Search results for: state machine

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 335

Authors: Marcelino Caetano Noronha, Vosco Pereira, Jose Soares Pinto, Ferdinando Da C. Saores

Abstract:

One particularly popular social media platform is Youtube. It’s a video-sharing platform where users can submit videos, and other users can like, dislike or comment on the videos. In this study, we conduct a binary classification task on YouTube’s video comments and review from the users regarding the accession process of Timor Leste to become the eleventh member of the Association of South East Asian Nations (ASEAN). We scrape the data directly from the public YouTube video and apply several pre-processing and weighting techniques. Before conducting the classification, we categorized the data into two classes, namely positive and negative. In the classification part, we apply Support Vector Machine (SVM) algorithm. By comparing with Naïve Bayes Algorithm, the experiment showed SVM achieved 84.1% of Accuracy, 94.5% of Precision, and Recall 73.8% simultaneously.

Keywords: classification, YouTube, sentiment analysis, support sector machine

Procedia PDF Downloads 99

Authors: Chandra Mukherjee

Abstract:

The prevalent knowledge of the biological systems is based on the standard scientific perception of natural equilibrium, determination and predictability. Recently, a rethinking of concepts was presented and a new scientific perspective emerged that involves complexity theory with deterministic chaos theory, nonlinear dynamics and theory of fractals. The unpredictability of the chaotic processes probably would change our understanding of diseases and their management. The mathematical definition of chaos is defined by deterministic behavior with irregular patterns that obey mathematical equations which are critically dependent on initial conditions. The chaos theory is the branch of sciences with an interest in nonlinear dynamics, fractals, bifurcations, periodic oscillations and complexity. Recently, the biomedical interest for this scientific field made these mathematical concepts available to medical researchers and practitioners. Any biological network system is considered to have a nominal state, which is recognized as a homeostatic state. In reality, the different physiological systems are not under normal conditions in a stable state of homeostatic balance, but they are in a dynamically stable state with a chaotic behavior and complexity. Biological systems like heart rhythm and brain electrical activity are dynamical systems that can be classified as chaotic systems with sensitive dependence on initial conditions. In biological systems, the state of a disease is characterized by a loss of the complexity and chaotic behavior, and by the presence of pathological periodicity and regulatory behavior. The failure or the collapse of nonlinear dynamics is an indication of disease rather than a characteristic of health.

Keywords: HRV, HRVI, LF, HF, DII

Procedia PDF Downloads 416

Authors: Stepanov Ivan, Musalimov Viktor, Monahov Uriy

Abstract:

This report examines the current state of human gait simulator development based on the human hip joint model. This unit will create a database of human gait types, useful for setting up and calibrating mechano devices, as well as the creation of new systems of rehabilitation, exoskeletons and walking robots. The system has ample opportunity to configure the dimensions and stiffness, while maintaining relative simplicity.

Keywords: hip joint, human gait, physiotherapy, simulation

Procedia PDF Downloads 400

Authors: Robert Caulk

Abstract:

A generalized framework for adaptive machine learning deployments in algorithmic trading is introduced, tested, and released as open-source code. The presented software aims to test the hypothesis that recent data contains enough information to form a probabilistically favorable short-term price prediction. Further, the framework contains various adaptive machine learning techniques that are geared toward generating profit during strong trends and minimizing losses during trend changes. Results demonstrate that this adaptive machine learning approach is capable of capturing trends and generating profit. The presentation also discusses the importance of defining the parameter space associated with the dynamic training data-set and using the parameter space to identify and remove outliers from prediction data points. Meanwhile, the generalized architecture enables common users to exploit the powerful machinery while focusing on high-level feature engineering and model testing. The presentation also highlights common strengths and weaknesses associated with the presented technique and presents a broad range of well-tested starting points for feature set construction, target setting, and statistical methods for enforcing risk management and maintaining probabilistically favorable entry and exit points. The presentation also describes the end-to-end data processing tools associated with FreqAI, including automatic data fetching, data aggregation, feature engineering, safe and robust data pre-processing, outlier detection, custom machine learning and statistical tools, data post-processing, and adaptive training backtest emulation, and deployment of adaptive training in live environments. Finally, the generalized user interface is also discussed in the presentation. Feature engineering is simplified so that users can seed their feature sets with common indicator libraries (e.g. TA-lib, pandas-ta). The user also feeds data expansion parameters to fill out a large feature set for the model, which can contain as many as 10,000+ features. The presentation describes the various object-oriented programming techniques employed to make FreqAI agnostic to third-party libraries and external data sources. In other words, the back-end is constructed in such a way that users can leverage a broad range of common regression libraries (Catboost, LightGBM, Sklearn, etc) as well as common Neural Network libraries (TensorFlow, PyTorch) without worrying about the logistical complexities associated with data handling and API interactions. The presentation finishes by drawing conclusions about the most important parameters associated with a live deployment of the adaptive learning framework and provides the road map for future development in FreqAI.

Keywords: machine learning, market trend detection, open-source, adaptive learning, parameter space exploration

Procedia PDF Downloads 82

Authors: Qurbanov Huseyn Nuraddin

Abstract:

The results of scientific research on a machine that pours an equal amount of mineral fertilizer under the soil to increase the productivity of grain in mountain farming and obtain quality grain are substantiated. The average yield of the crop depends on the nature of the distribution of fertilizers in the soil. Therefore, the study of effective energy-saving methods for the application of mineral fertilizers is the actual task of modern agriculture. Depending on the type and variety of plants in mountain farming, there is an optimal norm of mineral fertilizers. Applying an equal amount of fertilizer to the soil is one of the conditions that increase the efficiency of the field. One of the main agro-technical indicators of the work of mineral fertilizing machines is to ensure equal distribution of mineral fertilizers in the field. Taking into account the above-mentioned issues, a combined plough has been improved in our laboratory.

Keywords: combined plough, mineral fertilizers, sprinkle fluently, fertilizer rate, cereals

Procedia PDF Downloads 71

Authors: Nomfundo Ngombane, Topside E. Mathonsi

Abstract:

Remote sensing and satellite imaging have been widely used to detect wildfires; nevertheless, the technologies present some limitations in terms of early wildfire detection as the technologies are greatly influenced by weather conditions and can miss small fires. The fires need to have spread a few kilometers for the technologies to provide accurate detection. The South African Advanced Fire Information System uses MODIS (Moderate Resolution Imaging Spectroradiometer) as satellite imaging. MODIS has limitations as it can exclude small fires and can fall short in validating fire vulnerability. Thus in the future, a Machine Learning algorithm will be designed and implemented for the early detection of wildfires. A simulator will be used to evaluate the effectiveness of the proposed solution, and the results of the simulation will be presented.

Keywords: moderate resolution imaging spectroradiometer, advanced fire information system, machine learning algorithm, detection of wildfires

Procedia PDF Downloads 75

Authors: Muhammad Ali Sarwar, Muhammad Farooq, Nayab Hassan, Hammad Hassan

Abstract:

Pakistan is highly recognized for its agriculture and is well known for producing substantial amounts of wheat, cotton, and sugarcane. However, some factors contribute to a decline in crop quality and a reduction in overall output. One of the main factors contributing to this decline is the presence of weed and its late detection. This process of detection is manual and demands a detailed inspection to be done by the farmer itself. But by the time detection of weed, the farmer will be able to save its cost and can increase the overall production. The focus of this research is to identify and classify the four main types of weeds (Small-Flowered Cranesbill, Chick Weed, Prickly Acacia, and Black-Grass) that are prevalent in our region’s major crops. In this work, we implemented three different deep learning techniques: YOLO-v5, Inception-v3, and Deep CNN on the same Dataset, and have concluded that deep convolutions neural network performed better with an accuracy of 97.45% for such classification. In relative to the state of the art, our proposed approach yields 2% better results. We devised the architecture in an efficient way such that it can be used in real-time.

Keywords: deep convolution networks, Yolo, machine learning, agriculture

Procedia PDF Downloads 108

Authors: Mauro Cristeche

Abstract:

This work begins with a very simple question: How does the State spend? Argentina is witnessing a process of growing nationalization of social life, so it is necessary to find out the explanations of the phenomenon on the specific dynamic of the capitalist mode of production in Argentina and its transformations in the last decades. Then the new question is: what happened in Argentina that could explain this phenomenon? Since the seventies, the capital growth in Argentina faces deep competitive problems. Until that moment the agrarian wealth had worked as a compensation mechanism, but it began to find its limits. In the meantime, some important demographical and structural changes had happened. The strategy of the capitalist class had to become to seek in the cheapness of the labor force the main source of compensation of its weakness. As a result, a tendency to worsen the living conditions and fragmentation of the working class started to develop, manifested by unemployment, underemployment, and the fall of the purchasing power of the salary as a highlighted fact. As a consequence, it is suggested that the role of the State became stronger and public expenditure increased, as a historical trend, because it has to intervene to face the contradictions and constant growth problems posed by the development of capitalism in Argentina. On the one hand, the State has to guarantee the process of buying the cheapened workforce and at the same time the process of reproduction of the working class. On the other hand, it has to help to reproduce the individual capitals but needs to ‘attack’ them in different ways. This is why the role of the State is said to be the general political representative to the national portion of the total social capital. What will be studied is the dynamic of the intervention of the Argentine State in the context of the particular national process of capital growth, and its dynamics in the last decades. What this paper wants to show are the main general causes that could explain the phenomenon of nationalization of the social life and how it has impacted the life conditions of the working class and the system of rights.

Keywords: Argentina, nationalization, public policies, rights, state

Procedia PDF Downloads 131

Authors: N. Kaewpraek, W. Assawinchaichote

Abstract:

This paper considers an H_∞ TS fuzzy state-derivative feedback controller for a class of nonlinear dynamical systems. A Takagi-Sugeno (TS) fuzzy model is used to approximate a class of nonlinear dynamical systems. Then, based on a linear matrix inequality (LMI) approach, we design an H_∞ TS fuzzy state-derivative feedback control law which guarantees L₂-gain of the mapping from the exogenous input noise to the regulated output to be less or equal to a prescribed value. We derive a sufficient condition such that the system with the fuzzy controller is asymptotically stable and H_∞ performance is satisfied. Finally, we provide and simulate a numerical example is provided to illustrate the stability and the effectiveness of the proposed controller.

Keywords: h-infinity fuzzy control, an LMI approach, Takagi-Sugano (TS) fuzzy system, the photovoltaic systems

Procedia PDF Downloads 380

Authors: Mehrnaz Mostafavi

Abstract:

The assessment and categorization of incidental lung nodules present a considerable challenge in healthcare, often necessitating resource-intensive multiple computed tomography (CT) scans for growth confirmation. This research addresses this issue by introducing a distinct computational approach leveraging radiomics and deep-learning methods. However, understanding local services is essential before implementing these advancements. With diverse tracking methods in place, there is a need for efficient and accurate identification approaches, especially in the context of managing lung nodules alongside pre-existing cancer scenarios. This study explores the integration of text-based algorithms in medical data curation, indicating their efficacy in conjunction with machine learning and deep-learning models for identifying lung nodules. Combining medical images with text data has demonstrated superior data retrieval compared to using each modality independently. While deep learning and text analysis show potential in detecting previously missed nodules, challenges persist, such as increased false positives. The presented research introduces a Structured-Query-Language (SQL) algorithm designed for identifying pulmonary nodules in a tertiary cancer center, externally validated at another hospital. Leveraging natural language processing (NLP) and machine learning, the algorithm categorizes lung nodule reports based on sentence features, aiming to facilitate research and assess clinical pathways. The hypothesis posits that the algorithm can accurately identify lung nodule CT scans and predict concerning nodule features using machine-learning classifiers. Through a retrospective observational study spanning a decade, CT scan reports were collected, and an algorithm was developed to extract and classify data. Results underscore the complexity of lung nodule cohorts in cancer centers, emphasizing the importance of careful evaluation before assuming a metastatic origin. The SQL and NLP algorithms demonstrated high accuracy in identifying lung nodule sentences, indicating potential for local service evaluation and research dataset creation. Machine-learning models exhibited strong accuracy in predicting concerning changes in lung nodule scan reports. While limitations include variability in disease group attribution, the potential for correlation rather than causality in clinical findings, and the need for further external validation, the algorithm's accuracy and potential to support clinical decision-making and healthcare automation represent a significant stride in lung nodule management and research.

Keywords: lung cancer diagnosis, structured-query-language (SQL), natural language processing (NLP), machine learning, CT scans

Procedia PDF Downloads 83

Authors: Yegetaneh T. Dejenu, Delesa Kejela, Abdulak Alemu

Abstract:

From the earliest time of humankind, the trenches were used for water to flow along and for soldiers to hide in during enemy attacks. Now a day due to civilization, the needs of the human being become endless, and the living condition becomes sophisticated. The unbalance between the needs and resource obligates them to find the way to manage this condition. The attempt to use the scares resource in very efficient and effective way makes the trench an endeavor practice in the world in all countries. A trencher is a construction equipment used to dig trenches, especially for laying pipes or cables, installing drainage, irrigation, installing fencing, and in preparation for trench warfare. It is a machine used to make a ditch by cutting the soil ground and effectively used in agricultural irrigation. The most common types of trencher are wheel trencher, chain trencher, micro trencher, portable trencher. In Ethiopia people have been trenching the ditch for many purposes and the tools they are using are Pickaxe, Shovel and some are using Micro Excavators. The adverse effect of using traditional equipment is, time and energy consuming, less productive, difficult and more man power is required. Hence it is necessary to design and produce low price, and simple machine to narrow this gap. Our objective is to design and model a light duty trencher that is used for trenching the ground or soil for making ditch and used for agricultural, ground cabling, ground piping, and drainage system. The designed machine trenches, maximum of 1-meter depth, 30 cm width, and the required length. The working mechanism is fully hydraulic, and the engine with 12.7 hp will provide suitable power for the pump that delivers 23 l/min at 1500 rpm to drive hydraulic motors and actuators.

Keywords: hydraulics, modelling, trenching, ditch

Procedia PDF Downloads 208

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 189

Authors: S. K. Maanju, K. Saha, Sonam Yadav

Abstract:

Rapid urbanization growth and multi-faceted regional level industrialization is posing serious threat to natural groundwater resource in State of Rajasthan which constitute major semi-arid part of India. The groundwater resources of the State are limited and cannot withstand the present rate of exploitation for quite a long time. Recharging of groundwater particularly in the western part, where annual precipitation does not exceed a few centimeters, is extremely slow and cannot replenish the exploited quantum. Hence, groundwater in most of the parts of this region has become an exhausting resource. In major parts water table is lowering down rapidly and continuously. The human beings of this semi-arid region are used to suffering from extreme climatic conditions of arid to semi-arid nature and acute shortage of water. The quality of groundwater too in many areas of this region is not up to the standards prescribed by the health organizations like WHO and BIS. This semi-arid region is one of the highly fluoride contaminated area of India as well as have excess, nitrates, sulphates, chlorides and total dissolved solids at various locations. Therefore, concerted efforts are needed towards sustainable development of groundwater in this State of India.

Keywords: Rajasthan, water, exploitation, sustainable, development and resource

Procedia PDF Downloads 344

Authors: Chanida Tangjai Benchalak Muangmeesri, Dechrit Maneetham

Abstract:

Collection of marine garbage in the modern world, where technology is vital to existence. Consequently, technology can assist in reducing the duplicate labor in the subject of collecting trash in the water that must be done the same way repeatedly owing to the consequence of suffering an emerging disease or COVID-19. This is due to the rapid advancement of technology. As a result, solid trash and plastic garbage are increasing. Agricultural gardens, canals, ponds, and water basins are all sources of water. Building boat-like instruments for rubbish collection in the water will be done this time. It has two control options, boat control via remote control and boat control via an Internet of Things system. A solar panel with a power output of 40 watts powers the system being able to store so accurate and precise waste collection, allowing for thorough water cleaning. The primary goals are to keep the water's surface clean and assess its quality to support the aquatic ecology.

Keywords: automatic boat, water treatment, cleaning machine, iot

Procedia PDF Downloads 89

Authors: Shyh Ming Chern

Abstract:

Cubic equations of state (EoS), popular due to their simple mathematical form, ease of use, semi-theoretical nature and, reasonable accuracy are normally fitted to vapor-liquid equilibrium P-v-T data. As a result, They often show poor accuracy in the region near and above the critical point. In this study, the performance of the renowned Peng-Robinson (PR) and Patel-Teja (PT) EoS’s around the critical area has been examined against the P-v-T data of water. Both of them display large deviations at critical point. For instance, PR-EoS exhibits discrepancies as high as 47% for the specific volume, 28% for the enthalpy departure and 43% for the entropy departure at critical point. It is shown that incorporating P-v-T data of the supercritical region into the retuning of a cubic EoS can improve its performance above the critical point dramatically. Adopting a retuned acentric factor of 0.5491 instead of its genuine value of 0.344 for water in PR-EoS and a new F of 0.8854 instead of its original value of 0.6898 for water in PT-EoS reduces the discrepancies to about one third or less.

Keywords: equation of state, EoS, supercritical water, SCW

Procedia PDF Downloads 527

Authors: David Ming Liu, Benjamin Hirsch, Bashir Aden

Abstract:

Syndromic surveillance is to detect or predict disease outbreaks through the analysis of medical sources of data. Using social media data like tweets to do syndromic surveillance becomes more and more popular with the aid of open platform to collect data and the advantage of microblogging text and mobile geographic location features. In this paper, a Syndromic Surveillance Framework is presented with machine learning kernel using tweets data analytics. Influenza and the three cities Abu Dhabi, Al Ain and Dubai of United Arabic Emirates are used as the test disease and trial areas. Hospital cases data provided by the Health Authority of Abu Dhabi (HAAD) are used for the correlation purpose. In our model, Latent Dirichlet allocation (LDA) engine is adapted to do supervised learning classification and N-Fold cross validation confusion matrix are given as the simulation results with overall system recall 85.595% performance achieved.

Keywords: Syndromic surveillance, Tweets, Machine Learning, data mining, Latent Dirichlet allocation (LDA), Influenza

Procedia PDF Downloads 107

Authors: Ehsan Atefi, Michael Grigware

Abstract:

Respiratory failure secondary to surfactant deficiency resulting from respiratory distress syndrome is considered one major cause of morbidity in preterm infants. Surfactant replacement treatment (SRT) is considered an effective treatment for this disease. Here, we introduce an AI-mediated approach for estimating the distribution of surfactant in the lung airway of a newborn infant during SRT. Our approach implements machine learning to precisely estimate the splitting ratio of a liquid drop during bifurcation at different injection velocities and patient orientations. This technique can be used to calculate the surfactant residue remaining on the airway wall during the surfactant injection process. Our model works by minimizing the pressure drop difference between the two airway branches at each generation, subject to mass and momentum conservation. Our platform can be used to generate feedback for immediately adjusting the velocity of injection and patient orientation during SRT.

Keywords: respiratory failure, surfactant deficiency, surfactant replacement, machine learning

Procedia PDF Downloads 121

Authors: R. R. Govind

Abstract:

In the digital age, artificial intelligence (AI) is having a significant impact on the rapid changes that cities are experiencing. This study explores the profound impact of AI on urban morphology, especially with regard to promoting friendly design choices. It addresses a significant research gap by examining the real-world effects of integrating AI into urban design and management. The main objective is to outline a framework for integrating AI to transform urban settings. The study employs an urban design framework to effectively navigate complicated urban environments, emphasize the need for urban management, and provide efficient planning and design strategies. Taking Gangtok's informal settlements as a focal point, the study employs AI methodologies such as machine learning, predictive analytics, and generative AI to tackle issues of 'urban informality'. The insights garnered not only offer valuable perspectives but also unveil AI's transformative potential in addressing contemporary urban challenges.

Keywords: urban design, artificial intelligence, urban challenges, machine learning, urban informality

Procedia PDF Downloads 55

Authors: George Abu-Aqil, Leah Tsror, Elad Shufan, Shaul Mordechai, Mahmoud Huleihel, Ahmad Salman

Abstract:

Pectobacterium and Dickeya spp which negatively affect a wide range of crops are the main causes of the aggressive diseases of agricultural crops. These aggressive diseases are responsible for a huge economic loss in agriculture including a severe decrease in the quality of the stored vegetables and fruits. Therefore, it is important to detect these pathogenic bacteria at their early stages of infection to control their spread and consequently reduce the economic losses. In addition, early detection is vital for producing non-infected propagative material for future generations. The currently used molecular techniques for the identification of these bacteria at the strain level are expensive and laborious. Other techniques require a long time of ~48 h for detection. Thus, there is a clear need for rapid, non-expensive, accurate and reliable techniques for early detection of these bacteria. In this study, infrared spectroscopy, which is a well-known technique with all its features, was used for rapid detection of Pectobacterium and Dickeya spp. at the strain level. The bacteria were isolated from potato plants and tubers with soft rot symptoms and measured by infrared spectroscopy. The obtained spectra were analyzed using different machine learning algorithms. The performances of our approach for taxonomic classification among the bacterial samples were evaluated in terms of success rates. The success rates for the correct classification of the genus, species and strain levels were ~100%, 95.2% and 92.6% respectively.

Keywords: soft rot enterobacteriaceae (SRE), pectobacterium, dickeya, plant infections, potato, solanum tuberosum, infrared spectroscopy, machine learning

Procedia PDF Downloads 95

Authors: Beulah Rani Inbanathan

Abstract:

In the present era, it is vivid from the numerous outcomes that data privacy is being compromised in various ways. Machine learning is one technology that uses the centralized server, and then data is given as input which is being analyzed by the algorithms present on this mentioned server, and hence outputs are predicted. However, each time the data must be sent by the user as the algorithm will analyze the input data in order to predict the output, which is prone to threats. The solution to overcome this issue is federated learning, where the models alone get updated while the data resides on the local machine and does not get exchanged with the other local models. Nevertheless, even on these local models, there are chances of data poisoning, and it is crystal clear from various experiments done by many people. This paper delves into many ways where data poisoning occurs and the many methods through which it is prevalent that data poisoning still exists. It includes the poisoning attacks on IoT devices, Edge devices, Autoregressive model, and also, on Industrial IoT systems and also, few points on how these could be evadible in order to protect our data which is personal, or sensitive, or harmful when exposed.

Keywords: data poisoning, federated learning, Internet of Things, edge computing

Procedia PDF Downloads 82

Authors: Jazim Sohail, Filipe Teixeira-Dias

Abstract:

Mild traumatic brain injury (mTBI) within non-helmeted contact sports is a growing concern due to the serious risk of potential injury. Extensive research is being conducted looking into head kinematics in non-helmeted contact sports utilizing instrumented mouthguards that allow researchers to record accelerations and velocities of the head during and after an impact. This does not, however, allow the location of the impact on the head, and its magnitude and orientation, to be determined. This research proposes and validates two methods to quantify impact locations from instrumented mouthguard kinematic data, one using rigid body dynamics, the other utilizing machine learning. The rigid body dynamics technique focuses on establishing and matching moments from Euler’s and torque equations in order to find the impact location on the head. The methodology is validated with impact data collected from a lab test with the dummy head fitted with an instrumented mouthguard. Additionally, a Hybrid III Dummy head finite element model was utilized to create synthetic kinematic data sets for impacts from varying locations to validate the impact location algorithm. The algorithm calculates accurate impact locations; however, it will require preprocessing of live data, which is currently being done by cross-referencing data timestamps to video footage. The machine learning technique focuses on eliminating the preprocessing aspect by establishing trends within time-series signals from instrumented mouthguards to determine the impact location on the head. An unsupervised learning technique is used to cluster together impacts within similar regions from an entire time-series signal. The kinematic signals established from mouthguards are converted to the frequency domain before using a clustering algorithm to cluster together similar signals within a time series that may span the length of a game. Impacts are clustered within predetermined location bins. The same Hybrid III Dummy finite element model is used to create impacts that closely replicate on-field impacts in order to create synthetic time-series datasets consisting of impacts in varying locations. These time-series data sets are used to validate the machine learning technique. The rigid body dynamics technique provides a good method to establish accurate impact location of impact signals that have already been labeled as true impacts and filtered out of the entire time series. However, the machine learning technique provides a method that can be implemented with long time series signal data but will provide impact location within predetermined regions on the head. Additionally, the machine learning technique can be used to eliminate false impacts captured by sensors saving additional time for data scientists using instrumented mouthguard kinematic data as validating true impacts with video footage would not be required.

Keywords: head impacts, impact location, instrumented mouthguard, machine learning, mTBI

Procedia PDF Downloads 211

Authors: Subrato Saha, Yun-Hyun Cho

Abstract:

In electric power steering (EPS), spoke type brushless ac (BLAC) motors offer distinct advantages over other electric motor types in terms torque smoothness, reliability and efficiency. This paper deals with the shape optimization of spoke type BLAC motor, in order to reduce cogging torque. This paper examines 3 steps skewing rotor angle, optimizing rotor core edge and rotor overlap length for reducing cogging torque in spoke type BLAC motor. The methods were applied to existing machine designs and their performance was calculated using finite- element analysis (FEA). Prototypes of the machine designs were constructed and experimental results obtained. It is shown that the FEA predicted the cogging torque to be nearly reduce using those methods.

Keywords: EPS, 3-Step skewing, spoke type BLAC, cogging torque, FEA, optimization

Procedia PDF Downloads 485

Authors: Magdalena Igras, Joanna Grzybowska, Mariusz Ziółko

Abstract:

The study of emotions expressed in emergency phone call is presented, covering both statistical analysis of emotions configurations and an attempt to automatically classify emotions. An emergency call is a situation usually accompanied by intense, authentic emotions. They influence (and may inhibit) the communication between caller and responder. In order to support responders in their responsible and psychically exhaustive work, we studied when and in which combinations emotions appeared in calls. A corpus of 45 hours of conversations (about 3300 calls) from emergency call center was collected. Each recording was manually tagged with labels of emotions valence (positive, negative or neutral), type (sadness, tiredness, anxiety, surprise, stress, anger, fury, calm, relief, compassion, satisfaction, amusement, joy) and arousal (weak, typical, varying, high) on the basis of perceptual judgment of two annotators. As we concluded, basic emotions tend to appear in specific configurations depending on the overall situational context and attitude of speaker. After performing statistical analysis we distinguished four main types of emotional behavior of callers: worry/helplessness (sadness, tiredness, compassion), alarm (anxiety, intense stress), mistake or neutral request for information (calm, surprise, sometimes with amusement) and pretension/insisting (anger, fury). The frequency of profiles was respectively: 51%, 21%, 18% and 8% of recordings. A model of presenting the complex emotional profiles on the two-dimensional (tension-insecurity) plane was introduced. In the stage of acoustic analysis, a set of prosodic parameters, as well as Mel-Frequency Cepstral Coefficients (MFCC) were used. Using these parameters, complex emotional states were modeled with machine learning techniques including Gaussian mixture models, decision trees and discriminant analysis. Results of classification with several methods will be presented and compared with the state of the art results obtained for classification of basic emotions. Future work will include optimization of the algorithm to perform in real time in order to track changes of emotions during a conversation.

Keywords: acoustic analysis, complex emotions, emotion recognition, machine learning

Procedia PDF Downloads 390

Authors: Hai Zeng, Anqing Liu, Shuguang Dan, Ying Zhang, Yan Li, Zihang Zeng

Abstract:

Children are strong; the country strong, the development of children Basketball is a strategic advantage. Common forms of basketball equipment has been difficult to meet the needs of young children teaching the game of basketball, basketball development for 3-6 years old children in the form of appropriate teaching aids is a breakthrough basketball game teaching children bottlenecks, improve teaching critical path pleasure, but also the development of early childhood basketball a necessary requirement. In this study, literature, questionnaires, focus group interviews, comparative analysis, for domestic and foreign use of 12 kinds of basketball teaching aids (cloud computing MINI basketball, adjustable basketball MINI, MINI basketball court, shooting assist paw print ball, dribble goggles, dribbling machine, machine cartoon shooting, rebounding machine, against the mat, elastic belt, ladder, fitness ball), from fun and improve early childhood shooting technique, dribbling technology, as well as offensive and defensive rebounding against technology conduct research on conversion technology. The results show that by using appropriate forms of teaching children basketball aids, can effectively improve children's fun basketball game, targeted to improve a technology, different types of aids from different perspectives enrich the connotation of children basketball game. Recommended for children of color psychology, cartoon and environmentally friendly material production aids, and increase research efforts basketball aids children, encourage children to sports teachers aids applications.

Keywords: appropriate forms of children basketball, auxiliary equipment, appli, MINI basketball, 3-6 years old children, teaching

Procedia PDF Downloads 381

Authors: Min Kyu Kim, Eun Young Lee, Dong Woo Son, Yoon Seok Chang

Abstract:

In this paper, we introduce a flexible box erecting machine (BEM) that swiftly and automatically transforms cardboard into a three dimensional box. Recently, the parcel service and home-shopping industries have grown rapidly, and there is an increasing need for various box types to ship various products. However, workers cannot fold thousands of boxes manually in a day. As such, automatic BEMs are garnering greater attention. This study takes equipment operation into consideration as well as mechanical improvements in order to design a BEM that is able to outperform its conventional counterparts. We analyzed six dispatching rules – First In First Out (FIFO), Shortest Processing Time (SPT), Earliest Due Date (EDD), Setup Avoidance, EDD + SPT, and EDD + Setup Avoidance – to determine which one was most suitable for BEM operation. Consequently, SPT and Setup Avoidance were found to be the most critical rules, followed by EDD + Setup Avoidance, EDD + SPT, EDD, and FIFO. This hierarchy was valid for both our conventional BEM and our new flexible BEM from the viewpoint of processing time. We believe that this research can contribute to flexible BEM management, which has the potential to increase productivity and convenience.

Keywords: automation, box erecting machine, dispatching rule, setup time

Procedia PDF Downloads 358

Authors: Parthiban Srinivasan

Abstract:

With recent advances in computational power and access to enough data in biosciences, artificial intelligence methods are increasingly being used in drug discovery research. These methods are essentially a series of advanced statistics based exercises that review the past to indicate the likely future. Our goal is to develop a model that accurately predicts biological activity and toxicity parameters for novel compounds. We have compiled a robust library of over 150,000 chemical compounds with different pharmacological properties from literature and public domain databases. The compounds are stored in simplified molecular-input line-entry system (SMILES), a commonly used text encoding for organic molecules. We utilize an automated process to generate an array of numerical descriptors (features) for each molecule. Redundant and irrelevant descriptors are eliminated iteratively. Our prediction engine is based on a portfolio of machine learning algorithms. We found Random Forest algorithm to be a better choice for this analysis. We captured non-linear relationship in the data and formed a prediction model with reasonable accuracy by averaging across a large number of randomized decision trees. Our next step is to apply deep neural network (DNN) algorithm to predict the biological activity and toxicity properties. We expect the DNN algorithm to give better results and improve the accuracy of the prediction. This presentation will review all these prominent machine learning and deep learning methods, our implementation protocols and discuss these techniques for their usefulness in biomedical and health informatics.

Keywords: deep learning, drug discovery, health informatics, machine learning, toxicity prediction

Procedia PDF Downloads 354

Authors: Jae-Yong Lee, Gyu-Hyun Bae, Yun-Soo Chung, Dae-Sub Kim, Jae-Sung Bae

Abstract:

In general, fabric is heat-treated using a stenter machine in order to dry and fix its shape. It is important to shape before the heat treatment because it is difficult to revert back once the fabric is formed. To produce the product of right shape, camera type weft straightener has been applied recently to capture and process fabric images quickly. It is more powerful in determining the final textile quality rather than photo-sensor. Positioning in front of a stenter machine, weft straightener helps to spread fabric evenly and control the angle between warp and weft constantly as right angle by handling skew and bow rollers. To process this tricky procedure, the structural analysis should be carried out in advance, based on which, its control technology can be drawn. A structural analysis is to figure out the specific contact/slippage characteristics between fabric and roller. We already examined the applicability of camera type weft straightener to plain weave fabric and found its possibility and the specific working condition of machine and rollers. In this research, we aimed to explore another applicability of camera type weft straightener. Namely, we tried to figure out camera type weft straightener can be used for fabrics. To find out the optimum condition, we increased the number of rollers. The analysis is done by ANSYS software using Finite Element Analysis method. The control function is demonstrated by experiment. In conclusion, the structural analysis of weft straightener is done to identify a specific characteristic between roller and fabrics. The control of skew and bow roller is done to decrease the error of the angle between warp and weft. Finally, it is proved that camera type straightener can also be used for the special fabrics.

Keywords: camera type weft straightener, structure analysis, control, skew and bow roller

Procedia PDF Downloads 288

Authors: Mohammad Arabi

Abstract:

The development of advanced technologies in the field of signal processing and vibration analysis has enabled more accurate analysis and fault detection in electrical systems. This research investigates the application of temporal and frequency features in detecting faults in electric motor bearings, aiming to enhance fault detection accuracy and prevent unexpected failures. The use of methods such as deep learning algorithms and neural networks in this process can yield better results. The main objective of this research is to evaluate the efficiency and accuracy of methods based on temporal and frequency features in identifying faults in electric motor bearings to prevent sudden breakdowns and operational issues. Additionally, the feasibility of using techniques such as machine learning and optimization algorithms to improve the fault detection process is also considered. This research employed an experimental method and random sampling. Vibration signals were collected from electric motors under normal and faulty conditions. After standardizing the data, temporal and frequency features were extracted. These features were then analyzed using statistical methods such as analysis of variance (ANOVA) and t-tests, as well as machine learning algorithms like artificial neural networks and support vector machines (SVM). The results showed that using temporal and frequency features significantly improves the accuracy of fault detection in electric motor bearings. ANOVA indicated significant differences between normal and faulty signals. Additionally, t-tests confirmed statistically significant differences between the features extracted from normal and faulty signals. Machine learning algorithms such as neural networks and SVM also significantly increased detection accuracy, demonstrating high effectiveness in timely and accurate fault detection. This study demonstrates that using temporal and frequency features combined with machine learning algorithms can serve as an effective tool for detecting faults in electric motor bearings. This approach not only enhances fault detection accuracy but also simplifies and streamlines the detection process. However, challenges such as data standardization and the cost of implementing advanced monitoring systems must also be considered. Utilizing temporal and frequency features in fault detection of electric motor bearings, along with advanced machine learning methods, offers an effective solution for preventing failures and ensuring the operational health of electric motors. Given the promising results of this research, it is recommended that this technology be more widely adopted in industrial maintenance processes.

Keywords: electric motor, fault detection, frequency features, temporal features

Procedia PDF Downloads 38

Authors: Ali Ocholi

Abstract:

The study was conducted to analyze the impact of agro-allied industries on rural dwellers in Benue state, Nigeria. Stratified random sampling technique was used to select the respondents for the study. Primary data were collected through the use of structured questionnaires administered on 366 respondents from the selected communities; the data were analyzed using both descriptive and inferential statistics. The result of Mann-Whitney (U) statistics showed that water availability (14350) and good road network (15082.00) were the only social impact derived from the industries by the rural dwellers. The study recommended that right and proper policies and programmes should be put in place by the government to mandate all private and public agro-allied industries to embark on projects that would be in favour of the rural dwellers where the agro-allied industries are situated.

Keywords: agriculture, agro-allied industry, rural dwellers, Benue state

Procedia PDF Downloads 241