Adoption of machine learning technology for failure prediction in industrial maintenance: A systematic review

Towards edge computing in intelligent manufacturing: Past, present and future

Diagnosis on the basis of a computerized acoustic examination may play an incredibly important role in early diagnosis and in monitoring and even improving effective pathological speech diagnostics. Various acoustic metrics test the health of the voice. The precision of these parameters also has to do with algorithms for the detection of speech noise. The idea is to detect the disease pathology from the voice. First, we apply the feature extraction on the SVD dataset. After the feature extraction, the system input goes into the 27 neuronal layer neural networks that are convolutional and recurrent neural network. We divided the dataset into training and testing, and after 10 k-fold validation, the reported accuracies of CNN and RNN are 87.11% and 86.52%, respectively. A 10-fold cross-validation is used to evaluate the performance of the classifier. On a Linux workstation with one NVidia Titan X GPU, program code was written in Python using the TensorFlow package.

/pdf/comparative-analysis-of-cnn-and-rnn-for-voice-pathology-46k8ufldai.pdf

Comparative Analysis of CNN and RNN for Voice Pathology Detection.

The single-row facility layout problem (SRFLP) decides upon the arrangement of facilities in a straight row so as to minimise the material handling cost. Generally, this problem allows the placemen...

An improved fireworks algorithm for the constrained single-row facility layout problem

How to accurately estimate the probability integral parameters based on the measured data has always been a difficult point in the application of the probability integral method. This paper introdu...

Estimation of parameters of probability integral method model based on improved fireworks algorithm

LearningADD: Machine learning based acoustic defect detection in factory automation

Hardware/software partitioning is a crucial step in the co-design of embedded system. It can not only shorten the R&D cycle, but also improve the performance of the product. In the co-design of embedded system, the hardware/software partitioning algorithm plays the most important role and many heuristic algorithms have been applied to solve this problem. In this paper, we introduce a novel swarm intelligence optimization algorithm called firework algorithm (FWA) and apply it to hardware/software partitioning. In order to improve the optimization accuracy and decrease the time consumed, operators in the conventional FWA are analyzed and their disadvantages are revealed. Then these operators are modified and an improved version of the conventional FWA called improved firework algorithm (IFWA) is proposed. To avoid overwhelming effects, the IFWA provides an innovative calculation of explosion amplitude and spark’s number by setting up dynamic boundaries. Besides, according to grouping and elite strategy, a new selection strategy is put forward to accelerate the convergence speed of the algorithm. Experiments on 8 instances of hardware/software partitioning are conducted in order to illustrate the performance of the proposed algorithm. Experimental results show that the IFWA outperforms significantly the FWA and several other heuristic algorithms in terms of optimization accuracy, time consumed, and convergence speed.

An improved firework algorithm for hardware/software partitioning

Individuals, such as voice-related professionals, elderly people and smokers, are increasingly suffering from voice disorder, which implies the importance of pathological voice repair. Previous work on pathological voice repair only concerned about sustained vowel /a/, but multiple vowels repair is still challenging due to the unstable extraction of pitch and the unsatisfactory reconstruction of formant. In this paper, a multiple vowels repair based on pitch extraction and Line Spectrum Pair feature for voice disorder is proposed, which broadened the research subjects of voice repair from only single vowel /a/ to multiple vowels /a/, /i/ and /u/ and achieved the repair of these vowels successfully. Considering deep neural network as a classifier, a voice recognition is performed to classify the normal and pathological voices. Wavelet Transform and Hilbert-Huang Transform are applied for pitch extraction. Based on Line Spectrum Pair (LSP) feature, the formant is reconstructed. The final repaired voice is obtained by synthesizing the pitch and the formant. The proposed method is validated on Saarbrucken Voice Database (SVD) database. The achieved improvements of three metrics, Segmental Signal-to-Noise Ratio, LSP distance measure and Mel cepstral distance measure, are respectively 45.87%, 50.37% and 15.56%. Besides, an intuitive analysis based on spectrogram has been done and a prominent repair effect has been achieved.

Multiple Vowels Repair Based on Pitch Extraction and Line Spectrum Pair Feature for Voice Disorder

At present, pathological voice recognition is mainly based on the classification of pathological voice. However, almost all the researches are based on the single vowel \a\ samples, but few on multi-vowels. In addition, the current researches on multi-vowels recognition are mainly for normal voices, which are unsuitable for the speech recognition of normal and pathological multi-vowels simultaneously. This paper concentrates on developing an accurate and robust feature called enhanced-bark line spectrum pair (E-BLSP) to detect and classify normal and pathological multi-vowels. We explore the impact of E-BLSP feature on recognition performance and propose an effective method based on the combination of three features including E-BLSP for pathological and normal multi-vowels. In this paper, first LSP and difference of adjacent LSP (DAL) features of a vowel are extracted. Then LSP feature is warped at bark domain to get bark line spectrum pair (BLSP). In addition, then E-BLSP feature is calculated by adjusting BLSP using DAL feature. Finally, the adjusted E-BLSP feature and other two traditional features, including linear prediction cepstrum coefficient (LPCC) and mel-frequency cepstrum coefficients (MFCC) are applied to support vector machine (SVM) and deep neural network (DNN) classifiers to explore the classification performance of single feature and feature combinations for pathological and normal vowels /a/, /i/ and /u/. The results show that the highest achieved accuracies for DNN and SVM network are 98.6190% and 96.2693%, while the largest achieved area under curves (AUC) are 0.9925 and 0.9868, correspondingly with the combination of three features including LPCC, MFCC, and E-BLSP.

/pdf/a-pathological-multi-vowels-recognition-algorithm-based-on-269a68e98m.pdf

A Pathological Multi-Vowels Recognition Algorithm Based on LSP Feature

Hardware/software partitioning plays an important role in the co-design system of software and hardware. It can improve the performance of the embedded system to a great degree. Multi-objective hardware/software partitioning aims to optimize the system performance from multi-aspects simultaneously. In recent years, more and more heuristic algorithms are utilized to solve multi-objective problems. In this paper, we apply a firework algorithm (FWA) to solve the problem of multi-objective hardware/software partitioning. The sorting method for multi-objective solutions is described in detail. The calculation of explosion amplitude is modified according to the number of iterations. Due to binary coding, the method of generating new solutions is updated. Finally, a multi-objective FWA (MOFWA) for multi-objective hardware/software partitioning is proposed. To validate the performance of the MOFWA, experiments on six instances are conducted. The proposed MOFWA is compared with three famous multi-objective optimization algorithms, the nondominated sorting genetic algorithm II, the strength Pareto evolutionary algorithm 2, and the Pareto envelope-based selection algorithm in terms of S-metric. The experimental results show that the MOFWA significantly outperforms the three other algorithms.

Ganjun Liu

Papers

LearningADD: Machine learning based acoustic defect detection in factory automation

An improved firework algorithm for hardware/software partitioning

Multiple Vowels Repair Based on Pitch Extraction and Line Spectrum Pair Feature for Voice Disorder

A Pathological Multi-Vowels Recognition Algorithm Based on LSP Feature

Using Firework Algorithm for Multi-Objective Hardware/Software Partitioning