS. 1998;20:1418-1421.
93. Dokur Z and Ölmez T. ECG beat classification by a novel hybrid neural network. Computer Methods & Programs in Biomedicine. 2001;66:167-181.
94. Zümray D. Segmentation of MR and CT Images Using a Hybrid Neural Network Trained by Genetic Algorithms, Neural Processing Letters. 2002;16:211-225.
95. Zümray D and Tamer Ö. Segmentation of ultrasound images by using a hybrid neural network, Pattern Recognition Letters. 2002;23:1825-1836.
96. Fritzke B. A growing neural Gas network learns topology. 1994.
97. Bernd F. Growing cell structures—a self-organizing network for unsupervised and supervised learning. Neural Networks. 1994;7:1441-1460.
98. Huiying L. A heart sound segmentation using wavelet decomposition and reconstruction. 1997;1630-1633.
99. Leung TS. Acoustic diagnosis of heart diseases. 1998;389-398.