Voice activity detection based on deep belief networks using likelihood ratio

A novel technique is proposed to improve the performance of voice activity detection(VAD) by using deep belief networks(DBN) with a likelihood ratio(LR). The likelihood ratio is derived from the speech and noise spectral components that are assumed to follow the Gaussian probability density function(PDF). The proposed algorithm employs DBN learning in order to classify voice activity by using the input signal to calculate the likelihood ratio. Experiments show that the proposed algorithm yields improved results in various noise environments, compared to the conventional VAD algorithms. Furthermore, the DBN based algorithm decreases the detection probability of error with [0.7, 2.6] compared to the support vector machine based algorithm.

Virtual Nursing Using Deep Belief Networks for Elderly People (DBN-EP)

The demand for better health services has resulted in the advancementof remote monitoring health, i.e., virtual nursing systems, to watch and supportthe elderly with innovative concepts such as being patient-centric, easier to use,and having smarter interactions and more accurate conclusions. While virtual nursing services attempt to provide consumers and medical practitioners with continuous medical and health monitoring services, access to allied healthcare expertssuch as nurses remains a challenge. In this research, we present Virtual NursingUsing Deep Belief Networks for Elderly People (DBN-EP), a new framework thatprovides a virtual nurse agent deployed on a senior citizen’s home, workplace, orcare centre to help manage their health condition on a continuous basis. Using thismethod, healthcare providers can assign various jobs to nurses by utilizing a general task definition mechanism, in which a task is defined as a combination ofmedical workflow, operational guidelines, and data gathered from a remotelymonitored virtual nursing system. Practitioners are in charge of DBN-EP andmake treatment decisions for patients. This allows a DBN-EP to act as a personalized full-time nurse for a client by carrying out practitioner support activitiesbased on information gathered about the client’s health. An electronic PersonalHealth Record (ePHR) system, such as a specialized web portal and mobile apps,could provide such patient information to elderly person family members and carecentres. We created a prototype system using a DBN-EP system that allows traditional client applications and healthcare provider systems to collaborate. Finally,we demonstrate how this system may benefit the elderly through a result anddebate.

Multi-channel electromyography pattern classification using deep belief networks for enhanced user experience

An enhanced algorithm is proposed to recognize multi-channel electromyography(EMG) patterns using deep belief networks(DBNs). It is difficult to classify the EMG features because an EMG signal has nonlinear and time-varying characteristics.Therefore, in several previous studies, various machine-learning methods have been applied. A DBN is a fast, greedy learning algorithm that can find a fairly good set of weights rapidly, even in deep networks with a large number of parameters and many hidden layers. To evaluate this model, we acquired EMG signals, extracted their features, and then compared the model with the DBN and other conventional classifiers. The accuracy of the DBN is higher than that of the other algorithms. The classification performance of the DBN model designed is approximately 88.60%. It is 7.55%(p=9.82×10-12) higher than linear discriminant analysis(LDA) and 2.89%(p=1.94×10-5) higher than support vector machine(SVM). Further, the DBN is better than shallow learning algorithms or back propagation(BP), and this model is effective for an EMG-based user-interfaced system.

Finite-sensor fault-diagnosis simulation study of gas turbine engine using information entropy and deep belief networks

Precise fault diagnosis is an important part of prognostics and health management. It can avoid accidents, extend the service life of the machine, and also reduce maintenance costs. For gas turbine engine fault diagnosis, we cannot install too many sensors in the engine because the operating environment of the engine is harsh and the sensors will not work in high temperature, at high rotation speed, or under high pressure. Thus, there is not enough sensory data from the working engine to diagnose potential failures using existing approaches. In this paper, we consider the problem of engine fault diagnosis using finite sensory data under complicated circumstances, and propose deep belief networks based on information entropy, IE-DBNs, for engine fault diagnosis. We first introduce several information entropies and propose joint complexity entropy based on single signal entropy. Second, the deep belief networks （DBNs） is analyzed and a logistic regression layer is added to the output of the DBNs. Then, information entropy is used in fault diagnosis and as the input for the DBNs. Comparison between the proposed IE-DBNs method and state-of-the-art machine learning approaches shows that the IE-DBNs method achieves higher accuracy.

Tandem hidden Markov models using deep belief networks for offline handwriting recognition

Unconstrained offiine handwriting recognition is a challenging task in the areas of document analysis and pattern recognition. In recent years, to sufficiently exploit the supervisory information hidden in document images, much effort has been made to integrate multi-layer perceptrons （MLPs） in either a hybrid or a tandem fashion into hidden Markov models （HMMs）. However, due to the weak learnability of MLPs, the learnt features are not necessarily optimal for subsequent recognition tasks. In this paper, we propose a deep architecture-based tandem approach for unconstrained offiine handwriting recognition. In the proposed model, deep belief networks arc adopted to learn the compact representations of sequential data, while HMMs are applied for （sub-）word recognition. We evaluate the proposed model on two publicly available datasets, i.e., RIMES and IFN/ENIT, which are based on Latin and Arabic languages respectively, and one dataset collected by ourselves called Devanagari （all Indian script）. Extensive experiments show the advantage of the proposed model, especially over the MLP-HMMs taudem approaches.

Tunnelling performance prediction of cantilever boring machine in sedimentary hard-rock tunnel using deep belief network

Evaluating the adaptability of cantilever boring machine(CBM) through in-depth excavation and analysis of tunnel excavation data and rock mass parameters is the premise of mechanical design and efficient excavation in the field of underground space engineering.This paper presented a case study of tunnelling performance prediction method of CBM in sedimentary hard-rock tunnel of Karst landform type by using tunneling data and surrounding rock parameters.The uniaxial compressive strength(UCS),rock integrity factor(Kv),basic quality index([BQ]),rock quality index RQD,brazilian tensile strength(BTS) and brittleness index(BI) were introduced to construct a performance prediction database based on the hard-rock tunnel of Guiyang Metro Line 1 and Line 3,and then established the performance prediction model of cantilever boring machine.Then the deep belief network(DBN) was introduced into the performance prediction model,and the reliability of performance prediction model was verified by combining with engineering data.The study showed that the influence degree of surrounding rock parameters on the tunneling performance of the cantilever boring machine is UCS > [BQ] > BTS >RQD > Kv > BI.The performance prediction model shows that the instantaneous cutting rate(ICR) has a good correlation with the surrounding rock parameters,and the predicting model accuracy is related to the reliability of construction data.The prediction of limestone and dolomite sections of Line 3 based on the DBN performance prediction model shows that the measured ICR and predicted ICR is consistent and the built performance prediction model is reliable.The research results have theoretical reference significance for the applicability analysis and mechanical selection of cantilever boring machine for hard rock tunnel.

Deep Belief Network for Lung Nodule Segmentation and Cancer Detection

Cancer disease is a deadliest disease cause more dangerous one.By identifying the disease through Artificial intelligence to getting the mage features directly from patients.This paper presents the lung knob division and disease characterization by proposing an enhancement calculation.Most of the machine learning techniques failed to observe the feature dimensions leads inaccuracy in feature selection and classification.This cause inaccuracy in sensitivity and specificity rate to reduce the identification accuracy.To resolve this problem,to propose a Chicken Sine Cosine Algorithm based Deep Belief Network to identify the disease factor.The general technique of the created approach includes four stages,such as pre-processing,segmentation,highlight extraction,and the order.From the outset,the Computerized Tomography(CT)image of the lung is taken care of to the division.When the division is done,the highlights are extricated through morphological factors for feature observation.By getting the features are analysed and the characterization is done dependent on the Deep Belief Network(DBN)which is prepared by utilizing the proposed Chicken-Sine Cosine Algorithm(CSCA)which distinguish the lung tumour,giving two classes in particular,knob or non-knob.The proposed system produce high performance as well compared to the other system.The presentation assessment of lung knob division and malignant growth grouping dependent on CSCA is figured utilizing three measurements to be specificity,precision,affectability,and the explicitness.

PSO-DBNet for Peak-to-Average Power Ratio Reduction Using Deep Belief Network

Data transmission through a wireless network has faced various signal problems in the past decades.The orthogonal frequency division multiplexing(OFDM)technique is widely accepted in multiple data transfer patterns at various frequency bands.A recent wireless communication network uses OFDM in longterm evolution(LTE)and 5G,among others.The main problem faced by 5G wireless OFDM is distortion of transmission signals in the network.This transmission loss is called peak-to-average power ratio(PAPR).This wireless signal distortion can be reduced using various techniques.This study uses machine learning-based algorithm to solve the problem of PAPR in 5G wireless communication.Partial transmit sequence(PTS)helps in the fast transfer of data in wireless LTE.PTS is merged with deep belief neural network(DBNet)for the efficient processing of signals in wireless 5G networks.Result indicates that the proposed system outperforms other existing techniques.Therefore,PAPR reduction in OFDM by DBNet is optimized with the help of an evolutionary algorithm called particle swarm optimization.Hence,the specified design supports in improving the proposed PAPR reduction architecture.

DeepQ Based Automated Irrigation Systems Using Deep Belief WSN

Deep learning is the subset of artificial intelligence and it is used for effective decision making.Wireless Sensor based automated irrigation system is proposed to monitor and cultivate crop.Our system consists of Distributed wire-less sensor environment to handle the moisture of the soil and temperature levels.It is automated process and useful for minimizing the usage of resources such as water level,quality of the soil,fertilizer values and controlling the whole system.The mobile app based smart control system is designed using deep belief network.This system has multiple sensors placed in agriculturalfield and collect the data.The collected transmitted to cloud server and deep learning process is applied for making decisions.DeepQ residue analysis method is proposed for analyzing auto-mated and sensor captured data.Here,we used 512×512×3 layers deep belief network and 10000 trained data and 2500 test data are taken for evaluations.It is automated process once data is collected deep belief network is generated.The performance is compared with existing results and our process method has 94%of accuracy factor.Also,our system has low cost and energy consumption also suitable for all kind of agriculturalfields.

FG-SMOTE:Fuzzy-based Gaussian synthetic minority oversampling with deep belief networks classifier for skewed class distribution

Purpose-Adequate resources for learning and training the data are an important constraint to develop an efficient classifier with outstanding performance.The data usually follows a biased distribution of classes that reflects an unequal distribution of classes within a dataset.This issue is known as the imbalance problem,which is one of the most common issues occurring in real-time applications.Learning of imbalanced datasets is a ubiquitous challenge in the field of data mining.Imbalanced data degrades the performance of the classifier by producing inaccurate results.Design/methodology/approach-In the proposed work,a novel fuzzy-based Gaussian synthetic minority oversampling(FG-SMOTE)algorithm is proposed to process the imbalanced data.The mechanism of the Gaussian SMOTE technique is based on finding the nearest neighbour concept to balance the ratio between minority and majority class datasets.The ratio of the datasets belonging to the minority and majority class is balanced using a fuzzy-based Levenshtein distance measure technique.Findings-The performance and the accuracy of the proposed algorithm is evaluated using the deep belief networks classifier and the results showed the efficiency of the fuzzy-based Gaussian SMOTE technique achieved an AUC:93.7%.F1 Score Prediction:94.2%,Geometric Mean Score:93.6%predicted from confusion matrix.Research limitations/implications-The proposed research still retains some of the challenges that need to be focused such as application FG-SMOTE to multiclass imbalanced dataset and to evaluate dataset imbalance problem in a distributed environment.Originality/value-The proposed algorithm fundamentally solves the data imbalance issues and challenges involved in handling the imbalanced data.FG-SMOTE has aided in balancing minority and majority class datasets.

Developing Soft Sensors for Polymer Melt Index in an Industrial Polymerization Process Using Deep Belief Networks

This paper presents developing soft sensors for polymer melt index in an industrial polymerization process by using deep belief network(DBN).The important quality variable melt index of polypropylene is hard to measure in industrial processes.Lack of online measurement instruments becomes a problem in polymer quality control.One effective solution is to use soft sensors to estimate the quality variables from process data.In recent years,deep learning has achieved many successful applications in image classification and speech recognition.DBN as one novel technique has strong generalization capability to model complex dynamic processes due to its deep architecture.It can meet the demand of modelling accuracy when applied to actual processes.Compared to the conventional neural networks,the training of DBN contains a supervised training phase and an unsupervised training phase.To mine the valuable information from process data,DBN can be trained by the process data without existing labels in an unsupervised training phase to improve the performance of estimation.Selection of DBN structure is investigated in the paper.The modelling results achieved by DBN and feedforward neural networks are compared in this paper.It is shown that the DBN models give very accurate estimations of the polymer melt index.

Deep belief network-based drug identification using near infrared spectroscopy

Near infrared spectroscopy(NIRS)analysis technology,combined with chemometrics,can be effectively used in quick and nondestructive analysis of quality and category.In this paper,an effective drug identification method by using deep belief network(DBN)with dropout mecha-nism(dropout-DBN)to model NIRS is introduced,in which dropout is employed to overcome the overfitting problem coming from the small sample.This paper tests proposed method under datasets of different sizes with the example of near infrared diffuse refectance spectroscopy of erythromycin ethylsuccinate drugs and other drugs,aluminum and nonaluminum packaged.Meanwhile,it gives experiments to compare the proposed method's performance with back propagation(BP)neural network,support vector machines(SVMs)and sparse denoising auto-encoder(SDAE).The results show that for both binary classification and multi-classification,dropout mechanism can improve the classification accuracy,and dropout-DBN can achieve best classification accuracy in almost all cases.SDAE is similar to dropout-DBN in the aspects of classification accuracy and algorithm stability,which are higher than that of BP neural network and SVM methods.In terms of training time,dropout-DBN model is superior to SDAE model,but inferior to BP neural network and SVM methods.Therefore,dropout-DBN can be used as a modeling tool with effective binary and multi-class classification performance on a spectrum sample set of small size.

Integrated Approach of Brain Disorder Analysis by Using Deep Learning Based on DNA Sequence

In order to research brain problems using MRI,PET,and CT neuroimaging,a correct understanding of brain function is required.This has been considered in earlier times with the support of traditional algorithms.Deep learning process has also been widely considered in these genomics data processing system.In this research,brain disorder illness incliding Alzheimer’s disease,Schizophrenia and Parkinson’s diseaseis is analyzed owing to misdetection of disorders in neuroimaging data examined by means fo traditional methods.Moeover,deep learning approach is incorporated here for classification purpose of brain disorder with the aid of Deep Belief Networks(DBN).Images are stored in a secured manner by using DNA sequence based on JPEG Zig Zag Encryption algorithm(DBNJZZ)approach.The suggested approach is executed and tested by using the performance metric measure such as accuracy,root mean square error,Mean absolute error and mean absolute percentage error.Proposed DBNJZZ gives better performance than previously available methods.

Nonlinear inversion for magnetotelluric sounding based on deep belief network

To improve magnetotelluric(MT)nonlinear inversion accuracy and stability,this work introduces the deep belief network(DBN)algorithm.Firstly,a network frame is set up for training in different 2D MT models.The network inputs are the apparent resistivities of known models,and the outputs are the model parameters.The optimal network structure is achieved by determining the numbers of hidden layers and network nodes.Secondly,the learning process of the DBN is implemented to obtain the optimal solution of network connection weights for known geoelectric models.Finally,the trained DBN is verified through inversion tests,in which the network inputs are the apparent resistivities of unknown models,and the outputs are the corresponding model parameters.The experiment results show that the DBN can make full use of the global searching capability of the restricted Boltzmann machine(RBM)unsupervised learning and the local optimization of the back propagation(BP)neural network supervised learning.Comparing to the traditional neural network inversion,the calculation accuracy and stability of the DBN for MT data inversion are improved significantly.And the tests on synthetic data reveal that this method can be applied to MT data inversion and achieve good results compared with the least-square regularization inversion.

Flash flood susceptibility mapping using a novel deep learning model based on deep belief network,back propagation and genetic algorithm

Flash floods are responsible for loss of life and considerable property damage in many countries.Flood susceptibility maps contribute to flood risk reduction in areas that are prone to this hazard if appropriately used by landuse planners and emergency managers.The main objective of this study is to prepare an accurate flood susceptibility map for the Haraz watershed in Iran using a novel modeling approach(DBPGA)based on Deep Belief Network(DBN)with Back Propagation(BP)algorithm optimized by the Genetic Algorithm(GA).For this task,a database comprising ten conditioning factors and 194 flood locations was created using the One-R Attribute Evaluation(ORAE)technique.Various well-known machine learning and optimization algorithms were used as benchmarks to compare the prediction accuracy of the proposed model.Statistical metrics include sensitivity,specificity accuracy,root mean square error(RMSE),and area under the receiver operatic characteristic curve(AUC)were used to assess the validity of the proposed model.The result shows that the proposed model has the highest goodness-of-fit(AUC=0.989)and prediction accuracy(AUC=0.985),and based on the validation dataset it outperforms benchmark models including LR(0.885),LMT(0.934),BLR(0.936),ADT(0.976),NBT(0.974),REPTree(0.811),ANFIS-BAT(0.944),ANFIS-CA(0.921),ANFIS-IWO(0.939),ANFIS-ICA(0.947),and ANFIS-FA(0.917).We conclude that the DBPGA model is an excellent alternative tool for predicting flash flood susceptibility for other regions prone to flash floods.

Damage identification of steel truss bridges based on deep belief network

To improve the accuracy and anti-noise ability of the structural damage identification method,a bridge damage identification method is proposed based on a deep belief network(DBN).The output vector is used to establish the nonlinear mapping relationship between the mode shape and structural damage.The hidden layer of the DBN is trained through a layer-by-layer pre-training.Finally,the backpropagation algorithm is used to fine-tune the entire network.The method is validated using a numerical model of a steel truss bridge.The results show that under the influence of noise and modeling uncertainty,the damage identification method based on the DBN can identify the accurate damage location and degree identification compared with the traditional damage identification method based on an artificial neural network.

Novel DDoS Feature Representation Model Combining Deep Belief Network and Canonical Correlation Analysis

Distributed denial of service(DDoS)attacks launch more and more frequently and are more destructive.Feature representation as an important part of DDoS defense technology directly affects the efficiency of defense.Most DDoS feature extraction methods cannot fully utilize the information of the original data,resulting in the extracted features losing useful features.In this paper,a DDoS feature representation method based on deep belief network(DBN)is proposed.We quantify the original data by the size of the network flows,the distribution of IP addresses and ports,and the diversity of packet sizes of different protocols and train the DBN in an unsupervised manner by these quantified values.Two feedforward neural networks(FFNN)are initialized by the trained deep belief network,and one of the feedforward neural networks continues to be trained in a supervised manner.The canonical correlation analysis(CCA)method is used to fuse the features extracted by two feedforward neural networks per layer.Experiments show that compared with other methods,the proposed method can extract better features.

Intelligent Deep Learning Enabled Human Activity Recognition for Improved Medical Services

Human Activity Recognition(HAR)has been made simple in recent years,thanks to recent advancements made in Artificial Intelligence(AI)techni-ques.These techniques are applied in several areas like security,surveillance,healthcare,human-robot interaction,and entertainment.Since wearable sensor-based HAR system includes in-built sensors,human activities can be categorized based on sensor values.Further,it can also be employed in other applications such as gait diagnosis,observation of children/adult’s cognitive nature,stroke-patient hospital direction,Epilepsy and Parkinson’s disease examination,etc.Recently-developed Artificial Intelligence(AI)techniques,especially Deep Learning(DL)models can be deployed to accomplish effective outcomes on HAR process.With this motivation,the current research paper focuses on designing Intelligent Hyperparameter Tuned Deep Learning-based HAR(IHPTDL-HAR)technique in healthcare environment.The proposed IHPTDL-HAR technique aims at recogniz-ing the human actions in healthcare environment and helps the patients in mana-ging their healthcare service.In addition,the presented model makes use of Hierarchical Clustering(HC)-based outlier detection technique to remove the out-liers.IHPTDL-HAR technique incorporates DL-based Deep Belief Network(DBN)model to recognize the activities of users.Moreover,Harris Hawks Opti-mization(HHO)algorithm is used for hyperparameter tuning of DBN model.Finally,a comprehensive experimental analysis was conducted upon benchmark dataset and the results were examined under different aspects.The experimental results demonstrate that the proposed IHPTDL-HAR technique is a superior per-former compared to other recent techniques under different measures.

Task Offloading and Resource Allocation in IoT Based Mobile Edge Computing Using Deep Learning

Recently,computation offloading has become an effective method for overcoming the constraint of a mobile device(MD)using computationintensivemobile and offloading delay-sensitive application tasks to the remote cloud-based data center.Smart city benefitted from offloading to edge point.Consider a mobile edge computing(MEC)network in multiple regions.They comprise N MDs and many access points,in which everyMDhasM independent real-time tasks.This study designs a new Task Offloading and Resource Allocation in IoT-based MEC using Deep Learning with Seagull Optimization(TORA-DLSGO)algorithm.The proposed TORA-DLSGO technique addresses the resource management issue in the MEC server,which enables an optimum offloading decision to minimize the system cost.In addition,an objective function is derived based on minimizing energy consumption subject to the latency requirements and restricted resources.The TORA-DLSGO technique uses the deep belief network(DBN)model for optimum offloading decision-making.Finally,the SGO algorithm is used for the parameter tuning of the DBN model.The simulation results exemplify that the TORA-DLSGO technique outperformed the existing model in reducing client overhead in the MEC systems with a maximum reward of 0.8967.

Deep Learning Based Autonomous Transport System for Secure Vehicle and Cargo Matching

The latest 6G improvements secured autonomous driving's realism in Intelligent Autonomous Transport Systems(IATS).Despite the IATS's benefits,security remains a significant challenge.Blockchain technology has grown in popularity as a means of implementing safe,dependable,and decentralised independent IATS systems,allowing for more utilisation of legacy IATS infrastructures and resources,which is especially advantageous for crowdsourcing technologies.Blockchain technology can be used to address security concerns in the IATS and to aid in logistics development.In light of the inadequacy of reliance and inattention to rights created by centralised and conventional logistics systems,this paper discusses the creation of a blockchain-based IATS powered by deep learning for secure cargo and vehicle matching(BDL-IATS).The BDL-IATS approach utilises Ethereum as the primary blockchain for storing private data such as order and shipment details.Additionally,the deep belief network(DBN)model is used to select suitable vehicles and goods for transportation.Additionally,the chaotic krill herd technique is used to tune the DBN model’s hyper-parameters.The performance of the BDL-IATS technique is validated,and the findings are inspected under a variety of conditions.The simulationfindings indicated that the BDL-IATS strategy outperformed recent state-of-the-art approaches.