Search results for: machine vision
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 3794

Search results for: machine vision

2534 Modelling the Behavior of Commercial and Test Textiles against Laundering Process by Statistical Assessment of Their Performance

Authors: M. H. Arslan, U. K. Sahin, H. Acikgoz-Tufan, I. Gocek, I. Erdem

Abstract:

Various exterior factors have perpetual effects on textile materials during wear, use and laundering in everyday life. In accordance with their frequency of use, textile materials are required to be laundered at certain intervals. The medium in which the laundering process takes place have inevitable detrimental physical and chemical effects on textile materials caused by the unique parameters of the process inherently existing. Connatural structures of various textile materials result in many different physical, chemical and mechanical characteristics. Because of their specific structures, these materials have different behaviors against several exterior factors. By modeling the behavior of commercial and test textiles as group-wise against laundering process, it is possible to disclose the relation in between these two groups of materials, which will lead to better understanding of their behaviors in terms of similarities and differences against the washing parameters of the laundering. Thus, the goal of the current research is to examine the behavior of two groups of textile materials as commercial textiles and as test textiles towards the main washing machine parameters during laundering process such as temperature, load quantity, mechanical action and level of water amount by concentrating on shrinkage, pilling, sewing defects, collar abrasion, the other defects other than sewing, whitening and overall properties of textiles. In this study, cotton fabrics were preferred as commercial textiles due to the fact that garments made of cotton are the most demanded products in the market by the textile consumers in daily life. Full factorial experimental set-up was used to design the experimental procedure. All profiles always including all of the commercial and the test textiles were laundered for 20 cycles by commercial home laundering machine to investigate the effects of the chosen parameters. For the laundering process, a modified version of ‘‘IEC 60456 Test Method’’ was utilized. The amount of detergent was altered as 0.5% gram per liter depending on varying load quantity levels. Datacolor 650®, EMPA Photographic Standards for Pilling Test and visual examination were utilized to test and characterize the textiles. Furthermore, in the current study the relation in between commercial and test textiles in terms of their performance was deeply investigated by the help of statistical analysis performed by MINITAB® package program modeling their behavior against the parameters of the laundering process. In the experimental work, the behaviors of both groups of textiles towards washing machine parameters were visually and quantitatively assessed in dry state.

Keywords: behavior against washing machine parameters, performance evaluation of textiles, statistical analysis, commercial and test textiles

Procedia PDF Downloads 358
2533 Service Information Integration Platform as Decision Making Tools for the Service Industry Supply Chain-Indonesia Service Integration Project

Authors: Haikal Achmad Thaha, Pujo Laksono, Dhamma Nibbana Putra

Abstract:

Customer service is one of the core interest in a service sector of a company, whether as the core business or as service part of the operation. Most of the time, the people and the previous research in service industry is focused on finding the best business model solution for the service sector, usually to decide between total in house customer service, outsourcing, or something in between. Conventionally, to take this decision is some important part of the management job, and this is a process that usually takes some time and staff effort, meanwhile market condition and overall company needs may change and cause loss of income and temporary disturbance in the companies operation . However, in this paper we have offer a new concept model to assist decision making process in service industry. This model will featured information platform as central tool to integrate service industry operation. The result is service information model which would ideally increase response time and effectivity of the decision making. it will also help service industry in switching the service solution system quickly through machine learning when the companies growth and the service solution needed are changing.

Keywords: service industry, customer service, machine learning, decision making, information platform

Procedia PDF Downloads 620
2532 Prediction of Survival Rate after Gastrointestinal Surgery Based on The New Japanese Association for Acute Medicine (JAAM Score) With Neural Network Classification Method

Authors: Ayu Nabila Kusuma Pradana, Aprinaldi Jasa Mantau, Tomohiko Akahoshi

Abstract:

The incidence of Disseminated intravascular coagulation (DIC) following gastrointestinal surgery has a poor prognosis. Therefore, it is important to determine the factors that can predict the prognosis of DIC. This study will investigate the factors that may influence the outcome of DIC in patients after gastrointestinal surgery. Eighty-one patients were admitted to the intensive care unit after gastrointestinal surgery in Kyushu University Hospital from 2003 to 2021. Acute DIC scores were estimated using the new Japanese Association for Acute Medicine (JAAM) score from before and after surgery from day 1, day 3, and day 7. Acute DIC scores will be compared with The Sequential Organ Failure Assessment (SOFA) score, platelet count, lactate level, and a variety of biochemical parameters. This study applied machine learning algorithms to predict the prognosis of DIC after gastrointestinal surgery. The results of this study are expected to be used as an indicator for evaluating patient prognosis so that it can increase life expectancy and reduce mortality from cases of DIC patients after gastrointestinal surgery.

Keywords: the survival rate, gastrointestinal surgery, JAAM score, neural network, machine learning, disseminated intravascular coagulation (DIC)

Procedia PDF Downloads 255
2531 Data Refinement Enhances The Accuracy of Short-Term Traffic Latency Prediction

Authors: Man Fung Ho, Lap So, Jiaqi Zhang, Yuheng Zhao, Huiyang Lu, Tat Shing Choi, K. Y. Michael Wong

Abstract:

Nowadays, a tremendous amount of data is available in the transportation system, enabling the development of various machine learning approaches to make short-term latency predictions. A natural question is then the choice of relevant information to enable accurate predictions. Using traffic data collected from the Taiwan Freeway System, we consider the prediction of short-term latency of a freeway segment with a length of 17 km covering 5 measurement points, each collecting vehicle-by-vehicle data through the electronic toll collection system. The processed data include the past latencies of the freeway segment with different time lags, the traffic conditions of the individual segments (the accumulations, the traffic fluxes, the entrance and exit rates), the total accumulations, and the weekday latency profiles obtained by Gaussian process regression of past data. We arrive at several important conclusions about how data should be refined to obtain accurate predictions, which have implications for future system-wide latency predictions. (1) We find that the prediction of median latency is much more accurate and meaningful than the prediction of average latency, as the latter is plagued by outliers. This is verified by machine-learning prediction using XGBoost that yields a 35% improvement in the mean square error of the 5-minute averaged latencies. (2) We find that the median latency of the segment 15 minutes ago is a very good baseline for performance comparison, and we have evidence that further improvement is achieved by machine learning approaches such as XGBoost and Long Short-Term Memory (LSTM). (3) By analyzing the feature importance score in XGBoost and calculating the mutual information between the inputs and the latencies to be predicted, we identify a sequence of inputs ranked in importance. It confirms that the past latencies are most informative of the predicted latencies, followed by the total accumulation, whereas inputs such as the entrance and exit rates are uninformative. It also confirms that the inputs are much less informative of the average latencies than the median latencies. (4) For predicting the latencies of segments composed of two or three sub-segments, summing up the predicted latencies of each sub-segment is more accurate than the one-step prediction of the whole segment, especially with the latency prediction of the downstream sub-segments trained to anticipate latencies several minutes ahead. The duration of the anticipation time is an increasing function of the traveling time of the upstream segment. The above findings have important implications to predicting the full set of latencies among the various locations in the freeway system.

Keywords: data refinement, machine learning, mutual information, short-term latency prediction

Procedia PDF Downloads 167
2530 GIS Data Governance: GIS Data Submission Process for Build-in Project, Replacement Project at Oman Electricity Transmission Company

Authors: Rahma Al Balushi

Abstract:

Oman Electricity Transmission Company's (OETC) vision is to be a renowned world-class transmission grid by 2025, and one of the indications of achieving the vision is obtaining Asset Management ISO55001 certification, which required setting out a documented Standard Operating Procedures (SOP). Hence, documented SOP for the Geographical information system data process has been established. Also, to effectively manage and improve OETC power transmission, asset data and information need to be governed as such by Asset Information & GIS dept. This paper will describe in detail the GIS data submission process and the journey to develop the current process. The methodology used to develop the process is based on three main pillars, which are system and end-user requirements, Risk evaluation, data availability, and accuracy. The output of this paper shows the dramatic change in the used process, which results subsequently in more efficient, accurate, updated data. Furthermore, due to this process, GIS has been and is ready to be integrated with other systems as well as the source of data for all OETC users. Some decisions related to issuing No objection certificates (NOC) and scheduling asset maintenance plans in Computerized Maintenance Management System (CMMS) have been made consequently upon GIS data availability. On the Other hand, defining agreed and documented procedures for data collection, data systems update, data release/reporting, and data alterations salso aided to reduce the missing attributes of GIS transmission data. A considerable difference in Geodatabase (GDB) completeness percentage was observed between the year 2017 and the year 2021. Overall, concluding that by governance, asset information & GIS department can control GIS data process; collect, properly record, and manage asset data and information within OETC network. This control extends to other applications and systems integrated with/related to GIS systems.

Keywords: asset management ISO55001, standard procedures process, governance, geodatabase, NOC, CMMS

Procedia PDF Downloads 206
2529 Single Imputation for Audiograms

Authors: Sarah Beaver, Renee Bryce

Abstract:

Audiograms detect hearing impairment, but missing values pose problems. This work explores imputations in an attempt to improve accuracy. This work implements Linear Regression, Lasso, Linear Support Vector Regression, Bayesian Ridge, K Nearest Neighbors (KNN), and Random Forest machine learning techniques to impute audiogram frequencies ranging from 125Hz to 8000Hz. The data contains patients who had or were candidates for cochlear implants. Accuracy is compared across two different Nested Cross-Validation k values. Over 4000 audiograms were used from 800 unique patients. Additionally, training on data combines and compares left and right ear audiograms versus single ear side audiograms. The accuracy achieved using Root Mean Square Error (RMSE) values for the best models for Random Forest ranges from 4.74 to 6.37. The R\textsuperscript{2} values for the best models for Random Forest ranges from .91 to .96. The accuracy achieved using RMSE values for the best models for KNN ranges from 5.00 to 7.72. The R\textsuperscript{2} values for the best models for KNN ranges from .89 to .95. The best imputation models received R\textsuperscript{2} between .89 to .96 and RMSE values less than 8dB. We also show that the accuracy of classification predictive models performed better with our best imputation models versus constant imputations by a two percent increase.

Keywords: machine learning, audiograms, data imputations, single imputations

Procedia PDF Downloads 80
2528 Aesthetic and Social Vision in Abubakar Gimba’s a Toast in the Cemetery

Authors: James Funsho Tope

Abstract:

Being the prolific writer that he is, Gimba’s collection of Short Stories, A Toast in the Cemetery, brings out the themes of decay and corruption in the urban setting through the use of images, symbols, setting and character. Gimba seeks through these media to reveal the decay and corruption in the society. Gimba uses aesthetics to convey his message, thus making a call for change in the fabrics of society.

Keywords: corruption, decay, character, setting, symbolism, images, society

Procedia PDF Downloads 603
2527 Vieira Da Silva's Tiles at Universidade Federal Rural Do Rio de Janeiro: A Conservation and Restoration Project

Authors: Adriana Anselmo Oliveira

Abstract:

The present project showcases a tile work from the Franco-Portuguese artist Maria Helena Vieira da Silva (1908-1992). It is a set of 8 panels composed of figurative and geometric tiles, with extra tiles framing nearby doors and windows in a study room in the (UFRRJ, Universidade Federal Rural do Rio de Janeiro). The aforementioned work was created between 1942 and 1943, during the artist's 6 year exile in the Brazilian city. This one-of-a-kind tileset was designed and made by Vieira da Silva between 1942 and 1943. Over the years, several units were lost, which led to their replacement in the nineties. However, these replacements don't do justice to the original work of art. In 2007, a project was initiated to fully repair and maintain the set. Three panels are removed and restored, but the project is halted. To this day, the three fully restored panels remain in boxes. In 2016 a new restoration project is submitted by the (Faculdade de Belas Artes da Universidade de Lisboa) in collaboration with de (Fundacão Árpád Szenes-Vieira da Silva). There are many varied opinions on restoring and conserving older pieces of art, however, we have the moral duty to safeguard the original materials used by the artist along with the artists original vision and also to care for the future generations of students who will use the space in which the tile-work was inserted. Many tiles have been replaced by white tiles, tiles with a divergent colour pallet and technique, and in a few cases, the incorrect place or way around. These many factors make it increasingly difficult to maintain the artists original vision and destroy and chance of coherence within the artwork itself. The conservative technician cannot make new images to fill the empty spaces or mark the remaining images with their own creative input. with reliable photographic documentation that can provide us with the necessary vision to allow us to proceed with an accurate reconstruction, we have the obligation to proceed and return the piece of art to its true form, as in its current state, it is impossible to maintain its original glory. Using the information we have, we must find a way to differentiate the original tiles from the reconstructions in order to recreate and reclaim the original message from the artist. The objective of this project is to understand the significance of tiles in Vieira da Silva's art as well as the influence they had on the artist's pictorial language since the colour definition on tile work is vastly different from the painting process as the materials change during their merger. Another primary goal is to understand what the previous interventions achieved besides increasing the artworks durability. The main objective is to submit a proposal that can salvage the artist's visual intention and supports it for posteriority. In summary, this proposal goes further than the usual conservative interventions as it intends to recreate the original artistic worth, prioritising the aesthetics and keeping its soul alive.

Keywords: Vieira da Silva, tiles, conservation, restoration

Procedia PDF Downloads 152
2526 Transforming Data Science Curriculum Through Design Thinking

Authors: Samar Swaid

Abstract:

Today, corporates are moving toward the adoption of Design-Thinking techniques to develop products and services, putting their consumer as the heart of the development process. One of the leading companies in Design-Thinking, IDEO (Innovation, Design, Engineering Organization), defines Design-Thinking as an approach to problem-solving that relies on a set of multi-layered skills, processes, and mindsets that help people generate novel solutions to problems. Design thinking may result in new ideas, narratives, objects or systems. It is about redesigning systems, organizations, infrastructures, processes, and solutions in an innovative fashion based on the users' feedback. Tim Brown, president and CEO of IDEO, sees design thinking as a human-centered approach that draws from the designer's toolkit to integrate people's needs, innovative technologies, and business requirements. The application of design thinking has been witnessed to be the road to developing innovative applications, interactive systems, scientific software, healthcare application, and even to utilizing Design-Thinking to re-think business operations, as in the case of Airbnb. Recently, there has been a movement to apply design thinking to machine learning and artificial intelligence to ensure creating the "wow" effect on consumers. The Association of Computing Machinery task force on Data Science program states that" Data scientists should be able to implement and understand algorithms for data collection and analysis. They should understand the time and space considerations of algorithms. They should follow good design principles developing software, understanding the importance of those principles for testability and maintainability" However, this definition hides the user behind the machine who works on data preparation, algorithm selection and model interpretation. Thus, the Data Science program includes design thinking to ensure meeting the user demands, generating more usable machine learning tools, and developing ways of framing computational thinking. Here, describe the fundamentals of Design-Thinking and teaching modules for data science programs.

Keywords: data science, design thinking, AI, currculum, transformation

Procedia PDF Downloads 79
2525 Methods for Enhancing Ensemble Learning or Improving Classifiers of This Technique in the Analysis and Classification of Brain Signals

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 74
2524 A Predictive Model for Turbulence Evolution and Mixing Using Machine Learning

Authors: Yuhang Wang, Jorg Schluter, Sergiy Shelyag

Abstract:

The high cost associated with high-resolution computational fluid dynamics (CFD) is one of the main challenges that inhibit the design, development, and optimisation of new combustion systems adapted for renewable fuels. In this study, we propose a physics-guided CNN-based model to predict turbulence evolution and mixing without requiring a traditional CFD solver. The model architecture is built upon U-Net and the inception module, while a physics-guided loss function is designed by introducing two additional physical constraints to allow for the conservation of both mass and pressure over the entire predicted flow fields. Then, the model is trained on the Large Eddy Simulation (LES) results of a natural turbulent mixing layer with two different Reynolds number cases (Re = 3000 and 30000). As a result, the model prediction shows an excellent agreement with the corresponding CFD solutions in terms of both spatial distributions and temporal evolution of turbulent mixing. Such promising model prediction performance opens up the possibilities of doing accurate high-resolution manifold-based combustion simulations at a low computational cost for accelerating the iterative design process of new combustion systems.

Keywords: computational fluid dynamics, turbulence, machine learning, combustion modelling

Procedia PDF Downloads 89
2523 Selecting Answers for Questions with Multiple Answer Choices in Arabic Question Answering Based on Textual Entailment Recognition

Authors: Anes Enakoa, Yawei Liang

Abstract:

Question Answering (QA) system is one of the most important and demanding tasks in the field of Natural Language Processing (NLP). In QA systems, the answer generation task generates a list of candidate answers to the user's question, in which only one answer is correct. Answer selection is one of the main components of the QA, which is concerned with selecting the best answer choice from the candidate answers suggested by the system. However, the selection process can be very challenging especially in Arabic due to its particularities. To address this challenge, an approach is proposed to answer questions with multiple answer choices for Arabic QA systems based on Textual Entailment (TE) recognition. The developed approach employs a Support Vector Machine that considers lexical, semantic and syntactic features in order to recognize the entailment between the generated hypotheses (H) and the text (T). A set of experiments has been conducted for performance evaluation and the overall performance of the proposed method reached an accuracy of 67.5% with C@1 score of 80.46%. The obtained results are promising and demonstrate that the proposed method is effective for TE recognition task.

Keywords: information retrieval, machine learning, natural language processing, question answering, textual entailment

Procedia PDF Downloads 144
2522 mKDNAD: A Network Flow Anomaly Detection Method Based On Multi-teacher Knowledge Distillation

Authors: Yang Yang, Dan Liu

Abstract:

Anomaly detection models for network flow based on machine learning have poor detection performance under extremely unbalanced training data conditions and also have slow detection speed and large resource consumption when deploying on network edge devices. Embedding multi-teacher knowledge distillation (mKD) in anomaly detection can transfer knowledge from multiple teacher models to a single model. Inspired by this, we proposed a state-of-the-art model, mKDNAD, to improve detection performance. mKDNAD mine and integrate the knowledge of one-dimensional sequence and two-dimensional image implicit in network flow to improve the detection accuracy of small sample classes. The multi-teacher knowledge distillation method guides the train of the student model, thus speeding up the model's detection speed and reducing the number of model parameters. Experiments in the CICIDS2017 dataset verify the improvements of our method in the detection speed and the detection accuracy in dealing with the small sample classes.

Keywords: network flow anomaly detection (NAD), multi-teacher knowledge distillation, machine learning, deep learning

Procedia PDF Downloads 119
2521 Comparison of Machine Learning-Based Models for Predicting Streptococcus pyogenes Virulence Factors and Antimicrobial Resistance

Authors: Fernanda Bravo Cornejo, Camilo Cerda Sarabia, Belén Díaz Díaz, Diego Santibañez Oyarce, Esteban Gómez Terán, Hugo Osses Prado, Raúl Caulier-Cisterna, Jorge Vergara-Quezada, Ana Moya-Beltrán

Abstract:

Streptococcus pyogenes is a gram-positive bacteria involved in a wide range of diseases and is a major-human-specific bacterial pathogen. In Chile, this year the 'Ministerio de Salud' declared an alert due to the increase in strains throughout the year. This increase can be attributed to the multitude of factors including antimicrobial resistance (AMR) and Virulence Factors (VF). Understanding these VF and AMR is crucial for developing effective strategies and improving public health responses. Moreover, experimental identification and characterization of these pathogenic mechanisms are labor-intensive and time-consuming. Therefore, new computational methods are required to provide robust techniques for accelerating this identification. Advances in Machine Learning (ML) algorithms represent the opportunity to refine and accelerate the discovery of VF associated with Streptococcus pyogenes. In this work, we evaluate the accuracy of various machine learning models in predicting the virulence factors and antimicrobial resistance of Streptococcus pyogenes, with the objective of providing new methods for identifying the pathogenic mechanisms of this organism.Our comprehensive approach involved the download of 32,798 genbank files of S. pyogenes from NCBI dataset, coupled with the incorporation of data from Virulence Factor Database (VFDB) and Antibiotic Resistance Database (CARD) which contains sequences of AMR gene sequence and resistance profiles. These datasets provided labeled examples of both virulent and non-virulent genes, enabling a robust foundation for feature extraction and model training. We employed preprocessing, characterization and feature extraction techniques on primary nucleotide/amino acid sequences and selected the optimal more for model training. The feature set was constructed using sequence-based descriptors (e.g., k-mers and One-hot encoding), and functional annotations based on database prediction. The ML models compared are logistic regression, decision trees, support vector machines, neural networks among others. The results of this work show some differences in accuracy between the algorithms, these differences allow us to identify different aspects that represent unique opportunities for a more precise and efficient characterization and identification of VF and AMR. This comparative analysis underscores the value of integrating machine learning techniques in predicting S. pyogenes virulence and AMR, offering potential pathways for more effective diagnostic and therapeutic strategies. Future work will focus on incorporating additional omics data, such as transcriptomics, and exploring advanced deep learning models to further enhance predictive capabilities.

Keywords: antibiotic resistance, streptococcus pyogenes, virulence factors., machine learning

Procedia PDF Downloads 29
2520 Image Based Landing Solutions for Large Passenger Aircraft

Authors: Thierry Sammour Sawaya, Heikki Deschacht

Abstract:

In commercial aircraft operations, almost half of the accidents happen during approach or landing phases. Automatic guidance and automatic landings have proven to bring significant safety value added for this challenging landing phase. This is why Airbus and ScioTeq have decided to work together to explore the capability of image-based landing solutions as additional landing aids to further expand the possibility to perform automatic approach and landing to runways where the current guiding systems are either not fitted or not optimum. Current systems for automated landing often depend on radio signals provided by airport ground infrastructure on the airport or satellite coverage. In addition, these radio signals may not always be available with the integrity and performance required for safe automatic landing. Being independent from these radio signals would widen the operations possibilities and increase the number of automated landings. Airbus and ScioTeq are joining their expertise in the field of Computer Vision in the European Program called Clean Sky 2 Large Passenger Aircraft, in which they are leading the IMBALS (IMage BAsed Landing Solutions) project. The ultimate goal of this project is to demonstrate, develop, validate and verify a certifiable automatic landing system guiding an airplane during the approach and landing phases based on an onboard camera system capturing images, enabling automatic landing independent from radio signals and without precision instrument for landing. In the frame of this project, ScioTeq is responsible for the development of the Image Processing Platform (IPP), while Airbus is responsible for defining the functional and system requirements as well as the testing and integration of the developed equipment in a Large Passenger Aircraft representative environment. The aim of this paper will be to describe the system as well as the associated methods and tools developed for validation and verification.

Keywords: aircraft landing system, aircraft safety, autoland, avionic system, computer vision, image processing

Procedia PDF Downloads 99
2519 The Current Home Hemodialysis Practices and Patients’ Safety Related Factors: A Case Study from Germany

Authors: Ilyas Khan. Liliane Pintelon, Harry Martin, Michael Shömig

Abstract:

The increasing costs of healthcare on one hand, and the rise in aging population and associated chronic disease, on the other hand, are putting increasing burden on the current health care system in many Western countries. For instance, chronic kidney disease (CKD) is a common disease and in Europe, the cost of renal replacement therapy (RRT) is very significant to the total health care cost. However, the recent advancement in healthcare technology, provide the opportunity to treat patients at home in their own comfort. It is evident that home healthcare offers numerous advantages apparently, low costs and high patients’ quality of life. Despite these advantages, the intake of home hemodialysis (HHD) therapy is still low in particular in Germany. Many factors are accounted for the low number of HHD intake. However, this paper is focusing on patients’ safety-related factors of current HHD practices in Germany. The aim of this paper is to analyze the current HHD practices in Germany and to identify risks related factors if any exist. A case study has been conducted in a dialysis center which consists of four dialysis centers in the south of Germany. In total, these dialysis centers have 350 chronic dialysis patients, of which, four patients are on HHD. The centers have 126 staff which includes six nephrologists and 120 other staff i.e. nurses and administration. The results of the study revealed several risk-related factors. Most importantly, these centers do not offer allied health services at the pre-dialysis stage, the HHD training did not have an established curriculum; however, they have just recently developed the first version. Only a soft copy of the machine manual is offered to patients. Surprisingly, the management was not aware of any standard available for home assessment and installation. The home assessment is done by a third party (i.e. the machines and equipment provider) and they may not consider the hygienic quality of the patient’s home. The type of machine provided to patients at home is similar to the one in the center. The model may not be suitable at home because of its size and complexity. Even though portable hemodialysis machines, which are specially designed for home use, are available in the market such as the NxStage series. Besides the type of machine, no assistance is offered for space management at home in particular for placing the machine. Moreover, the centers do not offer remote assistance to patients and their carer at home. However, telephonic assistance is available. Furthermore, no alternative is offered if a carer is not available. In addition, the centers are lacking medical staff including nephrologists and renal nurses.

Keywords: home hemodialysis, home hemodialysis practices, patients’ related risks in the current home hemodialysis practices, patient safety in home hemodialysis

Procedia PDF Downloads 117
2518 Seashore Debris Detection System Using Deep Learning and Histogram of Gradients-Extractor Based Instance Segmentation Model

Authors: Anshika Kankane, Dongshik Kang

Abstract:

Marine debris has a significant influence on coastal environments, damaging biodiversity, and causing loss and damage to marine and ocean sector. A functional cost-effective and automatic approach has been used to look up at this problem. Computer vision combined with a deep learning-based model is being proposed to identify and categorize marine debris of seven kinds on different beach locations of Japan. This research compares state-of-the-art deep learning models with a suggested model architecture that is utilized as a feature extractor for debris categorization. The model is being proposed to detect seven categories of litter using a manually constructed debris dataset, with the help of Mask R-CNN for instance segmentation and a shape matching network called HOGShape, which can then be cleaned on time by clean-up organizations using warning notifications of the system. The manually constructed dataset for this system is created by annotating the images taken by fixed KaKaXi camera using CVAT annotation tool with seven kinds of category labels. A pre-trained HOG feature extractor on LIBSVM is being used along with multiple templates matching on HOG maps of images and HOG maps of templates to improve the predicted masked images obtained via Mask R-CNN training. This system intends to timely alert the cleanup organizations with the warning notifications using live recorded beach debris data. The suggested network results in the improvement of misclassified debris masks of debris objects with different illuminations, shapes, viewpoints and litter with occlusions which have vague visibility.

Keywords: computer vision, debris, deep learning, fixed live camera images, histogram of gradients feature extractor, instance segmentation, manually annotated dataset, multiple template matching

Procedia PDF Downloads 104
2517 Sepiolite as a Processing Aid in Fibre Reinforced Cement Produced in Hatschek Machine

Authors: R. Pérez Castells, J. M. Carbajo

Abstract:

Sepiolite is used as a processing aid in the manufacture of fibre cement from the start of the replacement of asbestos in the 80s. Sepiolite increases the inter-laminar bond between cement layers and improves homogeneity of the slurries. A new type of sepiolite processed product, Wollatrop TF/C, has been checked as a retention agent for fine particles in the production of fibre cement in a Hatschek machine. The effect of Wollatrop T/FC on filtering and fine particle losses was studied as well as the interaction with anionic polyacrylamide and microsilica. The design of the experiments were factorial and the VDT equipment used for measuring retention and drainage was modified Rapid Köethen laboratory sheet former. Wollatrop TF/C increased the fine particle retention improving the economy of the process and reducing the accumulation of solids in recycled process water. At the same time, drainage time increased sharply at high concentration, however drainage time can be improved by adjusting APAM concentration. Wollatrop TF/C and microsilica are having very small interactions among them. Microsilica does not control fine particle losses while Wollatrop TF/C does efficiently. Further research on APAM type (molecular weight and anionic character) is advisable to improve drainage.

Keywords: drainage, fibre-reinforced cement, fine particle losses, flocculation, microsilica, sepiolite

Procedia PDF Downloads 322
2516 Modification of a Human Powered Lawn Mower

Authors: Akinwale S. O., Koya O. A.

Abstract:

The need to provide ecologically-friendly and effective lawn mowing solution is crucial for the well-being of humans. This study involved the modification of a human-powered lawn mower designed to cut tall grasses in residential areas. This study designed and fabricated a reel-type mower blade system and a pedal-powered test rig for the blade system. It also evaluated the performance of the machine. The machine was tested on some overgrown grass plots at College of Education Staff School Ilesa. Parameters such as theoretical field capacity, field efficiency and effective field capacity were determined from the data gathered. The quality of cut achieved by the unit was also documented. Test results showed that the fabricated cutting system produced a theoretical field capacity of 0.11 ha/h and an effective field capacity of 0.08ha/h. Moreover, the unit’s cutting system showed a substantial improvement over existing reel mower designs in its ability to cut on both the forward and reverse phases of its motion. This study established that the blade system described herein has the capacity to cut tall grasses. Hence, this device can therefore eliminate the need for powered mowers entirely on small residential lawns.

Keywords: effective field capacity, field efficiency, theoretical field capacity, quality of cut

Procedia PDF Downloads 146
2515 Vaccination Coverage and Its Associated Factors in India: An ML Approach to Understand the Hierarchy and Inter-Connections

Authors: Anandita Mitro, Archana Srivastava, Bidisha Banerjee

Abstract:

The present paper attempts to analyze the hierarchy and interconnection of factors responsible for the uptake of BCG vaccination in India. The study uses National Family Health Survey (NFHS-5) data which was conducted during 2019-21. The univariate logistic regression method is used to understand the univariate effects while the interconnection effects have been studied using the Categorical Inference Tree (CIT) which is a non-parametric Machine Learning (ML) model. The hierarchy of the factors is further established using Conditional Inference Forest which is an extension of the CIT approach. The results suggest that BCG vaccination coverage was influenced more by system-level factors and awareness than education or socio-economic status. Factors such as place of delivery, antenatal care, and postnatal care were crucial, with variations based on delivery location. Region-specific differences were also observed which could be explained by the factors. Awareness of the disease was less impactful along with the factor of wealth and urban or rural residence, although awareness did appear to substitute for inadequate ANC. Thus, from the policy point of view, it is revealed that certain subpopulations have less prevalence of vaccination which implies that there is a need for population-specific policy action to achieve a hundred percent coverage.

Keywords: vaccination, NFHS, machine learning, public health

Procedia PDF Downloads 58
2514 Predictive Analytics in Traffic Flow Management: Integrating Temporal Dynamics and Traffic Characteristics to Estimate Travel Time

Authors: Maria Ezziani, Rabie Zine, Amine Amar, Ilhame Kissani

Abstract:

This paper introduces a predictive model for urban transportation engineering, which is vital for efficient traffic management. Utilizing comprehensive datasets and advanced statistical techniques, the model accurately forecasts travel times by considering temporal variations and traffic dynamics. Machine learning algorithms, including regression trees and neural networks, are employed to capture sequential dependencies. Results indicate significant improvements in predictive accuracy, particularly during peak hours and holidays, with the incorporation of traffic flow and speed variables. Future enhancements may integrate weather conditions and traffic incidents. The model's applications range from adaptive traffic management systems to route optimization algorithms, facilitating congestion reduction and enhancing journey reliability. Overall, this research extends beyond travel time estimation, offering insights into broader transportation planning and policy-making realms, empowering stakeholders to optimize infrastructure utilization and improve network efficiency.

Keywords: predictive analytics, traffic flow, travel time estimation, urban transportation, machine learning, traffic management

Procedia PDF Downloads 82
2513 Wear and Mechanical Properties of Nodular Iron Modified with Copper

Authors: J. Ramos, V. Gil, A. F. Torres

Abstract:

The nodular iron is a material that has shown great advantages respect to other materials (steel and gray iron) in the production of machine elements. The engineering industry, especially automobile, are potential users of this material. As it is known, the alloying elements modify the properties of steels and castings. Copper has been investigated as a structural modifier of nodular iron, but studies of its mechanical and tribological implications still need to be addressed for industrial use. With the aim of improving the mechanical properties of nodular iron, alloying elements (Mn, Si, and Cu) are added in order to increase their pearlite (or ferrite) structure according to the percentage of the alloying element. In this research (using induction furnace process) nodular iron with three different percentages of copper (residual, 0,5% and 1,2%) was obtained. Chemical analysis was performed by optical emission spectrometry and microstructures were characterized by Optical Microscopy (ASTM E3) and Scanning Electron Microscopy (SEM). The study of mechanical behavior was carried out in a mechanical test machine (ASTM E8) and a Pin on disk tribometer (ASTM G99) was used to assess wear resistance. It is observed that copper increases the pearlite structure improving the wear behavior; tension behavior. This improvement is observed in higher proportion with 0,5% due to the fact that too much increase of pearlite leads to ductility loss.

Keywords: copper, mechanical properties, nodular iron, pearlite structure, wear

Procedia PDF Downloads 382
2512 Automatic Adjustment of Thresholds via Closed-Loop Feedback Mechanism for Solder Paste Inspection

Authors: Chia-Chen Wei, Pack Hsieh, Jeffrey Chen

Abstract:

Surface Mount Technology (SMT) is widely used in the area of the electronic assembly in which the electronic components are mounted to the surface of the printed circuit board (PCB). Most of the defects in the SMT process are mainly related to the quality of solder paste printing. These defects lead to considerable manufacturing costs in the electronics assembly industry. Therefore, the solder paste inspection (SPI) machine for controlling and monitoring the amount of solder paste printing has become an important part of the production process. So far, the setting of the SPI threshold is based on statistical analysis and experts’ experiences to determine the appropriate threshold settings. Because the production data are not normal distribution and there are various variations in the production processes, defects related to solder paste printing still occur. In order to solve this problem, this paper proposes an online machine learning algorithm, called the automatic threshold adjustment (ATA) algorithm, and closed-loop architecture in the SMT process to determine the best threshold settings. Simulation experiments prove that our proposed threshold settings improve the accuracy from 99.85% to 100%.

Keywords: big data analytics, Industry 4.0, SPI threshold setting, surface mount technology

Procedia PDF Downloads 115
2511 Treating Voxels as Words: Word-to-Vector Methods for fMRI Meta-Analyses

Authors: Matthew Baucum

Abstract:

With the increasing popularity of fMRI as an experimental method, psychology and neuroscience can greatly benefit from advanced techniques for summarizing and synthesizing large amounts of data from brain imaging studies. One promising avenue is automated meta-analyses, in which natural language processing methods are used to identify the brain regions consistently associated with certain semantic concepts (e.g. “social”, “reward’) across large corpora of studies. This study builds on this approach by demonstrating how, in fMRI meta-analyses, individual voxels can be treated as vectors in a semantic space and evaluated for their “proximity” to terms of interest. In this technique, a low-dimensional semantic space is built from brain imaging study texts, allowing words in each text to be represented as vectors (where words that frequently appear together are near each other in the semantic space). Consequently, each voxel in a brain mask can be represented as a normalized vector sum of all of the words in the studies that showed activation in that voxel. The entire brain mask can then be visualized in terms of each voxel’s proximity to a given term of interest (e.g., “vision”, “decision making”) or collection of terms (e.g., “theory of mind”, “social”, “agent”), as measured by the cosine similarity between the voxel’s vector and the term vector (or the average of multiple term vectors). Analysis can also proceed in the opposite direction, allowing word cloud visualizations of the nearest semantic neighbors for a given brain region. This approach allows for continuous, fine-grained metrics of voxel-term associations, and relies on state-of-the-art “open vocabulary” methods that go beyond mere word-counts. An analysis of over 11,000 neuroimaging studies from an existing meta-analytic fMRI database demonstrates that this technique can be used to recover known neural bases for multiple psychological functions, suggesting this method’s utility for efficient, high-level meta-analyses of localized brain function. While automated text analytic methods are no replacement for deliberate, manual meta-analyses, they seem to show promise for the efficient aggregation of large bodies of scientific knowledge, at least on a relatively general level.

Keywords: FMRI, machine learning, meta-analysis, text analysis

Procedia PDF Downloads 448
2510 A Machining Method of Cross-Shape Nano Channel and Experiments for Silicon Substrate

Authors: Zone-Ching Lin, Hao-Yuan Jheng, Zih-Wun Jhang

Abstract:

The paper innovatively proposes using the concept of specific down force energy (SDFE) and AFM machine to establish a machining method of cross-shape nanochannel on single-crystal silicon substrate. As for machining a cross-shape nanochannel by AFM machine, the paper develop a method of machining cross-shape nanochannel groove at a fixed down force by using SDFE theory and combining the planned cutting path of cross-shape nanochannel up to 5th machining layer it finally achieves a cross-shape nanochannel at a cutting depth of around 20nm. Since there may be standing burr at the machined cross-shape nanochannel edge, the paper uses a smaller down force to cut the edge of the cross-shape nanochannel in order to lower the height of standing burr and converge the height of standing burr at the edge to below 0.54nm as set by the paper. Finally, the paper conducts experiments of machining cross-shape nanochannel groove on single-crystal silicon by AFM probe, and compares the simulation and experimental results. It is proved that this proposed machining method of cross-shape nanochannel is feasible.

Keywords: atomic force microscopy (AFM), cross-shape nanochannel, silicon substrate, specific down force energy (SDFE)

Procedia PDF Downloads 370
2509 Validating Texture Analysis as a Tool for Determining Bioplastic (Bio)Degradation

Authors: Sally J. Price, Greg F. Walker, Weiyi Liu, Craig R. Bunt

Abstract:

Plastics, due to their long lifespan, are becoming more of an environmental concern once their useful life has been completed. There are a vast array of different types of plastic, and they can be found in almost every ecosystem on earth and are of particular concern in terrestrial environments where they can become incorporated into the food chain. Hence bioplastics have become more of interest to manufacturers and the public recently as they have the ability to (bio)degrade in commercial and in home composting situations. However, tools in which to quantify how they degrade in response to environmental variables are still being developed -one such approach is texture analysis using a TA.XT Texture Analyser, Stable Microsystems, was used to determine the force required to break or punch holes in standard ASTM D638 Type IV 3D printed bioplastic “dogbones” depending on the thicknesses of them. Manufacturers’ recommendations for calibrating the Texture Analyser are one such approach for standardising results; however, an independent technique using dummy dogbones and a substitute for the bioplastic was used alongside the samples. This approach was unexpectedly more valuable than realised at the start of the trial as irregular results were later discovered with the substitute material before valuable samples collected from the field were lost due to possible machine malfunction. This work will show the value of having an independent approach to machine calibration for accurate sample analysis with a Texture Analyser when analysing bioplastic samples.

Keywords: bioplastic, degradation, environment, texture analyzer

Procedia PDF Downloads 203
2508 A Comprehensive Survey on Machine Learning Techniques and User Authentication Approaches for Credit Card Fraud Detection

Authors: Niloofar Yousefi, Marie Alaghband, Ivan Garibay

Abstract:

With the increase of credit card usage, the volume of credit card misuse also has significantly increased, which may cause appreciable financial losses for both credit card holders and financial organizations issuing credit cards. As a result, financial organizations are working hard on developing and deploying credit card fraud detection methods, in order to adapt to ever-evolving, increasingly sophisticated defrauding strategies and identifying illicit transactions as quickly as possible to protect themselves and their customers. Compounding on the complex nature of such adverse strategies, credit card fraudulent activities are rare events compared to the number of legitimate transactions. Hence, the challenge to develop fraud detection that are accurate and efficient is substantially intensified and, as a consequence, credit card fraud detection has lately become a very active area of research. In this work, we provide a survey of current techniques most relevant to the problem of credit card fraud detection. We carry out our survey in two main parts. In the first part, we focus on studies utilizing classical machine learning models, which mostly employ traditional transnational features to make fraud predictions. These models typically rely on some static physical characteristics, such as what the user knows (knowledge-based method), or what he/she has access to (object-based method). In the second part of our survey, we review more advanced techniques of user authentication, which use behavioral biometrics to identify an individual based on his/her unique behavior while he/she is interacting with his/her electronic devices. These approaches rely on how people behave (instead of what they do), which cannot be easily forged. By providing an overview of current approaches and the results reported in the literature, this survey aims to drive the future research agenda for the community in order to develop more accurate, reliable and scalable models of credit card fraud detection.

Keywords: Credit Card Fraud Detection, User Authentication, Behavioral Biometrics, Machine Learning, Literature Survey

Procedia PDF Downloads 119
2507 Career Guidance System Using Machine Learning

Authors: Mane Darbinyan, Lusine Hayrapetyan, Elen Matevosyan

Abstract:

Artificial Intelligence in Education (AIED) has been created to help students get ready for the workforce, and over the past 25 years, it has grown significantly, offering a variety of technologies to support academic, institutional, and administrative services. However, this is still challenging, especially considering the labor market's rapid change. While choosing a career, people face various obstacles because they do not take into consideration their own preferences, which might lead to many other problems like shifting jobs, work stress, occupational infirmity, reduced productivity, and manual error. Besides preferences, people should properly evaluate their technical and non-technical skills, as well as their personalities. Professional counseling has become a difficult undertaking for counselors due to the wide range of career choices brought on by changing technological trends. It is necessary to close this gap by utilizing technology that makes sophisticated predictions about a person's career goals based on their personality. Hence, there is a need to create an automated model that would help in decision-making based on user inputs. Improving career guidance can be achieved by embedding machine learning into the career consulting ecosystem. There are various systems of career guidance that work based on the same logic, such as the classification of applicants, matching applications with appropriate departments or jobs, making predictions, and providing suitable recommendations. Methodologies like KNN, Neural Networks, K-means clustering, D-Tree, and many other advanced algorithms are applied in the fields of data and compute some data, which is helpful to predict the right careers. Besides helping users with their career choice, these systems provide numerous opportunities which are very useful while making this hard decision. They help the candidate to recognize where he/she specifically lacks sufficient skills so that the candidate can improve those skills. They are also capable to offer an e-learning platform, taking into account the user's lack of knowledge. Furthermore, users can be provided with details on a particular job, such as the abilities required to excel in that industry.

Keywords: career guidance system, machine learning, career prediction, predictive decision, data mining, technical and non-technical skills

Procedia PDF Downloads 80
2506 GIS Data Governance: GIS Data Submission Process for Build-in Project, Replacement Project at Oman electricity Transmission Company

Authors: Rahma Saleh Hussein Al Balushi

Abstract:

Oman Electricity Transmission Company's (OETC) vision is to be a renowned world-class transmission grid by 2025, and one of the indications of achieving the vision is obtaining Asset Management ISO55001 certification, which required setting out a documented Standard Operating Procedures (SOP). Hence, documented SOP for the Geographical information system data process has been established. Also, to effectively manage and improve OETC power transmission, asset data and information need to be governed as such by Asset Information & GIS department. This paper will describe in detail the current GIS data submission process and the journey for developing it. The methodology used to develop the process is based on three main pillars, which are system and end-user requirements, Risk evaluation, data availability, and accuracy. The output of this paper shows the dramatic change in the used process, which results subsequently in more efficient, accurate, and updated data. Furthermore, due to this process, GIS has been and is ready to be integrated with other systems as well as the source of data for all OETC users. Some decisions related to issuing No objection certificates (NOC) for excavation permits and scheduling asset maintenance plans in Computerized Maintenance Management System (CMMS) have been made consequently upon GIS data availability. On the Other hand, defining agreed and documented procedures for data collection, data systems update, data release/reporting and data alterations has also contributed to reducing the missing attributes and enhance data quality index of GIS transmission data. A considerable difference in Geodatabase (GDB) completeness percentage was observed between the years 2017 and year 2022. Overall, concluding that by governance, asset information & GIS department can control the GIS data process; collect, properly record, and manage asset data and information within the OETC network. This control extends to other applications and systems integrated with/related to GIS systems.

Keywords: asset management ISO55001, standard procedures process, governance, CMMS

Procedia PDF Downloads 123
2505 Career Guidance System Using Machine Learning

Authors: Mane Darbinyan, Lusine Hayrapetyan, Elen Matevosyan

Abstract:

Artificial Intelligence in Education (AIED) has been created to help students get ready for the workforce, and over the past 25 years, it has grown significantly, offering a variety of technologies to support academic, institutional, and administrative services. However, this is still challenging, especially considering the labor market's rapid change. While choosing a career, people face various obstacles because they do not take into consideration their own preferences, which might lead to many other problems like shifting jobs, work stress, occupational infirmity, reduced productivity, and manual error. Besides preferences, people should evaluate properly their technical and non-technical skills, as well as their personalities. Professional counseling has become a difficult undertaking for counselors due to the wide range of career choices brought on by changing technological trends. It is necessary to close this gap by utilizing technology that makes sophisticated predictions about a person's career goals based on their personality. Hence, there is a need to create an automated model that would help in decision-making based on user inputs. Improving career guidance can be achieved by embedding machine learning into the career consulting ecosystem. There are various systems of career guidance that work based on the same logic, such as the classification of applicants, matching applications with appropriate departments or jobs, making predictions, and providing suitable recommendations. Methodologies like KNN, neural networks, K-means clustering, D-Tree, and many other advanced algorithms are applied in the fields of data and compute some data, which is helpful to predict the right careers. Besides helping users with their career choice, these systems provide numerous opportunities which are very useful while making this hard decision. They help the candidate to recognize where he/she specifically lacks sufficient skills so that the candidate can improve those skills. They are also capable of offering an e-learning platform, taking into account the user's lack of knowledge. Furthermore, users can be provided with details on a particular job, such as the abilities required to excel in that industry.

Keywords: career guidance system, machine learning, career prediction, predictive decision, data mining, technical and non-technical skills

Procedia PDF Downloads 69