Search results for: feature analysis

Authors: Hee-Jeong Ahn, Kee-Won Kim, Seung-Hoon Kim

Abstract:

The knowledge of the relationship between characters can help readers to understand the overall story or plot of the literary fiction. In this paper, we present a method for extracting the specific relationship between characters from a Korean literary fiction. Generally, methods for extracting relationships between characters in text are statistical or computational methods based on the sentence distance between characters without considering Korean linguistic features. Furthermore, it is difficult to extract the relationship with direction from text, such as one-sided love, because they consider only the weight of relationship, without considering the direction of the relationship. Therefore, in order to identify specific relationships between characters, we propose a statistical method considering linguistic features, such as syntactic patterns and speech verbs in Korean. The result of our method is represented by a weighted directed graph of the relationship between the characters. Furthermore, we expect that proposed method could be applied to the relationship analysis between characters of other content like movie or TV drama.

Keywords: data mining, Korean linguistic feature, literary fiction, relationship extraction

Procedia PDF Downloads 383

Authors: Faruk Ozdemir, Roy Kalawsky, Peter Hubbard

Abstract:

Accurate estimation of RUL provides a basis for effective predictive maintenance, reducing unexpected downtime for industrial equipment. However, while models such as the Random Forest have effective predictive capabilities, they are the so-called ‘black box’ models, where interpretability is at a threshold to make critical diagnostic decisions involved in industries related to aviation. The purpose of this work is to present a prognostic framework that embeds Explainable Artificial Intelligence (XAI) techniques in order to provide essential transparency in Machine Learning methods' decision-making mechanisms based on sensor data, with the objective of procuring actionable insights for the aviation industry. Sensor readings have been gathered from critical equipment such as turbofan jet engine and landing gear, and the prediction of the RUL is done by a Random Forest model. It involves steps such as data gathering, feature engineering, model training, and evaluation. These critical components’ datasets are independently trained and evaluated by the models. While suitable predictions are served, their performance metrics are reasonably good; such complex models, however obscure reasoning for the predictions made by them and may even undermine the confidence of the decision-maker or the maintenance teams. This is followed by global explanations using SHAP and local explanations using LIME in the second phase to bridge the gap in reliability within industrial contexts. These tools analyze model decisions, highlighting feature importance and explaining how each input variable affects the output. This dual approach offers a general comprehension of the overall model behavior and detailed insight into specific predictions. The proposed framework, in its third component, incorporates the techniques of causal analysis in the form of Granger causality tests in order to move beyond correlation toward causation. This will not only allow the model to predict failures but also present reasons, from the key sensor features linked to possible failure mechanisms to relevant personnel. The causality between sensor behaviors and equipment failures creates much value for maintenance teams due to better root cause identification and effective preventive measures. This step contributes to the system being more explainable. Surrogate Several simple models, including Decision Trees and Linear Models, can be used in yet another stage to approximately represent the complex Random Forest model. These simpler models act as backups, replicating important jobs of the original model's behavior. If the feature explanations obtained from the surrogate model are cross-validated with the primary model, the insights derived would be more reliable and provide an intuitive sense of how the input variables affect the predictions. We then create an iterative explainable feedback loop, where the knowledge learned from the explainability methods feeds back into the training of the models. This feeds into a cycle of continuous improvement both in model accuracy and interpretability over time. By systematically integrating new findings, the model is expected to adapt to changed conditions and further develop its prognosis capability. These components are then presented to the decision-makers through the development of a fully transparent condition monitoring and alert system. The system provides a holistic tool for maintenance operations by leveraging RUL predictions, feature importance scores, persistent sensor threshold values, and autonomous alert mechanisms. Since the system will provide explanations for the predictions given, along with active alerts, the maintenance personnel can make informed decisions on their end regarding correct interventions to extend the life of the critical machinery.

Keywords: predictive maintenance, explainable artificial intelligence, prognostic, RUL, machine learning, turbofan engines, C-MAPSS dataset

Procedia PDF Downloads 9

Authors: K. Umbleja, M. Ichino

Abstract:

Symbolic data mining has been developed to analyze data in very large datasets. It is also useful in cases when entry specific details should remain hidden. Symbolic data mining is quickly gaining popularity as datasets in need of analyzing are becoming ever larger. One type of such symbolic data is a histogram, which enables to save huge amounts of information into a single variable with high-level of granularity. Other types of symbolic data can also be described in histograms, therefore making histogram a very important and general symbolic data type - a method developed for histograms - can also be applied to other types of symbolic data. Due to its complex structure, analyzing histograms is complicated. This paper proposes a method, which allows to compare two histogram-valued variables and therefore find a dissimilarity between two histograms. Proposed method uses the Ichino-Yaguchi dissimilarity measure for mixed feature-type data analysis as a base and develops a dissimilarity measure specifically for histogram data, which allows to compare histograms with different number of bins and bin widths (so called general histogram). Proposed dissimilarity measure is then used as a measure for clustering. Furthermore, linkage method based on weighted averages is proposed with the concept of cluster compactness to measure the quality of clustering. The method is then validated with application on real datasets. As a result, the proposed dissimilarity measure is found producing adequate and comparable results with general histograms without the loss of detail or need to transform the data.

Keywords: dissimilarity measure, hierarchical clustering, histograms, symbolic data analysis

Procedia PDF Downloads 162

Authors: Angelina Anani, Ignacio Ortiz Flores, Haitao Li

Abstract:

The use of underground mining methods have increased significantly over the past decades. This increase has also been spared on by several mines transitioning from surface to underground mining. However, determining the transition depth can be a challenging task, especially when coupled with production schedule optimization. Several researchers have simplified the problem by excluding operational features relevant to production schedule optimization. Our research objective is to investigate the extent to which operational features of transition mines accounted for affect the optimal production schedule. We also provide a framework for factors to consider in production schedule optimization for transition mines. An integrated mixed-integer linear programming (MILP) model is developed that maximizes the NPV as a function of production schedule and transition depth. A case study is performed to validate the model, with a comparative sensitivity analysis to obtain operational insights.

Keywords: underground mining, transition mines, mixed-integer linear programming, production schedule

Procedia PDF Downloads 169

Authors: Mohammad Yousuf Khan, Bhavya Alankar

Abstract:

Blockchain is a promising technology with its features such as immutability and decentralized database. It has applications in various fields such as pharmaceutical, finance, & the food industry. At the core of its heart lies its feature, traceability which is the most desired key in supply chains. However, supply chains have always been hit rock bottom by scandals and controversies. In this review paper, we have explored the advancement and research gaps of blockchain technology (BT) in supply chain management (SCM). We have used the Prisma framework for systematic literature review (SLR) and included a minuscule amount of grey literature to reduce publication bias. We found that supply chain traceability and transparency is the most researched objective in SCM. There was hardly any research in supply chain resilience. Further, we found that 40 % of the papers were application based. Most articles have focused on the advantages of BT, rather than analyzing it critically. This study will help identify gaps and suitable actions to be followed for an efficient implementation of BT in SCM.

Keywords: blockchain technology, supply chain management, supply chain transparency, supply chain resilience

Procedia PDF Downloads 162

Authors: Mafel Obhuo, Dodeye I. Igbong, Duabari S. Aziaka, Pericles Pilidis

Abstract:

An important feature of the exploitation of associated gas as fuel for gas turbine engines is a declining supply. So when exploiting this resource, the divestment of prime movers is very important as the fuel supply diminishes with time. This paper explores the influence of engine degradation on the timing of divestments. Hypothetical but realistic gas turbine engines were modelled with Turbomatch, the Cranfield University gas turbine performance simulation tool. The results were deployed in three degradation scenarios within the TERA (Techno-economic and environmental risk analysis) framework to develop economic models. An optimisation with Genetic Algorithms was carried out to maximize the economic benefit. The results show that degradation will have a significant impact. It will delay the divestment of power plants, while they are running less efficiently. Over a 20 year investment, a decrease of $0.11bn, $0.26bn and $0.45bn (billion US dollars) were observed for the three degradation scenarios as against the clean case.

Keywords: economic return, flared associated gas, net present value, optimization

Procedia PDF Downloads 137

Authors: Sardorbek Numonov, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Dongeun Choi, Byung-Woo Hong

Abstract:

The detection of curvilinear structures often plays an important role in the analysis of images. In particular, it is considered as a crucial step for the diagnosis of chronic respiratory diseases to localize the fissures in chest CT imagery where the lung is divided into five lobes by the fissures that are characterized by linear features in appearance. However, the characteristic linear features for the fissures are often shown to be subtle due to the high intensity variability, pathological deformation or image noise involved in the imaging procedure, which leads to the uncertainty in the quantification of anatomical or functional properties of the lung. Thus, it is desired to enhance the linear features present in the chest CT images so that the distinctiveness in the delineation of the lobe is improved. We propose a recursive diffusion process that prefers coherent features based on the analysis of structure tensor in an anisotropic manner. The local image features associated with certain scales and directions can be characterized by the eigenanalysis of the structure tensor that is often regularized via isotropic diffusion filters. However, the isotropic diffusion filters involved in the computation of the structure tensor generally blur geometrically significant structure of the features leading to the degradation of the characteristic power in the feature space. Thus, it is required to take into consideration of local structure of the feature in scale and direction when computing the structure tensor. We apply an anisotropic diffusion in consideration of scale and direction of the features in the computation of the structure tensor that subsequently provides the geometrical structure of the features by its eigenanalysis that determines the shape of the anisotropic diffusion kernel. The recursive application of the anisotropic diffusion with the kernel the shape of which is derived from the structure tensor leading to the anisotropic scale-space where the geometrical features are preserved via the eigenanalysis of the structure tensor computed from the diffused image. The recursive interaction between the anisotropic diffusion based on the geometry-driven kernels and the computation of the structure tensor that determines the shape of the diffusion kernels yields a scale-space where geometrical properties of the image structure are effectively characterized. We apply our recursive anisotropic diffusion algorithm to the detection of curvilinear structure in the chest CT imagery where the fissures present curvilinear features and define the boundary of lobes. It is shown that our algorithm yields precise detection of the fissures while overcoming the subtlety in defining the characteristic linear features. The quantitative evaluation demonstrates the robustness and effectiveness of the proposed algorithm for the detection of fissures in the chest CT in terms of the false positive and the true positive measures. The receiver operating characteristic curves indicate the potential of our algorithm as a segmentation tool in the clinical environment. This work was supported by the MISP(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by the IITP(Institute for Information and Communications Technology Promotion).

Keywords: anisotropic diffusion, chest CT imagery, chronic respiratory disease, curvilinear structure, fissure detection, structure tensor

Procedia PDF Downloads 233

Authors: Oxana Lukoshus

Abstract:

The methods of corpus linguistics, a well-established field of research, are being increasingly applied in cognitive linguistics. Corpora data are especially useful for different quantitative studies of grammatical and other aspects of language. The main objective of this paper is to demonstrate how present-day corpora can be applied in semantic studies in general and in semantic studies of adjectives in particular. Polysemantic adjectives have been the subject of numerous studies. But most of them have been carried out on dictionaries. Undoubtedly, dictionaries are viewed as one of the basic data sources, but only at the initial steps of a research. The author usually starts with the analysis of the lexicographic data after which s/he comes up with a hypothesis. In the research conducted three polysemantic synonyms true, loyal, faithful have been analyzed in terms of differences and similarities in their semantic structure. A corpus-based approach in the study of the above-mentioned adjectives involves the following. After the analysis of the dictionary data there was the reference to the following corpora to study the distributional patterns of the words under study – the British National Corpus (BNC) and the Corpus of Contemporary American English (COCA). These corpora are continually updated and contain thousands of examples of the words under research which make them a useful and convenient data source. For the purpose of this study there were no special needs regarding genre, mode or time of the texts included in the corpora. Out of the range of possibilities offered by corpus-analysis software (e.g. word lists, statistics of word frequencies, etc.), the most useful tool for the semantic analysis was the extracting a list of co-occurrence for the given search words. Searching by lemmas, e.g. true, true to, and grouping the results by lemmas have proved to be the most efficient corpora feature for the adjectives under the study. Following the search process, the corpora provided a list of co-occurrences, which were then to be analyzed and classified. Not every co-occurrence was relevant for the analysis. For example, the phrases like An enormous sense of responsibility to protect the minds and hearts of the faithful from incursions by the state was perceived to be the basic duty of the church leaders or ‘True,’ said Phoebe, ‘but I'd probably get to be a Union Official immediately were left out as in the first example the faithful is a substantivized adjective and in the second example true is used alone with no other parts of speech. The subsequent analysis of the corpora data gave the grounds for the distribution groups of the adjectives under the study which were then investigated with the help of a semantic experiment. To sum it up, the corpora-based approach has proved to be a powerful, reliable and convenient tool to get the data for the further semantic study.

Keywords: corpora, corpus-based approach, polysemantic adjectives, semantic studies

Procedia PDF Downloads 315

Authors: Dalyah Y. Al-Jamal, Maryam H. Eshtaiwi, Liyakathunisa Syed

Abstract:

Connecting health services with technology has a huge demand as people health situations are becoming worse day by day. In fact, engaging new technologies such as Internet of Things (IOT) into the medical services can enhance the patient care services. Specifically, patients suffering from chronic diseases such as cardiac patients need a special care and monitoring. In reality, some efforts were previously taken to automate and improve the patient monitoring systems. However, the previous efforts have some limitations and lack the real-time feature needed for chronic kind of diseases. In this paper, an improved process model for patient monitoring system specialized for cardiac patients is presented. A survey was distributed and interviews were conducted to gather the needed requirements to improve the cardiac patient monitoring system. Business Process Model and Notation (BPMN) language was used to model the proposed process. In fact, the proposed system uses the IOT Technology to assist doctors to remotely monitor and follow-up with their heart patients in real-time. In order to validate the effectiveness of the proposed solution, simulation analysis was performed using Bizagi Modeler tool. Analysis results show performance improvements in the heart monitoring process. For the future, authors suggest enhancing the proposed system to cover all the chronic diseases.

Keywords: IoT, process model, remote patient monitoring system, smart watch

Procedia PDF Downloads 333

Authors: Kyungbae Pi, Kibeom Lee, Yongil Kim, Eun-Jung Lee

Abstract:

Abnormal adipocyte growth, in terms of increased cell numbers and increased cell differentiation, is considered to be a major pathological feature of obesity. Thus, the inhibition of preadipocyte mitogenesis and differentiation could help prevent and suppress obesity. The aim of this study was to assess whether extracts from Weissella koreensis 521 cells isolated from kimchi could exert anti-adipogenic effects in 3T3-L1 cells (fat cells). Differentiating 3T3-L1 cells were treated with W. koreensis 521 cell extracts (W. koreensis 521_CE), and cell viability was assessed by MTT assays. At concentrations below 0.2 mg/ml, W. koreensis 521_CE did not exert any cytotoxic effect in 3T3-L1 cells. However, treatment with W. koreensis 521_CE significantly inhibited adipocyte differentiation, as assessed by morphological analysis and Oil Red O staining of fat. W. koreensis 521_CE treatment (0.2 mg/ml) also reduced lipid accumulation by 24% in fully differentiated 3T3-L1 adipocytes. These findings collectively indicate that Weissella koreensis 521 may help prevent obesity.

Keywords: Weissella koreensis 521, 3T3-L1 cells, adipocyte differentiation, obesity

Procedia PDF Downloads 252

Authors: Ming-Hong Chen

Abstract:

In the study, the mechanical and financial feasibility for the compressed air energy storage (CAES) system in the porous media reservoir in Taiwan is evaluated. In 2035, Taiwan aims to install 16.7 GW of wind power and 40 GW of photovoltaic (PV) capacity. However, renewable energy sources often generate more electricity than needed, particularly during winter. Consequently, Taiwan requires long-term, large-scale energy storage systems to ensure the security and stability of its power grid. Currently, the primary large-scale energy storage options are Pumped Hydro Storage (PHS) and Compressed Air Energy Storage (CAES). Taiwan has not ventured into CAES-related technologies due to geological and cost constraints. However, with the imperative of achieving net-zero carbon emissions by 2050, there's a substantial need for the development of a considerable amount of renewable energy. PHS has matured, boasting an overall installed capacity of 4.68 GW. CAES, presenting a similar scale and power generation duration to PHS, is now under consideration. Taiwan's geological composition, being a porous medium unlike salt caves, introduces flow field resistance affecting gas injection and extraction. This study employs a program analysis model to establish the system performance analysis capabilities of CAES. The finite volume model is then used to assess the impact of porous media, and the findings are fed back into the system performance analysis for correction. Subsequently, the financial implications are calculated and compared with existing literature. For Taiwan, the strategic development of CAES technology is crucial, not only for meeting energy needs but also for decentralizing energy allocation, a feature of great significance in regions lacking alternative natural resources.

Keywords: compressed-air energy storage, efficiency, porous media, financial feasibility

Procedia PDF Downloads 67

Authors: Kosuri Harshitha Durga, Ritesh Yaduwanshi

Abstract:

Potholes are one of the most significant problems that affect road safety and the quality of infrastructure. The aim of pothole detection using OpenCV is to design an automated system that will detect and create a map of potholes on the road surfaces to improve the safety of roads and ease the maintenance process. This system is based on high-powered computer vision methods that use still images or video footage taken by cameras located in cars or drones. This paper presents an analysis of the implementation of the YOLOv11 model in pedestrian detection and demonstrates greater effectiveness of this method in regards to accuracy, speed, and efficiency of inference. The improved system now supports enhanced prompt diagnosis and timely repair leaving little or no damage on the infrastructure and also ensuring that enhanced road safety is achieved. This technology can also be used as a safety feature for the car itself by being installed in ADAS systems that would alert drivers in real-time while driving to avoid driving over potholes.

Keywords: deep learning, Potholes, segmentation, object detection, YOLO

Procedia PDF Downloads 5

Authors: Qurratulain Safdar

Abstract:

Drought is a temporary aberration in contrast to aridity, as it is a permanent feature of climate. Virtually, it takes place in all types of climatic regions that range from high to low rainfall areas. Due to the wide latitudinal extent of Pakistan, there is seasonal and annual variability in rainfall. The south-central part of the country is arid and hyper-arid. This study focuses on the spatio-temporal analysis of droughts in arid and hyperarid region of Cholistan using the standardized precipitation index (SPI) approach. This study has assessed the extent of recurrences of drought and its temporal vulnerability to drought in Cholistan region. Initially, the paper described the geographic setup of the study area along with a brief description of the drought conditions that prevail in Pakistan. The study also provides a scientific foundation for preparing literature and theoretical framework in-line with the selected parameters and indicators. Data were collected both from primary and secondary data sources. Rainfall and temperature data were obtained from Pakistan Meteorology Department. By applying geostatistical approach, a standardized precipitation index (SPI) was calculated for the study region, and the value of spatio-temporal variability of drought and its severity was explored. As a result, in-depth spatial analysis of drought conditions in Cholistan area was found. Parallel to this, drought-prone areas with seasonal variation were also identified using Kriging spatial interpolation techniques in a GIS environment. The study revealed that there is temporal variation in droughts' occurrences both in time series and SPI values. The paper is finally concluded, and strategic plan was suggested to minimize the impacts of drought.

Keywords: Cholistan desert, climate anomalies, metrological droughts, standardized precipitation index

Procedia PDF Downloads 213

Authors: Joo-Heon Lee, Ho-Won Jang, Hyung-Won Cho, Tae-Woong Kim

Abstract:

Drought is a recurrent climatic feature that occurs in virtually every climatic zone around the world. Korea experiences the drought almost every year at the regional scale mainly during in the winter and spring seasons. Moreover, extremely severe droughts at a national scale also occurred at a frequency of six to seven years. Various drought indices had developed as tools to quantitatively monitor different types of droughts and are utilized in the field of drought analysis. Since drought is closely related with climatological and topographic characteristics of the drought prone areas, the basins where droughts are frequently occurred need separate drought preparedness and contingency plans. In this study, an analysis using statistical methods was carried out for the historical droughts occurred in the five major river basins in Korea so that drought characteristics can be quantitatively investigated. It was also aimed to provide information with which differentiated and customized drought preparedness plans can be established based on the basin level analysis results. Conventional methods which quantifies drought execute an evaluation by applying a various drought indices. However, the evaluation results for same drought event are different according to different analysis technique. Especially, evaluation of drought event differs depend on how we view the severity or duration of drought in the evaluation process. Therefore, it was intended to draw a drought history for the most severely affected five major river basins of Korea by investigating a magnitude of drought that can simultaneously consider severity, duration, and the damaged areas by applying drought run theory with the use of SPI (Standardized Precipitation Index) that can efficiently quantifies meteorological drought. Further, quantitative analysis for the historical extreme drought at various viewpoints such as average severity, duration, and magnitude of drought was attempted. At the same time, it was intended to quantitatively analyze the historical drought events by estimating the return period by derived SDF (severity-duration-frequency) curve for the five major river basins through parametric regional drought frequency analysis. Analysis results showed that the extremely severe drought years were in the years of 1962, 1988, 1994, and 2014 in the Han River basin. While, the extreme droughts were occurred in 1982 and 1988 in the Nakdong river basin, 1994 in the Geumg basin, 1988 and 1994 in Youngsan river basin, 1988, 1994, 1995, and 2000 in the Seomjin river basin. While, the extremely severe drought years at national level in the Korean Peninsula were occurred in 1988 and 1994. The most damaged drought were in 1981~1982 and 1994~1995 which lasted for longer than two years. The return period of the most severe drought at each river basin was turned out to be at a frequency of 50~100 years.

Keywords: drought magnitude, regional frequency analysis, SPI, SDF(severity-duration-frequency) curve

Procedia PDF Downloads 407

Authors: Mohammad Aladwan

Abstract:

Alzheimer’s disease (AD) is a widespread dementing illness with a complex and poorly understood etiology. An important role in improving our understanding of the AD process is the modeling of disease-associated changes in tau protein phosphorylation, a protein known to mediate events essential to the onset and progression of AD. A main feature of AD is the abnormal phosphorylation of tau protein and the presence of neurofibrillary tangles. In order to evaluate the respective roles of the microtubule-binding region (MTBR) and alternatively spliced exons in the N-terminal projection domains in AD, we have constructed SHSY-5Y cell lines that stably overexpress four different species of tau protein (4R2N, 4R0N, N(E-2), N(E+2)). Since the toxicity and spreading of tau lesions in AD depends on the interactions of tau with other proteins, we have performed a proteomic analysis of exosome-fraction interactomes for cell lysates and media samples that were isolated from SHSY-5Y cell lines. Functional analysis of tau interactomes based on gene ontology (GO) terms was performed using the String 10.5 database program. The highest number of exosomes proteomes and tau associated proteins were found with 4R2N isoform (2771 and 159) in cell lysate and they have a high strength of connectivity (78%) between proteins, while N(E-2) isoform in the media proteomes has the highest number of proteins and tau associated protein (1829 and 205). Moreover, known AD markers were significantly enriched in secreted interactomes relative to lysate interactomes in the SHSY-5Y cells of tau isoforms lacking exons 2 and 3 in the N-terminal. The lack of exon 2 (E-2) from tau protein can be mediated by tau secretion and spreading to different cells. Enriched functions in the secreted E-2 interactome include signaling and developmental pathways that have been linked to a) tau misprocessing and lesion development and b) tau secretion and which, therefore, could play novel roles in AD pathogenesis.

Keywords: Alzheimer's disease, dementia, tau protein, neurodegenration disease

Procedia PDF Downloads 100

Authors: Milos Travar, Jovana Nikolov, Andrej Vranicar, Natasa Todorovic

Abstract:

Over the years, High Purity Germanium (HPGe) detectors proved to be an excellent practical tool and, as such, have established their today's wide use in low background γ-spectrometry. One of the advantages of gamma-ray spectrometry is its easy sample preparation as chemical processing and separation of the studied subject are not required. Thus, with a single measurement, one can simultaneously perform both qualitative and quantitative analysis. One of the most prominent features of HPGe detectors, besides their excellent efficiency, is their superior resolution. This feature virtually allows a researcher to perform a thorough analysis by discriminating photons of similar energies in the studied spectra where otherwise they would superimpose within a single-energy peak and, as such, could potentially scathe analysis and produce wrongly assessed results. Naturally, this feature is of great importance when the identification of radionuclides, as well as their activity concentrations, is being practiced where high precision comes as a necessity. In measurements of this nature, in order to be able to reproduce good and trustworthy results, one has to have initially performed an adequate full-energy peak (FEP) efficiency calibration of the used equipment. However, experimental determination of the response, i.e., efficiency curves for a given detector-sample configuration and its geometry, is not always easy and requires a certain set of reference calibration sources in order to account for and cover broader energy ranges of interest. With the goal of overcoming these difficulties, a lot of researches turned towards the application of different software toolkits that implement the Monte Carlo method (e.g., MCNP, FLUKA, PENELOPE, Geant4, etc.), as it has proven time and time again to be a very powerful tool. In the process of creating a reliable model, one has to have well-established and described specifications of the detector. Unfortunately, the documentation that manufacturers provide alongside the equipment is rarely sufficient enough for this purpose. Furthermore, certain parameters tend to evolve and change over time, especially with older equipment. Deterioration of these parameters consequently decreases the active volume of the crystal and can thus affect the efficiencies by a large margin if they are not properly taken into account. In this study, the optimisation method of two HPGe detectors through the implementation of the Geant4 toolkit developed by CERN is described, with the goal of further improving simulation accuracy in calculations of FEP efficiencies by investigating the influence of certain detector variables (e.g., crystal-to-window distance, dead layer thicknesses, inner crystal’s void dimensions, etc.). Detectors on which the optimisation procedures were carried out were a standard traditional co-axial extended range detector (XtRa HPGe, CANBERRA) and a broad energy range planar detector (BEGe, CANBERRA). Optimised models were verified through comparison with experimentally obtained data from measurements of a set of point-like radioactive sources. Acquired results of both detectors displayed good agreement with experimental data that falls under an average statistical uncertainty of ∼ 4.6% for XtRa and ∼ 1.8% for BEGe detector within the energy range of 59.4−1836.1 [keV] and 59.4−1212.9 [keV], respectively.

Keywords: HPGe detector, γ spectrometry, efficiency, Geant4 simulation, Monte Carlo method

Procedia PDF Downloads 121

Authors: Sadia Nasrin Tisha, Mushfika Sharmin Rahman, Javier Orduz

Abstract:

Machine learning is applied in a variety of fields throughout the world. The healthcare sector has benefited enormously from it. One of the most effective approaches for predicting human heart diseases is to use machine learning applications to classify data and predict the outcome as a classification. However, with the rapid advancement of quantum technology, quantum computing has emerged as a potential game-changer for many applications. Quantum algorithms have the potential to execute substantially faster than their classical equivalents, which can lead to significant improvements in computational performance and efficiency. In this study, we applied quantum machine learning concepts to predict coronary heart diseases from text data. We experimented thrice with three different features; and three feature sets. The data set consisted of 100 data points. We pursue to do a comparative analysis of the two approaches, highlighting the potential benefits of quantum machine learning for predicting heart diseases.

Keywords: quantum machine learning, SVM, QSVM, matrix product state

Procedia PDF Downloads 94

Authors: Yulan Wu

Abstract:

The spread of fake news on social media has posed significant societal harm to the public and the nation, with its threats spanning various domains, including politics, economics, health, and more. News on social media often covers multiple domains, and existing models studied by researchers and relevant organizations often perform well on datasets from a single domain. However, when these methods are applied to social platforms with news spanning multiple domains, their performance significantly deteriorates. Existing research has attempted to enhance the detection performance of multi-domain datasets by adding single-domain labels to the data. However, these methods overlook the fact that a news article typically belongs to multiple domains, leading to the loss of domain knowledge information contained within the news text. To address this issue, research has found that news records in different domains often use different vocabularies to describe their content. In this paper, we propose a fake news detection framework that combines domain knowledge and expert knowledge. Firstly, it utilizes an unsupervised domain discovery module to generate a low-dimensional vector for each news article, representing domain embeddings, which can retain multi-domain knowledge of the news content. Then, a feature extraction module uses the domain embeddings discovered through unsupervised domain knowledge to guide multiple experts in extracting news knowledge for the total feature representation. Finally, a classifier is used to determine whether the news is fake or not. Experiments show that this approach can improve multi-domain fake news detection performance while reducing the cost of manually labeling domain labels.

Keywords: fake news, deep learning, natural language processing, multiple domains

Procedia PDF Downloads 75

Authors: Liu M. Hanmin

Abstract:

Wong Kar-Wai’s multi-genre film 2046, world premiered in 2004, comes with a vibrant mediascape made up of multiple named languages, code-switching, intertitles, news footage from the real world, and extra-linguistic means of communication. In film- and multilingual studies it is still a challenge to incorporate non-languages into an analytical framework with conventional languages. This paper uses translanguaging theory to read silent practices in Wong Kar-Wai’ 2046. Two scenes that feature the silence experience the most are taken as case studies. In these two scenes, we can identify two tropes of intersemiotic relationships that are co-articulated by silence: patriarchy and unfinished romance, respectively. The conclusion argues that silence in Wong Kar-Wai’s 2046 exerts multimodal agency by ‘speaking’ directly to the audience and in mutual directions to characters. Thereby, it moves beyond the passive role of merely accentuating or assisting the aural register of a film.

Keywords: translanguaging, Wong Kar-Wai, multimodality, semiotics, inter semiotics, Hong Kong media, film culture

Procedia PDF Downloads 103

Authors: Reshmita Nath

Abstract:

In this study, we investigate the spatiotemporal characteristics of drought in India and its impact on agriculture during the summer season (April to September). For our analysis, we have used Standardized Precipitation Evapotranspiration Index (SPEI) datasets between 1982 and 2012 at six-month timescale. Based on the criteria SPEI<-1 we obtain the vulnerability map and have found that the Humid subtropical Upper Middle Gangetic Plain (UMGP) region is highly drought prone with an occurrence frequency of 40-45%. This UMGP region contributes at least 18-20% of India’s annual cereal production. Not only the probability, but the region becomes more and more drought-prone in the recent decades. Moreover, the cereal production in the UMGP has experienced a gradual declining trend from 2000 onwards and this feature is consistent with the increase in drought affected areas from 20-25% to 50-60%, before and after 2000, respectively. The higher correlation coefficient (-0.69) between the changes in cereal production and drought affected areas confirms that at least 50% of the agricultural (cereal) losses is associated with drought. While analyzing the individual impact of precipitation and surface temperature anomalies on SPEI (6), we have found that in the UMGP region surface temperature plays the primary role in lowering of SPEI. The linkage is further confirmed by the correlation analysis between the SPEI (6) and surface temperature rise, which exhibits strong negative values in the UMGP region. Higher temperature might have caused more evaporation and drying, which therefore increases the area affected by drought in the recent decade.

Keywords: drought, agriculture, SPEI, Indo-Gangetic plain

Procedia PDF Downloads 258

Authors: Cecile Laval, Harriet Lowe

Abstract:

Processing Instruction is a psycholinguistic pedagogical approach drawing insights from the Input Processing Model which establishes the initial innate strategies used by second language learners to connect form and meaning of linguistic features. With the ever-growing use of technology in Second Language Acquisition research, the present study uses eye-tracking to measure the effectiveness of Processing Instruction in the acquisition of French and its effects on learner’s cognitive strategies. The experiment was designed using a TOBII Pro-TX300 eye-tracker to measure participants’ default strategies when processing French linguistic input and any cognitive changes after receiving Processing Instruction treatment. Participants were drawn from lower intermediate adult learners of French at the University of Greenwich and randomly assigned to two groups. The study used a pre-test/post-test methodology. The pre-tests (one per linguistic item) were administered via the eye-tracker to both groups one week prior to instructional treatment. One group received full Processing Instruction treatment (explicit information on the grammatical item and on the processing strategies, and structured input activities) on the primary target linguistic feature (French past tense imperfective aspect). The second group received Processing Instruction treatment except the explicit information on the processing strategies. Three immediate post-tests on the three grammatical structures under investigation (French past tense imperfective aspect, French Subjunctive used for the expression of doubt, and the French causative construction with Faire) were administered with the eye-tracker. The eye-tracking data showed the positive change in learners’ processing of the French target features after instruction with improvement in the interpretation of the three linguistic features under investigation. 100% of participants in both groups made a statistically significant improvement (p=0.001) in the interpretation of the primary target feature (French past tense imperfective aspect) after treatment. 62.5% of participants made an improvement in the secondary target item (French Subjunctive used for the expression of doubt) and 37.5% of participants made an improvement in the cumulative target feature (French causative construction with Faire). Statistically there was no significant difference between the pre-test and post-test scores in the cumulative target feature; however, the variance approximately tripled between the pre-test and the post-test (3.9 pre-test and 9.6 post-test). This suggests that the treatment does not affect participants homogenously and implies a role for individual differences in the transfer-of-training effect of Processing Instruction. The use of eye-tracking provides an opportunity for the study of unconscious processing decisions made during moment-by-moment comprehension. The visual data from the eye-tracking demonstrates changes in participants’ processing strategies. Gaze plots from pre- and post-tests display participants fixation points changing from focusing on content words to focusing on the verb ending. This change in processing strategies can be clearly seen in the interpretation of sentences in both primary and secondary target features. This paper will present the research methodology, design and results of the experimental study using eye-tracking to investigate the primary effects and transfer-of-training effects of Processing Instruction. It will then provide evidence of the cognitive benefits of Processing Instruction in Second Language Acquisition and offer suggestion in second language teaching of grammar.

Keywords: eye-tracking, language teaching, processing instruction, second language acquisition

Procedia PDF Downloads 280

Authors: Golnush Masghati-Amoli, Paul Chin

Abstract:

Over the past recent years, with the rapid increases in data availability and computing power, Machine Learning (ML) techniques have been called on in a range of different industries for their strong predictive capability. However, the use of Machine Learning in commercial banking has been limited due to a special challenge imposed by numerous regulations that require lenders to be able to explain their analytic models, not only to regulators but often to consumers. In other words, although Machine Leaning techniques enable better prediction with a higher level of accuracy, in comparison with other industries, they are adopted less frequently in commercial banking especially for scoring purposes. This is due to the fact that Machine Learning techniques are often considered as a black box and fail to provide information on why a certain risk score is given to a customer. In order to bridge this gap between the explain-ability and performance of Machine Learning techniques, a Hybrid Model is developed at Dun and Bradstreet that is focused on blending Machine Learning algorithms with traditional approaches such as scorecards. The Hybrid Model maximizes efficiency of traditional scorecards by merging its practical benefits, such as explain-ability and the ability to input domain knowledge, with the deep insights of Machine Learning techniques which can uncover patterns scorecard approaches cannot. First, through development of Machine Learning models, engineered features and latent variables and feature interactions that demonstrate high information value in the prediction of customer risk are identified. Then, these features are employed to introduce observed non-linear relationships between the explanatory and dependent variables into traditional scorecards. Moreover, instead of directly computing the Weight of Evidence (WoE) from good and bad data points, the Hybrid Model tries to match the score distribution generated by a Machine Learning algorithm, which ends up providing an estimate of the WoE for each bin. This capability helps to build powerful scorecards with sparse cases that cannot be achieved with traditional approaches. The proposed Hybrid Model is tested on different portfolios where a significant gap is observed between the performance of traditional scorecards and Machine Learning models. The result of analysis shows that Hybrid Model can improve the performance of traditional scorecards by introducing non-linear relationships between explanatory and target variables from Machine Learning models into traditional scorecards. Also, it is observed that in some scenarios the Hybrid Model can be almost as predictive as the Machine Learning techniques while being as transparent as traditional scorecards. Therefore, it is concluded that, with the use of Hybrid Model, Machine Learning algorithms can be used in the commercial banking industry without being concerned with difficulties in explaining the models for regulatory purposes.

Keywords: machine learning algorithms, scorecard, commercial banking, consumer risk, feature engineering

Procedia PDF Downloads 136

Authors: H. Agbaria, A. Salman, M. Huleihel, G. Beck, D. H. Rich, S. Mordechai, J. Kapelushnik

Abstract:

Viral and bacterial infections are responsible for variety of diseases. These infections have similar symptoms like fever, sneezing, inflammation, vomiting, diarrhea and fatigue. Thus, physicians may encounter difficulties in distinguishing between viral and bacterial infections based on these symptoms. Bacterial infections differ from viral infections in many other important respects regarding the response to various medications and the structure of the organisms. In many cases, it is difficult to know the origin of the infection. The physician orders a blood, urine test, or 'culture test' of tissue to diagnose the infection type when it is necessary. Using these methods, the time that elapses between the receipt of patient material and the presentation of the test results to the clinician is typically too long ( > 24 hours). This time is crucial in many cases for saving the life of the patient and for planning the right medical treatment. Thus, rapid identification of bacterial and viral infections in the lab is of great importance for effective treatment especially in cases of emergency. Blood was collected from 50 patients with confirmed viral infection and 50 with confirmed bacterial infection. White blood cells (WBCs) and plasma were isolated and deposited on a zinc selenide slide, dried and measured under a Fourier transform infrared (FTIR) microscope to obtain their infrared absorption spectra. The acquired spectra of WBCs and plasma were analyzed in order to differentiate between the two types of infections. In this study, the potential of FTIR microscopy in tandem with multivariate analysis was evaluated for the identification of the agent that causes the human infection. The method was used to identify the infectious agent type as either bacterial or viral, based on an analysis of the blood components [i.e., white blood cells (WBC) and plasma] using their infrared vibrational spectra. The time required for the analysis and evaluation after obtaining the blood sample was less than one hour. In the analysis, minute spectral differences in several bands of the FTIR spectra of WBCs were observed between groups of samples with viral and bacterial infections. By employing the techniques of feature extraction with linear discriminant analysis (LDA), a sensitivity of ~92 % and a specificity of ~86 % for an infection type diagnosis was achieved. The present preliminary study suggests that FTIR spectroscopy of WBCs is a potentially feasible and efficient tool for the diagnosis of the infection type.

Keywords: viral infection, bacterial infection, linear discriminant analysis, plasma, white blood cells, infrared spectroscopy

Procedia PDF Downloads 224

Authors: Xun Li, Haojie Wang

Abstract:

Federated learning is a kind of distributed training and centralized training mode, which is of great value in the protection of user privacy. In order to solve the problem that the model is vulnerable to backdoor attacks in federated learning, a backdoor attack detection method based on a weighted k-medoids algorithm is proposed. First of all, this paper collates the update parameters of the client to construct a vector group, then uses the principal components analysis (PCA) algorithm to extract the corresponding feature information from the vector group, and finally uses the improved k-medoids clustering algorithm to identify the normal and backdoor update parameters. In this paper, the backdoor is implanted in the federation learning model through the model replacement attack method in the simulation experiment, and the update parameters from the attacker are effectively detected and removed by the defense method proposed in this paper.

Keywords: federated learning, backdoor attack, PCA, k-medoids, backdoor defense

Procedia PDF Downloads 115

Authors: Seyed Mehdi Ghezi, Hesam Hasanpoor

Abstract:

This scientific article explores enhancement methods for ensemble learning with the aim of improving the performance of classifiers in the analysis and classification of brain signals. The research approach in this field consists of two main parts, each with its own strengths and weaknesses. The choice of approach depends on the specific research question and available resources. By combining these approaches and leveraging their respective strengths, researchers can enhance the accuracy and reliability of classification results, consequently advancing our understanding of the brain and its functions. The first approach focuses on utilizing machine learning methods to identify the best features among the vast array of features present in brain signals. The selection of features varies depending on the research objective, and different techniques have been employed for this purpose. For instance, the genetic algorithm has been used in some studies to identify the best features, while optimization methods have been utilized in others to identify the most influential features. Additionally, machine learning techniques have been applied to determine the influential electrodes in classification. Ensemble learning plays a crucial role in identifying the best features that contribute to learning, thereby improving the overall results. The second approach concentrates on designing and implementing methods for selecting the best classifier or utilizing meta-classifiers to enhance the final results in ensemble learning. In a different section of the research, a single classifier is used instead of multiple classifiers, employing different sets of features to improve the results. The article provides an in-depth examination of each technique, highlighting their advantages and limitations. By integrating these techniques, researchers can enhance the performance of classifiers in the analysis and classification of brain signals. This advancement in ensemble learning methodologies contributes to a better understanding of the brain and its functions, ultimately leading to improved accuracy and reliability in brain signal analysis and classification.

Keywords: ensemble learning, brain signals, classification, feature selection, machine learning, genetic algorithm, optimization methods, influential features, influential electrodes, meta-classifiers

Procedia PDF Downloads 76

Authors: Alessandro Preziosi, Antonio Prioletti, Luca Castangia

Abstract:

Deformable part models achieve high precision in pedestrian recognition, but all publicly available implementations are too slow for real-time applications. We implemented a deformable part model algorithm fast enough for real-time use by exploiting information about the camera position and orientation. This implementation is both faster and more precise than alternative DPM implementations. These results are obtained by computing convolutions in the frequency domain and using lookup tables to speed up feature computation. This approach is almost an order of magnitude faster than the reference DPM implementation, with no loss in precision. Knowing the position of the camera with respect to horizon it is also possible prune many hypotheses based on their size and location. The range of acceptable sizes and positions is set by looking at the statistical distribution of bounding boxes in labelled images. With this approach it is not needed to compute the entire feature pyramid: for example higher resolution features are only needed near the horizon. This results in an increase in mean average precision of 5% and an increase in speed by a factor of two. Furthermore, to reduce misdetections involving small pedestrians near the horizon, input images are supersampled near the horizon. Supersampling the image at 1.5 times the original scale, results in an increase in precision of about 4%. The implementation was tested against the public KITTI dataset, obtaining an 8% improvement in mean average precision over the best performing DPM-based method. By allowing for a small loss in precision computational time can be easily brought down to our target of 100ms per image, reaching a solution that is faster and still more precise than all publicly available DPM implementations.

Keywords: autonomous vehicles, deformable part model, dpm, pedestrian detection, real time

Procedia PDF Downloads 282

Authors: Ali Ulvi Uzer

Abstract:

Data reduction is an important topic in the field of pattern recognition applications. The basic concept is the reduction of multitudinous amounts of data down to the meaningful parts. The Principal Component Analysis (PCA) method is frequently used for data reduction. The Support Vector Machine (SVM) method is a discriminative classifier formally defined by a separating hyperplane. In other words, given labeled training data, the algorithm outputs an optimal hyperplane which categorizes new examples. This study offers a hybrid approach that uses the PCA for data reduction and Support Vector Machines (SVM) for classification. In order to detect the accuracy of the suggested system, two boreholes taken from the soil sample was used. The classification accuracies for this dataset were obtained through using ten-fold cross-validation method. As the results suggest, this system, which is performed through size reduction, is a feasible system for faster recognition of dataset so our study result appears to be very promising.

Keywords: feature selection, sequential forward selection, support vector machines, soil sample

Procedia PDF Downloads 455

Authors: Yufeng Li, Yinan Ma, Jing Wu, Chengnian Long

Abstract:

Infrared object detection aims at separating small and dim target from clutter background and its capabilities extend beyond the limits of visible light, making it invaluable in a wide range of applications such as improving safety, security, efficiency, and functionality. However, existing methods are usually sensitive to the noise of the input infrared image, leading to a decrease in target detection accuracy and an increase in the false alarm rate in high-noise environments. To address this issue, an infrared small target detection algorithm called YOLO-IR is proposed in this paper to improve the robustness to high infrared noise. To address the problem that high noise significantly reduces the clarity and reliability of target features in infrared images, we design a soft-threshold coordinate attention mechanism to improve the model’s ability to extract target features and its robustness to noise. Since the noise may overwhelm the local details of the target, resulting in the loss of small target features during depth down-sampling, we propose a deep and shallow feature fusion neck to improve the detection accuracy. In addition, because the generalized Intersection over Union (IoU)-based loss functions may be sensitive to noise and lead to unstable training in high-noise environments, we introduce a Wasserstein-distance based loss function to improve the training of the model. The experimental results show that YOLO-IR achieves a 5.0% improvement in recall and a 6.6% improvement in F1-score over existing state-of-art model.

Keywords: infrared small target detection, high noise, robustness, soft-threshold coordinate attention, feature fusion

Procedia PDF Downloads 79

Authors: Adrian Forca, Simeon Cainday III

Abstract:

The Electronic Payment Recording with Payment History Retrieval Module is developed intendedly for the College of Science and Technology. This system software innovates the manual process of recording the payments done in the department through the development of electronic payment recording system software shifting from the slow and time-consuming procedure to quick yet reliable and accurate way of recording payments because it immediately generates receipts for every transaction. As an added feature to its software process, generation of recorded payment report is integrated eliminating the manual reporting to a more easy and consolidated report. As an added feature to the system, all recorded payments of the students can be retrieved immediately making the system transparent and reliable payment recording software. Viewing the whole process, the system software will shift from the manual process to an organized software technology because the information will be stored in a logically correct and normalized database. Further, the software will be developed using the modern programming language and implement strict programming methods to validate all users accessing the system, evaluate all data passed into the system and information retrieved to ensure data accuracy and reliability. In addition, the system will identify the user and limit its access privilege to establish boundaries of the specific access to information allowed for the store, modify, and update making the information secure against unauthorized data manipulation. As a result, the System software will eliminate the manual procedure and replace with an innovative modern information technology resulting to the improvement of the whole process of payment recording fast, secure, accurate and reliable software innovations.

Keywords: collection, information system, manual procedure, payment

Procedia PDF Downloads 168

Authors: Samuel Onyije Igbedion

Abstract:

The Nigerian film industry, commonly known as Nollywood, has grown to become the second largest in the world in terms of the volumes of films produced. Many scholars have argued that the themes in most Nollywood films do not let themselves to the issue of film-induced tourism, which can be used to improve tourism in Nigeria and the economy at large. This study, therefore, seeks to examine the validity of this statement in the context of one film that attempts to address the issue. This paper examines the features of tourism-induced films to determine if tourism-inducing themes were used in the film and how they were used in order to confirm or refute the thesis statement. The agenda-setting theory of the media underpinned the study. A qualitative research approach was adopted and content analysis was used to review literature from relevant secondary sources that determined the content criteria, which was then used to analyze the film. The findings reveal that the filmmakers of Up North (2018) did feature themes and scenes that promoted tourism through the use and filming of exotic scenery. It also revealed that the film introduced these tourism-inducing features of the north through the setting, the storyline, the choice of locations and chosen shot types. The study concludes that the prominent and intentional featuring all of these beautiful scenery, history, culture, adventure activities and personalities point to a deliberate attempt at convincing the audiences of the tourist potential of Nigeria. Thus, the validity of the statement does not apply to the film Up North (2018).

Keywords: film-tourism, nollywood, agenda-setting theory, filmmaking, culture

Procedia PDF Downloads 78