Search results for: automatic

Authors: Pablo Chico De Guzman, Cesar Sanchez

Abstract:

Microservices are a software development methodology in which applications are built by composing a set of independently deploy-able, small, modular services. Each service runs a unique process and it gets instantiated and deployed in one or more machines (we assume that different microservices are deployed into different machines). Microservices are becoming the de facto standard for developing distributed cloud applications due to their reduced release cycles. In principle, the responsibility of a microservice can be as simple as implementing a single function, which can lead to the following issues: - Resource fragmentation due to the virtual machine boundary. - Poor communication performance between microservices. Two composition techniques can be used to optimize resource fragmentation and communication performance: aggregation and embedding of microservices. Aggregation allows the deployment of a set of microservices on the same machine using a proxy server. Aggregation helps to reduce resource fragmentation, and is particularly useful when the aggregated services have a similar scalability behavior. Embedding deals with communication performance by deploying on the same virtual machine those microservices that require a communication channel (localhost bandwidth is reported to be about 40 times faster than cloud vendor local networks and it offers better reliability). Embedding can also reduce dependencies on load balancer services since the communication takes place on a single virtual machine. For example, assume that microservice A has two instances, a1 and a2, and it communicates with microservice B, which also has two instances, b1 and b2. One embedding can deploy a1 and b1 on machine m1, and a2 and b2 are deployed on a different machine m2. This deployment configuration allows each pair (a1-b1), (a2-b2) to communicate using the localhost interface without the need of a load balancer between microservices A and B. Aggregation and embedding techniques are complex since different microservices might have incompatible runtime dependencies which forbid them from being installed on the same machine. There is also a security concern since the attack surface between microservices can be larger. Luckily, container technology allows to run several processes on the same machine in an isolated manner, solving the incompatibility of running dependencies and the previous security concern, thus greatly simplifying aggregation/embedding implementations by just deploying a microservice container on the same machine as the aggregated/embedded microservice container. Therefore, a wide variety of deployment configurations can be described by combining aggregation and embedding to create an efficient and robust microservice architecture. This paper presents a formal method that receives a declarative definition of a microservice architecture and proposes different optimized deployment configurations by aggregating/embedding microservices. The first prototype is based on i2kit, a deployment tool also submitted to ICWS 2018. The proposed prototype optimizes the following parameters: network/system performance, resource usage, resource costs and failure tolerance.

Keywords: aggregation, deployment, embedding, resource allocation

Procedia PDF Downloads 172

Authors: Mohamed Alimoussa, Alice Porebski, Nicolas Vandenbroucke, Rachid Oulad Haj Thami, Sana El Fkihi

Abstract:

Color and texture are highly discriminant visual cues that provide an essential information in many types of images. Color texture representation and classification is therefore one of the most challenging problems in computer vision and image processing applications. Color textures can be represented in different color spaces by using multiple image descriptors which generate a high dimensional set of texture features. In order to reduce the dimensionality of the feature set, feature selection techniques can be used. The goal of feature selection is to find a relevant subset from an original feature space that can improve the accuracy and efficiency of a classification algorithm. Traditionally, feature selection is focused on removing irrelevant features, neglecting the possible redundancy between relevant ones. This is why some feature selection approaches prefer to use feature clustering analysis to aid and guide the search. These techniques can be divided into two categories. i) Feature clustering-based ranking algorithm uses feature clustering as an analysis that comes before feature ranking. Indeed, after dividing the feature set into groups, these approaches perform a feature ranking in order to select the most discriminant feature of each group. ii) Feature clustering-based subset search algorithms can use feature clustering following one of three strategies; as an initial step that comes before the search, binded and combined with the search or as the search alternative and replacement. In this paper, we propose a new feature clustering-based sequential selection approach for the purpose of color texture representation and classification. Our approach is a three step algorithm. First, irrelevant features are removed from the feature set thanks to a class-correlation measure. Then, introducing a new automatic feature clustering algorithm, the feature set is divided into several feature clusters. Finally, a sequential search algorithm, based on a filter model and a separability measure, builds a relevant and non redundant feature subset: at each step, a feature is selected and features of the same cluster are removed and thus not considered thereafter. This allows to significantly speed up the selection process since large number of redundant features are eliminated at each step. The proposed algorithm uses the clustering algorithm binded and combined with the search. Experiments using a combination of two well known texture descriptors, namely Haralick features extracted from Reduced Size Chromatic Co-occurence Matrices (RSCCMs) and features extracted from Local Binary patterns (LBP) image histograms, on five color texture data sets, Outex, NewBarktex, Parquet, Stex and USPtex demonstrate the efficiency of our method compared to seven of the state of the art methods in terms of accuracy and computation time.

Keywords: feature selection, color texture classification, feature clustering, color LBP, chromatic cooccurrence matrix

Procedia PDF Downloads 100

Authors: Hortènsia Curell, Ana Fernández-Montraveta

Abstract:

This paper presents the creation, development, and analysis of a corpus designed to study the presence of attitude markers and author’s stance in research articles in two different areas of linguistics (theoretical linguistics and sociolinguistics). These two disciplines are expected to behave differently in this respect, given the disparity in their discursive conventions. Attitude markers in this work are understood as the linguistic elements (adjectives, nouns and verbs) used to convey the writer's stance towards the content presented in the article, and are crucial in understanding writer-reader interaction and the writer's position. These attitude markers are divided into three broad classes: assessment, significance, and emotion. In addition to them, we also consider first-person singular and plural pronouns and possessives, modal verbs, and passive constructions, which are other linguistic elements expressing the author’s stance. The corpus, Corpus of Attitude in Academic Writing (CAAW), comprises a collection of 21 articles, collected from six journals indexed in JCR. These articles were originally written in English by a single native-speaker author from the UK or USA and were published between 2022 and 2023. The total number of words in the corpus is approximately 222,400, with 106,422 from theoretical linguistics (Lingua, Linguistic Inquiry and Journal of Linguistics) and 116,022 from sociolinguistics journals (International Journal of the Sociology of Language, Language in Society and Journal of Sociolinguistics). Together with the corpus, we present the tool created for the creation and storage of the corpus, along with a tool for automatic annotation. The steps followed in the compilation of the corpus are as follows. First, the articles were selected according to the parameters explained above. Second, they were downloaded and converted to txt format. Finally, examples, direct quotes, section titles and references were eliminated, since they do not involve the author’s stance. The resulting texts were the input for the annotation of the linguistic features related to stance. As for the annotation, two articles (one from each subdiscipline) were annotated manually by the two researchers. An existing list was used as a baseline, and other attitude markers were identified, together with the other elements mentioned above. Once a consensus was reached, the rest of articles were annotated automatically using the tool created for this purpose. The annotated corpus will serve as a resource for scholars working in discourse analysis (both in linguistics and communication) and related fields, since it offers new insights into the expression of attitude. The tools created for the compilation and annotation of the corpus will be useful to study author’s attitude and stance in articles from any academic discipline: new data can be uploaded and the list of markers can be enlarged. Finally, the tool can be expanded to other languages, which will allow cross-linguistic studies of author’s stance.

Keywords: academic writing, attitude, corpus, english

Procedia PDF Downloads 27

Authors: Despoina Mouratidis, Katia Lida Kermanidis

Abstract:

Machine translation (MT) is a very important task in Natural Language Processing (NLP). MT evaluation is crucial in MT development, as it constitutes the means to assess the success of an MT system, and also helps improve its performance. Several methods have been proposed for the evaluation of (MT) systems. Some of the most popular ones in automatic MT evaluation are score-based, such as the BLEU score, and others are based on lexical similarity or syntactic similarity between the MT outputs and the reference involving higher-level information like part of speech tagging (POS). This paper presents a language-independent machine learning framework for classifying pairwise translations. This framework uses vector representations of two machine-produced translations, one from a statistical machine translation model (SMT) and one from a neural machine translation model (NMT). The vector representations consist of automatically extracted word embeddings and string-like language-independent features. These vector representations used as an input to a multi-layer neural network (NN) that models the similarity between each MT output and the reference, as well as between the two MT outputs. To evaluate the proposed approach, a professional translation and a "ground-truth" annotation are used. The parallel corpora used are English-Greek (EN-GR) and English-Italian (EN-IT), in the educational domain and of informal genres (video lecture subtitles, course forum text, etc.) that are difficult to be reliably translated. They have tested three basic deep learning (DL) architectures to this schema: (i) fully-connected dense, (ii) Convolutional Neural Network (CNN), and (iii) Long Short-Term Memory (LSTM). Experiments show that all tested architectures achieved better results when compared against those of some of the well-known basic approaches, such as Random Forest (RF) and Support Vector Machine (SVM). Better accuracy results are obtained when LSTM layers are used in our schema. In terms of a balance between the results, better accuracy results are obtained when dense layers are used. The reason for this is that the model correctly classifies more sentences of the minority class (SMT). For a more integrated analysis of the accuracy results, a qualitative linguistic analysis is carried out. In this context, problems have been identified about some figures of speech, as the metaphors, or about certain linguistic phenomena, such as per etymology: paronyms. It is quite interesting to find out why all the classifiers led to worse accuracy results in Italian as compared to Greek, taking into account that the linguistic features employed are language independent.

Keywords: machine learning, machine translation evaluation, neural network architecture, pairwise classification

Procedia PDF Downloads 103

Authors: Tadele Tesfaw, Ajit Pal Singh, Abebaw Mekonnen Gezahegn

Abstract:

Welding is a basic manufacturing process for making components or assemblies. Recent welding economics research has focused on developing the reliable machinery database to ensure optimum production. Research on welding of materials like steel is still critical and ongoing. Welding input parameters play a very significant role in determining the quality of a weld joint. The metal active gas (MAG) welding parameters are the most important factors affecting the quality, productivity and cost of welding in many industrial operations. The aim of this study is to investigate the optimization process parameters for metal active gas welding for 60x60x5mm dead mild steel plate work-piece using Taguchi method to formulate the statistical experimental design using semi-automatic welding machine. An experimental study was conducted at Bishoftu Automotive Industry, Bishoftu, Ethiopia. This study presents the influence of four welding parameters (control factors) like welding voltage (volt), welding current (ampere), wire speed (m/min.), and gas (CO2) flow rate (lit./min.) with three different levels for variability in the welding hardness. The objective functions have been chosen in relation to parameters of MAG welding i.e., welding hardness in final products. Nine experimental runs based on an L9 orthogonal array Taguchi method were performed. An orthogonal array, signal-to-noise (S/N) ratio and analysis of variance (ANOVA) are employed to investigate the welding characteristics of dead mild steel plate and used in order to obtain optimum levels for every input parameter at 95% confidence level. The optimal parameters setting was found is welding voltage at 22 volts, welding current at 125 ampere, wire speed at 2.15 m/min and gas flow rate at 19 l/min by using the Taguchi experimental design method within the constraints of the production process. Finally, six conformations welding have been carried out to compare the existing values; the predicated values with the experimental values confirm its effectiveness in the analysis of welding hardness (quality) in final products. It is found that welding current has a major influence on the quality of welded joints. Experimental result for optimum setting gave a better hardness of welding condition than initial setting. This study is valuable for different material and thickness variation of welding plate for Ethiopian industries.

Keywords: Weld quality, metal active gas welding, dead mild steel plate, orthogonal array, analysis of variance, Taguchi method

Procedia PDF Downloads 460

Authors: Chiyoung Kim, Jaegeol Yim

Abstract:

Bus service is often either main or the only public transportation available in cities. In metropolitan areas, both subways and buses are available whereas in the medium sized cities buses are usually the only type of public transportation available. Bus Information Systems (BIS) provide current locations of running buses, efficient routes to travel from one place to another, points of interests around a given bus stop, a series of bus stops consisting of a given bus route, and so on to users. Thanks to BIS, people do not have to waste time at a bus stop waiting for a bus because BIS provides exact information on bus arrival times at a given bus stop. Therefore, BIS does a lot to promote the use of buses contributing to pollution reduction and saving natural resources. BIS implementation costs a huge amount of budget as it requires a lot of special equipment such as road side equipment, automatic vehicle identification and location systems, trunked radio systems, and so on. Consequently, medium and small sized cities with a low budget cannot afford to install BIS even though people in these cities need BIS service more desperately than people in metropolitan areas. It is possible to provide BIS service at virtually no cost under the assumption that everybody carries a smartphone and there is at least one person with a smartphone in a running bus who is willing to reveal his/her location details while he/she is sitting in a bus. This assumption is usually true in the real world. The smartphone penetration rate is greater than 100% in the developed countries and there is no reason for a bus driver to refuse to reveal his/her location details while driving. We have developed a mobile app that periodically reads values of sensors including GPS and sends GPS data to the server when the bus stops or when the elapsed time from the last send attempt is greater than a threshold. This app detects the bus stop state by investigating the sensor values. The server that receives GPS data from this app has also been developed. Under the assumption that the current locations of all running buses collected by the mobile app are recorded in a database, we have also developed a web site that provides all kinds of information that most BISs provide to users through the Internet. The development environment is: OS: Windows 7 64bit, IDE: Eclipse Luna 4.4.1, Spring IDE 3.7.0, Database: MySQL 5.1.7, Web Server: Apache Tomcat 7.0, Programming Language: Java 1.7.0_79. Given a start and a destination bus stop, it finds a shortest path from the start to the destination using the Dijkstra algorithm. Then, it finds a convenient route considering number of transits. For the user interface, we use the Google map. Template classes that are used by the Controller, DAO, Service and Utils classes include BUS, BusStop, BusListInfo, BusStopOrder, RouteResult, WalkingDist, Location, and so on. We are now integrating the mobile app system and the web app system.

Keywords: bus information system, GPS, mobile app, web site

Procedia PDF Downloads 184

Authors: Ruchi B. Semwal, Deepak K. Semwal, Thobile A. N. Nkosi, Alvaro M. Viljoen

Abstract:

The use of Lawsonia inermis L. (Lythraeae), commonly known as henna, has many medicinal benefits and is used as a remedy for the treatment of diarrhoea, cancer, inflammation, headache, jaundice and skin diseases in folk medicine. Although widely used for hair dyeing and temporary tattooing, henna body art has popularized over the last 15 years and changed from being a traditional bridal and festival adornment to an exotic fashion accessory. The naphthoquinone, lawsone, is one of the main constituents of the plant and responsible for its dyeing property. Henna leaves typically contain 1.8–1.9% lawsone, which is used as a marker compound for the quality control of henna products. Adulteration of henna with various toxic chemicals such as p-phenylenediamine, p-methylaminophenol, p-aminobenzene and p-toluenodiamine to produce a variety of colours, is very common and has resulted in serious health problems, including allergic reactions. This study aims to assess the quality of henna products collected from different parts of the world by determining the lawsone content, as well as the concentrations of any adulterants present. Ultra high performance liquid chromatography-mass spectrometry (UPLC-MS) was used to determine the lawsone concentrations in 172 henna products. Separation of the chemical constituents was achieved on an Acquity UPLC BEH C18 column using gradient elution (0.1% formic acid and acetonitrile). The results from UPLC-MS revealed that of 172 henna products, 11 contained 1.0-1.8% lawsone, 110 contained 0.1-0.9% lawsone, whereas 51 samples did not contain detectable levels of lawsone. High performance thin layer chromatography was investigated as a cheaper, more rapid technique for the quality control of henna in relation to the lawsone content. The samples were applied using an automatic TLC Sampler 4 (CAMAG) to pre-coated silica plates, which were subsequently developed with acetic acid, acetone and toluene (0.5: 1.0: 8.5 v/v). A Reprostar 3 digital system allowed the images to be captured. The results obtained corresponded to those from UPLC-MS analysis. Vibrational spectroscopy analysis (MIR or NIR) of the powdered henna, followed by chemometric modelling of the data, indicates that this technique shows promise as an alternative quality control method. Principal component analysis (PCA) was used to investigate the data by observing clustering and identifying outliers. Partial least squares (PLS) multivariate calibration models were constructed for the quantification of lawsone. In conclusion, only a few of the samples analysed contain lawsone in high concentrations, indicating that they are of poor quality. Currently, the presence of adulterants that may have been added to enhance the dyeing properties of the products, is being investigated.

Keywords: Lawsonia inermis, paraphenylenediamine, temporary tattooing, lawsone

Procedia PDF Downloads 430

Authors: Begum Koru, Isik Aybay, Demet Celik Ulusoy

Abstract:

The discipline of law is quite complex and has its own terminology. Apart from written legal rules, there is also living law, which refers to legal practice. Basic legal rules aim at the happiness of individuals in social life and have different characteristics in different branches such as public or private law. On the other hand, law is a national phenomenon. The law of one nation and the legal system applied on the territory of another nation may be completely different. People who are experts in a particular field of law in one country may have insufficient expertise in the law of another country. Today, in addition to the local nature of law, international and even supranational law rules are applied in order to protect basic human values and ensure the protection of human rights around the world. Systems that offer algorithmic solutions to legal problems using artificial intelligence (AI) tools will perhaps serve to produce very meaningful results in terms of human rights. However, algorithms to be used should not be developed by only computer experts, but also need the contribution of people who are familiar with law, values, judicial decisions, and even the social and political culture of the society to which it will provide solutions. Otherwise, even if the algorithm works perfectly, it may not be compatible with the values of the society in which it is applied. The latest developments involving the use of AI techniques in legal systems indicate that artificial law will emerge as a new field in the discipline of law. More AI systems are already being applied in the field of law, with examples such as predicting judicial decisions, text summarization, decision support systems, and classification of documents. Algorithms for legal systems employing AI tools, especially in the field of prediction of judicial decisions and decision support systems, have the capacity to create automatic decisions instead of judges. When the judge is removed from this equation, artificial intelligence-made law created by an intelligent algorithm on its own emerges, whether the domain is national or international law. In this work, the aim is to make a general analysis of this new topic. Such an analysis needs both a literature survey and a perspective from computer experts' and lawyers' point of view. In some societies, the use of prediction or decision support systems may be useful to integrate international human rights safeguards. In this case, artificial law can serve to produce more comprehensive and human rights-protective results than written or living law. In non-democratic countries, it may even be thought that direct decisions and artificial intelligence-made law would be more protective instead of a decision "support" system. Since the values of law are directed towards "human happiness or well-being", it requires that the AI algorithms should always be capable of serving this purpose and based on the rule of law, the principle of justice and equality, and the protection of human rights.

Keywords: AI and law, artificial law, protection of human rights, AI tools for legal systems

Procedia PDF Downloads 43

Authors: Anderson Braga Mendes

Abstract:

Itaipu Hydroelectric Power Plant is settled on the Paraná River, which is a natural boundary between Brazil and Paraguay; thus, the facility is shared by both countries. Itaipu Power Plant is the biggest hydroelectric generator in the world, and provides clean and renewable electrical energy supply for 17% and 76% of Brazil and Paraguay, respectively. The plant started its generation in 1984. It counts on 20 Francis turbines and has installed capacity of 14,000 MWh. Its historic generation record occurred in 2016 (103,098,366 MWh), and since the beginning of its operation until the last day of 2016 the plant has achieved the sum of 2,415,789,823 MWh. The distinct sedimentologic aspects of the drainage area of Itaipu Power Plant, from its stretch upstream (Porto Primavera and Rosana dams) to downstream (Itaipu dam itself), were taken into account in order to best estimate the increase/decrease in the sediment yield by using data from 2001 to 2016. Such data are collected through a network of 14 automatic sedimentometric stations managed by the company itself and operating in an hourly basis, covering an area of around 136,000 km² (92% of the incremental drainage area of the undertaking). Since 1972, a series of lifespan studies for the Itaipu Power Plant have been made, being first assessed by Sir Hans Albert Einstein, at the time of the feasibility studies for the enterprise. From that date onwards, eight further studies were made through the last 44 years aiming to confer more precision upon the estimates based on more updated data sets. From the analysis of each monitoring station, it was clearly noticed strong increase tendencies in the sediment yield through the last 14 years, mainly in the Iguatemi, Ivaí, São Francisco Falso and Carapá Rivers, the latter situated in Paraguay, whereas the others are utterly in Brazilian territory. Five lifespan scenarios considering different sediment yield tendencies were simulated with the aid of the softwares SEDIMENT and DPOSIT, both developed by the author of the present work. Such softwares thoroughly follow the Borland & Miller methodology (empirical method of area-reduction). The soundest scenario out of the five ones under analysis indicated a lifespan foresight of 168 years, being the reservoir only 1.8% silted by the end of 2016, after 32 years of operation. Besides, the mass balance in the reservoir (water inflows minus outflows) between 1986 and 2016 shows that 2% of the whole Itaipu lake is silted nowadays. Owing to the convergence of both results, which were acquired by using different methodologies and independent input data, it is worth concluding that the mathematical modeling is satisfactory and calibrated, thus assigning credibility to this most recent lifespan estimate.

Keywords: Borland and Miller method, hydroelectricity, Itaipu Power Plant, lifespan, mass balance

Procedia PDF Downloads 244

Authors: Asmamaw Yehun

Abstract:

The name “TANA” is one of International Geodetic Service (IGS) Global Positioning System (GPS) station which is found in Bahir Dar University in Institute of Land Administration. The station name taken from one of big Lakes in Africa ,Lake Tana. The Institute of Land Administration (ILA) is part of Bahir Dar University, located in the capital of the Amhara National Regional State, Bahir Dar. The institute is the first of its kind in East Africa. The station is installed by cooperation of ILA and Sweden International Development Agency (SIDA) fund support. The Continues Operating Reference Station (CORS) is a network of stations that provide global satellite system navigation data to help three dimensional positioning, meteorology, space, weather, and geophysical applications throughout the globe. TANA station was as CORS since 2013 and sites are independently owned and operated by governments, research and education facilities and others. The data collected by the reference station is downloadable through Internet for post processing purpose by interested parties who carry out GNSS measurements and want to achieve a higher accuracy. We made a first observation on TANA, monitor stations on May 29th 2013. We used Leica 1200 receivers and AX1202GG antennas and made observations from 11:30 until 15:20 for about 3h 50minutes. Processing of data was done in an automatic post processing service CSRS-PPP by Natural Resources Canada (NRCan) . Post processing was done June 27th 2013 so precise ephemeris was used 30 days after observation. We found Latitude (ITRF08): 11 34 08.6573 (dms) / 0.008 (m), Longitude (ITRF08): 37 19 44.7811 (dms) / 0.018 (m) and Ellipsoidal Height (ITRF08): 1850.958 (m) / 0.037 (m). We were compared this result with GAMIT/GLOBK processed data and it was very closed and accurate. TANA station is one of the second IGS station for Ethiopia since 2015 up to now. It provides data for any civilian users, researchers, governmental and nongovernmental users. TANA station is installed with very advanced choke ring antenna and GR25 Leica receiver and also the site is very good for satellite accessibility. In order to test hydrostatic and wet zenith delay for positional data quality, we used GAMIT/GLOBK and we found that TANA station is the most accurate IGS station in East Africa. Due to lower tropospheric zenith and ionospheric delay, TANA and ADIS IGS stations has 2 and 1.9 meters 3D positional accuracy respectively.

Keywords: atmosphere, GNSS, neutral atmosphere, precipitable water vapour

Procedia PDF Downloads 44

Authors: Elia Favarelli, Enrico Testi, Andrea Giorgetti

Abstract:

Autonomous structural health monitoring (SHM) of many structures and bridges became a topic of paramount importance for maintenance purposes and safety reasons. This paper proposes a set of machine learning (ML) tools to perform automatic feature selection and detection of anomalies in a bridge from vibrational data and compare different feature extraction schemes to increase the accuracy and reduce the amount of data collected. As a case study, the Z-24 bridge is considered because of the extensive database of accelerometric data in both standard and damaged conditions. The proposed framework starts from the first four fundamental frequencies extracted through operational modal analysis (OMA) and clustering, followed by density-based time-domain filtering (tracking). The fundamental frequencies extracted are then fed to a dimensionality reduction block implemented through two different approaches: feature selection (intelligent multiplexer) that tries to estimate the most reliable frequencies based on the evaluation of some statistical features (i.e., mean value, variance, kurtosis), and feature extraction (auto-associative neural network (ANN)) that combine the fundamental frequencies to extract new damage sensitive features in a low dimensional feature space. Finally, one class classifier (OCC) algorithms perform anomaly detection, trained with standard condition points, and tested with normal and anomaly ones. In particular, a new anomaly detector strategy is proposed, namely one class classifier neural network two (OCCNN2), which exploit the classification capability of standard classifiers in an anomaly detection problem, finding the standard class (the boundary of the features space in normal operating conditions) through a two-step approach: coarse and fine boundary estimation. The coarse estimation uses classics OCC techniques, while the fine estimation is performed through a feedforward neural network (NN) trained that exploits the boundaries estimated in the coarse step. The detection algorithms vare then compared with known methods based on principal component analysis (PCA), kernel principal component analysis (KPCA), and auto-associative neural network (ANN). In many cases, the proposed solution increases the performance with respect to the standard OCC algorithms in terms of F1 score and accuracy. In particular, by evaluating the correct features, the anomaly can be detected with accuracy and an F1 score greater than 96% with the proposed method.

Keywords: anomaly detection, frequencies selection, modal analysis, neural network, sensor network, structural health monitoring, vibration measurement

Procedia PDF Downloads 91

Authors: Cinzia Federico, Gaetano Giudice, Salvatore Inguaggiato, Marco Liuzzo, Maria Pedone, Fabio Vita, Christoph Kern, Leonardo La Pica, Giovannella Pecoraino, Lorenzo Calderone, Vincenzo Francofonte

Abstract:

The periods of increased fumarolic activity at La Fossa volcano have been characterized, since early 80's, by changes in the gas chemistry and in the output rate of fumaroles. Excepting the direct measurements of the steam output from fumaroles performed from 1983 to 1995, the mass output of the single gas species has been recently measured, with various methods, only sporadically or for short periods. Since 2008, a scanning DOAS system is operating in the Palizzi area for the remote measurement of the in-plume SO₂ flux. On these grounds, the need of a cross-comparison of different methods for the in situ measurement of the output rate of different gas species is envisaged. In 2015, two field campaigns have been carried out, aimed at: 1. The mapping of the concentration of CO₂, H₂S and SO₂ in the fumarolic plume at 1 m from the surface, by using specific open-path diode tunable lasers (GasFinder Boreal Europe Ltd.) and an Active DOAS for SO₂, respectively; these measurements, coupled to simultaneous ultrasonic wind speed and meteorological data, have been elaborated to obtain the dispersion map and the output rate of single species in the overall fumarolic field; 2. The mapping of the concentrations of CO₂, H₂S, SO₂, H₂O in the fumarolic plume at 0.5 m from the soil, by using an integrated system, including IR spectrometers and specific electrochemical sensors; this has provided the concentration ratios of the analysed gas species and their distribution in the fumarolic field; 3. The in-fumarole sampling of vapour and measurement of the steam output, to validate the remote measurements. The dispersion map of CO₂, obtained from the tunable laser measurements, shows a maximum CO₂ concentration at 1m from the soil of 1000 ppmv along the rim, and 1800 ppmv in the inner slopes. As observed, the largest contribution derives from a wide fumarole of the inner-slope, despite its present outlet temperature of 230°C, almost 200°C lower than those measured at the rim fumaroles. Actually, fumaroles in the inner slopes are among those emitting the largest amount of magmatic vapour and, during the 1989-1991 crisis, reached the temperature of 690°C. The estimated CO₂ and H₂S fluxes are 400 t/d and 4.4 t/d, respectively. The coeval SO₂ flux, measured by the scanning DOAS system, is 9±1 t/d. The steam output, recomputed from CO₂ flux measurements, is about 2000 t/d. The various direct and remote methods (as described at points 1-3) have produced coherent results, which encourage to the use of daily and automatic DOAS SO₂ data, coupled with periodic in-plume measurements of different acidic gases, to obtain the total mass rates.

Keywords: DOAS, fumaroles, plume, tunable laser

Procedia PDF Downloads 369

Authors: Jiangbo Li, Wenqian Huang

Abstract:

Early detection of fungal infection in citrus fruit is one of the major problems in the postharvest commercialization process. The automatic and nondestructive detection of infected fruits is still a challenge for the citrus industry. At present, the visual inspection of rotten citrus fruits is commonly performed by workers through the ultraviolet induction fluorescence technology or manual sorting in citrus packinghouses to remove fruit subject with fungal infection. However, the former entails a number of problems because exposing people to this kind of lighting is potentially hazardous to human health, and the latter is very inefficient. Orange is used as a research object. This study would focus on this problem and proposed an effective method based on Vis-NIR hyperspectral imaging in the wavelength range of 400-1000 nm with a spectroscopic resolution of 2.8 nm. In this work, three normalization approaches are applied prior to analysis to reduce the effect of sample curvature on spectral profiles, and it is found that mean normalization was the most effective pretreatment for decreasing spectral variability due to curvature. Then, principal component analysis (PCA) was applied to a dataset composing of average spectra from decayed and normal tissue to reduce the dimensionality of data and observe the ability of Vis-NIR hyper-spectra to discriminate data from two classes. In this case, it was observed that normal and decayed spectra were separable along the resultant first principal component (PC1) axis. Subsequently, five wavelengths (band) centered at 577, 702, 751, 808, and 923 nm were selected as the characteristic wavelengths by analyzing the loadings of PC1. A multispectral combination image was generated based on five selected characteristic wavelength images. Based on the obtained multispectral combination image, the intensity slicing pseudocolor image processing method is used to generate a 2-D visual classification image that would enhance the contrast between normal and decayed tissue. Finally, an image segmentation algorithm for detection of decayed fruit was developed based on the pseudocolor image coupled with a simple thresholding method. For the investigated 238 independent set samples including infected fruits infected by Penicillium digitatum and normal fruits, the total success rate is 100% and 97.5%, respectively, and, the proposed algorithm also used to identify the orange infected by penicillium italicum with a 100% identification accuracy, indicating that the proposed multispectral algorithm here is an effective method and it is potential to be applied in citrus industry.

Keywords: citrus fruit, early rotten, fungal infection, hyperspectral imaging

Procedia PDF Downloads 270

Authors: Rafael do Amaral Teodoro, Leandro Augusto da Silva

Abstract:

Originated from graphite, graphene is a two-dimensional (2D) material that promises to revolutionize technology in many different areas, such as energy, telecommunications, civil construction, aviation, textile, and medicine. This is possible because its structure, formed by carbon bonds, provides desirable optical, thermal, and mechanical characteristics that are interesting to multiple areas of the market. Thus, several research and development centers are studying different manufacturing methods and material applications of graphene, which are often compromised by the scarcity of more agile and accurate methodologies to characterize the material – that is to determine its composition, shape, size, and the number of layers and crystals. To engage in this search, this study proposes a computational methodology that applies deep learning to identify graphene oxide crystals in order to characterize samples by crystal sizes. To achieve this, a fully convolutional neural network called U-net has been trained to segment SEM graphene oxide images. The segmentation generated by the U-net is fine-tuned with a standard deviation technique by classes, which allows crystals to be distinguished with different labels through an object delimitation algorithm. As a next step, the characteristics of the position, area, perimeter, and lateral measures of each detected crystal are extracted from the images. This information generates a database with the dimensions of the crystals that compose the samples. Finally, graphs are automatically created showing the frequency distributions by area size and perimeter of the crystals. This methodological process resulted in a high capacity of segmentation of graphene oxide crystals, presenting accuracy and F-score equal to 95% and 94%, respectively, over the test set. Such performance demonstrates a high generalization capacity of the method in crystal segmentation, since its performance considers significant changes in image extraction quality. The measurement of non-overlapping crystals presented an average error of 6% for the different measurement metrics, thus suggesting that the model provides a high-performance measurement for non-overlapping segmentations. For overlapping crystals, however, a limitation of the model was identified. To overcome this limitation, it is important to ensure that the samples to be analyzed are properly prepared. This will minimize crystal overlap in the SEM image acquisition and guarantee a lower error in the measurements without greater efforts for data handling. All in all, the method developed is a time optimizer with a high measurement value, considering that it is capable of measuring hundreds of graphene oxide crystals in seconds, saving weeks of manual work.

Keywords: characterization, graphene oxide, nanomaterials, U-net, deep learning

Procedia PDF Downloads 134

Authors: Shabnam Sarwar, Franck Lacoeuille, Nadia Withofs, Roland Hustinx

Abstract:

After the development of a potential surrogate of MAA, and its successful application for the diagnosis of pulmonary embolism in artificially embolized rats’ lungs, this microparticulate system were radiolabelled with gallium-68 to synthesize 68Ga-SBMP with high radiochemical purity >99%. As a prerequisite step of clinical trials, 68Ga- labelled starch based microparticles (SBMP) were analysed for their in-vivo behavior in small animals. The purpose of the presented work includes the ex-vivo biodistribution studies of 68Ga-SBMP in order to assess the activity uptake in target organs with respect to time, excretion pathways of the radiopharmaceutical, %ID/g in major organs, T/NT ratios, in-vivo stability of the radiotracer and subsequently the microparticles in the target organs. Radiolabelling of starch based microparticles was performed by incubating it with 68Ga generator eluate (430±26 MBq) at room temperature and pressure without using any harsh reaction condition. For Ex-vivo biodistribution studies healthy White Wistar rats weighing between 345-460 g were injected intravenously 68Ga-SBMP 20±8 MBq, containing about 2,00,000-6,00,000 SBMP particles in a volume of 700µL. The rats were euthanized at predefined time intervals (5min, 30min, 60min and 120min) and their organ parts were cut, washed, and put in the pre-weighed tubes and measured for radioactivity counts through automatic Gamma counter. The 68Ga-SBMP produced >99% RCP just after 10-20 min incubation through a simple and robust procedure. Biodistribution of 68Ga-SBMP showed that initially just after 5 min post injection major uptake was observed in the lungs following by blood, heart, liver, kidneys, bladder, urine, spleen, stomach, small intestine, colon, skin and skeleton, thymus and at last the smallest activity was found in brain. Radioactivity counts stayed stable in lungs with gradual decrease with the passage of time, and after 2h post injection, almost half of the activity were seen in lungs. This is a sufficient time to perform PET/CT lungs scanning in humans while activity in the liver, spleen, gut and urinary system decreased with time. The results showed that urinary system is the excretion pathways instead of hepatobiliary excretion. There was a high value of T/NT ratios which suggest fine tune images for PET/CT lung perfusion studies henceforth further pre-clinical studies and then clinical trials should be planned in order to utilize this potential lung perfusion agent.

Keywords: starch based microparticles, gallium-68, biodistribution, target organs, excretion pathways

Procedia PDF Downloads 142

Authors: Henda Gnakate Biba, Ndassa Mouafon Issa

Abstract:

Dictionaries modeled on the Western model [tonic accent languages] are not suitable and do not account for tonal languages phonologically, which is why the [prosodic and phonological] ethnographic dictionary was designed. It is a glossary that expresses the tones and the rhythm of words. It recreates exactly the speaking or singing of a tonal language, and allows the non-speaker of this language to pronounce the words as if they were a native. It is a dictionary adapted to tonal languages. It was built from ethnomusicological theorems and phonological processes, according to Jean. J. Rousseau 1776 hypothesis /To say and to sing were once the same thing/. Each word in the French dictionary finds its corresponding language, ekaη. And each word ekaη is written on a musical staff. This ethnographic dictionary is also an inventive, original and innovative research thesis, but it is also an inventive, original and innovative research thesis. A contribution to the theoretical, musicological, ethno musicological and linguistic conceptualization of languages, giving rise to the practice of interlocution between the social and cognitive sciences, the activities of artistic creation and the question of modeling in the human sciences: mathematics, computer science, translation automation and artificial intelligence. When you apply this theory to any text of a folksong of a world-tone language, you do not only piece together the exact melody, rhythm, and harmonies of that song as if you knew it in advance but also the exact speaking of this language. The author believes that the issue of the disappearance of tonal languages and their preservation has been structurally resolved, as well as one of the greatest cultural equations related to the composition and creation of tonal, polytonal and random music. The experimentation confirming the theorization designed a semi-digital, semi-analog application which translates the tonal languages of Africa (about 2,100 languages) into blues, jazz, world music, polyphonic music, tonal and anatonal music and deterministic and random music). To test this application, I use a music reading and writing software that allows me to collect the data extracted from my mother tongue, which is already modeled in the musical staves saved in the ethnographic (semiotic) dictionary for automatic translation ( volume 2 of the book). Translation is done (from writing to writing, from writing to speech and from writing to music). Mode of operation: you type a text on your computer, a structured song (chorus-verse), and you command the machine a melody of blues, jazz and, world music or, variety etc. The software runs, giving you the option to choose harmonies, and then you select your melody.

Keywords: music, language, entenglement, science, research

Procedia PDF Downloads 35

Authors: Catariny C. Aleman, Flavio B. Campos, Matheus A. Caliman, Everardo C. Mantovani

Abstract:

The seedling production stage is a critical point in the vegetable production system. Obtaining high-quality seedlings is a prerequisite for subsequent cropping to occur well and productivity optimization is required. The water management is an important step in agriculture production. The adequate water requirement in horticulture seedlings can provide higher quality and increase field production. The practice of irrigation is indispensable and requires a duly adjusted quality irrigation system, together with a specific water management plan to meet the water demand of the crop. Irrigation management in seedling management requires a great deal of specific information, especially when it involves the use of inputs such as hydrorentering polymers and automation technologies of the data acquisition and irrigation system. The experiment was conducted in a greenhouse at the Federal University of Viçosa, Viçosa - MG. Tomato seedlings (Lycopersicon esculentum Mill) were produced in plastic trays of 128 cells, suspended at 1.25 m from the ground. The seedlings were irrigated by 4 micro sprinklers of fixed jet 360º per tray, duly isolated by sideboards, following the methodology developed for this work. During Phase 1, in January / February 2017 (duration of 24 days), the cultivation coefficient (Kc) of seedlings cultured in the presence and absence of hydrogel was evaluated by weighing lysimeter. In Phase 2, September 2017 (duration of 25 days), the seedlings were submitted to 4 irrigation managements (Kc, timer, 0.50 ETo, and 1.00 ETo), in the presence and absence of hydrogel and then evaluated in relation to quality parameters. The microclimate inside the greenhouse was monitored with the use of air temperature, relative humidity and global radiation sensors connected to a microcontroller that performed hourly calculations of reference evapotranspiration by Penman-Monteith standard method FAO56 modified for the balance of long waves according to Walker, Aldrich, Short (1983), and conducted water balance and irrigation decision making for each experimental treatment. Kc of seedlings cultured on a substrate with hydrogel (1.55) was higher than Kc on a pure substrate (1.39). The use of the hydrogel was a differential for the production of earlier tomato seedlings, with higher final height, the larger diameter of the colon, greater accumulation of a dry mass of shoot, a larger area of crown projection and greater the rate of relative growth. The handling 1.00 ETo promoted higher relative growth rate.

Keywords: automatic system; efficiency of water use; precision irrigation, micro sprinkler.

Procedia PDF Downloads 89

Authors: Ayesha Akbar

Abstract:

Pakistan is moving from a security state to a welfare state despite several security challenges both internal and external. Human security signifies a varied approach in different regions depending upon the leadership and policy priorities. The link between human development and economic growth is not automatic. It has to be created consciously by forward-looking policies and strategies by national governments. There are seven components or categories of human security these include: Economic Security, Personal Security, Health Security, Environmental Security, Food Security, Community Security and Political Security. The increasing interest of the international community to clearly understand the dimensions of human security provided the grounds to Pakistani scholars as well to ponder on the issue and delineate lines of human security. A great deal of work has been either done or in process to evaluate human security indicators in Pakistan. Notwithstanding, after having been done a great deal of work the human security in Pakistan is not satisfactory. A range of deteriorating indicators of human development that lies under the domain of human security leaves certain inquiries to be answered. What are the dimensions of human security in Pakistan? And how are they being dealt from the perspective of policy and institution in terms of its operationalization in Pakistan? Is the human security discourse reflects evidence-based policy changes. The methodology is broadly based on qualitative methods that include interviews, content analysis of policy documents. Pakistan is among the most populous countries in the world and faces high vulnerability to climate change. Literacy rate has gone down with the surge of youth bulge to accommodate in the job market. Increasing population is creating food problems as the resources have not been able to compete with the raising demands of food and other social amenities of life. Majority of the people are facing acute poverty. Health outcomes are also not satisfactory with the high infant and maternal mortality rate. Pakistan is on the verge of facing water crisis as the water resources are depleting so fast with the high demand in agriculture and energy sector. Pakistan is striving hard to deal with the declining state of human security but the dilemma is lack of resources that hinders in meeting up with the emerging demands. The government requires to bring about more change with scaling-up economic growth avenues with enhancing the capacity of human resources. A modern performance drive culture with the integration of technology is required to deliver efficient and effective service delivery. On an already fast track process of reforms; e-governance and evidence based policy mechanism is being instilled in the government process for better governance and evidence based decisions.

Keywords: governance, human development index, human security, Pakistan, policy

Procedia PDF Downloads 222

Authors: Jung-Hong Hong, Jing-Cen Yang, Cai-Yu Ou

Abstract:

The analysis of geographic inequality heavily relies on the use of location-enabled statistical data and quantitative measures to present the spatial patterns of the selected phenomena and analyze their differences. To protect the privacy of individual instance and link to administrative units, point-based datasets are spatially aggregated to area-based statistical datasets, where only the overall status for the selected levels of spatial units is used for decision making. The partition of the spatial units thus has dominant influence on the outcomes of the analyzed results, well known as the Modifiable Areal Unit Problem (MAUP). A new spatial reference framework, the Taiwan Geographical Statistical Classification (TGSC), was recently introduced in Taiwan based on the spatial partition principles of homogeneous consideration of the number of population and households. Comparing to the outcomes of the traditional township units, TGSC provides additional levels of spatial units with finer granularity for presenting spatial phenomena and enables domain experts to select appropriate dissemination level for publishing statistical data. This paper compares the results of respectively using TGSC and township unit on the mortality data and examines the spatial characteristics of their outcomes. For the mortality data between the period of January 1^st, 2008 and December 31^st, 2010 of the Taitung County, the all-cause age-standardized death rate (ASDR) ranges from 571 to 1757 per 100,000 persons, whereas the 2^nd dissemination area (TGSC) shows greater variation, ranged from 0 to 2222 per 100,000. The finer granularity of spatial units of TGSC clearly provides better outcomes for identifying and evaluating the geographic inequality and can be further analyzed with the statistical measures from other perspectives (e.g., population, area, environment.). The management and analysis of the statistical data referring to the TGSC in this research is strongly supported by the use of Geographic Information System (GIS) technology. An integrated workflow that consists of the tasks of the processing of death certificates, the geocoding of street address, the quality assurance of geocoded results, the automatic calculation of statistic measures, the standardized encoding of measures and the geo-visualization of statistical outcomes is developed. This paper also introduces a set of auxiliary measures from a geographic distribution perspective to further examine the hidden spatial characteristics of mortality data and justify the analyzed results. With the common statistical area framework like TGSC, the preliminary results demonstrate promising potential for developing a web-based statistical service that can effectively access domain statistical data and present the analyzed outcomes in meaningful ways to avoid wrong decision making.

Keywords: mortality map, spatial patterns, statistical area, variation

Procedia PDF Downloads 223

Authors: Yanheng Zhang, Lu Feng, Yilan Kang, Donghui Fu, Qian Zhang, Qiu Li, Wei Qiu

Abstract:

Diamond-reinforced Ni matrix composite has been widely applied in engineering for coating large-area structural parts owing to its high hardness, good wear resistance and corrosion resistance compared with those features of pure nickel. The mechanical properties of Ni-diamond composite coating can be promoted by the high incorporation and uniform distribution of diamond particles in the nickel matrix, while the distribution features of particles are affected by electrodeposition process parameters, especially the additives in the plating bath. Glycine has been utilized as an organic additive during the preparation of pure nickel coating, which can effectively increase the coating hardness. Nevertheless, to author’s best knowledge, no research about the effects of glycine on the Ni-diamond co-deposition has been reported. In this work, the diamond reinforced Ni nanocomposite coatings were fabricated by a co-electrodeposition technique from a modified Watt’s type bath in the presence of glycine. After preparation, the SEM morphology of the composite coatings was observed combined with energy dispersive X-ray spectrometer, and the diamond incorporation was analyzed. The surface morphology and roughness were obtained by a three-dimensional profile instrument. 3D-Debye rings formed by XRD were analyzed to characterize the nickel grain size and orientation in the coatings. The average coating thickness was measured by a digital micrometer to deduce the deposition rate. The microhardness was tested by automatic microhardness tester. The friction coefficient and wear volume were measured by reciprocating wear tester to characterize the coating wear resistance and cutting performance. The experimental results confirmed that the presence of glycine effectively improved the surface morphology and roughness of the composite coatings. By optimizing the glycine concentration, the incorporation of diamond particles was increased, while the nickel grain size decreased with increasing glycine. The hardness of the composite coatings was increased as the glycine concentration increased. The friction and wear properties were evaluated as the glycine concentration was optimized, showing a decrease in the wear volume. The wear resistance of the composite coatings increased as the glycine content was increased to an optimum value, beyond which the wear resistance decreased. Glycine complexation contributed to the nickel grain refinement and improved the diamond dispersion in the coatings, both of which made a positive contribution to the amount and uniformity of embedded diamond particles, thus enhancing the microhardness, reducing the friction coefficient, and hence increasing the wear resistance of the composite coatings. Therefore, additive glycine can be used during the co-deposition process to improve the mechanical properties of protective coatings.

Keywords: co-electrodeposition, glycine, mechanical properties, Ni-diamond nanocomposite coatings

Procedia PDF Downloads 91

Authors: Marcela De Oliveira, Marina P. Da Silva, Fernando C. G. Da Rocha, Jorge M. Santos, Jaime S. Cardoso, Paulo N. Lisboa-Filho

Abstract:

Multiple Sclerosis (MS) is an immune-mediated disease of the central nervous system characterized by neurodegeneration, inflammation, demyelination, and axonal loss. Magnetic resonance imaging (MRI), due to the richness in the information details provided, is the gold standard exam for diagnosis and follow-up of neurodegenerative diseases, such as MS. Brain atrophy, the gradual loss of brain volume, is quite extensive in multiple sclerosis, nearly 0.5-1.35% per year, far off the limits of normal aging. Thus, the brain volume quantification becomes an essential task for future analysis of the occurrence atrophy. The analysis of MRI has become a tedious and complex task for clinicians, who have to manually extract important information. This manual analysis is prone to errors and is time consuming due to various intra- and inter-operator variability. Nowadays, computerized methods for MRI segmentation have been extensively used to assist doctors in quantitative analyzes for disease diagnosis and monitoring. Thus, the purpose of this work was to evaluate the brain volume in MRI of MS patients. We used MRI scans with 30 slices of the five patients diagnosed with multiple sclerosis according to the McDonald criteria. The computational methods for the analysis of images were carried out in two steps: segmentation of the brain and brain volume quantification. The first image processing step was to perform brain extraction by skull stripping from the original image. In the skull stripper for MRI images of the brain, the algorithm registers a grayscale atlas image to the grayscale patient image. The associated brain mask is propagated using the registration transformation. Then this mask is eroded and used for a refined brain extraction based on level-sets (edge of the brain-skull border with dedicated expansion, curvature, and advection terms). In the second step, the brain volume quantification was performed by counting the voxels belonging to the segmentation mask and converted in cc. We observed an average brain volume of 1469.5 cc. We concluded that the automatic method applied in this work can be used for the brain extraction process and brain volume quantification in MRI. The development and use of computer programs can contribute to assist health professionals in the diagnosis and monitoring of patients with neurodegenerative diseases. In future works, we expect to implement more automated methods for the assessment of cerebral atrophy and brain lesions quantification, including machine-learning approaches. Acknowledgements: This work was supported by a grant from Brazilian agency Fundação de Amparo à Pesquisa do Estado de São Paulo (number 2019/16362-5).

Keywords: brain volume, magnetic resonance imaging, multiple sclerosis, skull stripper

Procedia PDF Downloads 100

Authors: Feiyu Yang, Chunfang Ni, Rong Wang, Yun Zou, Wenbin Liu, Chenggong Zhang, Fenjin Sun, Chun Wang

Abstract:

Cocaine is the most frequently used illegal drug globally, with the global annual prevalence of cocaine used ranging from 0.3% to 0.4 % of the adult population aged 15–64 years. Growing consumption trend of abused cocaine and drug crimes are a great concern, therefore urine sample testing has become an important noninvasive sampling whereas cocaine and its metabolites (COCs) are usually present in high concentrations and relatively long detection windows. However, direct analysis of urine samples is not feasible because urine complex medium often causes low sensitivity and selectivity of the determination. On the other hand, presence of low doses of analytes in urine makes an extraction and pretreatment step important before determination. Especially, in gathered taking drug cases, the pretreatment step becomes more tedious and time-consuming. So developing a sensitive, rapid and high-throughput method for detection of COCs in human body is indispensable for law enforcement officers, treatment specialists and health officials. In this work, a new automated magnetic dispersive solid-phase extraction (MDSPE) sampling method followed by high performance liquid chromatography-mass spectrometry (HPLC-MS) was developed for quantitative enrichment of COCs from human urine, using prepared magnetic nanoparticles as absorbants. The nanoparticles were prepared by silanizing magnetic Fe3O4 nanoparticles and modifying them with divinyl benzene and vinyl pyrrolidone, which possesses the ability for specific adsorption of COCs. And this kind of magnetic particle facilitated the pretreatment steps by electromagnetically controlled extraction to achieve full automation. The proposed device significantly improved the sampling preparation efficiency with 32 samples in one batch within 40mins. Optimization of the preparation procedure for the magnetic nanoparticles was explored and the performances of magnetic nanoparticles were characterized by scanning electron microscopy, vibrating sample magnetometer and infrared spectra measurements. Several analytical experimental parameters were studied, including amount of particles, adsorption time, elution solvent, extraction and desorption kinetics, and the verification of the proposed method was accomplished. The limits of detection for the cocaine and cocaine metabolites were 0.09-1.1 ng·mL-1 with recoveries ranging from 75.1 to 105.7%. Compared to traditional sampling method, this method is time-saving and environmentally friendly. It was confirmed that the proposed automated method was a kind of highly effective way for the trace cocaine and cocaine metabolites analyses in human urine.

Keywords: automatic magnetic dispersive solid-phase extraction, cocaine detection, magnetic nanoparticles, urine sample testing

Procedia PDF Downloads 170

Authors: Emily Wood, James K. Westphal, Itamar Lerner

Abstract:

Background: Polysomnography (PSG) recordings are regularly used in research and clinical settings to study sleep and sleep-related disorders. Typical PSG studies are conducted in professional laboratories and performed by qualified researchers. However, the number of sleep labs worldwide is disproportionate to the increasing number of individuals with sleep disorders like sleep apnea and insomnia. Consequently, there is a growing need to supply cheaper yet reliable means to measure sleep, preferably autonomously by subjects in their own home. Over the last decade, a variety of devices for self-monitoring of sleep became available in the market; however, very few have been directly validated against PSG to demonstrate their ability to perform reliable automatic sleep scoring. Two popular mobile EEG-based systems that have published validation results, the DREEM 3 headband and the Z-Machine, have never been directly compared one to the other by independent researchers. The current study aimed to compare the performance of DREEM 3 and the Z-Machine to help investigators and clinicians decide which of these devices may be more suitable for their studies. Methods: 26 participants have completed the study for credit or monetary compensation. Exclusion criteria included any history of sleep, neurological or psychiatric disorders. Eligible participants arrived at the lab in the afternoon and received the two devices. They then spent two consecutive nights monitoring their sleep at home. Participants were also asked to keep a sleep log, indicating the time they fell asleep, woke up, and the number of awakenings occurring during the night. Data from both devices, including detailed sleep hypnograms in 30-second epochs (differentiating Wake, combined N1/N2, N3; and Rapid Eye Movement sleep), were extracted and aligned upon retrieval. For analysis, the number of awakenings each night was defined as four or more consecutive wake epochs between sleep onset and termination. Total sleep time (TST) and the number of awakenings were compared to subjects’ sleep logs to measure consistency with the subjective reports. In addition, the sleep scores from each device were compared epoch-by-epoch to calculate the agreement between the two devices using Cohen’s Kappa. All analysis was performed using Matlab 2021b and SPSS 27. Results/Conclusion: Subjects consistently reported longer times spent asleep than the time reported by each device (M= 448 minutes for sleep logs compared to M= 406 and M= 345 minutes for the DREEM and Z-Machine, respectively; both ps<0.05). Linear correlations between the sleep log and each device were higher for the DREEM than the Z-Machine for both TST and the number of awakenings, and, likewise, the mean absolute bias between the sleep logs and each device was higher for the Z-Machine for both TST (p<0.001) and awakenings (p<0.04). There was some indication that these effects were stronger for the second night compared to the first night. Epoch-by-epoch comparisons showed that the main discrepancies between the devices were for detecting N2 and REM sleep, while N3 had a high agreement. Overall, the DREEM headband seems superior for reliably scoring sleep at home.

Keywords: DREEM, EEG, seep monitoring, Z-machine

Procedia PDF Downloads 79

Authors: A. A. Purohit, A. Basu, K. A. Chavan, M. D. Kudale

Abstract:

Many estuarine harbours in the world are facing the problem of siltation in docks, channel entrances, etc. The harbours in India are not an exception and require maintenance dredging to achieve navigable depths for keeping them operable. Hence, dredging is inevitable and is a costly affair. The heavy siltation in docks in well mixed tide dominated estuaries is mainly due to settlement of cohesive sediments in suspension. As such there is a need to have a permanent solution for minimising the siltation in such docks to alter the hydrodynamic flow field responsible for siltation by constructing structures outside the dock. One of such docks on the west coast of India, wherein siltation of about 2.5-3 m/annum prevails, was considered to understand the hydrodynamic flow field responsible for siltation. The dock is situated in such a region where macro type of semi-diurnal tide (range of about 5m) prevails. In order to change the flow field responsible for siltation inside the dock, suitability of Current Deflecting Wall (CDW) outside the dock was studied, which will minimise the sediment exchange rate and siltation in the dock. The well calibrated physical tidal model was used to understand the flow field during various phases of tide for the existing dock in Mumbai harbour. At the harbour entrance where the tidal flux exchanges in/out of the dock, measurements on water level and current were made to estimate the sediment transport capacity. The distorted scaled model (1:400 (H) & 1:80 (V)) of Mumbai area was used to study the tidal flow phenomenon, wherein tides are generated by automatic tide generator. Hydraulic model studies carried out under the existing condition (without CDW) reveal that, during initial hours of flood tide, flow hugs the docks breakwater and part of flow which enters the dock forms number of eddies of varying sizes inside the basin, while remaining part of flow bypasses the entrance of dock. During ebb, flow direction reverses, and part of the flow re-enters the dock from outside and creates eddies at its entrance. These eddies do not allow water/sediment-mass to come out and result in settlement of sediments in dock both due to eddies and more retention of sediment. At latter hours, current strength outside the dock entrance reduces and allows the water-mass of dock to come out. In order to improve flow field inside the dockyard, two CDWs of length 300 m and 40 m were proposed outside the dock breakwater and inline to Pier-wall at dock entrance. Model studies reveal that, during flood, major flow gets deflected away from the entrance and no eddies are formed inside the dock, while during ebb flow does not re-enter the dock, and sediment flux immediately starts emptying it during initial hours of ebb. This reduces not only the entry of sediment in dock by about 40% but also the deposition by about 42% due to less retention. Thus, CDW is a promising solution to significantly reduce siltation in dock.

Keywords: current deflecting wall, eddies, hydraulic model, macro tide, siltation

Procedia PDF Downloads 271

Authors: Shraddha Chaudhary, Raksha Agarwal, Niladri Chatterjee

Abstract:

This work demonstrates a web crawler-based generalized end-to-end open domain Question Answering (QA) system. An efficient QA system requires a significant amount of domain knowledge to answer any question with the aim to find an exact and correct answer in the form of a number, a noun, a short phrase, or a brief piece of text for the user's questions. Analysis of the question, searching the relevant document, and choosing an answer are three important steps in a QA system. This work uses a web scraper (Beautiful Soup) to extract K-documents from the web. The value of K can be calibrated on the basis of a trade-off between time and accuracy. This is followed by a passage ranking process using the MS-Marco dataset trained on 500K queries to extract the most relevant text passage, to shorten the lengthy documents. Further, a QA system is used to extract the answers from the shortened documents based on the query and return the top 3 answers. For evaluation of such systems, accuracy is judged by the exact match between predicted answers and gold answers. But automatic evaluation methods fail due to the linguistic ambiguities inherent in the questions. Moreover, reference answers are often not exhaustive or are out of date. Hence correct answers predicted by the system are often judged incorrect according to the automated metrics. One such scenario arises from the original Google Natural Question (GNQ) dataset which was collected and made available in the year 2016. Use of any such dataset proves to be inefficient with respect to any questions that have time-varying answers. For illustration, if the query is where will be the next Olympics? Gold Answer for the above query as given in the GNQ dataset is “Tokyo”. Since the dataset was collected in the year 2016, and the next Olympics after 2016 were in 2020 that was in Tokyo which is absolutely correct. But if the same question is asked in 2022 then the answer is “Paris, 2024”. Consequently, any evaluation based on the GNQ dataset will be incorrect. Such erroneous predictions are usually given to human evaluators for further validation which is quite expensive and time-consuming. To address this erroneous evaluation, the present work proposes an automated approach for evaluating time-dependent question-answer pairs. In particular, it proposes a metric using the current timestamp along with top-n predicted answers from a given QA system. To test the proposed approach GNQ dataset has been used and the system achieved an accuracy of 78% for a test dataset comprising 100 QA pairs. This test data was automatically extracted using an analysis-based approach from 10K QA pairs of the GNQ dataset. The results obtained are encouraging. The proposed technique appears to have the possibility of developing into a useful scheme for gathering precise, reliable, and specific information in a real-time and efficient manner. Our subsequent experiments will be guided towards establishing the efficacy of the above system for a larger set of time-dependent QA pairs.

Keywords: web-based information retrieval, open domain question answering system, time-varying QA, QA evaluation

Procedia PDF Downloads 73

Authors: Michael Mederle, Heinz Bernhardt

Abstract:

The Management of machine fleets or autonomous vehicle control will considerably increase efficiency in future agricultural production. Especially entire process chains, e.g. harvesting complexes with several interacting combine harvesters, grain carts, and removal trucks, provide lots of optimization potential. Organization and pre-planning ensure to get these efficiency reserves accessible. One way to achieve this is to optimize infield path planning. Particularly autonomous machinery requires precise specifications about infield logistics to be navigated effectively and process optimized in the fields individually or in machine complexes. In the past, a lot of theoretical optimization has been done regarding infield logistics, mainly based on field geometry. However, there are reasons why farmers often do not apply the infield strategy suggested by mathematical route planning tools. To make the computational optimization more useful for farmers this study focuses on these influencing factors by expert interviews. As a result practice-oriented navigation not only to the field but also within the field will be possible. The survey study is intended to cover the entire range of German agriculture. Rural mixed farms with simple technology equipment are considered as well as large agricultural cooperatives which farm thousands of hectares using track guidance and various other electronic assistance systems. First results show that farm managers using guidance systems increasingly attune their infield-logistics on direction giving obstacles such as power lines. In consequence, they can avoid inefficient boom flippings while doing plant protection with the sprayer. Livestock farmers rather focus on the application of organic manure with its specific requirements concerning road conditions, landscape terrain or field access points. Cultivation of sugar beets makes great demands on infield patterns because of its particularities such as the row crop system or high logistics demands. Furthermore, several machines working in the same field simultaneously influence each other, regardless whether or not they are of the equal type. Specific infield strategies always are based on interactions of several different influences and decision criteria. Single working steps like tillage, seeding, plant protection or harvest mostly cannot be considered each individually. The entire production process has to be taken into consideration to detect the right infield logistics. One long-term objective of this examination is to integrate the obtained influences on infield strategies as decision criteria into an infield navigation tool. In this way, path planning will become more practical for farmers which is a basic requirement for automatic vehicle control and increasing process efficiency.

Keywords: autonomous vehicle control, infield logistics, path planning, process optimizing

Procedia PDF Downloads 205

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 63

Authors: Elena Kokkoni, Prasanna Kannappan, Ashkan Zehfroosh, Effrosyni Mavroudi, Kristina Strother-Garcia, James C. Galloway, Jeffrey Heinz, Rene Vidal, Herbert G. Tanner

Abstract:

Early immobility affects the motor, cognitive, and social development. Current pediatric rehabilitation lacks the technology that will provide the dosage needed to promote mobility for young children at risk. The addition of socially assistive robots in early interventions may help increase the mobility dosage. The aim of this study is to examine the feasibility of an early intervention paradigm where non-walking infants experience independent mobility while socially interacting with robots. A dynamic environment is developed where both the child and the robot interact and learn from each other. The environment involves: 1) a range of physical activities that are goal-oriented, age-appropriate, and ability-matched for the child to perform, 2) the automatic functions that perceive the child’s actions through novel activity recognition algorithms, and decide appropriate actions for the robot, and 3) a networked visual data acquisition system that enables real-time assessment and provides the means to connect child behavior with robot decision-making in real-time. The environment was tested by bringing a two-year old boy with Down syndrome for eight sessions. The child presented delays throughout his motor development with the current being on the acquisition of walking. During the sessions, the child performed physical activities that required complex motor actions (e.g. climbing an inclined platform and/or staircase). During these activities, a (wheeled or humanoid) robot was either performing the action or was at its end point 'signaling' for interaction. From these sessions, information was gathered to develop algorithms to automate the perception of activities which the robot bases its actions on. A Markov Decision Process (MDP) is used to model the intentions of the child. A 'smoothing' technique is used to help identify the model’s parameters which are a critical step when dealing with small data sets such in this paradigm. The child engaged in all activities and socially interacted with the robot across sessions. With time, the child’s mobility was increased, and the frequency and duration of complex and independent motor actions were also increased (e.g. taking independent steps). Simulation results on the combination of the MDP and smoothing support the use of this model in human-robot interaction. Smoothing facilitates learning MDP parameters from small data sets. This paradigm is feasible and provides an insight on how social interaction may elicit mobility actions suggesting a new early intervention paradigm for very young children with motor disabilities. Acknowledgment: This work has been supported by NIH under grant #5R01HD87133.

Keywords: activity recognition, human-robot interaction, machine learning, pediatric rehabilitation

Procedia PDF Downloads 269

Authors: Yiea Funk Te, Daniel Mueller, Irena Pletikosa Cvijikj

Abstract:

Small and medium enterprises (SMEs) play an important role in the economy of many countries. When the overall world economy is considered, SMEs represent 95% of all businesses in the world, accounting for 66% of the total employment. Existing studies show that the current business environment is characterized as highly turbulent and strongly influenced by modern information and communication technologies, thus forcing SMEs to experience more severe challenges in maintaining their existence and expanding their business. To support SMEs at improving their competitiveness, researchers recently turned their focus on applying data mining techniques to build risk and growth prediction models. However, data used to assess risk and growth indicators is primarily obtained via questionnaires, which is very laborious and time-consuming, or is provided by financial institutes, thus highly sensitive to privacy issues. Recently, web mining (WM) has emerged as a new approach towards obtaining valuable insights in the business world. WM enables automatic and large scale collection and analysis of potentially valuable data from various online platforms, including companies’ websites. While WM methods have been frequently studied to anticipate growth of sales volume for e-commerce platforms, their application for assessment of SME risk and growth indicators is still scarce. Considering that a vast proportion of SMEs own a website, WM bears a great potential in revealing valuable information hidden in SME websites, which can further be used to understand SME risk and growth indicators, as well as to enhance current SME risk and growth prediction models. This study aims at developing an automated system to collect business-relevant data from the Web and predict future growth trends of SMEs by means of WM and data mining techniques. The envisioned system should serve as an 'early recognition system' for future growth opportunities. In an initial step, we examine how structured and semi-structured Web data in governmental or SME websites can be used to explain the success of SMEs. WM methods are applied to extract Web data in a form of additional input features for the growth prediction model. The data on SMEs provided by a large Swiss insurance company is used as ground truth data (i.e. growth-labeled data) to train the growth prediction model. Different machine learning classification algorithms such as the Support Vector Machine, Random Forest and Artificial Neural Network are applied and compared, with the goal to optimize the prediction performance. The results are compared to those from previous studies, in order to assess the contribution of growth indicators retrieved from the Web for increasing the predictive power of the model.

Keywords: data mining, SME growth, success factors, web mining

Procedia PDF Downloads 236

Authors: Mballa Abanda Serge, Henda Gnakate Biba, Romaric Guemno Kuate, Akono Rufine Nicole, Petfiang Sidonie, Bella Sidonie

Abstract:

The main hypotheses proposed around the definition of the syllable and of music, of the common origin of music and language, should lead the reader to reflect on the cross-cutting questions raised by the debate on the notion of universals in linguistics and musicology. These are objects of controversy, and there lies its interest: the debate raises questions that are at the heart of theories on language. It is an inventive, original and innovative research thesis. The main hypotheses proposed around the definition of the syllable and of music, of the common origin of music and language, should lead the reader to reflect on the cross-cutting questions raised by the debate on the notion of universals in linguistics and musicology. These are objects of controversy, and there lies its interest: the debate raises questions that are at the heart of theories on language. It is an inventive, original and innovative research thesis. A contribution to the theoretical, musicological, ethno musicological and linguistic conceptualization of languages, giving rise to the practice of interlocution between the social and cognitive sciences, the activities of artistic creation and the question of modeling in the human sciences: mathematics, computer science, translation automation and artificial intelligence. When you apply this theory to any text of a folksong of a world-tone language, you do not only piece together the exact melody, rhythm, and harmonies of that song as if you knew it in advance but also the exact speaking of this language. The author believes that the issue of the disappearance of tonal languages and their preservation has been structurally resolved, as well as one of the greatest cultural equations related to the composition and creation of tonal, polytonal and random music. The experimentation confirming the theorization, It designed a semi-digital, semi-analog application which translates the tonal languages of Africa (about 2,100 languages) into blues, jazz, world music, polyphonic music, tonal and anatonal music and deterministic and random music). To test this application, I use a music reading and writing software that allows me to collect the data extracted from my mother tongue, which is already modeled in the musical staves saved in the ethnographic (semiotic) dictionary for automatic translation ( volume 2 of the book). Translation is done (from writing to writing, from writing to speech and from writing to music). Mode of operation: you type a text on your computer, a structured song (chorus-verse), and you command the machine a melody of blues, jazz and world music or variety etc. The software runs, giving you the option to choose harmonies, and then you select your melody.

Keywords: music, entanglement, langauge, science

Procedia PDF Downloads 50