Search results for: neural machine translation (NMT)

Authors: Uraib Sharaha, Guy Beck, Joseph Kapelushnik, Adam H. Agbaria, Itshak Lapidot, Shaul Mordechai, Ahmad Salman, Mahmoud Huleihel

Abstract:

Infectious diseases cause a significant burden on the public health and the economic stability of societies all over the world for several centuries. A reliable detection of the causative agent of infection is not possible based on clinical features, since some of these infections have similar symptoms, including fever, sneezing, inflammation, vomiting, diarrhea, and fatigue. Moreover, physicians usually encounter difficulties in distinguishing between viral and bacterial infections based on symptoms. Therefore, there is an ongoing need for sensitive, specific, and rapid methods for identification of the etiology of the infection. This intricate issue perplex doctors and researchers since it has serious repercussions. In this study, we evaluated the potential of the mid-infrared spectroscopic method for rapid and reliable identification of bacterial and viral infections based on simple peripheral blood samples. Fourier transform infrared (FTIR) spectroscopy is considered a successful diagnostic method in the biological and medical fields. Many studies confirmed the great potential of the combination of FTIR spectroscopy and machine learning as a powerful diagnostic tool in medicine since it is a very sensitive method, which can detect and monitor the molecular and biochemical changes in biological samples. We believed that this method would play a major role in improving the health situation, raising the level of health in the community, and reducing the economic burdens in the health sector resulting from the indiscriminate use of antibiotics. We collected peripheral blood samples from young 364 patients, of which 93 were controls, 126 had bacterial infections, and 145 had viral infections, with ages lower than18 years old, limited to those who were diagnosed with fever-producing illness. Our preliminary results showed that it is possible to determine the infectious agent with high success rates of 82% for sensitivity and 80% for specificity, based on the WBC data.

Keywords: infectious diseases, (FTIR) spectroscopy, viral infections, bacterial infections.

Procedia PDF Downloads 110

Authors: Pascale Brasseur, Binu Gurung, Nicholas Halfpenny, James Eaton

Abstract:

Development of minimally invasive treatments in recent years provides a potential alternative to invasive surgical interventions which are of limited value to patients with spinal metastases due to short life expectancy. A systematic review was conducted to explore the efficacy and safety of radiofrequency ablation (RFA), a minimally invasive treatment in patients with spinal metastases. EMBASE, Medline and CENTRAL were searched from database inception to March 2017 for randomised controlled trials (RCTs) and non-randomised studies. Conference proceedings for ASCO and ESMO published in 2015 and 2016 were also searched. Fourteen studies were included: three prospective interventional studies, four prospective case series and seven retrospective case series. No RCTs or studies comparing RFA with another treatment were identified. RFA was followed by cement augmentation in all patients in seven studies and some patients (40-96%) in the remaining seven studies. Efficacy was assessed as pain relief in 13/14 studies with the use of a numerical rating scale (NRS) or a visual analogue scale (VAS) at various time points. Ten of the 13 studies reported a significant decrease in pain outcome, post-RFA compared to baseline. NRS scores improved significantly at 1 week (5.9 to 3.5, p < 0.0001; 8 to 4.3, p < 0.02 and 8 to 3.9, p < 0.0001) and this improvement was maintained at 1 month post-RFA compared to baseline (5.9 to 2.6, p < 0.0001; 8 to 2.9, p < 0.0003; 8 to 2.9, p < 0.0001). Similarly, VAS scores decreased significantly at 1 week (7.5 to 2.7, p=0.00005; 7.51 to 1.73, p < 0.0001; 7.82 to 2.82, p < 0.001) and this pattern was maintained at 1 month post-RFA compared to baseline (7.51 to 2.25, p < 0.0001; 7.82 to 3.3; p < 0.001). A significant pain relief was achieved regardless of whether patients had cement augmentation in two studies assessing the impact of RFA with or without cement augmentation on VAS pain scores. In these two studies, a significant decrease in pain scores was reported for patients receiving RFA alone and RFA+cement at 1 week (4.3 to 1.7. p=0.0004 and 6.6 to 1.7, p=0.003 respectively) and 15-36 months (7.9 to 4, p=0.008 and 7.6 to 3.5, p=0.005 respectively) after therapy. Few minor complications were reported and these included neural damage, radicular pain, vertebroplasty leakage and lower limb pain/numbness. In conclusion, the efficacy and safety of RFA were consistently positive between prospective and retrospective studies with reductions in pain and few procedural complications. However, the lack of control groups in the identified studies indicates the possibility of selection bias inherent in single arm studies. Controlled trials exploring efficacy and safety of RFA in patients with spinal metastases are warranted to provide robust evidence. The identified studies provide an initial foundation for such future trials.

Keywords: pain relief, radiofrequency ablation, spinal metastases, systematic review

Procedia PDF Downloads 150

Authors: Addin Osman, Anwar Ali Yahya, Mohammed Basit Kamal

Abstract:

Datasets or collections are becoming important assets by themselves and now they can be accepted as a primary intellectual output of a research. The quality and usage of the datasets depend mainly on the context under which they have been collected, processed, analyzed, validated, and interpreted. This paper aims to present a collection of program educational objectives mapped to student’s outcomes collected from self-study reports prepared by 32 engineering programs accredited by ABET. The manual mapping (classification) of this data is a notoriously tedious, time consuming process. In addition, it requires experts in the area, which are mostly not available. It has been shown the operational settings under which the collection has been produced. The collection has been cleansed, preprocessed, some features have been selected and preliminary exploratory data analysis has been performed so as to illustrate the properties and usefulness of the collection. At the end, the collection has been benchmarked using nine of the most widely used supervised multiclass classification techniques (Binary Relevance, Label Powerset, Classifier Chains, Pruned Sets, Random k-label sets, Ensemble of Classifier Chains, Ensemble of Pruned Sets, Multi-Label k-Nearest Neighbors and Back-Propagation Multi-Label Learning). The techniques have been compared to each other using five well-known measurements (Accuracy, Hamming Loss, Micro-F, Macro-F, and Macro-F). The Ensemble of Classifier Chains and Ensemble of Pruned Sets have achieved encouraging performance compared to other experimented multi-label classification methods. The Classifier Chains method has shown the worst performance. To recap, the benchmark has achieved promising results by utilizing preliminary exploratory data analysis performed on the collection, proposing new trends for research and providing a baseline for future studies.

Keywords: ABET, accreditation, benchmark collection, machine learning, program educational objectives, student outcomes, supervised multi-class classification, text mining

Procedia PDF Downloads 147

Authors: Fausto Morais

Abstract:

Artificial intelligence has been widely used in law. Programs are able to classify suits, to identify decision-making patterns, to predict outcomes, and to formalize legal arguments as well. In Brazil, the artificial intelligence victor has been classifying cases to supreme court’s standards. When those programs act doing those tasks, they simulate some kind of legal decision and legal arguments, raising doubts about how artificial intelligence can be integrated into legal reasoning. Taking this into account, the following three issues are identified; the problem of hypernormatization, the argument of legal anthropocentrism, and the artificial legal principles. Hypernormatization can be seen in the Brazilian legal context in the Supreme Court’s usage of the Victor program. This program generated efficiency and consistency. On the other hand, there is a feasible risk of over standardizing factual and normative legal features. Then legal clerks and programmers should work together to develop an adequate way to model legal language into computational code. If this is possible, intelligent programs may enact legal decisions in easy cases automatically cases, and, in this picture, the legal anthropocentrism argument takes place. Such an argument argues that just humans beings should enact legal decisions. This is so because human beings have a conscience, free will, and self unity. In spite of that, it is possible to argue against the anthropocentrism argument and to show how intelligent programs may work overcoming human beings' problems like misleading cognition, emotions, and lack of memory. In this way, intelligent machines could be able to pass legal decisions automatically by classification, as Victor in Brazil does, because they are binding by legal patterns and should not deviate from them. Notwithstanding, artificial intelligent programs can be helpful beyond easy cases. In hard cases, they are able to identify legal standards and legal arguments by using machine learning. For that, a dataset of legal decisions regarding a particular matter must be available, which is a reality in Brazilian Judiciary. Doing such procedure, artificial intelligent programs can support a human decision in hard cases, providing legal standards and arguments based on empirical evidence. Those legal features claim an argumentative weight in legal reasoning and should serve as references for judges when they must decide to maintain or overcome a legal standard.

Keywords: artificial intelligence, artificial legal principles, hypernormatization, legal anthropocentrism argument, legal reasoning

Procedia PDF Downloads 121

Authors: Deog-Gyu Seo, Jin-Soo Ahn

Abstract:

Objectives: Recently, the development of adhesive primers on stable bonding between zirconia and resin cement has been on the increase. The bond strength of zirconia-resin cement can be effectively increased with the treatment of primer composed of the adhesive monomer that can chemically bond with the oxide layer, which forms on the surface of zirconia. 10-methacryloyloxydecyl dihydrogen phosphate (10-MDP) that contains phosphate ester and acidic monomer 4-methacryloxyethyl trimellitic anhydride(4-META) have been suggested as monomers that can form chemical bond with the surface oxide layer of zirconia. Also, these suggested monomers have proved to be effective zirconia surface treatment for bonding to resin cement. The purpose of this study is to evaluate the effects of primer treatment on the bond strength of Zirconia-resin cement by using three different kinds of primers on the market. Methods: Zirconia blocks were prepared into 60 disk-shaped specimens by using a diamond saw. Specimens were divided into four different groups: first three groups were treated with zirconiaLiner(Sun Medical Co., Ltd., Furutaka-cho, Moriyama, Shiga, Japan), Alloy primer (Kuraray Noritake Dental Inc., Sakaju, Kurashiki, Okayama, Japan), and Universal primer (Tokuyama dental Corp., Taitou, Taitou-ku, Tokyo, Japan) respectively. The last group was the control with no surface treatment. Dual cured resin cement (Biscem, Bisco Inc., Schaumburg, IL, USA) was luted to each group of specimens. And then, shear bond strengths were measured by universal tesing machine. The significance of the result was statistically analyzed by one-way ANOVA and Tukey test. The failure sites in each group were inspected under a magnifier. Results: Mean shear bond strength were 0.60, 1.39, 1.03, 1.38 MPa for control, Zirconia Liner (ZL), Alloy primer (AP), Universal primer (UP), respectively. Groups with application of each of the three primers showed significantly higher shear bond strength compared to the control group (p < 0.05). Among the three groups with the treatment, ZL and UP showed significantly higher shear bond strength than AP (p < 0.05), and there were no significant differences in mean shear bond strength between ZL and UP (p < 0.05). While the most specimens of control groups showed adhesive failure (80%), the most specimens of three primer-treated groups showed cohesive or mixed failure (80%).

Keywords: primer, resin cement, shear bond strength, zirconia

Procedia PDF Downloads 178

Authors: E. Nakamachi, K. Matsumoto, K. Yamamoto, Y. Morita, H. Sakamoto

Abstract:

In recently, electromagnetic and mechanical stimulations have been recognized as the effective extracellular environment stimulation technique to enhance the defected peripheral nerve tissue regeneration. In this study, we developed a new hybrid bioreactor by adopting 50 Hz uniform alternative current (AC) magnetic stimulation and 4% strain mechanical stimulation. The guide tube for nerve regeneration is mesh structured tube made of biodegradable polymer, such as polylatic acid (PLA). However, when neural damage is large, there is a possibility that peripheral nerve undergoes necrosis. So it is quite important to accelerate the nerve tissue regeneration by achieving enhancement of nerve axonal extension rate. Therefore, we try to design and fabricate the system that can simultaneously load the uniform AC magnetic field stimulation and the stretch stimulation to cells for enhancement of nerve axonal extension. Next, we evaluated systems performance and the effectiveness of each stimulation for rat adrenal pheochromocytoma cells (PC12). First, we designed and fabricated the uniform AC magnetic field system and the stretch stimulation system. For the AC magnetic stimulation system, we focused on the use of pole piece structure to carry out in-situ microscopic observation. We designed an optimum pole piece structure using the magnetic field finite element analyses and the response surface methodology. We fabricated the uniform AC magnetic field stimulation system as a bio-reactor by adopting analytically determined design specifications. We measured magnetic flux density that is generated by the uniform AC magnetic field stimulation system. We confirmed that measurement values show good agreement with analytical results, where the uniform magnetic field was observed. Second, we fabricated the cyclic stretch stimulation device under the conditions of particular strains, where the chamber was made of polyoxymethylene (POM). We measured strains in the PC12 cell culture region to confirm the uniform strain. We found slightly different values from the target strain. Finally, we concluded that these differences were allowable in this mechanical stimulation system. We evaluated the effectiveness of each stimulation to enhance the nerve axonal extension using PC12. We confirmed that the average axonal extension length of PC12 under the uniform AC magnetic stimulation was increased by 16 % at 96 h in our bio-reactor. We could not confirm that the axonal extension enhancement under the stretch stimulation condition, where we found the exfoliating of cells. Further, the hybrid stimulation enhanced the axonal extension. Because the magnetic stimulation inhibits the exfoliating of cells. Finally, we concluded that the enhancement of PC12 axonal extension is due to the magnetic stimulation rather than the mechanical stimulation. Finally, we confirmed that the effectiveness of the uniform AC magnetic field stimulation for the nerve axonal extension using PC12 cells.

Keywords: nerve cell PC12, axonal extension, nerve regeneration, electromagnetic-mechanical stimulation, bioreactor

Procedia PDF Downloads 240

Authors: Nupur Karmaker, Hasin Aupama Azhari, Abdul Al Mortuza, Abhijit Chanda, Golam Abu Zakaria

Abstract:

Purpose: The purpose of gait analysis is to determine the biomechanics of the joint, phases of gait cycle, graphical and analytical analysis of degree of rotation, analysis of the electrical activity of muscles and force exerted on the hip joint at different locomotion during walking, running and cart pulling. Methods and Materials: Visual gait analysis and electromyography method has been used to detect the degree of rotation of joints and electrical activity of muscles. In cinematography method an object is observed from different sides and takes its video. Cart pulling length has been divided into frames with respect to time by using video splitter software. Phases of gait cycle, degree of rotation of joints, EMG profile and force analysis during walking and running has been taken from different papers. Gait cycle and degree of rotation of joints during cart pulling has been prepared by using video camera, stop watch, video splitter software and Microsoft Excel. Results and Discussion: During the cart pulling the force exerted on hip is the resultant of various forces. The force on hip is the vector sum of the force Fg= mg, due the body of weight of the person and Fa= ma, due to the velocity. Maximum stance phase shows during cart pulling and minimum shows during running. During cart pulling shows maximum degree of rotation of hip joint, knee: running, and ankle: cart pulling. During walking, it has been observed minimum degree of rotation of hip, ankle: during running. During cart pulling, dynamic force depends on the walking velocity, body weight and load weight. Conclusions: 80% people suffer gait related disease with increasing their age. Proper care should take during cart pulling. It will be better to establish the gait laboratory to determine the gait related diseases. If the way of cart pulling is changed i.e the design of cart pulling machine, load bearing system is changed then it would possible to reduce the risk of limb loss, flat foot syndrome and varicose vein in lower limb.

Keywords: kinematic, gait, gait lab, phase, force analysis

Procedia PDF Downloads 555

Authors: Monica Gonzalez Machorro

Abstract:

Dementia is hard to diagnose because of the lack of early physical symptoms. Early dementia recognition is key to improving the living condition of patients. Speech technology is considered a valuable biomarker for this challenge. Recent works have utilized conventional acoustic features and machine learning methods to detect dementia in speech. BERT-like classifiers have reported the most promising performance. One constraint, nonetheless, is that these studies are either based on human transcripts or on transcripts produced by automatic speech recognition (ASR) systems. This research contribution is to explore a method that does not require transcriptions to detect early Alzheimer’s disease (AD) and mild cognitive impairment (MCI). This is achieved by fine-tuning a pre-trained ASR model for the downstream early AD and MCI tasks. To do so, a subset of the thoroughly studied Pitt Corpus is customized. The subset is balanced for class, age, and gender. Data processing also involves cropping the samples into 10-second segments. For comparison purposes, a baseline model is defined by training and testing a Random Forest with 20 extracted acoustic features using the librosa library implemented in Python. These are: zero-crossing rate, MFCCs, spectral bandwidth, spectral centroid, root mean square, and short-time Fourier transform. The baseline model achieved a 58% accuracy. To fine-tune HuBERT as a classifier, an average pooling strategy is employed to merge the 3D representations from audio into 2D representations, and a linear layer is added. The pre-trained model used is ‘hubert-large-ls960-ft’. Empirically, the number of epochs selected is 5, and the batch size defined is 1. Experiments show that our proposed method reaches a 69% balanced accuracy. This suggests that the linguistic and speech information encoded in the self-supervised ASR-based model is able to learn acoustic cues of AD and MCI.

Keywords: automatic speech recognition, early Alzheimer’s recognition, mild cognitive impairment, speech impairment

Procedia PDF Downloads 101

Authors: Larissa Bolliger, Junoš Lukan, Mitja Lustrek, Dirk De Bacquer, Els Clays

Abstract:

Introduction and Aim: Chronic workplace stress and its health-related consequences like mental and cardiovascular diseases have been widely investigated. This project focuses on the sources and context of psychosocial daily workplace stress in a real-world setting. The main objective is to analyze and model real-time relationships between (1) psychosocial stress experiences within the natural work environment, (2) micro-level work activities and events, and (3) physiological signals and behaviors in office workers. Methods: An Ecological Momentary Assessment (EMA) protocol has been developed, partly building on machine learning techniques. Empatica® wristbands will be used for real-life detection of stress from physiological signals; micro-level activities and events at work will be based on smartphone registrations, further processed according to an automated computer algorithm. A field study including 100 office-based workers with high-level problem-solving tasks like managers and researchers will be implemented in Slovenia and Belgium (50 in each country). Data mining and state-of-the-art statistical methods – mainly multilevel statistical modelling for repeated data – will be used. Expected Results and Impact: The project findings will provide novel contributions to the field of occupational health research. While traditional assessments provide information about global perceived state of chronic stress exposure, the EMA approach is expected to bring new insights about daily fluctuating work stress experiences, especially micro-level events and activities at work that induce acute physiological stress responses. The project is therefore likely to generate further evidence on relevant stressors in a real-time working environment and hence make it possible to advise on workplace procedures and policies for reducing stress.

Keywords: ecological momentary assessment, real-time, stress, work

Procedia PDF Downloads 135

Authors: Fatih Frank Alparslan

Abstract:

The aviation industry is at a crucial turning point due to modern technologies, environmental concerns, and changing ways of transporting people and goods globally. The paper examines these challenges and opportunities comprehensively. It emphasizes the role of innovative management and advanced technology in shaping the future of air travel. This study begins with an overview of the current state of the aviation industry, identifying key areas where innovation and technology could be highly beneficial. It explores the latest advancements in airplane design, propulsion, and materials. These technological advancements are shown to enhance aircraft performance and environmental sustainability. The paper also discusses the use of artificial intelligence and machine learning in improving air traffic control, enhancing safety, and making flight operations more efficient. The management of these technologies is critically important. Therefore, the research delves into necessary changes in organization, culture, and operations to support innovation. It proposes a management approach that aligns with these modern technologies, underlining the importance of forward-thinking leaders who collaborate across disciplines and embrace innovative ideas. The paper addresses challenges in adopting these innovations, such as regulatory barriers, the need for industry-wide standards, and the impact of technological changes on jobs and society. It recommends that governments, aviation businesses, and educational institutions collaborate to address these challenges effectively, paving the way for a more innovative and eco-friendly aviation industry. In conclusion, the paper argues that the future of aviation relies on integrating new management practices with innovative technologies. It urges a collective effort to push beyond current capabilities, envisioning an aviation industry that is safer, more efficient, and environmentally responsible. By adopting a broad approach, this research contributes to the ongoing discussion about resolving the complex issues facing today's aviation sector, offering insights and guidance to prepare for future advancements.

Keywords: aviation innovation, technology integration, environmental sustainability, management strategies, multidisciplinary approach

Procedia PDF Downloads 19

Authors: L. Vivet, L. Benabou, O. Simon

Abstract:

With highly demanding applications in the field of power electronics, there is an increasing need to have interconnection materials with properties that can ensure both good mechanical assembly and high thermal/electrical conductivities. So far, lead-free solders have been considered an attractive solution, but recently, sintered joints based on nano-silver paste have been used for die attach and have proved to be a promising solution offering increased performances in high-temperature applications. In this work, the main parameters of the bonding process using silver oxalates are studied, i.e., the heating rate and the bonding pressure mainly. Their effects on both the mechanical and thermal properties of the sintered layer are evaluated following an experimental design. Pairs of copper substrates with gold metallization are assembled through the sintering process to realize the samples that are tested using a micro-traction machine. In addition, the obtained joints are examined through microscopy to identify the important microstructural features in relation to the measured properties. The formation of an intermetallic compound at the junction between the sintered silver layer and the gold metallization deposited on copper is also analyzed. Microscopy analysis exhibits a nanoporous structure of the sintered material. It is found that higher temperature and bonding pressure result in higher densification of the sintered material, with higher thermal conductivity of the joint but less mechanical flexibility to accommodate the thermo-mechanical stresses arising during service. The experimental design allows hence the determination of the optimal process parameters to reach sufficient thermal/mechanical properties for a given application. It is also found that the interphase formed between silver and gold metallization is the location where the fracture occurred after the mechanical testing, suggesting that the inter-diffusion mechanism between the different elements of the assembly leads to the formation of a relatively brittle compound.

Keywords: nanoporous structure, silver oxalate, sintering, mechanical strength, thermal conductivity, microelectronic packaging

Procedia PDF Downloads 75

Authors: Kougioumtzis Konstantin, Rylander Pär, Karlsteen Magnus

Abstract:

Ball skills as a subset of fundamental motor skills are predictors for performance in sports. Currently, most tools evaluate ball skills utilizing subjective ratings. The aim of this study was to examine the psychometric properties of a newly developed instrument to objectively measure ball handling skills (BHS-test) utilizing digital instrument. Participants were a convenience sample of 213 adolescents (age M = 17.1 years, SD =3.6; 55% females, 45% males) recruited from upper secondary schools and invited to a sports hall for the assessment. The 8-item instrument incorporated both accuracy-based ball skill tests and repetitive-performance tests with a ball. Testers counted performance manually in the four tests (one throwing and three juggling tasks). Furthermore, assessment was technologically enhanced in the other four tests utilizing a ball machine, a Kinect camera and balls with motion sensors (one balancing and three rolling tasks). 3D printing technology was used to construct equipment, while all results were administered digitally with smart phones/tablets, computers and a specially constructed application to send data to a server. The instrument was deemed reliable (α = .77) and principal component analysis was used in a random subset (53 of the participants). Furthermore, latent variable modeling was employed to confirm the structure with the remaining subset (160 of the participants). The analysis showed good factorial-related validity with one factor explaining 57.90 % of the total variance. Four loadings were larger than .80, two more exceeded .76 and the other two were .65 and .49. The one factor solution was confirmed by a first order model with one general factor and an excellent fit between model and data (χ² = 16.12, DF = 20; RMSEA = .00, CI90 .00–.05; CFI = 1.00; SRMR = .02). The loadings on the general factor ranged between .65 and .83. Our findings indicate good reliability and construct validity for the BHS-test. To develop the instrument further, more studies are needed with various age-groups, e.g. children. We suggest using the BHS-test for diagnostic or assessment purpose for talent development and sports participation interventions that focus on ball games.

Keywords: ball-handling skills, ball-handling ability, technologically-enhanced measurements, assessment

Procedia PDF Downloads 64

Authors: Yuta Nakano, Kozo Kajiwara, Atsushi Hori, Takeshi Fujita

Abstract:

In association with the wave of electric vehicles (EV), low energy consumption systems have become more and more important. One of the key technologies to realize low energy consumption is a dynamic vision sensor (DVS), or we can call it an event sensor, neuromorphic vision sensor and so on. This sensor has several features, such as high temporal resolution, which can achieve 1 Mframe/s, and a high dynamic range (120 DB). However, the point that can contribute to low energy consumption the most is its sparsity; to be more specific, this sensor only captures the pixels that have intensity change. In other words, there is no signal in the area that does not have any intensity change. That is to say, this sensor is more energy efficient than conventional sensors such as RGB cameras because we can remove redundant data. On the other side of the advantages, it is difficult to handle the data because the data format is completely different from RGB image; for example, acquired signals are asynchronous and sparse, and each signal is composed of x-y coordinate, polarity (two values: +1 or -1) and time stamp, it does not include intensity such as RGB values. Therefore, as we cannot use existing algorithms straightforwardly, we have to design a new processing algorithm to cope with DVS data. In order to solve difficulties caused by data format differences, most of the prior arts make a frame data and feed it to deep learning such as Convolutional Neural Networks (CNN) for object detection and recognition purposes. However, even though we can feed the data, it is still difficult to achieve good performance due to a lack of intensity information. Although polarity is often used as intensity instead of RGB pixel value, it is apparent that polarity information is not rich enough. Considering this context, we proposed to use the timestamp information as a data representation that is fed to deep learning. Concretely, at first, we also make frame data divided by a certain time period, then give intensity value in response to the timestamp in each frame; for example, a high value is given on a recent signal. We expected that this data representation could capture the features, especially of moving objects, because timestamp represents the movement direction and speed. By using this proposal method, we made our own dataset by DVS fixed on a parked car to develop an application for a surveillance system that can detect persons around the car. We think DVS is one of the ideal sensors for surveillance purposes because this sensor can run for a long time with low energy consumption in a NOT dynamic situation. For comparison purposes, we reproduced state of the art method as a benchmark, which makes frames the same as us and feeds polarity information to CNN. Then, we measured the object detection performances of the benchmark and ours on the same dataset. As a result, our method achieved a maximum of 7 points greater than the benchmark in the F1 score.

Keywords: event camera, dynamic vision sensor, deep learning, data representation, object recognition, low energy consumption

Procedia PDF Downloads 71

Authors: Moshe Wasserblat, Jonathan Mamou, Oren Pereg

Abstract:

Natural Language Processing (NLP) has made a major leap in the last few years, in practical integration into medical solutions; for example, extracting clinical concepts from medical texts such as medical condition, medication, treatment, and symptoms. However, training and deploying those models in real environments still demands a large amount of annotated data and NLP/Machine Learning (ML) expertise, which makes this process costly and time-consuming. We present a practical and efficient method for clinical concept extraction that does not require costly labeled data nor ML expertise. The method includes three steps: Step 1- the user injects a large in-domain text corpus (e.g., PubMed). Then, the system builds a contextual model containing vector representations of concepts in the corpus, in an unsupervised manner (e.g., Phrase2Vec). Step 2- the user provides a seed set of terms representing a specific medical concept (e.g., for the concept of the symptoms, the user may provide: ‘dry mouth,’ ‘itchy skin,’ and ‘blurred vision’). Then, the system matches the seed set against the contextual model and extracts the most semantically similar terms (e.g., additional symptoms). The result is a complete set of terms related to the medical concept. Step 3 –in production, there is a need to extract medical concepts from the unseen medical text. The system extracts key-phrases from the new text, then matches them against the complete set of terms from step 2, and the most semantically similar will be annotated with the same medical concept category. As an example, the seed symptom concepts would result in the following annotation: “The patient complaints on fatigue [symptom], dry skin [symptom], and Weight loss [symptom], which can be an early sign for Diabetes.” Our evaluations show promising results for extracting concepts from medical corpora. The method allows medical analysts to easily and efficiently build taxonomies (in step 2) representing their domain-specific concepts, and automatically annotate a large number of texts (in step 3) for classification/summarization of medical reports.

Keywords: clinical concepts, concept expansion, medical records annotation, medical records summarization

Procedia PDF Downloads 109

Authors: R. Hellmuth

Abstract:

The orientation of flexibility and adaptability with regard to factory planning is at machine and process level. Factory buildings are not the focus of current research. Factory planning has the task of designing products, plants, processes, organization, areas and the construction of a factory. The adaptability of a factory can be divided into three types: spatial, organizational and technical adaptability. Spatial adaptability indicates the ability to expand and reduce the size of a factory. Here, the area-related breathing capacity plays the essential role. It mainly concerns the factory site, the plant layout and the production layout. The organizational ability to change enables the change and adaptation of organizational structures and processes. This includes structural and process organization as well as logistical processes and principles. New and reconfigurable operating resources, processes and factory buildings are referred to as technical adaptability. These three types of adaptability can be regarded independently of each other as undirected potentials of different characteristics. If there is a need for change, the types of changeability in the change process are combined to form a directed, complementary variable that makes change possible. When planning adaptability, importance must be attached to a balance between the types of adaptability. The vision of the intelligent factory building and the 'Internet of Things' presupposes the comprehensive digitalization of the spatial and technical environment. Through connectivity, the factory building must be empowered to support a company's value creation process by providing media such as light, electricity, heat, refrigeration, etc. In the future, communication with the surrounding factory building will take place on a digital or automated basis. In the area of industry 4.0, the function of the building envelope belongs to secondary or even tertiary processes, but these processes must also be included in the communication cycle. An integrative view of a continuous communication of primary, secondary and tertiary processes is currently not yet available and is being developed with the aid of methods in this research work. A comparison of the digital twin from the point of view of production and the factory building will be developed. Subsequently, a tool will be elaborated to classify digital twins from the perspective of data, degree of visualization, and the trades. Thus a contribution is made to better integrate the secondary and tertiary processes in a factory into the added value.

Keywords: adaptability, digital factory twin, factory planning, industry 4.0

Procedia PDF Downloads 133

Authors: Dhouibi Mohamed, Stirbu Bogdan, Chabotier André, Pirlot Marc

Abstract:

Effects of erosion and wear on the performance of small caliber guns have been analyzed throughout numerical and experimental studies. Mainly, qualitative observations were performed. Correlations between the volume change of the chamber and the maximum pressure are limited. This paper focuses on the development of a numerical model to predict the maximum pressure evolution when the interior shape of the chamber changes in the different weapon’s life phases. To fulfill this goal, an experimental campaign, followed by a numerical simulation study, is carried out. Two test barrels, « 5.56x45mm NATO » and « 7.62x51mm NATO,» are considered. First, a Coordinate Measuring Machine (CMM) with a contact scanning probe is used to measure the interior profile of the barrels after each 300-shots cycle until their worn out. Simultaneously, the EPVAT (Electronic Pressure Velocity and Action Time) method with a special WEIBEL radar are used to measure: (i) the chamber pressure, (ii) the action time, (iii) and the bullet velocity in each barrel. Second, a numerical simulation study is carried out. Thus, a coupled interior ballistic model is developed using the dynamic finite element program LS-DYNA. In this work, two different models are elaborated: (i) coupled Eularien Lagrangian method using fluid-structure interaction (FSI) techniques and a coupled thermo-mechanical finite element using a lumped parameter model (LPM) as a subroutine. Those numerical models are validated and checked through three experimental results, such as (i) the muzzle velocity, (ii) the chamber pressure, and (iii) the surface morphology of fired projectiles. Results show a good agreement between experiments and numerical simulations. Next, a comparison between the two models is conducted. The projectile motions, the dynamic engraving resistances and the maximum pressures are compared and analyzed. Finally, using this obtained database, a statistical correlation between the muzzle velocity, the maximum pressure and the chamber volume is established.

Keywords: engraving process, finite element analysis, gun barrel erosion, interior ballistics, statistical correlation

Procedia PDF Downloads 186

Authors: Bharath Anantharamaiah, Tomas Bouda, Elke Deckers, Stijn Jonckheere, Wim Desmet, Juan J. Garcia

Abstract:

Automotive tyres are gaining importance recently in terms of their noise emission, not only with respect to reduction in noise, but also their perception and detection. Tyres exhibit a mechanical noise generation mechanism up to 1 kHz. However, owing to the fact that tyre is a composite of several materials, it has been difficult to model it using finite elements to predict noise at high frequencies. The currently available FE models have a reliability of about 500 Hz, the limit which, however, is not enough to perceive the roughness or sharpness of noise from tyre. These noise components are important in order to alert pedestrians on the street about passing by slow, especially electric vehicles. In order to model tyre noise behaviour up to 1 kHz, its dynamic behaviour must be accurately developed up to a 1 kHz limit using finite elements. Materials play a vital role in modelling the dynamic tyre behaviour precisely. Since tyre is a composition of several components, their precise definition in finite element simulations is necessary. However, during the tyre manufacturing process, these components are subjected to various pressures and temperatures, due to which these properties could change. Hence, material definitions are better described based on the tyre responses. In this work, the hyperelasticity of tyre component rubbers is calibrated, using the design of experiments technique from the tyre characteristic responses that are measured on a stiffness measurement machine. The viscoelasticity of rubbers are defined by the Prony series for rubbers, which are determined from the loss factor relationship between the loss and storage moduli, assuming that the rubbers are excited within the linear viscoelasticity ranges. These values of loss factor are measured and theoretically expressed as a function of rubber shore hardness or hyperelasticities. From the results of the work, there exists a good correlation between test and simulation vibrational transfer function up to 1 kHz. The model also allows flexibility, i.e., the frequency limit can also be extended, if required, by calibrating the Prony parameters of rubbers corresponding to the frequency of interest. As future work, these tyre models are used for noise generation at high frequencies and thus for tyre noise perception.

Keywords: tyre dynamics, rubber materials, prony series, hyperelasticity

Procedia PDF Downloads 169

Authors: Zahid Ullah, Atlas Khan

Abstract:

This abstract focuses on the advancements in mathematical modeling and optimization techniques that play a crucial role in enhancing the efficiency, reliability, and performance of these systems. In this era of rapidly evolving technology, mathematical modeling and optimization offer powerful tools to tackle the complex challenges faced by control, signal processing, and energy systems. This abstract presents the latest research and developments in mathematical methodologies, encompassing areas such as control theory, system identification, signal processing algorithms, and energy optimization. The abstract highlights the interdisciplinary nature of mathematical modeling and optimization, showcasing their applications in a wide range of domains, including power systems, communication networks, industrial automation, and renewable energy. It explores key mathematical techniques, such as linear and nonlinear programming, convex optimization, stochastic modeling, and numerical algorithms, that enable the design, analysis, and optimization of complex control and signal processing systems. Furthermore, the abstract emphasizes the importance of addressing real-world challenges in control, signal processing, and energy systems through innovative mathematical approaches. It discusses the integration of mathematical models with data-driven approaches, machine learning, and artificial intelligence to enhance system performance, adaptability, and decision-making capabilities. The abstract also underscores the significance of bridging the gap between theoretical advancements and practical applications. It recognizes the need for practical implementation of mathematical models and optimization algorithms in real-world systems, considering factors such as scalability, computational efficiency, and robustness. In summary, this abstract showcases the advancements in mathematical modeling and optimization techniques for control, signal processing, and energy systems. It highlights the interdisciplinary nature of these techniques, their applications across various domains, and their potential to address real-world challenges. The abstract emphasizes the importance of practical implementation and integration with emerging technologies to drive innovation and improve the performance of control, signal processing, and energy.

Keywords: mathematical modeling, optimization, control systems, signal processing, energy systems, interdisciplinary applications, system identification, numerical algorithms

Procedia PDF Downloads 87

Authors: Timine Suoware, Sylvester Edelugo, Charles Amgbari

Abstract:

The susceptibility of natural fibre polymer composites to flame has necessitated research to improve and develop flame retardant (FR) to delay the escape of combustible volatiles. Previous approaches relied mostly on FR such as aluminium tri-hydroxide (ATH) and ammonium polyphosphate (APP) to improve fire performances of wood sawdust polymer composites (WSPC) with emphasis on non-structural building applications. In this paper, APP was modified with gum Arabic powder (GAP) and then hybridized with ATH at 0, 12 and 18% loading ratio to form new FR species; WSPC12%APP-GAP and WSPC18%ATH/APP-GAP. The FR species were incorporated in wood sawdust waste reinforced in polyester resin to form panels for fireproof doors. The panels were produced using hand lay compression moulding technique and cured at room temperature. Specimen cut from panels were then tested for tensile strength (TS), flexural strength (FS) and impact strength (IS) using universal testing machine and impact tester; thermal stability using (TGA/DSC 1: Metler Toledo); time-to-ignition (Tig), heat release rates (HRR); peak HRR (HRRp), average HRR (HRRavg), total HRR (THR), peak mass loss rate (MLRp), average smoke production rate (SPRavg) and carbon monoxide production (COP ) were obtained using the cone calorimeter apparatus. From the mechanical properties obtained, improvements of IS for the panels were not noticeable whereas TS and FS for WSPC12%APP-GAP respectively stood at 12.44 MPa and 85.58 MPa more than those without FR (WSPC0%). For WSC18%ATH/APP-GAP TS and FS respectively stood at 16.45 MPa and 50.49 MPa more compared to (WSPC0%). From the thermal analysis, the panels did not exhibit any significant change as early degradation was observed. At 900 OC, the char residues improved by 15% for WSPC12%APP-GAP and 19% for WSPC18%ATH/APP-GAP more than (WSC0%) at 5%, confirming the APP-GAP to be a good FR. At 50 kW/m2 heat flux (HF), WSPC12%APP-GAP improved better the fire behaviour of the panels when compared to WSC0% as follows; Tig = 46 s, HRRp = 56.1 kW/2, HRRavg = 32.8 kW/m2, THR = 66.6 MJ/m2, MLRp = 0.103 g/s, TSR = 0.04 m2/s and COP = 0.051 kg/kg. These were respectively more than WSC0%. It can be concluded that the new concept of modifying FR with GAP in WSC could meet the requirement of a fireproof door for building applications.

Keywords: composite, flame retardant, wood sawdust, fireproof doors

Procedia PDF Downloads 82

Authors: Aphinan Phukaoluan, Surachai Dechkunakorn, Niwat Anuwongnukroh, Anak Khantachawana, Pongpan Kaewtathip, Julathep Kajornchaiyakul, Peerapong Tua-Ngam

Abstract:

Aims: The objectives of this study was to determine the load-deflecting characteristics of a fabricated orthodontic wire with alloy composition of 50.6% (atomic weight) Ni and 49.4% (atomic weight) Ti and to compare the results with Ormco, a commercially available pre-formed NiTi orthodontic archwire. Materials and Methods: The ingots alloys with atomic weight ratio 50.6 Ni: 49.4 Ti alloy were used in this study. Three specimens were cut to have wire dimensions of 0.016 inch x0.022 inch. For comparison, a commercially available pre-formed NiTi archwire, Ormco, with dimensions of 0.016 inch x 0.022 inch was used. Three-point bending tests were performed at the temperature 36+1 °C using a Universal Testing Machine on the newly fabricated and commercial archwires to assess the characteristics of the load-deflection curve with loading and unloading forces. The loading and unloading features at the deflection points 0.25, 0.50, 0.75. 1.0, 1.25, and 1.5 mm were compared. Descriptive statistics was used to evaluate each variables, and independent t-test at p < 0.05 was used to analyze the mean differences between the two groups. Results: The load-deflection curve of the 50.6Ni: 49.4Ti wires exhibited the characteristic features of superelasticity. The curves at the loading and unloading slope of Ormco NiTi archwire were more parallel than the newly fabricated NiTi wires. The average deflection force of the 50.6Ni: 49.4Ti wire was 304.98 g and 208.08 g for loading and unloading, respectively. Similarly, the values were 358.02 g loading and 253.98 g for unloading of Ormco NiTi archwire. The interval difference forces between each deflection points were in the range 20.40-121.38 g and 36.72-92.82 g for the loading and unloading curve of 50.6Ni: 49.4Ti wire, respectively, and 4.08-157.08 g and 14.28-90.78 g for the loading and unloading curve of commercial wire, respectively. The average deflection force of the 50.6Ni: 49.4Ti wire was less than that of Ormco NiTi archwire, which could have been due to variations in the wire dimensions. Although a greater force was required for each deflection point of loading and unloading for the 50.6Ni: 49.4Ti wire as compared to Ormco NiTi archwire, the values were still within the acceptable limits to be clinically used in orthodontic treatment. Conclusion: The 50.6Ni: 49.4Ti wires presented the characteristics of a superelastic orthodontic wire. The loading and unloading force were also suitable for orthodontic tooth movement. These results serve as a suitable foundation for further studies in the development of new orthodontic NiTi archwires.

Keywords: 50.6 ni 49.4 Ti alloy wire, load deflection curve, loading and unloading force, orthodontic

Procedia PDF Downloads 279

Authors: Aschalew C. Workneh, K. S. Hari Prasad, C. S. P. Ojha

Abstract:

The crop water stress index (CWSI) is a cost-effective, non-destructive, and simple technique for tracking the start of crop water stress. This study investigated the feasibility of CWSI derived from canopy temperature to detect the water status of wheat crops. Artificial intelligence (AI) techniques have become increasingly popular in recent years for determining CWSI. In this study, the performance of two AI techniques, adaptive neuro-fuzzy inference system (ANFIS) and self-organizing maps (SOM), are compared while determining the CWSI of paddy crops. Field experiments were conducted for varying irrigation water applications during two seasons in 2022 and 2023 at the irrigation field laboratory at the Civil Engineering Department, Indian Institute of Technology Roorkee, India. The ANFIS and SOM-simulated CWSI values were compared with the experimentally calculated CWSI (EP-CWSI). Multiple regression analysis was used to determine the upper and lower CWSI baselines. The upper CWSI baseline was found to be a function of crop height and wind speed, while the lower CWSI baseline was a function of crop height, air vapor pressure deficit, and wind speed. The performance of ANFIS and SOM were compared based on mean absolute error (MAE), mean bias error (MBE), root mean squared error (RMSE), index of agreement (d), Nash-Sutcliffe efficiency (NSE), and coefficient of correlation (R²). Both models successfully estimated the CWSI of the paddy crop with higher correlation coefficients and lower statistical errors. However, the ANFIS (R²=0.81, NSE=0.73, d=0.94, RMSE=0.04, MAE= 0.00-1.76 and MBE=-2.13-1.32) outperformed the SOM model (R²=0.77, NSE=0.68, d=0.90, RMSE=0.05, MAE= 0.00-2.13 and MBE=-2.29-1.45). Overall, the results suggest that ANFIS is a reliable tool for accurately determining CWSI in wheat crops compared to SOM.

Keywords: adaptive neuro-fuzzy inference system, canopy temperature, crop water stress index, self-organizing map, wheat

Procedia PDF Downloads 30

Authors: Uday Shanker Goel, Vinay Vasant Mahashabde, Biswajit Ghosh, Arvind Jha, Amit Kumar, Sanjay Kumar Patel, Uma Shanker Pattanaik, Vinit Kumar Shah, Chaitanya Bhanu

Abstract:

Pinch rolls of the Hot Mills must possess resistance to wear, thermal stability, high thermal conductivity and through hardness. Conventionally, pinch rolls have been procured either as new ones or refurbished ones. Discarded Work Rolls from the Cold Mill were taken and machined inhouse at Tata Steel to be used subsequently as the bottom pinch rolls of the Hot Mill. The hardness of the scrapped work rolls from CRM is close to 55HRC and the typical composition is ( C - 0.8% , Mn - 0.40 % , Si - 0.40% , Cr - 3.5% , Mo - 0.5% & V - 0.1% ).The Innovation was the use of a roll which would otherwise have been otherwise discarded as scrap. Also, the innovation helped in using the scrapped roll which had better wear and heat resistance. In a conventional Pinch roil (Hardness 50 HRC and typical chemistry - C - 10% , Mo+Co+V+Nb ~ 5 % ) , Pick-up is a condition whereby foreign material becomes adhered to the surface of the pinch roll during service. The foreign material is usually adhered metal from the actual product being rolled. The main attributes of the weld overlay rolls are wear resistance and crack resistance. However, the weld overlay roll has a strong tendency for strip pick-up particularly in the area of bead overlap. However, the greatest disadvantage is the depth of weld deposit, which is less than half of the usable shell thickness in most mills. Because of this, the stainless rolls require re-welding on a routine basis. By providing a significantly cheaper in house and more robust alternative of the existing bottom pinch rolls , this innovation results in significant lower worries for the roll shop. Pinch rolls now don't have to be sent outside Jamshedpur for refurbishment or for procuring new ones. Scrapped rolls from adjacent Cold Mill are procured and sent for machining to our Machine Shop inside Tata Steel works in Jamshedpur. This is far more convenient than the older methodology. The idea is also being deployed to the other hot mills of Tata Steel. Multiple campaigns have been tried out at both down coilers of Hot Strip with significantly lower wear.

Keywords: hot rolling flat, cold mill work roll, hot strip pinch roll, strip surface

Procedia PDF Downloads 87

Authors: Mohammad M. Khan, Gajendra Dixit

Abstract:

Partially lubricated sliding wear behaviour of a zinc-based alloy reinforced with 10wt% SiC particles has been studied as a function of applied load and solid lubricant particle size and has been compared with that of matrix alloy and conventionally used grey cast iron. The wear tests were conducted at the sliding velocities of 2.1m/sec in various partial lubricated conditions using pin on disc machine as per ASTM G-99-05. Base oil (SAE 20W-40) or mixture of the base oil with 5wt% graphite of particle sizes (7-10 µm) and (100 µm) were used for creating lubricated conditions. The matrix alloy revealed primary dendrites of a and eutectoid a + h and Î phases in the Inter dendritic regions. Similar microstructure has been depicted by the composite with an additional presence of the dispersoid SiC particles. In the case of cast iron, flakes of graphite were observed in the matrix; the latter comprised of (majority of) pearlite and (limited quantity of) ferrite. Results show a large improvement in wear resistance of the zinc-based alloy after reinforcement with SiC particles. The cast iron shows intermediate response between the matrix alloy and composite. The solid lubrication improved the wear resistance and friction behaviour of both the reinforced and base alloy. Moreover, minimum wear rate is obtained in oil+ 5wt % graphite (7-10 µm) lubricated environment for the matrix alloy and composite while for cast iron addition of solid lubricant increases the wear rate and minimum wear rate is obtained in case of oil lubricated environment. The cast iron experienced higher frictional heating than the matrix alloy and composite in all the cases especially at higher load condition. As far as friction coefficient is concerned, a mixed trend of behaviour was noted. The wear rate and frictional heating increased with load while friction coefficient was affected in an opposite manner. Test duration influenced the frictional heating and friction coefficient of the samples in a mixed manner.

Keywords: solid lubricant, sliding wear, grey cast iron, zinc based metal matrix composites

Procedia PDF Downloads 290

Authors: Mikhail O. Eremin

Abstract:

Present work is devoted to experimental study and numerical modelling of failure of rocks typical for Kuzbass coal basin (Russia). The main goal was to define strength and deformation characteristics of rocks on the base of uniaxial compression and three-point bending loadings and then to build a mathematical model of failure process for both types of loading. Depending on particular physical-mechanical characteristics typical rocks of Kuzbass coal basin (sandstones, siltstones, mudstones, etc. of different series – Kolchuginsk, Tarbagansk, Balohonsk) manifest brittle and quasi-brittle character of failure. The strength characteristics for both tension and compression are found. Other characteristics are also found from the experiment or taken from literature reviews. On the base of obtained characteristics and structure (obtained from microscopy) the mathematical and structural models are built and numerical modelling of failure under different types of loading is carried out. Effective characteristics obtained from modelling and character of failure correspond to experiment and thus, the mathematical model was verified. An Instron 1185 machine was used to carry out the experiments. Mathematical model includes fundamental conservation laws of solid mechanics – mass, impulse, energy. Each rock has a sufficiently anisotropic structure, however, each crystallite might be considered as isotropic and then a whole rock model has a quasi-isotropic structure. This idea gives an opportunity to use the Hooke’s law inside of each crystallite and thus explicitly accounting for the anisotropy of rocks and the stress-strain state at loading. Inelastic behavior is described in frameworks of two different models: von Mises yield criterion and modified Drucker-Prager yield criterion. The damage accumulation theory is also implemented in order to describe a failure process. Obtained effective characteristics of rocks are used then for modelling of rock mass evolution when mining is carried out both by an open-pit or underground opening.

Keywords: damage accumulation, Drucker-Prager yield criterion, failure, mathematical modelling, three-point bending, uniaxial compression

Procedia PDF Downloads 149

Authors: Wedad Albalawi

Abstract:

The mathematical inequalities have been the core of mathematical study and used in almost all branches of mathematics as well in various areas of science and engineering. The inequalities by Hardy, Littlewood and Polya were the first significant composition of several science. This work presents fundamental ideas, results and techniques, and it has had much influence on research in various branches of analysis. Since 1934, various inequalities have been produced and studied in the literature. Furthermore, some inequalities have been formulated by some operators; in 1989, weighted Hardy inequalities have been obtained for integration operators. Then, they obtained weighted estimates for Steklov operators that were used in the solution of the Cauchy problem for the wave equation. They were improved upon in 2011 to include the boundedness of integral operators from the weighted Sobolev space to the weighted Lebesgue space. Some inequalities have been demonstrated and improved using the Hardy–Steklov operator. Recently, a lot of integral inequalities have been improved by differential operators. Hardy inequality has been one of the tools that is used to consider integrity solutions of differential equations. Then, dynamic inequalities of Hardy and Coposon have been extended and improved by various integral operators. These inequalities would be interesting to apply in different fields of mathematics (functional spaces, partial differential equations, mathematical modeling). Some inequalities have been appeared involving Copson and Hardy inequalities on time scales to obtain new special version of them. A time scale is an arbitrary nonempty closed subset of the real numbers. Then, the dynamic inequalities on time scales have received a lot of attention in the literature and has become a major field in pure and applied mathematics. There are many applications of dynamic equations on time scales to quantum mechanics, electrical engineering, neural networks, heat transfer, combinatorics, and population dynamics. This study focuses on Hardy and Coposon inequalities, using Steklov operator on time scale in double integrals to obtain special cases of time-scale inequalities of Hardy and Copson on high dimensions. The advantage of this study is that it uses the one-dimensional classical Hardy inequality to obtain higher dimensional on time scale versions that will be applied in the solution of the Cauchy problem for the wave equation. In addition, the obtained inequalities have various applications involving discontinuous domains such as bug populations, phytoremediation of metals, wound healing, maximization problems. The proof can be done by introducing restriction on the operator in several cases. The concepts in time scale version such as time scales calculus will be used that allows to unify and extend many problems from the theories of differential and of difference equations. In addition, using chain rule, and some properties of multiple integrals on time scales, some theorems of Fubini and the inequality of H¨older.

Keywords: time scales, inequality of hardy, inequality of coposon, steklov operator

Procedia PDF Downloads 60

Authors: Shaukat Ali Shahee, Usha Ananthakumar

Abstract:

A data set exhibits class imbalance problem when one class has very few examples compared to the other class, and this is also referred to as between class imbalance. The traditional classifiers fail to classify the minority class examples correctly due to its bias towards the majority class. Apart from between-class imbalance, imbalance within classes where classes are composed of a different number of sub-clusters with these sub-clusters containing different number of examples also deteriorates the performance of the classifier. Previously, many methods have been proposed for handling imbalanced dataset problem. These methods can be classified into four categories: data preprocessing, algorithmic based, cost-based methods and ensemble of classifier. Data preprocessing techniques have shown great potential as they attempt to improve data distribution rather than the classifier. Data preprocessing technique handles class imbalance either by increasing the minority class examples or by decreasing the majority class examples. Decreasing the majority class examples lead to loss of information and also when minority class has an absolute rarity, removing the majority class examples is generally not recommended. Existing methods available for handling class imbalance do not address both between-class imbalance and within-class imbalance simultaneously. In this paper, we propose a method that handles between class imbalance and within class imbalance simultaneously for binary classification problem. Removing between class imbalance and within class imbalance simultaneously eliminates the biases of the classifier towards bigger sub-clusters by minimizing the error domination of bigger sub-clusters in total error. The proposed method uses model-based clustering to find the presence of sub-clusters or sub-concepts in the dataset. The number of examples oversampled among the sub-clusters is determined based on the complexity of sub-clusters. The method also takes into consideration the scatter of the data in the feature space and also adaptively copes up with unseen test data using Lowner-John ellipsoid for increasing the accuracy of the classifier. In this study, neural network is being used as this is one such classifier where the total error is minimized and removing the between-class imbalance and within class imbalance simultaneously help the classifier in giving equal weight to all the sub-clusters irrespective of the classes. The proposed method is validated on 9 publicly available data sets and compared with three existing oversampling techniques that rely on the spatial location of minority class examples in the euclidean feature space. The experimental results show the proposed method to be statistically significantly superior to other methods in terms of various accuracy measures. Thus the proposed method can serve as a good alternative to handle various problem domains like credit scoring, customer churn prediction, financial distress, etc., that typically involve imbalanced data sets.

Keywords: classification, imbalanced dataset, Lowner-John ellipsoid, model based clustering, oversampling

Procedia PDF Downloads 391

Authors: Mohammad Tarek Al Muallim, Ozhan Duzenli, Ceyhun Ilguy

Abstract:

Harbor protection systems are so important. The need for automatic protection systems has increased over the last years. Diver detection active sonar has great significance. It used to detect underwater threats such as divers and autonomous underwater vehicle. To automatically detect such threats the sonar image is processed by algorithms. These algorithms used to detect, track and classify of underwater objects. In this work, divers tracking and classification algorithm is improved be proposing a robust wake detection method. To detect objects the sonar images is normalized then segmented based on fixed threshold. Next, the centroids of the segments are found and clustered based on distance metric. Then to track the objects linear Kalman filter is applied. To reduce effect of noise and creation of false tracks, the Kalman tracker is fine tuned. The tuning is done based on our active sonar specifications. After the tracks are initialed and updated they are subjected to a filtering stage to eliminate the noisy and unstable tracks. Also to eliminate object with a speed out of the diver speed range such as buoys and fast boats. Afterwards the result tracks are subjected to a classification stage to deiced the type of the object been tracked. Here the classification stage is to deice wither if the tracked object is an open circuit diver or a close circuit diver. At the classification stage, a small area around the object is extracted and a novel wake detection method is applied. The morphological features of the object with his wake is extracted. We used support vector machine to find the best classifier. The sonar training images and the test images are collected by ARMELSAN Defense Technologies Company using the portable diver detection sonar ARAS-2023. After applying the algorithm to the test sonar data, we get fine and stable tracks of the divers. The total classification accuracy achieved with the diver type is 97%.

Keywords: harbor protection, diver detection, active sonar, wake detection, diver classification

Procedia PDF Downloads 212

Authors: Martin Pellon Consunji

Abstract:

Due to the rise in popularity of Bitcoin and other crypto assets as a store of wealth and speculative investment, there is an ever-growing demand for automated trading tools, such as bots, in order to gain an advantage over the market. Traditionally, trading in the stock market was done by professionals with years of training who understood patterns and exploited market opportunities in order to gain a profit. However, nowadays a larger portion of market participants are at minimum aided by market-data processing bots, which can generally generate more stable signals than the average human trader. The rise in trading bot usage can be accredited to the inherent advantages that bots have over humans in terms of processing large amounts of data, lack of emotions of fear or greed, and predicting market prices using past data and artificial intelligence, hence a growing number of approaches have been brought forward to tackle this task. However, the general limitation of these approaches can still be broken down to the fact that limited historical data doesn’t always determine the future, and that a lot of market participants are still human emotion-driven traders. Moreover, developing markets such as those of the cryptocurrency space have even less historical data to interpret than most other well-established markets. Due to this, some human traders have gone back to the tried-and-tested traditional technical analysis tools for exploiting market patterns and simplifying the broader spectrum of data that is involved in making market predictions. This paper proposes a method which uses neuro evolution techniques on both sentimental data and, the more traditionally human-consumed, technical analysis data in order to gain a more accurate forecast of future market behavior and account for the way both automated bots and human traders affect the market prices of Bitcoin and other cryptocurrencies. This study’s approach uses evolutionary algorithms to automatically develop increasingly improved populations of bots which, by using the latest inflows of market analysis and sentimental data, evolve to efficiently predict future market price movements. The effectiveness of the approach is validated by testing the system in a simulated historical trading scenario, a real Bitcoin market live trading scenario, and testing its robustness in other cryptocurrency and stock market scenarios. Experimental results during a 30-day period show that this method outperformed the buy and hold strategy by over 260% in terms of net profits, even when taking into consideration standard trading fees.

Keywords: neuro-evolution, Bitcoin, trading bots, artificial neural networks, technical analysis, evolutionary algorithms

Procedia PDF Downloads 94

Authors: Rafael do Amaral Teodoro, Leandro Augusto da Silva

Abstract:

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

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

Procedia PDF Downloads 137

Authors: Haniyeh Parhizkar

Abstract:

When Sarris came up with the "auteur theory" in 1962, he emphasized that the utmost premise of auteur theory is the inner meanings and concepts of a film and that a film is purely an art form. Today's mainstream movies are conceptually closer to what the Frankfurt School scholars regarded as "reproduced" and "mass culture" years ago. Hollywood goes on to be a huge movie-making machine that leads the dominant paradigms of films throughout the world and cinema is far from art. Although there are still movies, directors, and audiences who favor art cinema over Hollywood and mainstream movies, it's an almost undeniable fact that, for the most part, people's perception of movies is widely influenced by their American depiction and Hollywood's legacy of mass culture. With the uprising of Hollywood studios as the forerunners of the movie industry and cinema being largely dependent on economics rather than artistic values, this distinctive role of cinema has diminished and is replaced with a global standard. The Blockbuster 2022 film, 'Everything, Everywhere, All at Once' is now the most-awarded movie of all time, winning seven Oscars at the 95th Academy Awards. Despite its main cast being Asian, the movie is produced by American incorporation and is heavily influenced by Hollywood's dominant themes of superheroes, fantasy, action, and adventure. The New Yorker film critic, Richard Brody, called the movie "a pitch for a Marvel" and critiqued the film for being "universalized" and "empty of history and culture". Other critics of Variety pinpointed the movie's similarities to Marvel, particularly in their storylines of multi-universe which manifest traces of American legacy. As argued by these critics, 'Everything, Everywhere, All at Once' might appear as a unique and authentic film at first glance, but it can be argued that it is yet another version of a Marvel movie. While the movie's universal acclaim was regarded as recognition and an acknowledgment of its Asian cast, the issue that arises here is when the Hollywood influences and American themes are so robust in the film, is the movie industry honoring another culture or is it yet another celebration of Hollywood's dominant paradigm. This essay will employ a critical approach to Hollywood's dominance and mass-produced culture, which has deprived authenticity of non-American movies and is constantly reproducing the same formula of success.

Keywords: hollywoodization, universalization, blockbuster, dominant paradigm, marvel, authenticity, diversity

Procedia PDF Downloads 60