Search results for: Hidden%20Markov%20Model

Authors: K. Shiba, T. Kaburagi, Y. Kurihara

Abstract:

With global aging, people who require care, such as people with dementia (PwD), are increasing within many developed countries. And PwDs may wander and unconsciously set foot outdoors, it may lead serious accidents, such as, traffic accidents. Here, round-the-clock monitoring by caregivers is necessary, which can be a burden for the caregivers. Therefore, an automatic wandering detection system is required when an elderly person wanders outdoors, in which case the detection system transmits a ‘moving’ followed by an ‘absence’ state. In this paper, we focus on the transition from the ‘resting’ to the ‘absence’ state, via the ‘moving’ state as one of the wandering transitions. To capture the transition of the three states, our method based on the hidden Markov model (HMM) is built. Using our method, the restraint where the ‘resting’ state and ‘absence’ state cannot be transmitted to each other is applied. To validate our method, we conducted the experiment with 10 subjects. Our results show that the method can classify three states with 0.92 accuracy.

Keywords: wander, microwave Doppler sensor, respiratory frequency band, the state transition, hidden Markov model (HMM).

Procedia PDF Downloads 155

Authors: Joselito Medina-Marin, Maria G. Serna-Diaz, Alejandro Tellez-Jurado, Juan C. Seck-Tuoh-Mora, Eva S. Hernandez-Gress, Norberto Hernandez-Romero, Iaina P. Medina-Serna

Abstract:

Trichoderma harzianum is a fungus that has been utilized as a low-cost fungicide for biological control of pests, and it is important to determine the optimal conditions to produce the highest amount of conidiospores of Trichoderma harzianum. In this work, the conidiospore production of Trichoderma harzianum is modeled and optimized by using Artificial Neural Networks (AANs). In order to gather data of this process, 30 experiments were carried out taking into account the number of hours of culture (10 distributed values from 48 to 136 hours) and the culture humidity (70, 75 and 80 percent), obtained as a response the number of conidiospores per gram of dry mass. The experimental results were used to develop an iterative algorithm to create 1,110 ANNs, with different configurations, starting from one to three hidden layers, and every hidden layer with a number of neurons from 1 to 10. Each ANN was trained with the Levenberg-Marquardt backpropagation algorithm, which is used to learn the relationship between input and output values. The ANN with the best performance was chosen in order to simulate the process and be able to maximize the conidiospores production. The obtained ANN with the highest performance has 2 inputs and 1 output, three hidden layers with 3, 10 and 10 neurons in each layer, respectively. The ANN performance shows an R2 value of 0.9900, and the Root Mean Squared Error is 1.2020. This ANN predicted that 644175467 conidiospores per gram of dry mass are the maximum amount obtained in 117 hours of culture and 77% of culture humidity. In summary, the ANN approach is suitable to represent the conidiospores production of Trichoderma harzianum because the R2 value denotes a good fitting of experimental results, and the obtained ANN model was used to find the parameters to produce the biggest amount of conidiospores per gram of dry mass.

Keywords: Trichoderma harzianum, modeling, optimization, artificial neural network

Procedia PDF Downloads 122

Authors: Issam Alnader, Aboubaker Lasebae, Rand Raheem

Abstract:

Wireless sensor networks (WSNs) are distributed network systems used in a wide range of applications, including safety-critical systems. The latter provide critical services, often concerned with human life or assets. Therefore, ensuring the dependability requirements of Safety critical systems is of paramount importance. The purpose of this paper is to utilize the Hidden Markov Model (HMM) to elongate the service availability of WSNs by increasing the time it takes a node to become obsolete via optimal load balancing. We propose an HMM algorithm that, given a WSN, analyses and predicts undesirable situations, notably, nodes dying unexpectedly or prematurely. We apply this technique to improve on C. Lius’ algorithm, a scheduling-based algorithm which has served to improve the lifetime of WSNs. Our experiments show that our HMM technique improves the lifetime of the network, achieved by detecting nodes that die early and rebalancing their load. Our technique can also be used for diagnosis and provide maintenance warnings to WSN system administrators. Finally, our technique can be used to improve algorithms other than C. Liu’s.

Keywords: wireless sensor networks, IoT, dependability of safety WSNs, energy conservation, sleep awake schedule

Procedia PDF Downloads 71

Authors: Muhammad Muhammad Suleiman

Abstract:

Cloud Computing is a versatile concept that refers to a service that allows users to outsource their data without having to worry about local storage issues. However, the most pressing issues to be addressed are maintaining a secure and reliable data repository rather than relying on untrustworthy service providers. In this study, we look at how stenography approaches and collaboration with Digital Watermarking can greatly improve the system's effectiveness and data security when used for Cloud Computing. The main requirement of such frameworks, where data is transferred or exchanged between servers and users, is safe data management in cloud environments. Steganography is the cloud is among the most effective methods for safe communication. Steganography is a method of writing coded messages in such a way that only the sender and recipient can safely interpret and display the information hidden in the communication channel. This study presents a new text steganography method for hiding a loaded hidden English text file in a cover English text file to ensure data protection in cloud computing. Data protection, data hiding capability, and time were all improved using the proposed technique.

Keywords: cloud computing, steganography, information hiding, cloud storage, security

Procedia PDF Downloads 161

Authors: Insaf Ajili, Malik Mallem, Jean-Yves Didier

Abstract:

Human motion recognition has been extensively increased in recent years due to its importance in a wide range of applications, such as human-computer interaction, intelligent surveillance, augmented reality, content-based video compression and retrieval, etc. However, it is still regarded as a challenging task especially in realistic scenarios. It can be seen as a general machine learning problem which requires an effective human motion representation and an efficient learning method. In this work, we introduce a descriptor based on Laban Movement Analysis technique, a formal and universal language for human movement, to capture both quantitative and qualitative aspects of movement. We use Discrete Hidden Markov Model (DHMM) for training and classification motions. We improve the classification algorithm by proposing two DHMMs for each motion class to process the motion sequence in two different directions, forward and backward. Such modification allows avoiding the misclassification that can happen when recognizing similar motions. Two experiments are conducted. In the first one, we evaluate our method on a public dataset, the Microsoft Research Cambridge-12 Kinect gesture data set (MSRC-12) which is a widely used dataset for evaluating action/gesture recognition methods. In the second experiment, we build a dataset composed of 10 gestures(Introduce yourself, waving, Dance, move, turn left, turn right, stop, sit down, increase velocity, decrease velocity) performed by 20 persons. The evaluation of the system includes testing the efficiency of our descriptor vector based on LMA with basic DHMM method and comparing the recognition results of the modified DHMM with the original one. Experiment results demonstrate that our method outperforms most of existing methods that used the MSRC-12 dataset, and a near perfect classification rate in our dataset.

Keywords: human motion recognition, motion representation, Laban Movement Analysis, Discrete Hidden Markov Model

Procedia PDF Downloads 175

Authors: Khaled M. Alhawiti

Abstract:

This research study aims to present a retrospective study about speech recognition systems and artificial intelligence. Speech recognition has become one of the widely used technologies, as it offers great opportunity to interact and communicate with automated machines. Precisely, it can be affirmed that speech recognition facilitates its users and helps them to perform their daily routine tasks, in a more convenient and effective manner. This research intends to present the illustration of recent technological advancements, which are associated with artificial intelligence. Recent researches have revealed the fact that speech recognition is found to be the utmost issue, which affects the decoding of speech. In order to overcome these issues, different statistical models were developed by the researchers. Some of the most prominent statistical models include acoustic model (AM), language model (LM), lexicon model, and hidden Markov models (HMM). The research will help in understanding all of these statistical models of speech recognition. Researchers have also formulated different decoding methods, which are being utilized for realistic decoding tasks and constrained artificial languages. These decoding methods include pattern recognition, acoustic phonetic, and artificial intelligence. It has been recognized that artificial intelligence is the most efficient and reliable methods, which are being used in speech recognition.

Keywords: speech recognition, acoustic phonetic, artificial intelligence, hidden markov models (HMM), statistical models of speech recognition, human machine performance

Procedia PDF Downloads 445

Authors: Jingyuan Hu, Zhandong Liu

Abstract:

CRISPR genome editing technology has transformed molecular biology by accurately targeting and altering an organism’s DNA. Despite the state-of-art precision of CRISPR genome editing, the imprecise mutation outcome and off-target effects present considerable risk, potentially leading to unintended genetic changes. Targeted deep sequencing, combined with bioinformatics sequence alignment, can detect such unwanted mutations. Nevertheless, the classical method, Needleman-Wunsch (NW) algorithm may produce false alignment outcomes, resulting in inaccurate mutation identification. The key to precisely identifying CRISPR-induced mutations lies in determining optimal parameters for the sequence alignment algorithm. Hidden Markov models (HMM) are ideally suited for this task, offering flexibility across CRISPR systems by leveraging forward-backward algorithms for parameter estimation. In this study, we introduce CRISPR-HMM, a statistical software to precisely call CRISPR-induced mutations. We demonstrate that the software significantly improves precision in identifying CRISPR-induced mutations compared to NW-based alignment, thereby enhancing the overall understanding of the CRISPR gene-editing process.

Keywords: CRISPR, HMM, sequence alignment, gene editing

Procedia PDF Downloads 17

Authors: Ihtasham Hamza

Abstract:

In the contemporary world, where the West is afflicted by the diseases of excess nutrition, much of the rest globe suffers at the hands of hunger. A troubling constituent of hunger is micronutrient deficiency, also called hidden hunger. Major dependence on calorie-rich diets and low diet diversification are responsible for high malnutrition rates, especially in African and Asian countries. But the dilemma isn’t immune to solutions. Highlighting the substantial cause to be sole dependence on staples for food, biofortification has emerged as a novel tool to confront the widely distributed jeopardize of hidden hunger. Biofortification potentials the better nutritional approachability to commonalities overcoming various difficulties and reaching the doorstep. The crops associated with biofortification offer a rural-based involvement that, proposal, primarily reaches these more remote populations, which comprise a majority of the malnourished in many countries, and then penetrates to urban populations as assembly overages are marketed. Initial investments in agricultural research at a central location can generate high recurrent benefits at low cost as adapted biofortified cultivars become widely available in countries across time at low recurrent costs as opposed to supplementation which is comparatively expensive and requires continued financing over time, which may be imperilled by fluctuating political curiosity.

Keywords: biofortified crops, hunger, malnutrition, agricultural practices

Procedia PDF Downloads 258

Authors: M. A. Lahmer, K. Guergouri

Abstract:

In this work, Kinetic Monte Carlo (KMC) method was applied to study the thermal stability of hydrogen in ZnO bulk and thin films. Our simulation includes different possible events such as interstitial hydrogen (Hi) jumps, substitutional hydrogen (HO) formation and dissociation, oxygen and zinc vacancies jumps, hydrogen-VZn complexes formation and dissociation, HO-Hi complex formation and hydrogen molecule (H2) formation and dissociation. The obtained results show that the hidden hydrogen formed during thermal annealing or at room temperature is constituted of both hydrogen molecule and substitutional hydrogen. The ratio of this constituants depends on the initial defects concentration as well as the annealing temperature. For annealing temperature below 300°C hidden hydrogen was found to be constituted from both substitutional hydrogen and hydrogen molecule, however, for higher temperature it is composed essentially from HO defects only because H2 was found to be unstable. In the other side, our results show that the remaining hydrogen amount in sample during thermal annealing depend greatly on the oxygen vacancies in the material. H2 molecule was found to be stable for thermal annealing up to 200°C, VZnHn complexes are stable up to 350°C and HO was found to be stable up to 450°C.

Keywords: ZnO, hydrogen, thermal annealing, kinetic Monte Carlo

Procedia PDF Downloads 300

Authors: Crescentia Ugwuona

Abstract:

Considering the importance of proverbs in socio-cultural life through socialization in any given society, it is deemed important for people to understand the hidden meanings that proverbs may convey. So far, there has been hardly any systematic research in the representation of different genders in Nigeria. Although there are writings on the representation of women in Nigerian proverbs, they are based on the writers’ introspection. Beyond that, investigators often tend to overlook the representations of men in proverbs. This study therefore explores from the perspective of sociolinguistics and critical discourse analysis (CDA) how different genders (men and women) are represented in Nigerian proverbs with particular reference to Igbo-Nigerians; with the aim of uncovering hidden gender inequalities that exist in them. The analysis reveals that Igbo proverbs consistently perpetuate an ideology of gender inequality, that is, male proverbs depict male achievements, power, bravery, and male supremacy; while that of female connotes their submissions to cultural and traditional female domestic roles, chastity, less competent, and women subjugation. The study alerts to how gendered language in proverbs can reflect, create, and sustain gender inequality in societies; and contributes to an education aimed at gender equality, emancipator practice of appropriate language in proverbs, respect for human rights; and of the need to develop strategies for addressing the problem.

Keywords: critical discourse analysis, gender representation, gender stereotypes, Igbo-Nigerian, sociolinguistics analysis, proverbs

Procedia PDF Downloads 250

Authors: Sheena Christabel Pravin, M. Palanivelan

Abstract:

Speech disfluencies are common in spontaneous speech. The primary purpose of this study was to distinguish linguistic disfluencies from stuttering disfluencies in bilingual Tamil–English (TE) speaking children. The secondary purpose was to determine whether their disfluencies are mediated by native language dominance and/or on an early onset of developmental stuttering at childhood. A detailed study was carried out to identify the prosodic and acoustic features that uniquely represent the disfluent regions of speech. This paper focuses on statistical modeling of repetitions, prolongations, pauses and interjections in the speech corpus encompassing bilingual spontaneous utterances from school going children – English and Tamil. Two classifiers including Hidden Markov Models (HMM) and the Multilayer Perceptron (MLP), which is a class of feed-forward artificial neural network, were compared in the classification of disfluencies. The results of the classifiers document the patterns of disfluency in spontaneous speech samples of school-aged children to distinguish between Children Who Stutter (CWS) and Children with Language Impairment CLI). The ability of the models in classifying the disfluencies was measured in terms of F-measure, Recall, and Precision.

Keywords: bi-lingual, children who stutter, children with language impairment, hidden markov models, multi-layer perceptron, linguistic disfluencies, stuttering disfluencies

Procedia PDF Downloads 189

Authors: M. Abbasi Layegh, S. Haghipour, K. Athari, R. Khosravi, M. Tafkikialamdari

Abstract:

An approach to find the optimum mel-frequency cepstral coefficients (MFCCs) for the Radif of Mirzâ Ábdollâh, which is the principal emblem and the heart of Persian music, performed by most famous Iranian masters on two Iranian stringed instruments ‘Tar’ and ‘Setar’ is proposed. While investigating the variance of MFCC for each record in themusic database of 1500 gushe of the repertoire belonging to 12 modal systems (dastgâh and âvâz), we have applied the Fuzzy C-Mean clustering algorithm on each of the 12 coefficient and different combinations of those coefficients. We have applied the same experiment while increasing the number of coefficients but the clustering accuracy remained the same. Therefore, we can conclude that the first 7 MFCCs (V-7MFCC) are enough for classification of The Radif of Mirzâ Ábdollâh. Classical machine learning algorithms such as MLP neural networks, K-Nearest Neighbors (KNN), Gaussian Mixture Model (GMM), Hidden Markov Model (HMM) and Support Vector Machine (SVM) have been employed. Finally, it can be realized that SVM shows a better performance in this study.

Keywords: radif of Mirzâ Ábdollâh, Gushe, mel frequency cepstral coefficients, fuzzy c-mean clustering algorithm, k-nearest neighbors (KNN), gaussian mixture model (GMM), hidden markov model (HMM), support vector machine (SVM)

Procedia PDF Downloads 414

Authors: Gulseren Mutlu, Gurupdesh Pandher

Abstract:

This paper studies the strategic interplay between innovation, incentives, expropriation threat and disputes arising from expropriation from an intra-organization perspective. We present a simple principal-agent model with hidden actions and hidden information in which two employees can choose how much (innovative) effort to exert, whether to expropriate the innovation of the other employee and whether to dispute if innovation is expropriated. The organization maximizes its expected payoff by choosing the optimal reward scheme for both employees as well as whether to encourage or discourage disputes. We analyze two mechanisms under which innovative ideas are not expropriated. First, we show that under a non-contestable mechanism (in which the organization discourages disputes among employees), the organization has to offer a “rent” to the potential expropriator. However, under a contestable mechanism (in which the organization encourages disputes), there is no need for such rent. If the cost of resolving the dispute is negligible, the organization’s expected payoff is higher under a contestable mechanism. Second, we develop a comparable team mechanism in which innovation takes place as a result of the joint efforts of employees and innovation payments are made based on the team outcome. We show that if the innovation value is low and employees have similar productivity, then the organization is better off under a contestable mechanism. On the other hand, if the innovation value is high, the organization is better off under a team mechanism. Our results have important practical implications for the design of innovation reward system for employees, hiring policy and governance for different companies.

Keywords: innovation, incentives, expropriation threat, dispute resolution

Procedia PDF Downloads 589

Authors: Michelle Hand, Brieanne Beaujolais

Abstract:

Rape stereotypes have long involved the assault of young females by strangers desiring sex. As such, older adult women and men have largely been excluded from research, policies, and awareness raising initiatives to address sexual violence. Moreover sexual assault accounts for the most underreported type of abuse experienced by older adults, highlighting a need to expand our knowledge base in this area. Thus a systematic review of peer-reviewed scholarly articles and reports was conducted to explore the ways sexual assault has been prevented among older adults in recent years and to identify implications for researchers and practitioners as they aim to meet the needs of this population. Articles and reports published during or after 2007 were eligible if their focus included methods to address sex abuse among older adults as well as practice or research implications. Forty-four articles met this criteria and were included in this systematic review. The findings from this review will provide an in-depth understanding of the under-researched issue of sexual violence among older adult women and men as well as current prevention strategies. In addition, implications and recommendations will be provided for practitioners, educators and researchers as they aim to meet the hidden needs of this growing yet under-researched population.

Keywords: elder, rape, sexual assault, sexual violence

Procedia PDF Downloads 289

Authors: Geetanjali Sharma

Abstract:

There are always provincial variations which deserve more detailed treatment. Before the arrival of modern era, geography and cultural homogeneity were determining factors of human habitat and migration. Boundaries as if we see them, did not exist earlier. The connectivity of the world was also different as of now. The reinforcement of the old silk route will improve economic cooperation and connectivity between Asian, European and African countries, but obviously, it is designed to improve China’s geopolitical and geostrategic position in the world. The paper is based on the secondary sources of data. Analytical and historical approach has been used to clarify the ties between the old silk routes and new One-Belt-One-Road initiative China. The paper begins with an explanation of the historical background of the old Silk Route, its origin and development, trailed by an analysis of latest declarations by the Chinese leaders to revive it. It also discusses the impacts of this initiative on India’s economy and cultural exchange between associated regions. Lastly, the paper sums up the findings and suggestions for keeping a balance between the security and economic relationship between the countries. It concludes that the silk route is an effort in commencing a ‘grand strategy’ for global trade and cooperation with hidden objectives of China to increase the investment of China in other continents as well. The revival of silk route may prove to be a very helpful in reinforcing cooperation and raising it to a new level of economic establishments. However, China has yet to promote the much-needed political and strategic trust.

Keywords: OBOR (One-Belt-One-Road), geopolitics, economic relation, security concerns

Procedia PDF Downloads 245

Authors: Youngjae Jin, Daeshik Kim

Abstract:

This paper describes a cycle accurate simulation results of weight values learned by an auto-encoder behavior model in terms of pre-route simulation. Given the results we visualized the first layer representations with natural images. Many common deep learning threads have focused on learning high-level abstraction of unlabeled raw data by unsupervised feature learning. However, in the process of handling such a huge amount of data, the learning method’s computation complexity and time limited advanced research. These limitations came from the fact these algorithms were computed by using only single core CPUs. For this reason, parallel-based hardware, FPGAs, was seen as a possible solution to overcome these limitations. We adopted and simulated the ready-made auto-encoder to design a behavior model in Verilog HDL before designing hardware. With the auto-encoder behavior model pre-route simulation, we obtained the cycle accurate results of the parameter of each hidden layer by using MODELSIM. The cycle accurate results are very important factor in designing a parallel-based digital hardware. Finally this paper shows an appropriate operation of behavior model based pre-route simulation. Moreover, we visualized learning latent representations of the first hidden layer with Kyoto natural image dataset.

Keywords: auto-encoder, behavior model simulation, digital hardware design, pre-route simulation, Unsupervised feature learning

Procedia PDF Downloads 417

Authors: Cristóbal Moënne-Loccoz, Rodrigo C. Vergara, Vladimir López, Domingo Mery, Diego Cosmelli

Abstract:

Our daily interaction with computational interfaces is plagued of situations in which we go from inexperienced users to experts through self-motivated exploration of the same task. In many of these interactions, we must learn to find our way through a sequence of decisions and actions before obtaining the desired result. For instance, when drawing cash from an ATM machine, choices are presented in a step-by-step fashion so that a specific sequence of actions must be performed in order to produce the expected outcome. But, as they become experts in the use of such interfaces, do users adopt specific search and learning strategies? Moreover, if so, can we use this information to follow the process of expertise development and, eventually, predict future actions? This would be a critical step towards building truly adaptive interfaces that can facilitate interaction at different moments of the learning curve. Furthermore, it could provide a window into potential mechanisms underlying decision-making behavior in real world scenarios. Here we tackle this question using a simple game interface that instantiates a 4-level binary decision tree (BDT) sequential decision-making task. Participants have to explore the interface and discover an underlying concept-icon mapping in order to complete the game. We develop a Hidden Markov Model (HMM)-based approach whereby a set of stereotyped, hierarchically related search behaviors act as hidden states. Using this model, we are able to track the decision-making process as participants explore, learn and develop expertise in the use of the interface. Our results show that partitioning the problem space into such stereotyped strategies is sufficient to capture a host of exploratory and learning behaviors. Moreover, using the modular architecture of stereotyped strategies as a Mixture of Experts, we are able to simultaneously ask the experts about the user's most probable future actions. We show that for those participants that learn the task, it becomes possible to predict their next decision, above chance, approximately halfway through the game. Our long-term goal is, on the basis of a better understanding of real-world decision-making processes, to inform the construction of interfaces that can establish dynamic conversations with their users in order to facilitate the development of expertise.

Keywords: behavioral modeling, expertise acquisition, hidden markov models, sequential decision-making

Procedia PDF Downloads 225

Authors: Saad M. Darwish, Magda M. Madbouly, Murad B. Khorsheed

Abstract:

Sign Languages (SL) are the most accomplished forms of gestural communication. Therefore, their automatic analysis is a real challenge, which is interestingly implied to their lexical and syntactic organization levels. Hidden Markov models (HMM’s) have been used prominently and successfully in speech recognition and, more recently, in handwriting recognition. Consequently, they seem ideal for visual recognition of complex, structured hand gestures such as are found in sign language. In this paper, several results concerning static hand gesture recognition using an algorithm based on Type-2 Fuzzy HMM (T2FHMM) are presented. The features used as observables in the training as well as in the recognition phases are based on Singular Value Decomposition (SVD). SVD is an extension of Eigen decomposition to suit non-square matrices to reduce multi attribute hand gesture data to feature vectors. SVD optimally exposes the geometric structure of a matrix. In our approach, we replace the basic HMM arithmetic operators by some adequate Type-2 fuzzy operators that permits us to relax the additive constraint of probability measures. Therefore, T2FHMMs are able to handle both random and fuzzy uncertainties existing universally in the sequential data. Experimental results show that T2FHMMs can effectively handle noise and dialect uncertainties in hand signals besides a better classification performance than the classical HMMs. The recognition rate of the proposed system is 100% for uniform hand images and 86.21% for cluttered hand images.

Keywords: hand gesture recognition, hand detection, type-2 fuzzy logic, hidden Markov Model

Procedia PDF Downloads 431

Authors: Andrew N. Saylor, James R. Peters

Abstract:

Scoliosis is a complex 3D deformity of the thoracic and lumbar spines, clinically diagnosed by measurement of a Cobb angle of 10 degrees or more on a coronal X-ray. The Cobb angle is the angle made by the lines drawn along the proximal and distal endplates of the respective proximal and distal vertebrae comprising the curve. Traditionally, Cobb angles are measured manually using either a marker, straight edge, and protractor or image measurement software. The task of measuring the Cobb angle can also be represented by a function taking the spine geometry rendered using X-ray imaging as input and returning the approximate angle. Although the form of such a function may be unknown, it can be approximated using artificial neural networks (ANNs). The performance of ANNs is affected by many factors, including the choice of activation function and network architecture; however, the effects of these parameters on the accuracy of scoliotic deformity measurements are poorly understood. Therefore, the objective of this study was to systematically investigate the effect of ANN architecture and activation function on Cobb angle measurement from the coronal X-rays of scoliotic subjects. The data set for this study consisted of 609 coronal chest X-rays of scoliotic subjects divided into 481 training images and 128 test images. These data, which included labeled Cobb angle measurements, were obtained from the SpineWeb online database. In order to normalize the input data, each image was resized using bi-linear interpolation to a size of 500 × 187 pixels, and the pixel intensities were scaled to be between 0 and 1. A fully connected (dense) ANN with a fixed cost function (mean squared error), batch size (10), and learning rate (0.01) was developed using Python Version 3.7.3 and TensorFlow 1.13.1. The activation functions (sigmoid, hyperbolic tangent [tanh], or rectified linear units [ReLU]), number of hidden layers (1, 3, 5, or 10), and number of neurons per layer (10, 100, or 1000) were varied systematically to generate a total of 36 network conditions. Stochastic gradient descent with early stopping was used to train each network. Three trials were run per condition, and the final mean squared errors and mean absolute errors were averaged to quantify the network response for each condition. The network that performed the best used ReLU neurons had three hidden layers, and 100 neurons per layer. The average mean squared error of this network was 222.28 ± 30 degrees2, and the average mean absolute error was 11.96 ± 0.64 degrees. It is also notable that while most of the networks performed similarly, the networks using ReLU neurons, 10 hidden layers, and 1000 neurons per layer, and those using Tanh neurons, one hidden layer, and 10 neurons per layer performed markedly worse with average mean squared errors greater than 400 degrees2 and average mean absolute errors greater than 16 degrees. From the results of this study, it can be seen that the choice of ANN architecture and activation function has a clear impact on Cobb angle inference from coronal X-rays of scoliotic subjects.

Keywords: scoliosis, artificial neural networks, cobb angle, medical imaging

Procedia PDF Downloads 96

Authors: Rachid Belhachemi, Pierre Rostan, Alexandra Rostan

Abstract:

This paper develops a discrete-time option pricing model for index options. The model consists of two key ingredients. First, daily stock return innovations are driven by a continuous hidden threshold mixed skew-normal (HTSN) distribution which generates conditional non-normality that is needed to fit daily index return. The most important feature of the HTSN is the inclusion of a latent state variable with a continuum of states, unlike the traditional mixture distributions where the state variable is discrete with little number of states. The HTSN distribution belongs to the class of univariate probability distributions where parameters of the distribution capture the dependence between the variable of interest and the continuous latent state variable (the regime). The distribution has an interpretation in terms of a mixture distribution with time-varying mixing probabilities. It has been shown empirically that this distribution outperforms its main competitor, the mixed normal (MN) distribution, in terms of capturing the stylized facts known for stock returns, namely, volatility clustering, leverage effect, skewness, kurtosis and regime dependence. Second, heteroscedasticity in the model is captured by a threeexogenous-factor GARCH model (GARCHX), where the factors are taken from the principal components analysis of various world indices and presents an application to option pricing. The factors of the GARCHX model are extracted from a matrix of world indices applying principal component analysis (PCA). The empirically determined factors are uncorrelated and represent truly different common components driving the returns. Both factors and the eight parameters inherent to the HTSN distribution aim at capturing the impact of the state of the economy on price levels since distribution parameters have economic interpretations in terms of conditional volatilities and correlations of the returns with the hidden continuous state. The PCA identifies statistically independent factors affecting the random evolution of a given pool of assets -in our paper a pool of international stock indices- and sorting them by order of relative importance. The PCA computes a historical cross asset covariance matrix and identifies principal components representing independent factors. In our paper, factors are used to calibrate the HTSN-GARCHX model and are ultimately responsible for the nature of the distribution of random variables being generated. We benchmark our model to the MN-GARCHX model following the same PCA methodology and the standard Black-Scholes model. We show that our model outperforms the benchmark in terms of RMSE in dollar losses for put and call options, which in turn outperforms the analytical Black-Scholes by capturing the stylized facts known for index returns, namely, volatility clustering, leverage effect, skewness, kurtosis and regime dependence.

Keywords: continuous hidden threshold, factor models, GARCHX models, option pricing, risk-premium

Procedia PDF Downloads 276

Authors: Poonam A. Trambadia, Ashish V. Trambadia

Abstract:

The architecture of sultanate period of Ahmedabad had evolved just before the establishment of Mughal rule in North India. After shifting the capital of the kingdom from Patan to Ahmedabad, when the buildings and structures were being built, an interesting cultural blend happened in architecture. Many sultanate buildings in Ahmedabad historic city have resemblance with Patan including the names. Outer fortification walls and Gates were built during the rule of the third ruler in the late 15th century. All the gates had sandstone slabs supported by three arched entrance in sandstone with wooden shutter. A restoration project of Khanpur Gate was initiated in 2016. The paper identifies some evidences and some hidden layers of structures as important elements of cultural interchange while some were just forgotten in the process. The recycling of pre-existing elements of structures are examined and compared. There were layers uncovered that were hidden behind later repairs using traditional brick arch, which was taken out in the process. As the gate had partially collapsed, the restoration included piece by piece dismantling and restoring in the same sequence wherever required. The recycled materials found in the process were recorded and provided the basis for this study. The gate after this discovery sets a new example of fortification Gate built in Sultanate era. The comparison excludes Maratha and British Period Gates to avoid further confusion and focuses on 15th – 16th century sultanate architecture of Ahmedabad.

Keywords: Ahmedabad World Heritage, fortification, Indo-Islamic style, Sultanate architecture, cultural interchange

Procedia PDF Downloads 94

Authors: Hadri Hussain, M.Nasir Ibrahim, Chee-Ming Ting, Mariani Idroas, Fuad Numan, Alias Mohd Noor

Abstract:

A biometric security system has become an important application in client identification and verification system. A conventional biometric system is normally based on unimodal biometric that depends on either behavioural or physiological information for authentication purposes. The behavioural biometric depends on human body biometric signal (such as speech) and biosignal biometric (such as electrocardiogram (ECG) and phonocardiogram or heart sound (HS)). The speech signal is commonly used in a recognition system in biometric, while the ECG and the HS have been used to identify a person’s diseases uniquely related to its cluster. However, the conventional biometric system is liable to spoof attack that will affect the performance of the system. Therefore, a multimodal biometric security system is developed, which is based on biometric signal of ECG, HS, and speech. The biosignal data involved in the biometric system is initially segmented, with each segment Mel Frequency Cepstral Coefficients (MFCC) method is exploited for extracting the feature. The Hidden Markov Model (HMM) is used to model the client and to classify the unknown input with respect to the modal. The recognition system involved training and testing session that is known as client identification (CID). In this project, twenty clients are tested with the developed system. The best overall performance at 44 kHz was 93.92% for ECG and the worst overall performance was ECG at 88.47%. The results were compared to the best overall performance at 44 kHz for (20clients) to increment of clients, which was 90.00% for HS and the worst overall performance falls at ECG at 79.91%. It can be concluded that the difference multimodal biometric has a substantial effect on performance of the biometric system and with the increment of data, even with higher frequency sampling, the performance still decreased slightly as predicted.

Keywords: electrocardiogram, phonocardiogram, hidden markov model, mel frequency cepstral coeffiecients, client identification

Procedia PDF Downloads 252

Authors: B. R. Campomanes-Alvarez, P. Quiros, B. Fernandez

Abstract:

Automatic Speech Recognition (ASR) is a machine-based process of decoding and transcribing oral speech. A typical ASR system receives acoustic input from a speaker or an audio file, analyzes it using algorithms, and produces an output in the form of a text. Some speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian Mixture Models (GMMs) to determine how well each state of each HMM fits a short window of frames of coefficients that represents the acoustic input. Another way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition systems. Acoustic models for state-of-the-art ASR systems are usually training on massive amounts of data. However, audio files with their corresponding transcriptions can be difficult to obtain, especially in the Spanish language. Hence, in the case of these low-resource scenarios, building an ASR model is considered as a complex task due to the lack of labeled data, resulting in an under-trained system. Semi-supervised learning approaches arise as necessary tasks given the high cost of transcribing audio data. The main goal of this proposal is to develop a procedure based on acoustic semi-supervised learning for Spanish ASR systems by using DNNs. This semi-supervised learning approach consists of: (a) Training a seed ASR model with a DNN using a set of audios and their respective transcriptions. A DNN with a one-hidden-layer network was initialized; increasing the number of hidden layers in training, to a five. A refinement, which consisted of the weight matrix plus bias term and a Stochastic Gradient Descent (SGD) training were also performed. The objective function was the cross-entropy criterion. (b) Decoding/testing a set of unlabeled data with the obtained seed model. (c) Selecting a suitable subset of the validated data to retrain the seed model, thereby improving its performance on the target test set. To choose the most precise transcriptions, three confidence scores or metrics, regarding the lattice concept (based on the graph cost, the acoustic cost and a combination of both), was performed as selection technique. The performance of the ASR system will be calculated by means of the Word Error Rate (WER). The test dataset was renewed in order to extract the new transcriptions added to the training dataset. Some experiments were carried out in order to select the best ASR results. A comparison between a GMM-based model without retraining and the DNN proposed system was also made under the same conditions. Results showed that the semi-supervised ASR-model based on DNNs outperformed the GMM-model, in terms of WER, in all tested cases. The best result obtained an improvement of 6% relative WER. Hence, these promising results suggest that the proposed technique could be suitable for building ASR models in low-resource environments.

Keywords: automatic speech recognition, deep neural networks, machine learning, semi-supervised learning

Procedia PDF Downloads 317

Authors: Chih-Ping Chang

Abstract:

Different from traditional objective evidence, social media evidence has its own characteristics with easily tampering, recoverability, and cannot be read without using other devices (such as a computer). Simply taking a screenshot from social network sites must be questioned its original identity. When the police search and seizure digital information, a common way they use is to directly print out digital data obtained and ask the signature of the parties at the presence, without taking original digital data back. In addition to the issue on its original identity, this conduct to obtain evidence may have another two results. First, it will easily allege that is tampering evidence because the police wanted to frame the suspect and falsified evidence. Second, it is not easy to discovery hidden information. The core evidence associated with crime may not appear in the contents of files. Through discovery the original file, data related to the file, such as the original producer, creation time, modification date, and even GPS location display can be revealed from hidden information. Therefore, how to show this kind of evidence in the courtroom will be arguably the most important task for ruling social media evidence. This article, first, will introduce forensic software, like EnCase, TCT, FTK, and analyze their function to prove the identity with another digital data. Then turning back to the court, the second part of this article will discuss legal standard for authentication of social media evidence and application of that forensic software in the courtroom. As the conclusion, this article will provide a rethinking, that is, what kind of authenticity is this rule of evidence chase for. Does legal system automatically operate the transcription of scientific knowledge? Or furthermore, it wants to better render justice, not only under scientific fact, but through multivariate debating.

Keywords: federal rule of evidence, internet forensic, printouts as evidence, social media evidence, United States v. Vayner

Procedia PDF Downloads 267

Authors: Xiaohui Pan

Abstract:

As the most influential media for the dissemination of Chinese culture, films and television dramas have played cognitive orientation in guiding young audience to understand its cultural value. Taking a retrospective overview of the Chinese domestic film and television dramas in the last decade, it is tangible to notice that Westernization has become irresistible force in the presentation of Chinese youth culture, such as the rise of sensibility, publicity of subjectivity, and the resistance to mainstream discourse. However, the process of deconstruction and transition of these film and television works on Western youth culture brought about more comprehensive conflicts and integration rather than providing a panoramic interpretation to young Chinese. Issues of tradition and modernization, oriental and Western, and serious thinking and the spirit of entertainment overwhelmed those Chinese works. This study attempts to examine the mechanism of young Chinese’s resistance, compromise and re-construction in their marriages during the dynamic cultural intergration between traditional Chinese culture and Western culture. To investigate such a mechanism, this study analyzed four Chinese television dramas themed on family ethics to reveal the conflictions between two generations, mother-in-law and daughter-in-law, aiming to identify their strategies of their struggles. Incorporating the theory of Scott's weapons of the weak, this study examines the dynamic model of the struggles content analysis on their hidden language and the power. The finding shows that young Chinese identified their self-awakening during the resistance. The study also finds out that the external factors might have the functions of switching the power from the strong end to the weak end. The finding of this study can provide useful insights for researchers in this area and for those in the process of exploring cultural integration issues.

Keywords: intergration, integration, resistance, youth culture

Procedia PDF Downloads 394

Authors: Anthony Oppong Kyekyeku, Sussana Antwi-Boasiako, Emmanuel De-Graft Johnson Owusu Ansah

Abstract:

In this observational study, the performance of a known conventional storage system was tested and evaluated for fitness for its intended purpose. The system has a scope extended for the storage of dry cocoa beans. System sensitivity, reproducibility and uncertainties are not known in details. This study discusses the system performance in the context of existing literature on factors that influence the quality of cocoa beans during storage. Controlled conditions were defined precisely for the system to give reliable base line within specific established procedures. Minitab® 17 and R statistical software (R-3.3.1) were used for the statistical analyses. The approach to the storage system testing was to observe and compare through laboratory test methods the quality of the cocoa beans samples before and after storage. The samples were kept in Kilner jars and the temperature of the storage environment controlled and monitored over a period of 408 days. Standard test methods use in international trade of cocoa such as the cut test analysis, moisture determination with Aqua boy KAM III model and bean count determination were used for quality assessment. The data analysis assumed the entire population as a sample in order to establish a reliable baseline to the data collected. The study concluded a statistically significant mean value at 95% Confidence Interval (CI) for the performance data analysed before and after storage for all variables observed. Correlational graphs showed a strong positive correlation for all variables investigated with the exception of All Other Defect (AOD). The weak relationship between the before and after data for AOD had an explained variability of 51.8% with the unexplained variability attributable to the uncontrolled condition of hidden infestation before storage. The current study concluded with a high-performance criterion for the storage system.

Keywords: benchmarking performance data, cocoa beans, hidden infestation, storage system validation

Procedia PDF Downloads 145

Authors: Martins Y. Otache, John J. Musa, Abayomi I. Kuti, Mustapha Mohammed

Abstract:

The performance of an artificial neural network (ANN) is contingent on a host of factors, for instance, the network optimisation scheme. In view of this, the study examined the general implications of the ANN training optimisation algorithm on its forecast performance. To this end, the Bayesian regularisation (Br), Levenberg-Marquardt (LM), and the adaptive learning gradient descent: GDM (with momentum) algorithms were employed under different ANN structural configurations: (1) single-hidden layer, and (2) double-hidden layer feedforward back propagation network. Results obtained revealed generally that the gradient descent with momentum (GDM) optimisation algorithm, with its adaptive learning capability, used a relatively shorter time in both training and validation phases as compared to the Levenberg- Marquardt (LM) and Bayesian Regularisation (Br) algorithms though learning may not be consummated; i.e., in all instances considering also the prediction of extreme flow conditions for 1-day and 5-day ahead, respectively especially using the ANN model. In specific statistical terms on the average, model performance efficiency using the coefficient of efficiency (CE) statistic were Br: 98%, 94%; LM: 98 %, 95 %, and GDM: 96 %, 96% respectively for training and validation phases. However, on the basis of relative error distribution statistics (MAE, MAPE, and MSRE), GDM performed better than the others overall. Based on the findings, it is imperative to state that the adoption of ANN for real-time forecasting should employ training algorithms that do not have computational overhead like the case of LM that requires the computation of the Hessian matrix, protracted time, and sensitivity to initial conditions; to this end, Br and other forms of the gradient descent with momentum should be adopted considering overall time expenditure and quality of the forecast as well as mitigation of network overfitting. On the whole, it is recommended that evaluation should consider implications of (i) data quality and quantity and (ii) transfer functions on the overall network forecast performance.

Keywords: streamflow, neural network, optimisation, algorithm

Procedia PDF Downloads 116

Authors: Phakamani Xaba, Robert Huberts, Bilainu Oboirien

Abstract:

The present study was aimed at developing & comparing two neural-network-based predictive models to predict shelf-life/product age of South African margarine using free fatty acid (FFA), water droplet size (D3.3), water droplet distribution (e-sigma), moisture content, peroxide value (PV), anisidine valve (AnV) and total oxidation (totox) value as input variables to the model. Brick margarine products which had varying ages ranging from fresh i.e. week 0 to week 47 were sourced. The brick margarine products which had been stored at 10 & 25 °C and were characterized. JMP and MATLAB models to predict shelf-life/ margarine age were developed and their performances were compared. The key performance indicators to evaluate the model performances were correlation coefficient (CC), root mean square error (RMSE), and mean absolute percentage error (MAPE) relative to the actual data. The MATLAB-developed model showed a better performance in all three performance indicators. The correlation coefficient of the MATLAB model was 99.86% versus 99.74% for the JMP model, the RMSE was 0.720 compared to 1.005 and the MAPE was 7.4% compared to 8.571%. The MATLAB model was selected to be the most accurate, and then, the number of hidden neurons/ nodes was optimized to develop a single predictive model. The optimized MATLAB with 10 neurons showed a better performance compared to the models with 1 & 5 hidden neurons. The developed models can be used by margarine manufacturers, food research institutions, researchers etc, to predict shelf-life/ margarine product age, optimize addition of antioxidants, extend shelf-life of products and proactively troubleshoot for problems related to changes which have an impact on shelf-life of margarine without conducting expensive trials.

Keywords: margarine shelf-life, predictive modelling, neural networks, oil oxidation

Procedia PDF Downloads 165

Authors: Hadjer Sadoune, Liza Lamini, Scherazade Krim, Amel Djouadi, Rachida Rihani

Abstract:

Deep neural networks are highly regarded for their accuracy in predicting intricate fermentation processes. Their ability to learn from a large amount of datasets through artificial intelligence makes them particularly effective models. The primary obstacle in improving the performance of these models is to carefully choose the suitable hyperparameters, including the neural network architecture (number of hidden layers and hidden units), activation function, optimizer, learning rate, and other relevant factors. This study predicts biogas production from real wastewater treatment plant data using a sophisticated approach: hybrid Bayesian optimization with a tree-structured Parzen estimator (BO-TPE) for an optimised deep neural network (DNN) model. The plant utilizes an Upflow Anaerobic Sludge Blanket (UASB) digester that treats industrial wastewater from soft drinks and breweries. The digester has a working volume of 1574 m3 and a total volume of 1914 m3. Its internal diameter and height were 19 and 7.14 m, respectively. The data preprocessing was conducted with meticulous attention to preserving data quality while avoiding data reduction. Three normalization techniques were applied to the pre-processed data (MinMaxScaler, RobustScaler and StandardScaler) and compared with the Non-Normalized data. The RobustScaler approach has strong predictive ability for estimating the volume of biogas produced. The highest predicted biogas volume was 2236.105 Nm³/d, with coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE) values of 0.712, 164.610, and 223.429, respectively.

Keywords: anaerobic digestion, biogas production, deep neural network, hybrid bo-tpe, hyperparameters tuning

Procedia PDF Downloads 11

Authors: Mercedes Sepulveda, Saras Henderson, Dana Farrell, Gaby Heuft

Abstract:

In Australia, there is a significant number of Culturally and Linguistically Diverse (CALD) Grandparent Carers who are sole carers for their grandchildren. Services in the community such as accessible healthcare, financial support, legal aid, and transport to services can assist Grandparent Carers to continue to live in their own home whilst caring for their grandchildren. Community nurses can play a major role by being aware of the needs of these grandparents and link them to services via information and referrals. The CALD Grandparent Carer experiences have only been explored marginally and may be similar to the general Grandparent Carer population, although cultural aspects may add to their difficulties. This Needs-Gap Analysis aimed to uncover ‘hidden issues’ for CALD Grandparent Carers such as service gaps and actions needed to address these issues. The stakeholders selected for this Needs-Gap Analysis were drawn from relevant service providers such as community and aged care services, child and/or grandparents support services and CALD specific services. One hundred relevant service providers were surveyed using six structured questions via face to face, phone interviews, or email correspondence. CALD Grandparents who had a significant or sole role of being a carer for grandchildren were invited to participate through their CALD community leaders. Consultative Forums asking five questions that focused on the caring role, issues encountered, and what needed to be done, were conducted with the African, Asian, Spanish-Speaking, Middle Eastern, European, Pacific Islander and Maori Grandparent Carers living in South-east Queensland, Australia. Data from the service provider survey and the CALD Grandparent Carer forums were content analysed using thematic principles. Our findings highlighted social determinants of health grouped into six themes. These were; 1) service providers and Grandparent Carer perception that there was limited research data on CALD grandparents as carers; 2) inadequate legal and financial support; 3) barriers to accessing information and advice; 4) lack of childcare options in the light of aging and health issues; 5) difficulties around transport; and 6) inadequate technological skills often leading to social isolation for both carer and grandchildren. Our Needs-Gap Analysis provides insight to service providers especially health practitioners such as doctors and community nurses, particularly on the impact of caring for grandchildren on CALD Grandparent Carers. Furthermore, factors such as cultural differences, English language difficulties, and migration experiences also impacted on the way CALD Grandparent Carers are able to cope. The findings of this Need-Gap Analysis signposts some of the ‘ hidden issues’ that CALD Grandparents Carers face and draws together recommendations for the future as put forward by the stakeholders themselves.

Keywords: CALD grandparents, carer needs, community nurses, grandparent carers

Procedia PDF Downloads 291