Speaker identification refers to the process of recognizing human voice using artificial intelligence techniques. Speaker identification technologies are widely applied in voice authentication, security and surveillance, electronic voice eavesdropping, and identity verification. In the speaker identification process, extracting discriminative and salient features from speaker utterances is an important task to accurately identify speakers. Various features for speaker identification have been recently proposed by researchers. Most studies on speaker identification have utilized short-time features, such as perceptual linear predictive (PLP) coefficients and Mel frequency cepstral coefficients (MFCC), due to their capability to capture the repetitive nature and efficiency of signals. Various studies have shown the effectiveness of MFCC features in correctly identifying speakers. However, the performances of these features degrade on complex speech datasets, and therefore, these features fail to accurately identify speaker characteristics. To address this problem, this study proposes a novel fusion of MFCC and time-based features (MFCCT), which combines the effectiveness of MFCC and time-domain features to improve the accuracy of text-independent speaker identification (SI) systems. The extracted MFCCT features were fed as input to a deep neural network (DNN) to construct the speaker identification model. Results showed that the proposed MFCCT features coupled with DNN outperformed existing baseline MFCC and time-domain features on the LibriSpeech dataset. In addition, DNN obtained better classification results compared with five machine learning algorithms that were recently utilized in speaker recognition. Moreover, this study evaluated the effectiveness of one-level and two-level classification methods for speaker identification. The experimental results showed that two-level classification presented better results than one-level classification. The proposed features and classification model for identifying a speaker can be widely applied to different types of speaker datasets.

Text-Independent Speaker Identification through Feature Fusion and Deep Neural Network

A Novel Method for Indian Vehicle Registration Number Plate Detection and Recognition using Image Processing Techniques

Biometric authentication is a promising approach to securing the Internet of Things (IoT). Although existing research shows that using multiple biometrics for authentication helps increase recognition accuracy, the majority of biometric approaches for IoT today continue to rely on a single modality. We propose a multimodal biometric approach for IoT based on face and voice modalities that is designed to scale to the limited resources of an IoT device. Our work builds on the foundation of Gofman et al. [7] in implementing face and voice feature-level fusion on mobile devices. We used discriminant correlation analysis (DCA) to fuse features from face and voice and used the K-nearest neighbors (KNN) algorithm to classify the features. The approach was implemented on the Raspberry Pi IoT device and was evaluated on a dataset of face images and voice files acquired using a Samsung Galaxy S5 device in real-world conditions such as dark rooms and noisy settings. The results show that fusion increased recognition accuracy by 52.45% compared to using face alone and 81.62% compared to using voice alone. It took an average of 1.34 seconds to enroll a user and 0.91 seconds to perform the authentication. To further optimize execution speed and reduce power consumption, we implemented classification on a field-programmable gate array (FPGA) chip that can be easily integrated into an IoT device. Experimental results showed that the proposed FPGA-accelerated KNN could achieve 150x faster execution time and 12x lower energy consumption compared to a CPU.

Multimodal Biometrics for Enhanced IoT Security

Biometrics, as a computer science field, can be understood as the discipline that study how to generate computer models of the physical (e.g. hand geometry, fingerprints, iris and so on) and behavioral (e.g. signature; a kind of behavior pattern) characteristics of the human being for single or several individuals identification. Usually, these characteristics are used to provide authentication information for security systems. However, some of these characteristics are hard to obtain in a properly way and it is necessary to use several algorithms both to process them and to use them on a security systems. In this sense, in this paper it is presented an overview of some Machine Learning approaches for biometric pattern recognition.

/pdf/survey-of-biometric-pattern-recognition-via-machine-learning-4elxh44s2s.pdf

Survey of biometric pattern recognition via machine learning techniques

Electrocardiography (ECG) sensors play a vital role in the Internet of Medical Things, and these sensors help in monitoring the electrical activity of the heart. ECG signal analysis can improve human life in many ways, from diagnosing diseases among cardiac patients to managing the lifestyles of diabetic patients. Abnormalities in heart activities lead to different cardiac diseases and arrhythmia. However, some cardiac diseases, such as myocardial infarction (MI) and atrial fibrillation (Af), require special attention due to their direct impact on human life. The classification of flattened T wave cases of MI in ECG signals and how much of these cases are similar to ST-T changes in MI remain an open issue for researchers. This article presents a novel contribution to classify MI and Af. To this end, we propose a new approach called deep deterministic learning (DDL), which works by combining predefined heart activities with fused datasets. In this research, we used two datasets. The first dataset, Massachusetts Institute of Technology-Beth Israel Hospital, is publicly available, and we exclusively obtained the second dataset from the University of Malaya Medical Center, Kuala Lumpur Malaysia. We first initiated predefined activities on each individual dataset to recognize patterns between the ST-T change and flattened T wave cases and then used the data fusion approach to merge both datasets in a manner that delivers the most accurate pattern recognition results. The proposed DDL approach is a systematic stage-wise methodology that relies on accurate detection of R peaks in ECG signals, time domain features of ECG signals, and fine tune-up of artificial neural networks. The empirical evaluation shows high accuracy (i.e., ≤99.97%) in pattern matching ST-T changes and flattened T waves using the proposed DDL approach. The proposed pattern recognition approach is a significant contribution to the diagnosis of special cases of MI.

Deep Deterministic Learning for Pattern Recognition of Different Cardiac Diseases through the Internet of Medical Things

This paper presents a suitable and efficient implementation of a feature extraction algorithm (Pan Tompkins algorithm) on electrocardiography (ECG) signals, for detection and classification of four cardiac diseases: Sleep Apnea, Arrhythmia, Supraventricular Arrhythmia and Long Term Atrial Fibrillation (AF) and differentiating them from the normal heart beat by using pan Tompkins RR detection followed by feature extraction for classification purpose .The paper also presents a new approach towards signal classification using the existing neural networks classifiers.

Implementation of Neural Network and feature extraction to classify ECG signals

The most pressing challenge in the field of voice biometrics is selecting the most efficient technique of speaker recognition. Every individual's voice is peculiar, factors like physical differences in vocal organs, accent and pronunciation contributes to the problem's complexity. In this paper, we explore the various methods available in each block in the process of speaker recognition with the objective to identify best of techniques that could be used to get precise results. We study the results on text independent corpora. We use MFCC (Mel-frequency cepstral coefficient), LPCC (linear predictive cepstral coefficient) and PLP (perceptual linear prediction) algorithms for feature extraction, PCA (Principal Component Analysis) and t-SNE for dimensionality reduction and SVM (Support Vector Machine), feed forward, nearest neighbor and decision tree algorithms for classification block in speaker recognition system and comparatively analyze each block to determine the best technique.

A text-independent speaker verification model: A comparative analysis

Vehicles play a vital role in modern-day transportation systems. Number plate provides a standard means of identification for any vehicle. To serve this purpose, automatic license plate recognition system was developed. This consisted of four major steps: preprocessing of obtained image, extraction of license plate region, segmentation, and character recognition. In earlier research, direct application of Sobel edge detection algorithm or applying threshold was used as key steps to extract the license plate region, which do not produce efficient results when captured image is subjected to high intensity of light. The use of morphological operations causes deformity in the characters during segmentation. We propose a novel algorithm to tackle the mentioned issues through a unique edge detection algorithm. It is also a tedious task to create and update the database of required vehicles frequently. This problem is solved by the use of ‘Internet of things’ where an online database can be created and updated from any module instantly. Also, through IoT, we connect all the cameras in a geographical area to one server to create a ‘universal eye’ which drastically increases the probability of tracing a vehicle over having manual database attached to each camera for identification purpose.

Efficient License Plate Recognition System with Smarter Interpretation Through IoT

This paper presents an efficient approach for distinguishing ECG signals based on certain diseases by implementing Pan Tompkins algorithm and neural networks. Pan Tompkins algorithm is used for feature extraction on electrocardiography (ECG) signals, while neural networks help in detection and classification of the signal into four cardiac diseases: Sleep Apnea, Arrhythmia, Supraventricular Arrhythmia and Long-Term Atrial Fibrillation (AF) and normal heart beat. The paper also presents a new approach towards signal classification using the existing neural networks classifiers.

Implementation of Neural Network and Feature Extraction to Classify ECG Signals

The rising need of secret image sharing with high security has led to much advancement in lucrative exchange of important images which contain vital and confidential information. Multi secret image sharing system (MSIS) is an efficient and robust method for transmitting one or more secret images securely. In recent research, n secret images are encrypted into n or n+ 1 shared image's and stored in different database servers. Decoder has to receive all n or n+1 encrypted images to reproduce the secret image. One can recover partial secret information from n-1 or fewer shared images, which poses risk for the confidential information encrypted. In this proposed paper we developed a novel algorithm to increase the sharing capacity by using (n, n/8) multi secret sharing scheme with increased security by generating unique security key. An unrevealed comparison image is used to produce shares which makes the secret image invulnerable to the hackers.

R. Karthik

Papers

Implementation of Neural Network and feature extraction to classify ECG signals

A text-independent speaker verification model: A comparative analysis

Efficient License Plate Recognition System with Smarter Interpretation Through IoT

Implementation of Neural Network and Feature Extraction to Classify ECG Signals

High capacity, secure (n, n/8) multi secret image sharing scheme with security key