Search results for: cable splicing machine

Authors: Komal Ghafoor, Tauqir Ahmad, Murtaza Hanif, Hira Zaheer

Abstract:

Assistive technology has been developed to support visually impaired people in their social interactions. Conversation assistive technology is designed to enhance communication skills, facilitate social interaction, and improve the quality of life of visually impaired individuals. This technology includes speech recognition, text-to-speech features, and other communication devices that enable users to communicate with others in real time. The technology uses natural language processing and machine learning algorithms to analyze spoken language and provide appropriate responses. It also includes features such as voice commands and audio feedback to provide users with a more immersive experience. These technologies have been shown to increase the confidence and independence of visually impaired individuals in social situations and have the potential to improve their social skills and relationships with others. Overall, conversation-assistive technology is a promising tool for empowering visually impaired people and improving their social interactions. One of the key benefits of conversation-assistive technology is that it allows visually impaired individuals to overcome communication barriers that they may face in social situations. It can help them to communicate more effectively with friends, family, and colleagues, as well as strangers in public spaces. By providing a more seamless and natural way to communicate, this technology can help to reduce feelings of isolation and improve overall quality of life. The main objective of this research is to give blind users the capability to move around in unfamiliar environments through a user-friendly device by face, object, and activity recognition system. This model evaluates the accuracy of activity recognition. This device captures the front view of the blind, detects the objects, recognizes the activities, and answers the blind query. It is implemented using the front view of the camera. The local dataset is collected that includes different 1st-person human activities. The results obtained are the identification of the activities that the VGG-16 model was trained on, where Hugging, Shaking Hands, Talking, Walking, Waving video, etc.

Keywords: dataset, visually impaired person, natural language process, human activity recognition

Procedia PDF Downloads 58

Authors: Stephan Schiffer, Andreas Kain, Philipp Wilde, Maximilian Helbing, Bernard Bäker

Abstract:

Automobile manufacturers progressively focus on a downsizing strategy to meet the EU's CO2 requirements concerning type-approval consumption cycles. The reduction in naturally aspirated engine power is compensated by increased levels of turbocharging. By downsizing conventional engines, CO2 emissions are reduced. However, it also implicates major challenges regarding longitudinal dynamic characteristics. An example of this circumstance is the delayed turbocharger-induced torque reaction which leads to a partially poor response behavior of the vehicle during acceleration operations. That is why it is important to focus conventional drive train design on real customer driving again. The currently considered dynamic maneuvers like the acceleration time 0-100 km/h discussed by journals and car manufacturers describe longitudinal dynamics experienced by a driver inadequately. For that reason we present the realization and evaluation of a comprehensive proband study. Subjects are provided with different vehicle concepts (electrified vehicles, vehicles with naturally aspired engines and vehicles with different concepts of turbochargers etc.) in order to find out which dynamic criteria are decisive for a subjectively strong acceleration and response behavior of a vehicle. Subsequently, realistic acceleration criteria are derived. By weighing the criteria an evaluation metric is developed to objectify customer-oriented transient dynamics. Fully-electrified vehicles are the benchmark in terms of customer-oriented longitudinal dynamics. The electric machine provides the desired torque almost without delay. This advantage compared to combustion engines is especially noticeable at low engine speeds. In conclusion, we will show the degree to which extent customer-relevant longitudinal dynamics of conventional vehicles can be approximated to electrified vehicle concepts. Therefore, various technical measures (turbocharger concepts, 48V electrical chargers etc.) and drive train designs (e.g. varying the final drive) are presented and evaluated in order to strengthen the vehicle’s customer-relevant transient dynamics. As a rating size the newly developed evaluation metric will be used.

Keywords: 48V, customer-oriented driving dynamics, electric charger, electrified vehicles, vehicle concepts

Procedia PDF Downloads 407

Authors: Besma Khalfoun

Abstract:

In many current Human Activity Recognition (HAR) applications, users' data is frequently shared and centrally stored by third parties, posing a significant privacy risk. This practice makes these entities attractive targets for extracting sensitive information about users, including their identity, health status, and location, thereby directly violating users' privacy. To tackle the issue of centralized data storage, a relatively recent paradigm known as federated learning has emerged. In this approach, users' raw data remains on their smartphones, where they train the HAR model locally. However, users still share updates of their local models originating from raw data. These updates are vulnerable to several attacks designed to extract sensitive information, such as determining whether a data sample is used in the training process, recovering the training data with inversion attacks, or inferring a specific attribute or property from the training data. In this paper, we first introduce PUR-Attack, a parameter-based user re-identification attack developed for HAR applications within a federated learning setting. It involves associating anonymous model updates (i.e., local models' weights or parameters) with the originating user's identity using background knowledge. PUR-Attack relies on a simple yet effective machine learning classifier and produces promising results. Specifically, we have found that by considering the weights of a given layer in a HAR model, we can uniquely re-identify users with an attack success rate of almost 100%. This result holds when considering a small attack training set and various data splitting strategies in the HAR model training. Thus, it is crucial to investigate protection methods to mitigate this privacy threat. Along this path, we propose SAFER, a privacy-preserving mechanism based on adaptive local differential privacy. Before sharing the model updates with the FL server, SAFER adds the optimal noise based on the re-identification risk assessment. Our approach can achieve a promising tradeoff between privacy, in terms of reducing re-identification risk, and utility, in terms of maintaining acceptable accuracy for the HAR model.

Keywords: federated learning, privacy risk assessment, re-identification risk, privacy preserving mechanisms, local differential privacy, human activity recognition

Procedia PDF Downloads 11

Authors: Naeimehsadat Hosseininam, Rui Wang, Dishita Shah

Abstract:

In recent years, new experimental approaches with the help of the new technology have bridged the gaps between the application of natural materials and creating unconventional forms. Clay has been one of the oldest building materials in all ancient civilizations. The availability and workability of clay have contributed to the widespread application of this material around the world. The aim of this experimental research is to apply the Clay 3D printing technology to create a load bearing and visually dynamic and undulating façade. Creation of different unique pieces is the most significant goal of this research which justifies the application of 3D printing technology instead of the conventional mass industrial production. This study provides an abbreviated overview of the similar cases which have used the Clay 3D printing to generate the corresponding prototypes. The study of these cases also helps in understanding the potential and flexibility of the material and 3D printing machine in developing different forms. In the next step, experimental research carried out by 3D printing of six various options which designed considering the properties of clay as well as the methodology of them being 3D printed. Here, the ratio of water to clay (W/C) has a significant role in the consistency of the material and the workability of the clay. Also, the size of the selected nozzle impacts the shape and the smoothness of the final surface. Moreover, the results of these experiments show the limitations of clay toward forming various slopes. The most notable consequence of having steep slopes in the prototype is an unpredicted collapse which is the result of internal tension in the material. From the six initial design ideas, the final prototype selected with the aim of creating a self-supported component with unique blocks that provides a possibility of installing the insulation system within the component. Apart from being an undulated façade, the presented prototype has the potential to be used as a fence and an interior partition (double-sided). The central shaft also provides a space to run services or insulation in different parts of the wall. In parallel to present the capability and potential of the clay 3D printing technology, this study illustrates the limitations of this system in some certain areas. There are inevitable parameters such as printing speed, temperature, drying speed that need to be considered while printing each piece. Clay 3D printing technology provides the opportunity to create variations and design parametric building components with the application of the most practiced material in the world.

Keywords: clay 3D printing, material capability, undulating facade, load bearing facade

Procedia PDF Downloads 141

Authors: Shantam Gupta

Abstract:

The objective of this study is to address the critical need for automation in the domestic food processing sector and study its impact. Food is the one of the most basic physiological needs essential for the survival of a living being. Some of them have the capacity to prepare their own food (like most plants) and henceforth are designated as primary food producers; those who depend on these primary food producers for food form the primary consumers’ class (herbivores). Some of the organisms relying on the primary food are the secondary food consumers (carnivores). There is a third class of consumers called tertiary food consumers/apex food consumers that feed on both the primary and secondary food consumers. Humans form an essential part of the apex predators and are generally at the top of the food chain. But still further disintegration of the food habits of the modern human i.e. Homo sapiens, reveals that humans depend on other individuals for preparing their own food. The old notion of eating raw/brute food is long gone and food processing has become very trenchant in lives of modern human. This has led to an increase in dependence on other individuals for ‘processing’ the food before it can be actually consumed by the modern human. This has led to a further shift of humans in the classification of food chain of consumers. The effects of the shifts shall be systematically investigated in this paper. The processing of food has a direct impact on the economy of the individual (consumer). Also most individuals depend on other processing individuals for the preparation of food. This dependency leads to establishment of a vital link of dependency in the food web which when altered can adversely affect the food web and can have dire consequences on the health of the individual. This study investigates the challenges arising out due to this dependency and the impact of food processing on the economy of the individual. A comparison of Industrial food processing and processing at domestic platforms (households and restaurants) has been made to provide an idea about the present scenario of automation in the food processing sector. A lot of time and energy is also consumed while processing food at home for consumption. The high frequency of consumption of meals (greater than 2 times a day) makes it even more laborious. Through the medium of this study a pressing need for development of an automatic cooking machine is proposed with a mission to reduce the inter-dependency & human effort of individuals required for the preparation of food (by automation of the food preparation process) and make them more self-reliant The impact of development of this product has also further been profoundly discussed. Assumption used: The individuals those who process food also consume the food that they produce. (They are also termed as ‘independent’ or ‘self-reliant’ modern human beings.)

Keywords: automation, food processing, impact on economy, processing individual

Procedia PDF Downloads 470

Authors: Aya Al Masri, Stefaan Carpentier, Fabrice Leroy, Thibault Julien, Safoin Aktaou, Malorie Martin, Fouad Maaloul

Abstract:

Introduction: During an 'Interventional Radiology (IR)' procedure, the patient's skin-dose may become very high for a burn, necrosis and ulceration to appear. In order to prevent these deterministic effects, an accurate calculation of the patient skin-dose mapping is essential. For most machines, the 'Dose Area Product (DAP)' and fluoroscopy time are the only information available for the operator. These two parameters are a very poor indicator of the peak skin dose. We developed a mathematical model that reconstructs the magnitude (delivered dose), shape, and localization of each irradiation field on the patient skin. In case of critical dose exceeding, the system generates warning alerts. We present the results of its comparison with clinical studies. Materials and methods: Two series of comparison of the skin-dose mapping of our mathematical model with clinical studies were performed: 1. At a first time, clinical tests were performed on patient phantoms. Gafchromic films were placed on the table of the IR machine under of PMMA plates (thickness = 20 cm) that simulate the patient. After irradiation, the film darkening is proportional to the radiation dose received by the patient's back and reflects the shape of the X-ray field. After film scanning and analysis, the exact dose value can be obtained at each point of the mapping. Four experimentation were performed, constituting a total of 34 acquisition incidences including all possible exposure configurations. 2. At a second time, clinical trials were launched on real patients during real 'Chronic Total Occlusion (CTO)' procedures for a total of 80 cases. Gafchromic films were placed at the back of patients. We performed comparisons on the dose values, as well as the distribution, and the shape of irradiation fields between the skin dose mapping of our mathematical model and Gafchromic films. Results: The comparison between the dose values shows a difference less than 15%. Moreover, our model shows a very good geometric accuracy: all fields have the same shape, size and location (uncertainty < 5%). Conclusion: This study shows that our model is a reliable tool to warn physicians when a high radiation dose is reached. Thus, deterministic effects can be avoided.

Keywords: clinical experimentation, interventional radiology, mathematical model, patient's skin-dose mapping.

Procedia PDF Downloads 140

Authors: Vladyslav Povoroznyuk, Nataliia Dzerovych, Larysa Martynyuk, Tetiana Kovtun

Abstract:

Obesity and osteoporosis are the two diseases whose increasing prevalence and high impact on the global morbidity and mortality, during the two recent decades, have gained a status of major health threats worldwide. Obesity purports to affect the bone metabolism through complex mechanisms. Debated data on the connection between the bone mineral density and fracture prevalence in the obese patients are widely presented in literature. There is evidence that the correlation of weight and fracture risk is site-specific. The aim of this study was to evaluate the Bone Mineral Density (BMD) and Trabecular Bone Score (TBS) in the obese Ukrainian women. We examined 1025 40-89-year-old women, divided them into the groups according to their body mass index: Group a included 360 women with obesity whose BMI was ≥30 kg/m2, and Group B – 665 women with no obesity and BMI of < 30 kg/m2. The BMD of total body, lumbar spine at the site L1-L4, femur and forearm were measured by DXA (Prodigy, GEHC Lunar, Madison, WI, USA). The TBS of L1-L4 was assessed by means of TBS iNsight® software installed on our DXA machine (product of Med-Imaps, Pessac, France). In general, obese women had a significantly higher BMD of lumbar spine, femoral neck, proximal femur, total body, and ultradistal forearm (p<0.001) in comparison with women without obesity. The TBS of L1-L4 was significantly lower in obese women compared to non-obese women (p<0.001). The BMD of lumbar spine, femoral neck and total body differed to a significant extent in women of 40-49, 50-59, 60-69, and 70-79 years (p<0.05). At same time, in women aged 80-89 years the BMD of lumbar spine (p=0.09), femoral neck (p=0.22) and total body (p=0.06) barely differed. The BMD of ultradistal forearm was significantly higher in women of all age groups (p<0.05). The TBS of L1-L4 in all the age groups tended to reveal the lower parameters in obese women compared with the non-obese; however, those data were not statistically significant. By contrast, a significant positive correlation was observed between the fat mass and the BMD at different sites. The correlation between the fat mass and TBS of L1-L4 was also significant, although negative. Women with vertebral fractures had a significantly lower body weight, body mass index and total body fat mass in comparison with women without vertebral fractures in their anamnesis. In obese women the frequency of vertebral fractures was 27%, while in women without obesity – 57%.

Keywords: obesity, trabecular bone score, bone mineral density, women

Procedia PDF Downloads 443

Authors: Govind Kumar

Abstract:

The concept of ‘e-governance’ that was brought about by the new wave of reforms, namely ‘LPG’ in the early 1990s, has been enabling governments across the globe to digitally transform themselves. Digital transformation is leading the governments with qualitative decisions, optimization in rational use of resources, facilitation of cost-benefit analyses, and elimination of redundancy and corruption with the help of ICT-based applications interface. ICT-based applications/technologies have enormous potential for impacting positive change in the social lives of the global citizenry. Supercomputers test and analyze millions of drug molecules for developing candidate vaccines to combat the global pandemic. Further, e-commerce portals help distribute and supply household items and medicines, while videoconferencing tools provide a visual interface between the clients and hosts. Besides, crop yields are being maximized with the help of drones and machine learning, whereas satellite data, artificial intelligence, and cloud computing help governments with the detection of illegal mining, tackling deforestation, and managing freshwater resources. Such e-applications have the potential to take governance an extra mile by achieving 5 Es (effective, efficient, easy, empower, and equity) of e-governance and six Rs (reduce, reuse, recycle, recover, redesign and remanufacture) of sustainable development. If such digital transformation gains traction within the government framework, it will replace the traditional administration with the digitalization of public administration. On the other hand, it has brought in a new set of challenges, like the digital divide, e-illiteracy, technological divide, etc., and problems like handling e-waste, technological obsolescence, cyber terrorism, e-fraud, hacking, phishing, etc. before the governments. Therefore, it would be essential to bring in a rightful mixture of technological and humanistic interventions for addressing the above issues. This is on account of the reason that technology lacks an emotional quotient, and the administration does not work like technology. Both are self-effacing unless a blend of technology and a humane face are brought in into the administration. The paper will empirically analyze the significance of the technological framework of digital transformation within the government set up for the digitalization of public administration on the basis of the synthesis of two case studies undertaken from two diverse fields of administration and present a future framework of the study.

Keywords: digital transformation, electronic governance, public administration, knowledge framework

Procedia PDF Downloads 99

Authors: Ahmed M. Eed, Adam H. Burgoyne

Abstract:

Jojoba (Simmondsia chinensis (Link) Schneider), is a desert shrub which tolerates saline, alkyle soils and drought. The seeds contain a characteristic liquid wax of economic importance in industry as a machine lubricant and cosmetics. A major problem in seed propagation is that jojoba is a dioecious plant whose sex is not easily determined prior to flowering (3-4 years from germination). To overcome this phenomenon, asexual propagation using vegetative methods such as cutting can be used. This research was conducted to find out the effect of different Plant Growth Regulators (PGRs) and rooting media on Jojoba rhizogenesis. An experiment was carried out in a Factorial Completely Randomized Design (FCRD) with three replications, each with sixty cuttings per replication in fiberglass house of Natural Jojoba Corporation at Yemen. The different rooting media used were peat moss + perlite + vermiculite (1:1:1), peat moss + perlite (1:1) and peat moss + sand (1:1). Plant materials used were semi-hard wood cuttings of jojoba plants with length of 15 cm. The cuttings were collected in the month of June during 2012 and 2013 from the sub-terminal growth of the mother plants of Amman farm and introduced to Yemen. They were wounded, treated with Indole butyric acid (IBA), α-naphthalene acetic acid (NAA) or Indole-3-acetic acid (IAA) all @ 4000 ppm (part per million) and cultured on different rooting media under intermittent mist propagation conditions. IBA gave significantly higher percentage of rooting (66.23%) compared to NAA and IAA in all media used. However, the lowest percentage of rooting (5.33%) was recorded with IAA in the medium consisting of peat moss and sand (1:1). No significant difference was observed at all types of PGRs used with rooting media in respect of root length. Maximum number of roots was noticed in medium consisting of peat moss, perlite and vermiculite (1:1:1); peat moss and perlite (1:1) and peat moss and sand (1:1) using IBA, NAA and IBA, respectively. The interaction among rooting media was statistically significant with respect to rooting percentage character. Similarly, the interactions among PGRs were significant in terms of rooting percentage and also root length characters. The results demonstrated suitability of propagation of jojoba plants by semi-hard wood cuttings.

Keywords: cutting, IBA, Jojoba, propagation, rhizogenesis

Procedia PDF Downloads 342

Authors: Jhiamluka Zservando Solano Velasquez, Raul Palma, Alejandro Calderon, Servio Paguada, Erick Marin, Kellyn Funes, Hana Sandoval, Oscar Hernandez

Abstract:

Background: Screening cardiac conditions in primary care in developing countries can be challenging, and Honduras is not the exception. One of the main limitations is the underfunding of the Healthcare System in general, causing conventional ECG acquisition to become a secondary priority. Objective: Development of a low-cost ECG to improve screening of arrhythmias in primary care and communication with a specialist in secondary and tertiary care. Methods: Design a portable, pocket-size low-cost 3 lead ECG (Handy EKG). The device is autonomous and has Wi-Fi/Bluetooth connectivity options. A mobile app was designed which can access online servers with machine learning, a subset of artificial intelligence to learn from the data and aid clinicians in their interpretation of readings. Additionally, the device would use the online servers to transfer patient’s data and readings to a specialist in secondary and tertiary care. 50 randomized patients volunteer to participate to test the device. The patients had no previous cardiac-related conditions, and readings were taken. One reading was performed with the conventional ECG and 3 readings with the Handy EKG using different lead positions. This project was possible thanks to the funding provided by the National Autonomous University of Honduras. Results: Preliminary results show that the Handy EKG performs readings of the cardiac activity similar to those of a conventional electrocardiograph in lead I, II, and III depending on the position of the leads at a lower cost. The wave and segment duration, amplitude, and morphology of the readings were similar to the conventional ECG, and interpretation was possible to conclude whether there was an arrhythmia or not. Two cases of prolonged PR segment were found in both ECG device readings. Conclusion: Using a Frugal innovation approach can allow lower income countries to develop innovative medical devices such as the Handy EKG to fulfill unmet needs at lower prices without compromising effectiveness, safety, and quality. The Handy EKG provides a solution for primary care screening at a much lower cost and allows for convenient storage of the readings in online servers where clinical data of patients can then be accessed remotely by Cardiology specialists.

Keywords: low-cost hardware, portable electrocardiograph, prototype, remote healthcare

Procedia PDF Downloads 180

Authors: Libor Zachoval, Daire O Broin, Oisin Cawley

Abstract:

E-learning platforms, such as Blackboard have two major shortcomings: limited data capture as a result of the limitations of SCORM (Shareable Content Object Reference Model), and lack of incorporation of Artificial Intelligence (AI) and machine learning algorithms which could lead to better course adaptations. With the recent development of Experience Application Programming Interface (xAPI), a large amount of additional types of data can be captured and that opens a window of possibilities from which online education can benefit. In a corporate setting, where companies invest billions on the learning and development of their employees, some learner behaviours can be troublesome for they can hinder the knowledge development of a learner. Behaviours that hinder the knowledge development also raise ambiguity about learner’s knowledge mastery, specifically those related to gaming the system. Furthermore, a company receives little benefit from their investment if employees are passing courses without possessing the required knowledge and potential compliance risks may arise. Using xAPI and rules derived from a state-of-the-art review, we identified three learner behaviours, primarily related to guessing, in a corporate compliance course. The identified behaviours are: trying each option for a question, specifically for multiple-choice questions; selecting a single option for all the questions on the test; and continuously repeating tests upon failing as opposed to going over the learning material. These behaviours were detected on learners who repeated the test at least 4 times before passing the course. These findings suggest that gauging the mastery of a learner from multiple-choice questions test scores alone is a naive approach. Thus, next steps will consider the incorporation of additional data points, knowledge estimation models to model knowledge mastery of a learner more accurately, and analysis of the data for correlations between knowledge development and identified learner behaviours. Additional work could explore how learner behaviours could be utilised to make changes to a course. For example, course content may require modifications (certain sections of learning material may be shown to not be helpful to many learners to master the learning outcomes aimed at) or course design (such as the type and duration of feedback).

Keywords: artificial intelligence, corporate e-learning environment, knowledge maintenance, xAPI

Procedia PDF Downloads 121

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

Authors: Dona Shaini Abhilasha Nanayakkara, Kurugamage Jude Pravinda Gregory Perera

Abstract:

E-commerce platforms have revolutionized the shopping experience, offering convenient ways for consumers to make purchases. To improve interactions with customers and optimize marketing strategies, it is essential for businesses to understand user behavior, preferences, and needs on these platforms. This paper focuses on recommending businesses to customize interactions with users based on their behavioral patterns, leveraging data-driven analysis and machine learning techniques. Businesses can improve engagement and boost the adoption of e-commerce platforms by aligning behavioral patterns with user goals of usability and satisfaction. We propose TheAnalyzer, a clustering-based system designed to enhance business productivity by analyzing user-profiles and improving human-computer interaction. The Analyzer seamlessly integrates with business applications, collecting relevant data points based on users' natural interactions without additional burdens such as questionnaires or surveys. It defines five key user analytics as features for its dataset, which are easily captured through users' interactions with e-commerce platforms. This research presents a study demonstrating the successful distinction of users into specific groups based on the five key analytics considered by TheAnalyzer. With the assistance of domain experts, customized business rules can be attached to each group, enabling The Analyzer to influence business applications and provide an enhanced personalized user experience. The outcomes are evaluated quantitatively and qualitatively, demonstrating that utilizing TheAnalyzer’s capabilities can optimize business outcomes, enhance customer satisfaction, and drive sustainable growth. The findings of this research contribute to the advancement of personalized interactions in e-commerce platforms. By leveraging user behavioral patterns and analyzing both new and existing users, businesses can effectively tailor their interactions to improve customer satisfaction, loyalty and ultimately drive sales.

Keywords: data clustering, data standardization, dimensionality reduction, human computer interaction, user profiling

Procedia PDF Downloads 74

Authors: Xukai Fu

Abstract:

The concept of circular economy is interdisciplinary, intersecting environmental engineering, information technology, business, and social science domains. Over the course of its 15-year tenure in the sanitation industry, Jinkai has concentrated its efforts in the past five years on integrating artificial intelligence (AI) technology with street sanitation apparatus and systems. This endeavor has led to the development of various innovations, including the Intelligent Identification Sweeper Truck (Intelligent Waste Recognition and Energy-saving Control System), the Intelligent Identification Water Truck (Intelligent Flushing Control System), the intelligent food waste treatment machine, and the Intelligent City Road Sanitation Surveillance Platform. This study will commence with an examination of prevalent global challenges, elucidating how Jinkai effectively addresses each within the framework of circular economy principles. Utilizing a review and analysis of pertinent environmental management data, we will elucidate Jinkai's strategic approach. Following this, we will investigate how Jinkai utilizes the advantages of circular economy principles to guide the design of street sanitation machinery, with a focus on digitalization integration. Moreover, we will scrutinize Jinkai's sustainable practices throughout the invention and operation phases of street sanitation machinery, aligning with the triple bottom line theory. Finally, we will delve into the significance and enduring impact of corporate social responsibility (CSR) and environmental, social, and governance (ESG) initiatives. Special emphasis will be placed on Jinkai's contributions to community stakeholders, with a particular emphasis on human rights. Despite the widespread adoption of circular economy principles across various industries, achieving a harmonious equilibrium between environmental justice and social justice remains a formidable task. Jinkai acknowledges that the mere development of energy-saving technologies is insufficient for authentic circular economy implementation; rather, they serve as instrumental tools. To earnestly promote and embody circular economy principles, companies must consistently prioritize the UN Sustainable Development Goals and adapt their technologies to address the evolving exigencies of our world.

Keywords: circular economy, core principles, benefits, the tripple bottom line, CSR, ESG, social justice, human rights, Jinkai

Procedia PDF Downloads 47

Authors: Mazoun Nasser Rashid Al Kharusi, Nada Al Siyabi

Abstract:

Objectives: The main aim of this study is to Find the rate of susceptibility of ESBL E. coli causing UTI to oral antibiotics. Secondary objectives: Prevalence of ESBL E. coli from community urine samples, identify the best empirical oral antibiotics with the least resistance rate for UTI and identify alternative oral antibiotics for testing and utilization. Methods: This study is a retrospective descriptive study of the last three years in five major hospitals in Oman (Khowla Hospital, AN’Nahdha Hospital, Rustaq Hospital, Nizwa Hospital, and Ibri Hospital) equipped with a microbiologist. Inclusion criteria include all eligible outpatient urine culture isolates, excluding isolates from admitted patients with hospital-acquired urinary tract infections. Data was collected through the MOH database. The MOH hospitals are using different types of testing, automated methods like Vitek2 and manual methods. Vitek2 machine uses the principle of the fluorogenic method for organism identification and a turbidimetric method for susceptibility testing. The manual method is done by double disc diffusion for identifying ESBL and the disc diffusion method is for antibiotic susceptibility. All laboratories follow the clinical laboratory science institute (CLSI) guidelines. Analysis was done by SPSS statistical package. Results: Total urine cultures were (23048). E. coli grew in (11637) 49.6% of the urine, whereas (2199) 18.8% of those were confirmed as ESBL. As expected, the resistance rate to amoxicillin and cefuroxime is 100%. Moreover, the susceptibility of those ESBL-producing E. coli to nitrofurantoin, trimethoprim+sulfamethoxazole, ciprofloxacin and amoxicillin-clavulanate is progressing over the years; however, still low. ESBL E. coli was predominating in the female gender and those aged 66-74 years old throughout all the years. Other oral antibiotic options need to be explored and tested so that we add to the pool of oral antibiotics for ESBL E. coli causing UTI in the community. Conclusion: High rate of ESBL E. coli in urine from the community. The high resistance rates to oral antibiotics highlight the need for alternative treatment options for UTIs caused by these bacteria. Further research is needed to identify new and effective treatments for UTIs caused by ESBL-E. Coli.

Keywords: UTI, ESBL, oral antibiotics, E. coli, susceptibility

Procedia PDF Downloads 93

Authors: Yao Cheng, Weihua Zhang

Abstract:

Although the measured vibration signal contains rich information on machine health conditions, the white noise interferences and the discrete harmonic coming from blade, shaft and mash make the fault diagnosis of rolling element bearings difficult. In order to overcome the interferences of useless signals, a new fault diagnosis method combining Complete Ensemble Empirical Mode Decomposition with adaptive noise (CEEMDAN) and Multipoint Optimal Minimum Entropy Deconvolution (MOMED) is proposed for the fault diagnosis of high-speed train bearings. Firstly, the CEEMDAN technique is applied to adaptively decompose the raw vibration signal into a series of finite intrinsic mode functions (IMFs) and a residue. Compared with Ensemble Empirical Mode Decomposition (EEMD), the CEEMDAN can provide an exact reconstruction of the original signal and a better spectral separation of the modes, which improves the accuracy of fault diagnosis. An effective sensitivity index based on the Pearson's correlation coefficients between IMFs and raw signal is adopted to select sensitive IMFs that contain bearing fault information. The composite signal of the sensitive IMFs is applied to further analysis of fault identification. Next, for propose of identifying the fault information precisely, the MOMED is utilized to enhance the periodic impulses in composite signal. As a non-iterative method, the MOMED has better deconvolution performance than the classical deconvolution methods such Minimum Entropy Deconvolution (MED) and Maximum Correlated Kurtosis Deconvolution (MCKD). Third, the envelope spectrum analysis is applied to detect the existence of bearing fault. The simulated bearing fault signals with white noise and discrete harmonic interferences are used to validate the effectiveness of the proposed method. Finally, the superiorities of the proposed method are further demonstrated by high-speed train bearing fault datasets measured from test rig. The analysis results indicate that the proposed method has strong practicability.

Keywords: bearing, complete ensemble empirical mode decomposition with adaptive noise, fault diagnosis, multipoint optimal minimum entropy deconvolution

Procedia PDF Downloads 374

Authors: Adel Khorramrouz, Monireh Ahmadi Bani, Ehsan Norouzi

Abstract:

Background:-Due to the essential role of the foot in movement, foot disorders (FDs) have significant impacts on activity and quality of life. Many studies confirmed the association between FDs and demographic characteristics. On the other hand, recent advances in data collection and statistical analysis led to an increase in the volume of databases. Analysis of patient’s data through the decision tree can be used to explore the relationship between demographic characteristics and FDs. Significance of the study: This study aimed to investigate the relationship between demographic characteristics with common FDs. The second purpose is to better inform foot intervention, we classify FDs based on demographic variables. Methodologies: We analyzed 2323 subjects with pes-planus (PP), pes-cavus (PC), hallux-valgus (HV) and plantar-fasciitis (PF) who were referred to a foot therapy clinic between 2015 and 2021. Subjects had to fulfill the following inclusion criteria: (1) weight between 14 to 150 kilogram, (2) height between 30 to 220, (3) age between 3 to 100 years old, and (4) BMI between 12 to 35. Medical archives of 2323 subjects were recorded retrospectively and all the subjects examined by an experienced physician. Age and BMI were classified into five and four groups, respectively. 80% of the data were randomly selected as training data and 20% tested. We build a decision tree model to classify FDs using demographic characteristics. Findings: Results demonstrated 981 subjects from 2323 (41.9%) of people who were referred to the clinic with FDs were diagnosed as PP, 657 (28.2%) PC, 628 (27%) HV and 213 (9%) identified with PF. The results revealed that the prevalence of PP decreased in people over 18 years of age and in children over 7 years. In adults, the prevalence depends first on BMI and then on gender. About 10% of adults and 81% of children with low BMI have PP. There is no relationship between gender and PP. PC is more dependent on age and gender. In children under 7 years, the prevalence was twice in girls (10%) than boys (5%) and in adults over 18 years slightly higher in men (62% vs 57%). HV increased with age in women and decreased in men. Aging and obesity have increased the prevalence of PF. We conclude that the accuracy of our approach is sufficient for most research applications in FDs. Conclusion:-The increased prevalence of PP in children is probably due to the formation of the arch of the foot at this age. Increasing BMI by applying high pressure on the foot can increase the prevalence of this disorder in the foot. In PC, the Increasing prevalence of PC from women to men with age may be due to genetics and innate susceptibility of men to this disorder. HV is more common in adult women, which may be due to environmental reasons such as shoes, and the prevalence of PF in obese adult women may also be due to higher foot pressure and housekeeping activities.

Keywords: decision tree, demographic characteristics, foot disorders, machine learning

Procedia PDF Downloads 262

Authors: Nassima Noufail, Sara Bouhali

Abstract:

In this work, we develop a semi-supervised solution for the purpose of action detection in videos and propose an efficient algorithm for video segmentation. The approach is divided into video segmentation, feature extraction, and classification. In the first part, a video is segmented into clips, and we used the K-means algorithm for this segmentation; our goal is to find groups based on similarity in the video. The application of k-means clustering into all the frames is time-consuming; therefore, we started by the identification of transition frames where the scene in the video changes significantly, and then we applied K-means clustering into these transition frames. We used two image filters, the gaussian filter and the Laplacian of Gaussian. Each filter extracts a set of features from the frames. The Gaussian filter blurs the image and omits the higher frequencies, and the Laplacian of gaussian detects regions of rapid intensity changes; we then used this vector of filter responses as an input to our k-means algorithm. The output is a set of cluster centers. Each video frame pixel is then mapped to the nearest cluster center and painted with a corresponding color to form a visual map. The resulting visual map had similar pixels grouped. We then computed a cluster score indicating how clusters are near each other and plotted a signal representing frame number vs. clustering score. Our hypothesis was that the evolution of the signal would not change if semantically related events were happening in the scene. We marked the breakpoints at which the root mean square level of the signal changes significantly, and each breakpoint is an indication of the beginning of a new video segment. In the second part, for each segment from part 1, we randomly selected a 16-frame clip, then we extracted spatiotemporal features using convolutional 3D network C3D for every 16 frames using a pre-trained model. The C3D final output is a 512-feature vector dimension; hence we used principal component analysis (PCA) for dimensionality reduction. The final part is the classification. The C3D feature vectors are used as input to a multi-class linear support vector machine (SVM) for the training model, and we used a multi-classifier to detect the action. We evaluated our experiment on the UCF101 dataset, which consists of 101 human action categories, and we achieved an accuracy that outperforms the state of art by 1.2%.

Keywords: video segmentation, action detection, classification, Kmeans, C3D

Procedia PDF Downloads 77

Authors: John-Nelson Ekumah, Selorm Yao-Say Solomon Adade, Mingming Zhong, Yufan Sun, Qiufang Liang, Muhammad Safiullah Virk, Xorlali Nunekpeku, Nana Adwoa Nkuma Johnson, Bridget Ama Kwadzokpui, Xiaofeng Ren

Abstract:

Enhancing starch gel strength and stability is crucial. However, traditional gel property assessment methods are destructive, time-consuming, and resource-intensive. Thus, understanding ethanol treatment effects on kudzu starch gel strength and developing a rapid, nondestructive gel strength assessment method is essential for optimizing the treatment process and ensuring product quality consistency. This study investigated the effects of different ethanol concentrations on the microstructure of kudzu starch gels using a comprehensive microstructural analysis. We also developed a nondestructive method for predicting gel strength and classifying treatment levels using near-infrared (NIR) spectroscopy, and advanced data analytics. Scanning electron microscopy revealed progressive network densification and pore collapse with increasing ethanol concentration, correlating with enhanced mechanical properties. NIR spectroscopy, combined with various variable selection methods (CARS, GA, and UVE) and modeling algorithms (PLS, SVM, and ELM), was employed to develop predictive models for gel strength. The UVE-SVM model demonstrated exceptional performance, with the highest R² values (Rc = 0.9786, Rp = 0.9688) and lowest error rates (RMSEC = 6.1340, RMSEP = 6.0283). Pattern recognition algorithms (PCA, LDA, and KNN) successfully classified gels based on ethanol treatment levels, achieving near-perfect accuracy. This integrated approach provided a multiscale perspective on ethanol-induced starch gel modification, from molecular interactions to macroscopic properties. Our findings demonstrate the potential of NIR spectroscopy, coupled with advanced data analysis, as a powerful tool for rapid, nondestructive quality assessment in starch gel production. This study contributes significantly to the understanding of starch modification processes and opens new avenues for research and industrial applications in food science, pharmaceuticals, and biomaterials.

Keywords: kudzu starch gel, near-infrared spectroscopy, gel strength prediction, support vector machine, pattern recognition algorithms, ethanol treatment

Procedia PDF Downloads 37

Authors: Ariadna Manresa, Ines Ferrer

Abstract:

Introduction: Ultrasonic moulding process (USM) is a recent injection technology used to manufacture micro components. It is able to melt small amounts of material so the waste of material is certainly reduced comparing to microinjection molding. This is an important advantage when the materials are expensive like medical biopolymers. Micro-scaled components are involved in a variety of uses, such as biomedical applications. It is required replication fidelity so it is important to stabilize the process and minimize the variability of the responses. The aim of this research is to investigate the influence of the main process parameters on the filling behaviour, the dimensional accuracy and the cavity pressure when a micro-plate is manufactured by biomaterials such as PLA and PCL. Methodology or Experimental Procedure: The specimens are manufactured using a Sonorus 1G Ultrasound Micro Molding Machine. The used geometry is a rectangular micro-plate of 15x5mm and 1mm of thickness. The materials used for the investigation are PLA and PCL due to biocompatible and degradation properties. The experimentation is divided into two phases. Firstly, the influence of process parameters (vibration amplitude, sonotrodo velocity, ultrasound time and compaction force) on filling behavior is analysed, in Phase 1. Next, when filling cavity is assured, the influence of both cooling time and force compaction on the cavity pressure, part temperature and dimensional accuracy is instigated, which is done in Phase. Results and Discussion: Filling behavior depends on sonotrodo velocity and vibration amplitude. When the ultrasonic time is higher, more ultrasonic energy is applied and the polymer temperature increases. Depending on the cooling time, it is possible that when mold is opened, the micro-plate temperature is too warm. Consequently, the polymer relieve its stored internal energy (ultrasonic and thermal) expanding through the easier direction. This fact is reflected on dimensional accuracy, causing micro-plates thicker than the mold. It has also been observed the most important fact that affects cavity pressure is the compaction configuration during the manufacturing cycle. Conclusions: This research demonstrated the influence of process parameters on the final micro-plated manufactured. Future works will be focused in manufacturing other geometries and analysing the mechanical properties of the specimens.

Keywords: biomaterial, biopolymer, micro injection molding, ultrasound

Procedia PDF Downloads 284

Authors: Jonathan Gong

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deep learning, image processing, machine learning

Procedia PDF Downloads 130

Authors: L. Kanoksak, N. Sukanya, L. Napatsorn, T. Siriporn

Abstract:

A growing population and demand for packaging are driving up the usage of natural resources as raw materials in the pulp and paper industry. Long-term effects of environmental is disrupting people's way of life all across the planet. Finding pulp sources to replace wood pulp is therefore necessary. To produce wood pulp, various other potential plants or plant parts can be employed as substitute raw materials. For example, pulp and paper were made from agricultural residue that mainly included pulp can be used in place of wood. In this study, cocoa pod husks were an agricultural residue of the cocoa and chocolate industries. To develop composite materials to replace wood pulp in packaging materials. The paper was coated with polybutylene adipate-co-terephthalate (PBAT). By selecting and cleaning fresh cocoa pod husks, the size was reduced. And the cocoa pod husks were dried. The morphology and elemental composition of cocoa pod husks were studied. To evaluate the mechanical and physical properties, dried cocoa husks were extracted using the soda-pulping process. After selecting the best formulations, paper with a PBAT bioplastic coating was produced on a paper-forming machine Physical and mechanical properties were studied. By using the Field Emission Scanning Electron Microscope/Energy Dispersive X-Ray Spectrometer (FESEM/EDS) technique, the structure of dried cocoa pod husks showed the main components of cocoa pod husks. The appearance of porous has not been found. The fibers were firmly bound for use as a raw material for pulp manufacturing. Dry cocoa pod husks contain the major elements carbon (C) and oxygen (O). Magnesium (Mg), potassium (K), and calcium (Ca) were minor elements that were found in very small levels. After that cocoa pod husks were removed from the soda-pulping process. It found that the SAQ5 formula produced pulp yield, moisture content, and water drainage. To achieve the basis weight by TAPPI T205 sp-02 standard, cocoa pod husk pulp and modified starch were mixed. The paper was coated with bioplastic PBAT. It was produced using bioplastic resin from the blown film extrusion technique. It showed the contact angle, dispersion component and polar component. It is an effective hydrophobic material for rigid packaging applications.

Keywords: cocoa pod husks, agricultural residue, composite material, rigid packaging

Procedia PDF Downloads 76

Authors: Maxence Queyrel, Edi Prifti, Alexandre Templier, Jean-Daniel Zucker

Abstract:

Analysis of the human microbiome using metagenomic sequencing data has demonstrated high ability in discriminating various human diseases. Raw metagenomic sequencing data require multiple complex and computationally heavy bioinformatics steps prior to data analysis. Such data contain millions of short sequences read from the fragmented DNA sequences and stored as fastq files. Conventional processing pipelines consist in multiple steps including quality control, filtering, alignment of sequences against genomic catalogs (genes, species, taxonomic levels, functional pathways, etc.). These pipelines are complex to use, time consuming and rely on a large number of parameters that often provide variability and impact the estimation of the microbiome elements. Training Deep Neural Networks directly from raw sequencing data is a promising approach to bypass some of the challenges associated with mainstream bioinformatics pipelines. Most of these methods use the concept of word and sentence embeddings that create a meaningful and numerical representation of DNA sequences, while extracting features and reducing the dimensionality of the data. In this paper we present an end-to-end approach that classifies patients into disease groups directly from raw metagenomic reads: metagenome2vec. This approach is composed of four steps (i) generating a vocabulary of k-mers and learning their numerical embeddings; (ii) learning DNA sequence (read) embeddings; (iii) identifying the genome from which the sequence is most likely to come and (iv) training a multiple instance learning classifier which predicts the phenotype based on the vector representation of the raw data. An attention mechanism is applied in the network so that the model can be interpreted, assigning a weight to the influence of the prediction for each genome. Using two public real-life data-sets as well a simulated one, we demonstrated that this original approach reaches high performance, comparable with the state-of-the-art methods applied directly on processed data though mainstream bioinformatics workflows. These results are encouraging for this proof of concept work. We believe that with further dedication, the DNN models have the potential to surpass mainstream bioinformatics workflows in disease classification tasks.

Keywords: deep learning, disease prediction, end-to-end machine learning, metagenomics, multiple instance learning, precision medicine

Procedia PDF Downloads 125

Authors: Uraib Sharaha, Ahmad Salman, Eladio Rodriguez-Diaz, Elad Shufan, Klaris Riesenberg, Irving J. Bigio, Mahmoud Huleihel

Abstract:

Antimicrobial drugs have an important role in controlling illness associated with infectious diseases in animals and humans. However, the increasing resistance of bacteria to a broad spectrum of commonly used antibiotics has become a global health-care problem. Rapid determination of antimicrobial susceptibility of a clinical isolate is often crucial for the optimal antimicrobial therapy of infected patients and in many cases can save lives. The conventional methods for susceptibility testing like disk diffusion are time-consuming and other method including E-test, genotyping are relatively expensive. Fourier transform infrared (FTIR) microscopy is rapid, safe, and low cost method that was widely and successfully used in different studies for the identification of various biological samples including bacteria. The new modern infrared (IR) spectrometers with high spectral resolution enable measuring unprecedented biochemical information from cells at the molecular level. Moreover, the development of new bioinformatics analyses combined with IR spectroscopy becomes a powerful technique, which enables the detection of structural changes associated with resistivity. The main goal of this study is to evaluate the potential of the FTIR microscopy in tandem with machine learning algorithms for rapid and reliable identification of bacterial susceptibility to antibiotics in time span of few minutes. The bacterial samples, which were identified at the species level by MALDI-TOF and examined for their susceptibility by the routine assay (micro-diffusion discs), are obtained from the bacteriology laboratories in Soroka University Medical Center (SUMC). These samples were examined by FTIR microscopy and analyzed by advanced statistical methods. Our results, based on 550 E.coli samples, were promising and showed that by using infrared spectroscopic technique together with multivariate analysis, it is possible to classify the tested bacteria into sensitive and resistant with success rate higher than 85% for eight different antibiotics. Based on these preliminary results, it is worthwhile to continue developing the FTIR microscopy technique as a rapid and reliable method for identification antibiotic susceptibility.

Keywords: antibiotics, E. coli, FTIR, multivariate analysis, susceptibility

Procedia PDF Downloads 265

Authors: Roberta Facchinetti, Sara Corrizzato, Silvia Cavalieri

Abstract:

Increasing interconnection between data digitalization and linguistic investigation has given rise to unprecedented potentialities and challenges for corpus linguists, who need to master IT tools for data analysis and text processing, as well as to develop techniques for efficient and reliable annotation in specific mark-up languages that encode documents in a format that is both human and machine-readable. In the present paper, the challenges emerging from the compilation of a linguistic corpus will be taken into consideration, focusing on the English language in particular. To do so, the case study of the InterDiplo corpus will be illustrated. The corpus, currently under development at the University of Verona (Italy), represents a novelty in terms both of the data included and of the tag set used for its annotation. The corpus covers media interviews and debates with diplomats and international operators conversing in English with journalists who do not share the same lingua-cultural background as their interviewees. To date, this appears to be the first tagged corpus of international institutional spoken discourse and will be an important database not only for linguists interested in corpus analysis but also for experts operating in international relations. In the present paper, special attention will be dedicated to the structural mark-up, parts of speech annotation, and tagging of discursive traits, that are the innovational parts of the project being the result of a thorough study to find the best solution to suit the analytical needs of the data. Several aspects will be addressed, with special attention to the tagging of the speakers’ identity, the communicative events, and anthropophagic. Prominence will be given to the annotation of question/answer exchanges to investigate the interlocutors’ choices and how such choices impact communication. Indeed, the automated identification of questions, in relation to the expected answers, is functional to understand how interviewers elicit information as well as how interviewees provide their answers to fulfill their respective communicative aims. A detailed description of the aforementioned elements will be given using the InterDiplo-Covid19 pilot corpus. The data yielded by our preliminary analysis of the data will highlight the viable solutions found in the construction of the corpus in terms of XML conversion, metadata definition, tagging system, and discursive-pragmatic annotation to be included via Oxygen.

Keywords: spoken corpus, diplomats’ interviews, tagging system, discursive-pragmatic annotation, english linguistics

Procedia PDF Downloads 185

Authors: Misuk Kim, Seokho Kang, Jehyuk Lee, Hyunchang Cho, Sungzoon Cho

Abstract:

In semiconductor manufacturing, virtual metrology (VM) refers to methods to predict properties of a wafer based on machine parameters and sensor data of the production equipment, without performing the (costly) physical measurement of the wafer properties (Wikipedia). Additional benefits include avoidance of human bias and identification of important factors affecting the quality of the process which allow improving the process quality in the future. It is however rare to find VM applied to other areas of manufacturing. In this work, we propose to use VM to copper clad laminate (CCL) manufacturing. CCL is a core element of a printed circuit board (PCB) which is used in smartphones, tablets, digital cameras, and laptop computers. The manufacturing of CCL consists of three processes: Treating, lay-up, and pressing. Treating, the most important process among the three, puts resin on glass cloth, heat up in a drying oven, then produces prepreg for lay-up process. In this process, three important quality factors are inspected: Treated weight (T/W), Minimum Viscosity (M/V), and Gel Time (G/T). They are manually inspected, incurring heavy cost in terms of time and money, which makes it a good candidate for VM application. We developed prediction models of the three quality factors T/W, M/V, and G/T, respectively, with process variables, raw material, and environment variables. The actual process data was obtained from a CCL manufacturer. A variety of variable selection methods and learning algorithms were employed to find the best prediction model. We obtained prediction models of M/V and G/T with a high enough accuracy. They also provided us with information on “important” predictor variables, some of which the process engineers had been already aware and the rest of which they had not. They were quite excited to find new insights that the model revealed and set out to do further analysis on them to gain process control implications. T/W did not turn out to be possible to predict with a reasonable accuracy with given factors. The very fact indicates that the factors currently monitored may not affect T/W, thus an effort has to be made to find other factors which are not currently monitored in order to understand the process better and improve the quality of it. In conclusion, VM application to CCL’s treating process was quite successful. The newly built quality prediction model allowed one to reduce the cost associated with actual metrology as well as reveal some insights on the factors affecting the important quality factors and on the level of our less than perfect understanding of the treating process.

Keywords: copper clad laminate, predictive modeling, quality control, virtual metrology

Procedia PDF Downloads 350

Authors: Pavana Basavakumar, Devadas Bhat

Abstract:

Diabetes is a disease which often goes undiagnosed until its secondary effects are noticed. Early detection of the disease is necessary to avoid serious consequences which could lead to the death of the patient. Conventional invasive tests for screening of diabetes are mostly painful, time consuming and expensive. There’s also a risk of infection involved, therefore it is very essential to develop non-invasive methods to screen and estimate the level of blood glucose. Extensive research is going on with this perspective, involving various techniques that explore optical, electrical, chemical and thermal properties of the human body that directly or indirectly depend on the blood glucose concentration. Thus, non-invasive blood glucose monitoring has grown into a vast field of research. In this project, an attempt was made to device a prototype for screening of diabetes by measuring electrical impedance of the skin and building a model to predict a patient’s condition based on the measured impedance. The prototype developed, passes a negligible amount of constant current (0.5mA) across a subject’s index finger through tetra polar silver electrodes and measures output voltage across a wide range of frequencies (10 KHz – 4 MHz). The measured voltage is proportional to the impedance of the skin. The impedance was acquired in real-time for further analysis. Study was conducted on over 75 subjects with permission from the institutional ethics committee, along with impedance, subject’s blood glucose values were also noted, using conventional method. Nonlinear regression analysis was performed on the features extracted from the impedance data to obtain a model that predicts blood glucose values for a given set of features. When the predicted data was depicted on Clarke’s Error Grid, only 58% of the values predicted were clinically acceptable. Since the objective of the project was to screen diabetes and not actual estimation of blood glucose, the data was classified into three classes ‘NORMAL FASTING’,’NORMAL POSTPRANDIAL’ and ‘HIGH’ using linear Support Vector Machine (SVM). Classification accuracy obtained was 91.4%. The developed prototype was economical, fast and pain free. Thus, it can be used for mass screening of diabetes.

Keywords: Clarke’s error grid, electrical impedance of skin, linear SVM, nonlinear regression, non-invasive blood glucose monitoring, screening device for diabetes

Procedia PDF Downloads 325

Authors: Nilda Tri Putri, Muhammad Taufik

Abstract:

Tools and agricultural machinery (Alsintan) is a tool used in agribusiness activities. Alsintan used to change the traditional farming systems generally use manual equipment into modern agriculture with mechanization. CV Nugraha Chakti Consultant make an action plan for industrial development Alsintan West Sumatra in 2012 to develop medium industries of Alsintan become a major industry of Alsintan, one of efforts made is increase the production capacity of the industry Alsintan. Production capacity for superior products as hydrotiller and threshers set each for 2.000 units per year. CV Citra Dragon as one of the medium industry alsintan in West Sumatra has a plan to relocate the existing plant to meet growing consumer demand each year. Increased production capacity and plant relocation plan has led to a change in the layout; therefore need to design the layout of the plant facility CV Citra Dragon. First step the to design of plant layout is design the layout of the production floor. The design of the production floor layout is done by applying group technology layout. The initial step is to do a machine grouping and part family using the Average Linkage Clustering (ALC) and Rank Order Clustering (ROC). Furthermore done independent work station design and layout design using the Modified Spanning Tree (MST). Alternative selection layout is done to select the best production floor layout between ALC and ROC cell grouping. Furthermore, to design the layout of warehouses, offices and other production support facilities. Activity Relationship Chart methods used to organize the placement of factory facilities has been designed. After structuring plan facilities, calculated cost manufacturing facility plant establishment. Type of layout is used on the production floor layout technology group. The production floor is composed of four cell machinery, assembly area and painting area. The total distance of the displacement of material in a single production amounted to 1120.16 m which means need 18,7minutes of transportation time for one time production. Alsintan Factory has designed a circular flow pattern with 11 facilities. The facilities were designed consisting of 10 rooms and 1 parking space. The measure of factory building is 84 m x 52 m.

Keywords: Average Linkage Clustering (ALC), Rank Order Clustering (ROC), Modified Spanning Tree (MST), Activity Relationship Chart (ARC)

Procedia PDF Downloads 496

Authors: Nabiyeva Jamala

Abstract:

We divide water into drinking, mineral, industrial, technical and thermal-energetic types according to its use and purpose. Drinking water must comply with sanitary requirements and norms according to organoleptic devices and physical and chemical properties. Mineral water - must comply with the norms due to some components having therapeutic properties. Industrial water must fulfill its normative requirements by being used in the industrial field. Technical water should be suitable for use in the field of agriculture, household, and irrigation, and the normative requirements should be met. Heat-energy water is used in the national economy, and it consists of thermal and energy water. Water is a filter-accumulator of all types of pollutants entering the environment. This is explained by the fact that it has the property of dissolving compounds of mineral and gaseous water and regular water circulation. Environmentally clean, pure, non-toxic water is vital for the normal life activity of humans, animals and other living beings. Chemical pollutants enter water basins mainly with wastewater from non-ferrous and ferrous metallurgy, oil, gas, chemical, stone, coal, pulp and paper and forest materials processing industries and make them unusable. Wastewater from the chemical, electric power, woodworking and machine-building industries plays a huge role in the pollution of water sources. Chlorine compounds, phenols, and chloride-containing substances have a strong lethal-toxic effect on organisms when mixed with water. Heavy metals - lead, cadmium, mercury, nickel, copper, selenium, chromium, tin, etc. water mixed with ingredients cause poisoning in humans, animals and other living beings. Thus, the mixing of selenium with water causes liver diseases in people, the mixing of mercury with the nervous system, and the mixing of cadmium with kidney diseases. Pollution of the World's ocean waters and other water basins with oil and oil products is one of the most dangerous environmental problems facing humanity today. So, mixing even the smallest amount of oil and its products in drinking water gives it a bad, unpleasant smell. Mixing one ton of oil with water creates a special layer that covers the water surface in an area of 2.6 km2. As a result, the flood of light, photosynthesis and oxygen supply of water is getting weak and there is a great danger to the lives of living beings.

Keywords: chemical pollutants, wastewater, SSAM, polyacrylamide

Procedia PDF Downloads 73

Authors: Nazlı Çetindağ, Pelin Yılmaz Çetiner, Metin Mert İlgün, Emine Birci, Gizemnur Yıldız Uysal, Özcan Hatipoğlu, Ehsan Tuzcuoğlu, Gökhan Sır

Abstract:

Water scarcity is an unavoidable issue impacting an increasing number of individuals daily, representing a global crisis stemming from swift population growth, urbanization, and excessive resource exploitation. Consequently, solutions that involve the reclamation of wastewater are considered essential. In this context, household wastewater, categorized as greywater, plays a significant role in freshwater used for residential purposes and is attributed to washing. This type of wastewater comprises diverse elements, including organic substances, soaps, detergents, solvents, biological components, and inorganic elements such as certain metal ions and particles. The physical characteristics of wastewater vary depending on its source, whether commercial, domestic, or from a hospital setting. Consequently, the treatment strategy for this wastewater type necessitates comprehensive investigation and appropriate handling. The advanced oxidation process (AOP) emerges as a promising technique associated with the generation of reactive hydroxyl radicals highly effective in oxidizing organic pollutants. This method takes precedence over others like coagulation, flocculation, sedimentation, and filtration due to its avoidance of undesirable by-products. In the current study, the focus was on exploring the feasibility of the AOP for treating actual household wastewater. To achieve this, a laboratory-scale device was designed to effectively target the formed radicals toward organic pollutants, resulting in lower organic compounds in wastewater. Then, the number of microorganisms present in treated wastewater, in addition to the chemical content of the water, was analyzed to determine whether the lab-scale device eliminates microbial accumulation with AOP. This was also an important parameter since microbes can indirectly affect human health and machine hygiene. To do this, water samples were taken from treated and untreated conditions and then inoculated on general purpose agar to track down the total plate count. Analysis showed that AOP might be an option to treat household wastewater and lower microorganism growth.

Keywords: usage of household water, advanced oxidation process, water reuse, modelling

Procedia PDF Downloads 50