scholarly journals A Novel Approach of Audio Based Feature Optimisation for Bird Classification

2021 ◽  
Vol 29 (4) ◽  
Author(s):  
Murugaiya Ramashini ◽  
Pg Emeroylariffion Abas ◽  
Liyanage C De Silva
Keyword(s):  
Portable Devices ◽  
Optimum Number ◽  
Computing Power ◽  
Linear Discriminant ◽  
Processing Power ◽  
Novel Approach ◽  
Comparison Results ◽  
Audio Data ◽  
Artificial Neural Network Ann ◽  
Ann Classifier

Bird classification using audio data can be beneficial in assisting ornithologists, bird watchers and environmentalists. However, due to the complex environment in the jungles, it is difficult to identify birds by visual inspection. Hence, identification via acoustical means may be a better option in such an environment. This study aims to classify endemic Bornean birds using their sounds. Thirty-five (35) acoustic features have been extracted from the pre-recorded soundtracks of birds. In this paper, a novel approach for selecting an optimum number of features using Linear Discriminant Analysis (LDA) has been proposed to give better classification accuracy. It is found that using a Nearest Centroid (NC) technique with LDA produces the optimum classification results of bird sounds at 96.7% accuracy with reduced computational power. The low computational complexity is an added advantage for handheld portable devices with minimal computing power, which can be used in birdwatching expeditions. Comparison results have been provided with and without LDA using NC and Artificial Neural Network (ANN) classifiers. It has been demonstrated that both classifiers with LDA outperform those without LDA. Maximum accuracies for both NC and ANN with LDA, with NC and the ANN classifiers requiring 7 and 10 LDAs to achieve the optimum accuracy, respectively, are 96.7%. However, ANN classifier with LDA is more computationally complex. Hence, this is significant as the simpler NC classifier with LDA, which does not require expensive processing power, may be used on the portable and affordable device for bird classification purposes.

A COMBINED APPROACH TO TEXT-DEPENDENT SPEAKER IDENTIFICATION: COMPARISON WITH PURE NEURAL NET APPROACHES

1998 ◽  
Vol 08 (02) ◽  
pp. 273-281
Author(s):  
QIANHUI LIANG ◽  
MIAOLIANG ZHU
Keyword(s):  
Dynamic Time Warping ◽  
Speaker Identification ◽  
Neural Net ◽  
Combined Approach ◽  
Time Warping ◽  
Novel Approach ◽  
Artificial Neural Network Ann ◽  
Ann Classifier ◽  
Dynamic Time ◽  
Combined Classifier

A novel approach to automatic speaker identification (ASI) is presented. Most of the present automatic speaker identification systems based on neural networks have no definite mechanisms to compensate for time distortions due to elocution. Such models have less precise information about the intraspeaker measure. The new combined approach uses both distortion-based and discriminant-based methods. The distortion-based and discriminant-based methods are dynamic time warping (DTW) and artificial neural network (ANN) respectively. This paper compares this new classifier with a pure neural net classifier for speaker identification. The performance of the combined classifier surpasses that of a pure ANN classifier for the conditions tested.

scholarly journals Automated Confirmation of Protein Annotation Using NLP and the UniProtKB Database

2020 ◽  
Vol 11 (1) ◽  
pp. 24
Author(s):  
Jin Tao ◽  
Kelly Brayton ◽  
Shira Broschat
Keyword(s):  
Language Processing ◽  
Fine Tuning ◽  
Support Vector ◽  
Protein Annotation ◽  
Computing Power ◽  
Journal Publication ◽  
Novel Approach ◽  
Uniprotkb Database ◽  
Public Repositories ◽  
Annotation Errors

Advances in genome sequencing technology and computing power have brought about the explosive growth of sequenced genomes in public repositories with a concomitant increase in annotation errors. Many protein sequences are annotated using computational analysis rather than experimental verification, leading to inaccuracies in annotation. Confirmation of existing protein annotations is urgently needed before misannotation becomes even more prevalent due to error propagation. In this work we present a novel approach for automatically confirming the existence of manually curated information with experimental evidence of protein annotation. Our ensemble learning method uses a combination of recurrent convolutional neural network, logistic regression, and support vector machine models. Natural language processing in the form of word embeddings is used with journal publication titles retrieved from the UniProtKB database. Importantly, we use recall as our most significant metric to ensure the maximum number of verifications possible; results are reported to a human curator for confirmation. Our ensemble model achieves 91.25% recall, 71.26% accuracy, 65.19% precision, and an F1 score of 76.05% and outperforms the Bidirectional Encoder Representations from Transformers for Biomedical Text Mining (BioBERT) model with fine-tuning using the same data.

scholarly journals A Novel Method to Detect Inner Emotion States of Human using Artificial Neural Networks

2020 ◽  
Vol 8 (6) ◽  
pp. 5820-5825
Keyword(s):  
Physiological Signals ◽  
Classification Rate ◽  
Discrete Emotion ◽  
Novel Approach ◽  
Proposed Model ◽  
Depression Detection ◽  
Novel Method ◽  
Artificial Neural ◽  
Ann Classifier ◽  
Performance Rate

Human computer interaction is a fast growing area of research where in the physiological signals are used to identify human emotion states. Identifying emotion states can be done using various approaches. One such approach which gained interest of research is through physiological signals using EEG. In the present work, a novel approach is proposed to elicit emotion states using 3-D Video-audio stimuli. Around 66 subjects were involved during data acquisition using 32 channel Enobio device. FIR filter is used to preprocess the acquired raw EEG signals. The desired frequency bands like alpha, delta, beta and theta are extracted using 8-level DWT. The statistical features, Hurst exponential, entropy, power, energy, differential entropy of each bands are computed. Artificial Neural network is implemented using Sequential Keras model and applied on the extracted features to classify in to four classes (HVLA, HVHA, LVHA and LVLA) and eight discrete emotion states like clam, relax, happy, joy, sad, fear, tensed and bored. The performance of ANN classifier found to perform better for 4- classes than 8-classes with a classification rate of 90.835% and 74.0446% respectively. The proposed model achieved better performance rate in detecting discrete emotion states. This model can be used to build applications on health like stress / depression detection and on entertainment to build emotional DJ.

scholarly journals Modeling of daily runoff from a small agricultural watershed using artificial neural network with resampling techniques

2014 ◽  
Vol 17 (1) ◽  
pp. 56-74 ◽  
Author(s):  
Gurjeet Singh ◽  
Rabindra K. Panda ◽  
Marc Lamers
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Agricultural Watershed ◽  
Training Data ◽  
Optimum Number ◽  
Training Process ◽  
Data Set ◽  
Reported Study ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

The reported study was undertaken in a small agricultural watershed, namely, Kapgari in Eastern India having a drainage area of 973 ha. The watershed was subdivided into three sub-watersheds on the basis of drainage network and land topography. An attempt was made to relate the continuously monitored runoff data from the sub-watersheds and the whole-watershed with the rainfall and temperature data using the artificial neural network (ANN) technique. The reported study also evaluated the bias in the prediction of daily runoff with shorter length of training data set using different resampling techniques with the ANN modeling. A 10-fold cross-validation (CV) technique was used to find the optimum number of hidden neurons in the hidden layer and to avoid neural network over-fitting during the training process for shorter length of data. The results illustrated that the ANN models developed with shorter length of training data set avoid neural network over-fitting during the training process, using a 10-fold CV method. Moreover, the biasness was investigated using the bootstrap resampling technique based ANN (BANN) for short length of training data set. In comparison with the 10-fold CV technique, the BANN is more efficient in solving the problems of the over-fitting and under-fitting during training of models for shorter length of data set.

A Novel Approach for Dimensionality Reduction and Classification of Big Data Using Meta-Heuristic Approach

2020 ◽  
Vol 17 (11) ◽  
pp. 5182-5197
Author(s):  
Amrinder Kaur ◽  
Rakesh Kumar
Keyword(s):  
Big Data ◽  
User Interaction ◽  
Extraction Process ◽  
Support Vector ◽  
Novel Approach ◽  
Whale Optimization ◽  
Distribution Index ◽  
Artificial Neural Network Ann ◽  
Feature Selection Approach

User interaction over the internet is growing day by day. The social network users send massive information to the network to share with others on the network. This increases the information on social media, hence needed a mechanism to handle or manage such high dimensional data termed as Big Data. Big Data reduction can be performed by using a feature selection approach. But, the Classification of such massive data is a challenging task for all the researchers. To overcome this problem, a metaheuristic based Genetic Algorithm (GA) for the selection of most suitable rows which can be provided for training. The selected rows undergo a feature extraction process, which is attained by Principle Component Analysis (PCA). The extracted principle components are optimized using another meta-heuristic algorithm termed as Whale Optimization. As the proposed algorithm uses unlabelled data, clustering is done to label the data. Two different distribution indexes were calculated for data with GA selected rows and data with GA selected rows along with PCA and whale. The distribution index is the ratio of a total number of elements in one cluster to a total number of elements in the second cluster. High distribution index leads to better accuracy when it comes to classifying the text data. The data is clustered using the K-Means algorithm to find the cluster indexes. The proposed algorithm presents a hybrid classification mechanism with upper and lower boundaries of classified labels using Artificial Neural Network (ANN) and Support Vector Machine (SVM).

Cardiovascular Disease Prediction from Electrocardiogram by using Machine Learning Method: A Snapshot from the Subjects of the Malaysian Cohort

2020 ◽  
Author(s):  
Nazrul Anuar Nayan ◽  
Hafifah Ab Hamid ◽  
Mohd Zubir Suboh ◽  
Noraidatulakma Abdullah ◽  
Rosmina Jaafar ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cardiovascular Disease ◽  
Nearest Neighbor ◽  
Total Cholesterol Level ◽  
Population Based ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Cvd Risk ◽  
Linear Discriminant ◽  
Artificial Neural Network Ann

Abstract Background: Cardiovascular disease (CVD) is the leading cause of deaths worldwide. In 2017, CVD contributed to 13,503 deaths in Malaysia. The current approaches for CVD prediction are usually invasive and costly. Machine learning (ML) techniques allow an accurate prediction by utilizing the complex interactions among relevant risk factors. Results: This study presents a case–control study involving 60 participants from The Malaysian Cohort, which is a prospective population-based project. Five parameters, namely, the R–R interval and root mean square of successive differences extracted from electrocardiogram (ECG), systolic and diastolic blood pressures, and total cholesterol level, were statistically significant in predicting CVD. Six ML algorithms, namely, linear discriminant analysis, linear and quadratic support vector machines, decision tree, k-nearest neighbor, and artificial neural network (ANN), were evaluated to determine the most accurate classifier in predicting CVD risk. ANN, which achieved 90% specificity, 90% sensitivity, and 90% accuracy, demonstrated the highest prediction performance among the six algorithms. Conclusions: In summary, by utilizing ML techniques, ECG data can serve as a good parameter for CVD prediction among the Malaysian multiethnic population.

Towards a Programming Model for Ubiquitous Computing

2011 ◽  
pp. 634-648
Author(s):  
Jorge Barbosa ◽  
Fabiane Dillenburg ◽  
Alex Garzão ◽  
Gustavo Lermen ◽  
Cristiano Costa
Keyword(s):  
Mobile Computing ◽  
Ubiquitous Computing ◽  
Context Awareness ◽  
Programming Model ◽  
Distributed Applications ◽  
Portable Devices ◽  
Heterogeneous Devices ◽  
The Core ◽  
Processing Power ◽  
Execution Environment

Mobile computing is been driven by the proliferation of portable devices and wireless communication. Potentially, in the mobile computing scenario, the users can move in different environments and the applications can automatically explore their surroundings. This kind of context-aware application is emerging, but is not yet widely disseminated. Based on perceived context, the application can modify its behavior. This process, in which software modifies itself according to sensed data, is named Adaptation. This constitutes the core of Ubiquitous Computing. The ubiquitous computing scenario brings many new problems such as coping with the limited processing power of mobile devices, frequent disconnections, the migration of code and tasks between heterogeneous devices, and others. Current practical approaches to the ubiquitous computing problem usually rely upon traditional computing paradigms conceived back when distributed applications where not a concern. Holoparadigm (in short Holo) was proposed as a model to support the development of distributed systems. Based on Holo concepts, a new programming language called HoloLanguage (in short, HoloL) was created. In this chapter, we propose the use of Holo for developing and executing ubiquitous applications. We explore the HoloL for ubiquitous programming and propose a full platform to develop and execute Holo programs. The language supports mobility, adaptation, and context awareness. The execution environment is based on a virtual machine that implements the concepts proposed by Holo. The environment supports distribution and strong code mobility.

A New Islanding Detection Method Based on Wavelet-transform and ANN for Micro-grid Including Inverter Assisted Distributed Generator

2019 ◽  
Vol 20 (5) ◽  
Author(s):  
Zhengyuan Guan ◽  
Yuan Liao
Keyword(s):  
Wavelet Transform ◽  
Harmonic Distortion ◽  
Distribution Networks ◽  
Islanding Detection ◽  
Detection Zone ◽  
Distributed Generator ◽  
Voltage Unbalance ◽  
Typical Distribution ◽  
Artificial Neural Network Ann ◽  
Ann Classifier

Abstract This paper presents a new composite approach based on wavelet-transform and ANN for islanding detection of distributed generation (DG). The proposed method first uses wavelet-transform to detect the occurrence of events, and then uses artificial neural network (ANN) to classify islanding and non-islanding events. Total harmonic distortion and voltage unbalance are extracted as feature inputs for ANN classifier. The performance of the proposed method is tested by simulations for two typical distribution networks based on MATLAB/Simulink. The results show that the developed method can effectively detect islanding with low misclassification. The method has the advantages of small non-detection zone and robustness against noises.

Sign in / Sign up

Export Citation Format

Share Document