Search results for: manually annotated dataset

Authors: Abeer A. Aljohani

Abstract:

COVID-19 virus spread has been one of the extreme pandemics across the globe. It is also referred to as coronavirus, which is a contagious disease that continuously mutates into numerous variants. Currently, the B.1.1.529 variant labeled as omicron is detected in South Africa. The huge spread of COVID-19 disease has affected several lives and has surged exceptional pressure on the healthcare systems worldwide. Also, everyday life and the global economy have been at stake. This research aims to predict COVID-19 disease in its initial stage to reduce the death count. Machine learning (ML) is nowadays used in almost every area. Numerous COVID-19 cases have produced a huge burden on the hospitals as well as health workers. To reduce this burden, this paper predicts COVID-19 disease is based on the symptoms and medical history of the patient. This research presents a unique architecture for COVID-19 detection using ML techniques integrated with feature dimensionality reduction. This paper uses a standard UCI dataset for predicting COVID-19 disease. This dataset comprises symptoms of 5434 patients. This paper also compares several supervised ML techniques to the presented architecture. The architecture has also utilized 10-fold cross validation process for generalization and the principal component analysis (PCA) technique for feature reduction. Standard parameters are used to evaluate the proposed architecture including F1-Score, precision, accuracy, recall, receiver operating characteristic (ROC), and area under curve (AUC). The results depict that decision tree, random forest, and neural networks outperform all other state-of-the-art ML techniques. This achieved result can help effectively in identifying COVID-19 infection cases.

Keywords: supervised machine learning, COVID-19 prediction, healthcare analytics, random forest, neural network

Procedia PDF Downloads 67

Authors: Abdul Khalique Baloch, Ali Okatan

Abstract:

The quality analysis of food and vegetable from image is hot topic now a day, where researchers make them better then pervious findings through different technique and methods. In this research we have review the literature, and find gape from them, and suggest better proposed approach, design the algorithm, developed a software to measure the quality from images, where accuracy of image show better results, and compare the results with Perouse work done so for. The Application we uses an open-source dataset and python language with tensor flow lite framework. In this research we focus to sort food and vegetable from image, in the images, the application can sorts and make them grading after process the images, it could create less errors them human base sorting errors by manual grading. Digital pictures datasets were created. The collected images arranged by classes. The classification accuracy of the system was about 94%. As fruits and vegetables play main role in day-to-day life, the quality of fruits and vegetables is necessary in evaluating agricultural produce, the customer always buy good quality fruits and vegetables. This document is about quality detection of fruit and vegetables using images. Most of customers suffering due to unhealthy foods and vegetables by suppliers, so there is no proper quality measurement level followed by hotel managements. it have developed software to measure the quality of the fruits and vegetables by using images, it will tell you how is your fruits and vegetables are fresh or rotten. Some algorithms reviewed in this thesis including digital images, ResNet, VGG16, CNN and Transfer Learning grading feature extraction. This application used an open source dataset of images and language used python, and designs a framework of system.

Keywords: deep learning, computer vision, image processing, rotten fruit detection, fruits quality criteria, vegetables quality criteria

Procedia PDF Downloads 47

Authors: Amanuel Berhanu Kesamo

Abstract:

This paper presents both circuit simulation and hardware implementation of a robot vehicle that can be either controlled manually via Bluetooth with video streaming or navigate autonomously to a target point by avoiding obstacles. In manual mode, the user controls the mobile robot using C# windows form interfaced via Bluetooth. The camera mounted on the robot is used to capture and send the real time video to the user. In autonomous mode, the robot plans the shortest path to the target point while avoiding obstacles along the way. Ultrasonic sensor is used for sensing the obstacle in its environment. An efficient path planning algorithm is implemented to navigate the robot along optimal route.

Keywords: Arduino Uno, autonomous, Bluetooth module, path planning, remote controlled robot, ultra sonic sensor

Procedia PDF Downloads 118

Authors: Saima Suleman, Kalsoom Sughra, Naeem Mahmood Ashraf

Abstract:

Mycobacterium tuberculosis is a communicable chronic illness. This disease is being highly focused by researchers as it is present approximately in one third of world population either in active or latent form. The genetic makeup of a person plays an important part in producing immunity against disease. And one important factor association is single nucleotide polymorphism of relevant gene. In this study, we have studied association between single nucleotide polymorphism of CD-209 gene (encode DC-SIGN receptor) and patients of tuberculosis. Dry lab (in silico) and wet lab (RFLP) analysis have been carried out. GWAS catalogue and GEO database have been searched to find out previous association data. No association study has been found related to CD-209 nsSNPs but role of CD-209 in pulmonary tuberculosis have been addressed in GEO database.Therefore, CD-209 has been selected for this study. Different databases like ENSEMBLE and 1000 Genome Project has been used to retrieve SNP data in form of VCF file which is further submitted to different software to sort SNPs into benign and deleterious. Selected SNPs are further annotated by using 3-D modeling techniques using I-TASSER online software. Furthermore, selected nsSNPs were checked in Gujrat and Faisalabad population through RFLP analysis. In this study population two SNPs are found to be associated with tuberculosis while one nsSNP is not found to be associated with the disease.

Keywords: association, CD209, DC-SIGN, tuberculosis

Procedia PDF Downloads 286

Authors: Jia Li, Xing Wei, Yuchen Hong, Yang Lu

Abstract:

Detecting vehicle behavior has always been the focus of intelligent transportation, but with the explosive growth of the number of vehicles and the complexity of the road environment, the vehicle behavior videos captured by traditional surveillance have been unable to satisfy the study of vehicle behavior. The traditional method of manually labeling vehicle behavior is too time-consuming and labor-intensive, but the existing object detection and tracking algorithms have poor practicability and low behavioral location detection rate. This paper proposes a vehicle behavior detection algorithm based on the dual-stream convolution network and the multi-dimensional video dynamic detection network. In the videos, the straight-line behavior of the vehicle will default to the background behavior. The Changing lanes, turning and turning around are set as target behaviors. The purpose of this model is to automatically mark the target behavior of the vehicle from the untrimmed videos. First, the target behavior proposals in the long video are extracted through the dual-stream convolution network. The model uses a dual-stream convolutional network to generate a one-dimensional action score waveform, and then extract segments with scores above a given threshold M into preliminary vehicle behavior proposals. Second, the preliminary proposals are pruned and identified using the multi-dimensional video dynamic detection network. Referring to the hierarchical reinforcement learning, the multi-dimensional network includes a Timer module and a Spacer module, where the Timer module mines time information in the video stream and the Spacer module extracts spatial information in the video frame. The Timer and Spacer module are implemented by Long Short-Term Memory (LSTM) and start from an all-zero hidden state. The Timer module uses the Transformer mechanism to extract timing information from the video stream and extract features by linear mapping and other methods. Finally, the model fuses time information and spatial information and obtains the location and category of the behavior through the softmax layer. This paper uses recall and precision to measure the performance of the model. Extensive experiments show that based on the dataset of this paper, the proposed model has obvious advantages compared with the existing state-of-the-art behavior detection algorithms. When the Time Intersection over Union (TIoU) threshold is 0.5, the Average-Precision (MP) reaches 36.3% (the MP of baselines is 21.5%). In summary, this paper proposes a vehicle behavior detection model based on multi-dimensional dynamic detection network. This paper introduces spatial information and temporal information to extract vehicle behaviors in long videos. Experiments show that the proposed algorithm is advanced and accurate in-vehicle timing behavior detection. In the future, the focus will be on simultaneously detecting the timing behavior of multiple vehicles in complex traffic scenes (such as a busy street) while ensuring accuracy.

Keywords: vehicle behavior detection, convolutional neural network, long short-term memory, deep learning

Procedia PDF Downloads 100

Authors: Ravija Gunawardana, Banuka Athuraliya

Abstract:

Machine learning has emerged as a powerful tool for disease diagnosis and prediction. The use of machine learning algorithms has the potential to improve the accuracy of disease prediction, thereby enabling medical professionals to provide more effective and personalized treatments. This study focuses on developing a machine-learning model for disease prediction using symptoms and X-ray images. The importance of this study lies in its potential to assist medical professionals in accurately diagnosing diseases, thereby improving patient outcomes. Respiratory diseases are a significant cause of morbidity and mortality worldwide, and chest X-rays are commonly used in the diagnosis of these diseases. However, accurately interpreting X-ray images requires significant expertise and can be time-consuming, making it difficult to diagnose respiratory diseases in a timely manner. By incorporating machine learning algorithms, we can significantly enhance disease prediction accuracy, ultimately leading to better patient care. The study utilized the Mask R-CNN algorithm, which is a state-of-the-art method for object detection and segmentation in images, to process chest X-ray images. The model was trained and tested on a large dataset of patient information, which included both symptom data and X-ray images. The performance of the model was evaluated using a range of metrics, including accuracy, precision, recall, and F1-score. The results showed that the model achieved an accuracy rate of over 90%, indicating that it was able to accurately detect and segment regions of interest in the X-ray images. In addition to X-ray images, the study also incorporated symptoms as input data for disease prediction. The study used three different classifiers, namely Random Forest, K-Nearest Neighbor and Support Vector Machine, to predict diseases based on symptoms. These classifiers were trained and tested using the same dataset of patient information as the X-ray model. The results showed promising accuracy rates for predicting diseases using symptoms, with the ensemble learning techniques significantly improving the accuracy of disease prediction. The study's findings indicate that the use of machine learning algorithms can significantly enhance disease prediction accuracy, ultimately leading to better patient care. The model developed in this study has the potential to assist medical professionals in diagnosing respiratory diseases more accurately and efficiently. However, it is important to note that the accuracy of the model can be affected by several factors, including the quality of the X-ray images, the size of the dataset used for training, and the complexity of the disease being diagnosed. In conclusion, the study demonstrated the potential of machine learning algorithms for disease prediction using symptoms and X-ray images. The use of these algorithms can improve the accuracy of disease diagnosis, ultimately leading to better patient care. Further research is needed to validate the model's accuracy and effectiveness in a clinical setting and to expand its application to other diseases.

Keywords: K-nearest neighbor, mask R-CNN, random forest, support vector machine

Procedia PDF Downloads 113

Authors: Aprilia, Wei Liang Keith Nguyen, Shu Beng Tor, Gerald Gim Lee Seet, Chee Kai Chua

Abstract:

Automated remanufacturing process is of great interest in today’s marine and offshore industry. Most of the current remanufacturing processes are carried out manually and hence they are error prone, labour-intensive and costly. In this paper, a conceptual framework for automated remanufacturing is presented. This framework involves the integration of 3D non-contact digitization, adaptive surface reconstruction, additive manufacturing and machining operation. Each operation is operated and interconnected automatically as one system. The feasibility of adaptive surface reconstruction on marine and offshore engineering components is also discussed. Several engineering components were evaluated and the results showed that this proposed system is feasible. Conclusions are drawn and further research work is discussed.

Keywords: adaptive surface reconstruction, automated remanufacturing, automatic repair, reverse engineering

Procedia PDF Downloads 303

Authors: Nola Nahla Bacha

Abstract:

Research has indicated that ESL/EFL (nonnative students of English) students have difficulty in reading at the university as often times the requirements are long texts in which both cultural and linguistic factors impede their understanding and thus their motivation. This is especially the case in literature courses. It is the author’s view that if readings are selected according to the students’ interests and linguistic level, related to life situations and coupled with film study they will not only be motivated to read, but they will find reading interesting and exciting. They will view novels, and thus literature, as a picture of life. Students will also widen their vocabulary repertoire and overcome many of their linguistic problems. This study describes the procedure used in in a 20th Century American Novel class at one English medium university in Lebanon and explores students’ views on the novels assigned and their recommendations. Findings indicate that students significantly like to read novels, contrary to what some faculty claim and view the inclusion of novels as helping them with expanding their vocabulary repertoire and learning about real life which helps them linguistically, pedagogically, and above all personally during their life in and out of the university. Annotated texts, pictures and film will be used through technological aids to show how the class was conducted and how the students’ interacted with the novels assigned. Implications for teaching reading in the classroom are made.

Keywords: language, literature, novels, reading, university teaching

Procedia PDF Downloads 359

Authors: Asiri Wijesinghe, N. D. Kodikara, Damitha Sandaruwan

Abstract:

The Diabetic Retinopathy (DR) is a rapidly growing interrogation around the world which can be annotated by abortive metabolism of glucose that causes long-term infection in human retina. This is one of the preliminary reason of visual impairment and blindness of adults. Information on retinal pathological mutation can be recognized using ocular fundus images. In this research, we are mainly focused on resurrecting an automated diagnosis system to detect DR anomalies such as severity level classification of DR patient (Non-proliferative Diabetic Retinopathy approach) and vessel tortuosity measurement of untwisted vessels to assessment of vessel anomalies (Proliferative Diabetic Retinopathy approach). Severity classification method is obtained better results according to the precision, recall, F-measure and accuracy (exceeds 94%) in all formats of cross validation. In ROC (Receiver Operating Characteristic) curves also visualized the higher AUC (Area Under Curve) percentage (exceeds 95%). User level evaluation of severity capturing is obtained higher accuracy (85%) result and fairly better values for each evaluation measurements. Untwisted vessel detection for tortuosity measurement also carried out the good results with respect to the sensitivity (85%), specificity (89%) and accuracy (87%).

Keywords: fundus image, exudates, microaneurisms, hemorrhages, tortuosity, diabetic retinopathy, optic disc, fovea

Procedia PDF Downloads 315

Authors: Erin Micali, Katerina Tolstikova, Cheryl Maykel, Elizabeth Harwood

Abstract:

Female ASD is seldomly studied separately from males. Further, females with ASD are disproportionately underrepresented in the research at a rate of 3:1 (male to female). As such, much of the current understanding about female rigid repetitive behaviors (RRBs) stems from research’s understanding of male RRBs. This can be detrimental to understanding female ASD because this understanding of female RRBs largely discounts female camouflaging and the possibility that females present their autistic symptoms differently. Current literature suggests that females with ASD engage in fewer RRBs than males with ASD and when females do engage in RRBs, they are likely to engage in more subtle, less overt obsessions and repetitive behaviors than males. Method: The current study utilized a mixed methods research design to identify the type and frequency of RRBs that females with ASD engaged in by using a cross-sectional design. The researcher recruited only females to be part of the present study with the criteria they be at least age six and not have co-occurring cognitive impairment. Results: The researcher collected previous testing data (Autism Diagnostic Interview-Revised (ADI-R), Child or Adolescent/Adult Sensory Profile-2, Autism/ Empathy Quotient, Yale Brown Obsessive Compulsive Checklist, Rigid Repetitive Behavior Checklist (evaluator created list), and demographic questionnaire) from 25 total participants. The participants ages ranged from six to 52. The participants were 96% Caucasion and 4% Latin American. Qualitative analysis found the current participant pool engaged in six RRB themes including repetitive behaviors, socially restrictive behaviors, repetitive speech, difficulty with transition, obsessive behaviors, and restricted interests. The current dataset engaged in socially restrictive behaviors and restrictive interests most frequently. Within the main themes 40 subthemes were isolated, defined, and analyzed. Further, preliminary quantitative analysis was run to determine if age impacted camouflaging behaviors and overall presentation of RRBs. Within this dataset this was not founded. Further qualitative data will be run to determine if this dataset engaged in more overt or subtle RRBs to confirm or rebuff previous research. The researcher intends to run SPSS analysis to determine if there was statistical difference between each RRB theme and overall presentation. Secondly, each participant will be analyzed for presentation of RRB, age, and previous diagnoses. Conclusion: The present study aimed to assist in diagnostic clarity. This was achieved by collecting data from a female only participant pool across the lifespan. Current data aided in clarity of the type of RRBs engage in. A limited sample size was a barrier in this study.

Keywords: autism spectrum disorder, camouflaging, rigid repetitive behaviors, gender disparity

Procedia PDF Downloads 112

Authors: Rutusha Bhutada, Gaurav Chavan, Sarvesh Kasat, Varsha Mujumdar

Abstract:

This software system will be an Augmented Reality application designed to maximize the doctor’s productivity by providing tools to assist in automating the patient recognition and updating patient’s records using face and voice recognition features, which would otherwise have to be performed manually. By maximizing the doctor’s work efficiency and production, the application will meet the doctor’s needs while remaining easy to understand and use. More specifically, this application is designed to allow a doctor to manage his productive time in handling the patient without losing eye-contact with him and communicate with a group of other doctors for consultation, for in-place treatments through video streaming, as a video study. The system also contains a relational database containing a list of doctor, patient and display techniques.

Keywords: augmented reality, hand-held devices, head-mounted devices, marker based systems, speech recognition, face detection

Procedia PDF Downloads 411

Authors: Zhifang Liao, Yanbing Li, Li Xu, Yan Zhang, Xiaoping Fan, Jinsong Wu

Abstract:

Pull Request (PR) is the primary method for code contributions from the external contributors in Github. PR review is an essential part of open source software developments for maintaining the quality of software. Matching a new PR of an appropriate integrator will make the PR review more effective. However, PR and integrator matching are now organized manually in Github. To reduce this cost, we presented an AIPM model to predict highly relevant integrator of incoming PRs. AIPM uses topic model to extract topics from the PRs, and builds a one-to-one correspondence between topics and integrators. Then, AIPM finds the most suitable integrator according to the maximum entry of the topic-document distribution. On average, AIPM can reach a precision of 60%, and even in some projects, can reach a precision of 80%.

Keywords: pull Request, integrator matching, Github, open source project, topic model

Procedia PDF Downloads 273

Authors: Zhao Gao, Eran Edirisinghe

Abstract:

The production of an accurate sketch of a suspect based on a verbal description obtained from a witness is an essential task for most criminal investigations. The criminal investigation system employs specifically trained professional artists to manually draw a facial image of the suspect according to the descriptions of an eyewitness for subsequent identification. Within the advancement of Deep Learning, Recurrent Neural Networks (RNN) have shown great promise in Natural Language Processing (NLP) tasks. Additionally, Generative Adversarial Networks (GAN) have also proven to be very effective in image generation. In this study, a trained GAN conditioned on textual features such as keywords automatically encoded from a verbal description of a human face using an RNN is used to generate photo-realistic facial images for criminal investigations. The intention of the proposed system is to map corresponding features into text generated from verbal descriptions. With this, it becomes possible to generate many reasonably accurate alternatives to which the witness can use to hopefully identify a suspect from. This reduces subjectivity in decision making both by the eyewitness and the artist while giving an opportunity for the witness to evaluate and reconsider decisions. Furthermore, the proposed approach benefits law enforcement agencies by reducing the time taken to physically draw each potential sketch, thus increasing response times and mitigating potentially malicious human intervention. With publically available 'CelebFaces Attributes Dataset' (CelebA) and additionally providing verbal description as training data, the proposed architecture is able to effectively produce facial structures from given text. Word Embeddings are learnt by applying the RNN architecture in order to perform semantic parsing, the output of which is fed into the GAN for synthesizing photo-realistic images. Rather than the grid search method, a metaheuristic search based on genetic algorithms is applied to evolve the network with the intent of achieving optimal hyperparameters in a fraction the time of a typical brute force approach. With the exception of the ‘CelebA’ training database, further novel test cases are supplied to the network for evaluation. Witness reports detailing criminals from Interpol or other law enforcement agencies are sampled on the network. Using the descriptions provided, samples are generated and compared with the ground truth images of a criminal in order to calculate the similarities. Two factors are used for performance evaluation: The Structural Similarity Index (SSIM) and the Peak Signal-to-Noise Ratio (PSNR). A high percentile output from this performance matrix should attribute to demonstrating the accuracy, in hope of proving that the proposed approach can be an effective tool for law enforcement agencies. The proposed approach to criminal facial image generation has potential to increase the ratio of criminal cases that can be ultimately resolved using eyewitness information gathering.

Keywords: RNN, GAN, NLP, facial composition, criminal investigation

Procedia PDF Downloads 139

Authors: Pim Terachinda, Witaya Wannasuphoprasit, Wasuwat Kitisomprayoonkul, Anan Srikiatkhachorn

Abstract:

Restoration of hand function and dexterity remain challenges in rehabilitation after stroke. We have developed soft exoskeleton hand robot in which using tendon-driven mechanism. Finger flexion and extension can be triggered by a foot switch and force can be adjusted manually depending on patient’s grip strength. The objective of this study is to investigate feasibility and safety of this device. The study was done in 2 stroke patients with the strength of the finger flexors/extensors grade 1/0 and 3/1 on Medical Research Council scale, respectively. Grasp and release training was performed for 30 minutes. No complication was observed. Results demonstrated that the device is safe, and therapy can be tailored to individual patient’s need. However, further study is required to determine recovery and rehabilitation outcomes after training in patients after nervous system injury.

Keywords: hand, rehabilitation, robot, stroke

Procedia PDF Downloads 258

Authors: Qiong Hu, Ming Yue

Abstract:

Language variation signals the newest usage of language community, which might become the developmental trend of that language. However, language textbooks cannot keep up with these emergent usages. Most Chinese English learners nowadays are still exposed to traditional grammar prescribed in the textbook so that some variational usages cannot be acquired. The personal pronoun we is prescribed as a plural pronoun in the textbook grammar, but its number value is more flexible in actual use. Based on the Chinese Learner English Corpus (CLEC), and with the homemade Friends corpus as reference, the present research explores the number value of the first person pronoun we used by Chinese English learners. With consideration of the subjectivity of we, this paper annotated the number value of all the wes in “we+ PCU (Perception-cognation-utterance) verbs” collocations. Results show that though exposed to traditional textbooks which prescribe the plural reference of we, there still exists some unconventional usage (singular or vague in reference) in the writings of Chinese English learners, which is less frequent than that of the native speeches. Corpus data and results from manual semantic annotation show that this could be due to the impact of formulaic sequence on the learners and the positive transfer from their native language. An improved SLA model of native language, target language and interlanguage is put forward to recognize the existence of variation in second language acquisition, which should be given more attention during teaching.

Keywords: Chinese English learners, number, PCU verbs, Personal pronoun we

Procedia PDF Downloads 331

Authors: Swati Gupta, Shagun Sodhani, Dhaval Patel, Biplab Banerjee

Abstract:

It is generic that news sources publish news in different broad categories. These categories can either be generic such as Business, Sports, etc. or time-specific such as World Cup 2015 and Nepal Earthquake or both. It is up to the news agencies to build the categories. Extracting news categories automatically from numerous online news sources is expected to be helpful in many applications including news source recommendations and time specific news category extraction. To address this issue, existing systems like DMOZ directory and Yahoo directory are mostly considered though they are mostly human annotated and do not consider the time dynamism of categories of news websites. As a remedy, we propose an approach to automatically extract news category URLs from news websites in this paper. News category URL is a link which points to a category in news websites. We use the news category URL as a prior knowledge to develop a news source recommendation system which contains news sources listed in various categories in order of ranking. In addition, we also propose an approach to rank numerous news sources in different categories using various parameters like Traffic Based Website Importance, Social media Analysis and Category Wise Article Freshness. Experimental results on category URLs captured from GDELT project during April 2016 to December 2016 show the adequacy of the proposed method.

Keywords: news category, category network, news sources, ranking

Procedia PDF Downloads 362

Authors: Benchalak Muangmeesri

Abstract:

Glazes ceramics are ceramic materials produced through controlled crystallization of a parent glass. The great variety of compositions and the possibility of developing special micro structures with specific technological properties have allowed glass ceramic materials to be used in a wide range of applications. At the same time, glazes ceramics need to improvement in the mechanical and chemical properties of glazed. The pick and place station is equipped with a three-axis module. test piece housings placed on the vacuum are detected module picks up a test piece insert from the slide and places it on the test piece housing. Overall, glazes ceramics are compared with automatically and manually of speed and position control. The handling modules of automatic transfer are a new generation of high speed and precision then these color results from absorption and thickness than manual is also included.

Keywords: glaze, PID control, pick and place, ceramic

Procedia PDF Downloads 353

Authors: Dimitrios I. Tselentis, Simon P. Washington

Abstract:

Considerable literature has been focused over the last few decades on forecasting the consumer demand of Energy Efficient Vehicles (EEVs). These methodological issues range from how to capture recent purchase decisions in revealed choice studies and how to set up experiments in stated preference (SP) studies, and choice of analysis method for analyzing such data. This paper reviews the plethora of published studies on the field of forecasting demand of EEVs since 1980, and provides a review and annotated bibliography of that literature as it pertains to this particular demand forecasting problem. This detailed review addresses the literature not only to Transportation studies, but specifically to the problem and methodologies around forecasting to the time horizons of planning studies which may represent 10 to 20 year forecasts. The objectives of the paper are to identify where existing gaps in literature exist and to articulate where promising methodologies might guide longer term forecasting. One of the key findings of this review is that there are many common techniques used both in the field of new product demand forecasting and the field of predicting future demand for EEV. Apart from SP and RP methods, some of these new techniques that have emerged in the literature in the last few decades are survey related approaches, product diffusion models, time-series modelling, computational intelligence models and other holistic approaches.

Keywords: demand forecasting, Energy Efficient Vehicles (EEVs), forecasting methodologies review, methodological approaches

Procedia PDF Downloads 462

Authors: Muneeb Ullah, Daishihan, Xiadong Young

Abstract:

Deep learning plays a crucial role in identifying COVID-19 and preventing its spread. To improve the accuracy of COVID-19 diagnoses, it is important to have access to a sufficient number of training images of CXRs (chest X-rays) depicting the disease. However, there is currently a shortage of such images. To address this issue, this paper introduces COVID-19 GAN, a model that uses generative adversarial networks (GANs) to generate realistic CXR images of COVID-19, which can be used to train identification models. Initially, a generator model is created that uses digressive channels to generate images of CXR scans for COVID-19. To differentiate between real and fake disease images, an efficient discriminator is developed by combining the dense connectivity strategy and instance normalization. This approach makes use of their feature extraction capabilities on CXR hazy areas. Lastly, the deep regret gradient penalty technique is utilized to ensure stable training of the model. With the use of 4,062 grape leaf disease images, the Leaf GAN model successfully produces 8,124 COVID-19 CXR images. The COVID-19 GAN model produces COVID-19 CXR images that outperform DCGAN and WGAN in terms of the Fréchet inception distance. Experimental findings suggest that the COVID-19 GAN-generated CXR images possess noticeable haziness, offering a promising approach to address the limited training data available for COVID-19 model training. When the dataset was expanded, CNN-based classification models outperformed other models, yielding higher accuracy rates than those of the initial dataset and other augmentation techniques. Among these models, ImagNet exhibited the best recognition accuracy of 99.70% on the testing set. These findings suggest that the proposed augmentation method is a solution to address overfitting issues in disease identification and can enhance identification accuracy effectively.

Keywords: classification, deep learning, medical images, CXR, GAN.

Procedia PDF Downloads 57

Authors: Chloé Kernaléguen, Laura Kundun, Tessie Lery, Ryan Laleg, Zhangyun Tan

Abstract:

This study explores global disparities in respiratory syncytial virus (RSV) bronchiolitis incidence among children aged 0-2 years, focusing on the human development index (HDI) as a key determinant. RSV bronchiolitis poses a significant health risk to young children, influenced by factors, including socio-economic conditions captured by the HDI. Through a comprehensive systematic review and dataset selection (Switzerland, Brazil, United States of America), we formulated an HDI-SEIRS numerical model within the SEIRS framework. Results show variations in RSV bronchiolitis dynamics across countries, emphasizing the influence of HDI. Modelling reveals a correlation between higher HDI and increased bronchiolitis spread, notably in the USA and Switzerland. The ratios HDIcountry over HDImax strengthen this association, while climate disparities contribute to variations, especially in colder climates like the USA and Switzerland. The study raises the hypothesis of an indirect link between higher HDI and more frequent bronchiolitis, underlining the need for nuanced understanding. Factors like improved healthcare access, population density, mobility, and social behaviors in higher HDI countries might contribute to unexpected trends. Limitations include dataset quality and restricted RSV bronchiolitis data. Future research should encompass diverse HDI datasets to refine HDI's role in bronchiolitis dynamics. In conclusion, HDI-SEIRS models offer insights into factors influencing RSV bronchiolitis spread. While HDI is a significant indicator, its impact is indirect, necessitating a holistic approach to effective public health policies. This analysis sets the stage for further investigations into multifaceted interactions shaping bronchiolitis dynamics in diverse socio-economic contexts.

Keywords: bronchiolitis propagation, HDI influence, respiratory syncytial virus, SEIRS model

Procedia PDF Downloads 32

Authors: C. Hamamura, V. Gialluca

Abstract:

Much of the Eclectricity Distributors has about 70% of its electricity interruptions arising from cause "trees", alone or associated with wind and rain and with or without falling branch and / or trees. This contributes inexorably and significantly to outages, resulting in high costs as compensation in addition to the operation and maintenance costs. On the other hand, there is little data structure and solutions to better organize the trees pruning plan effectively, minimizing costs and environmentally friendly. This work describes the development of an algorithm to provide data of trees associated to power grid. The method is accomplished on several steps using satellite imagery and geographically vectorized grid. A sliding window like approach is performed to seek the area around the grid. The proposed method counted 764 trees on a patch of the grid, which was very close to the 738 trees counted manually. The trees data was used as a part of a larger project that implements a system to optimize tree pruning plan.

Keywords: image pattern recognition, trees pruning, trees recognition, neural network

Procedia PDF Downloads 478

Authors: Dasom Kim, William Xiu Shun Wong, Yoonjin Hyun, Donghoon Lee, Minji Paek, Sungho Byun, Namgyu Kim

Abstract:

There have been many researches on document classification for classifying voluminous documents automatically. Through document classification, we can assign a specific category to each unlabeled document on the basis of various machine learning algorithms. However, providing labeled documents manually requires considerable time and effort. To overcome the limitations, the semi-supervised learning which uses unlabeled document as well as labeled documents has been invented. However, traditional document classifiers, regardless of supervised or semi-supervised ones, cannot sufficiently explain the reason or the process of the classification. Thus, in this paper, we proposed a methodology to visualize major topics and class components of each document. We believe that our methodology for visualizing topics and classes of each document can enhance the reliability and explanatory power of document classifiers.

Keywords: data mining, document classifier, text mining, topic modeling

Procedia PDF Downloads 375

Authors: Fernanda A. P. Peres, Thiago N. Peres, Flavio S. Fogliatto, Michel J. Anzanello

Abstract:

Batch processes are widely used in food industry and have an important role in the production of high added value products, such as chocolate. Process performance is usually described by variables that are monitored as the batch progresses. Data arising from these processes are likely to display a strong correlation-autocorrelation structure, and are usually monitored using control charts based on multiway principal components analysis (MPCA). Process control of a new batch is carried out comparing the trajectories of its relevant process variables with those in a reference set of batches that yielded products within specifications; it is clear that proper determination of the reference set is key for the success of a correct signalization of non-conforming batches in such quality control schemes. In chocolate manufacturing, misclassifications of non-conforming batches in the conching phase may lead to significant financial losses. In such context, the accuracy of process control grows in relevance. In addition to that, the main assumption in MPCA-based monitoring strategies is that all batches are synchronized in duration, both the new batch being monitored and those in the reference set. Such assumption is often not satisfied in chocolate manufacturing process. As a consequence, traditional techniques as MPCA-based charts are not suitable for process control and monitoring. To address that issue, the objective of this work is to compare the performance of three dynamic time warping (DTW) methods in the alignment and synchronization of chocolate conching process variables’ trajectories, aimed at properly determining the reference distribution for multivariate statistical process control. The power of classification of batches in two categories (conforming and non-conforming) was evaluated using the k-nearest neighbor (KNN) algorithm. Real data from a milk chocolate conching process was collected and the following variables were monitored over time: frequency of soybean lecithin dosage, rotation speed of the shovels, current of the main motor of the conche, and chocolate temperature. A set of 62 batches with durations between 495 and 1,170 minutes was considered; 53% of the batches were known to be conforming based on lab test results and experts’ evaluations. Results showed that all three DTW methods tested were able to align and synchronize the conching dataset. However, synchronized datasets obtained from these methods performed differently when inputted in the KNN classification algorithm. Kassidas, MacGregor and Taylor’s (named KMT) method was deemed the best DTW method for aligning and synchronizing a milk chocolate conching dataset, presenting 93.7% accuracy, 97.2% sensitivity and 90.3% specificity in batch classification, being considered the best option to determine the reference set for the milk chocolate dataset. Such method was recommended due to the lowest number of iterations required to achieve convergence and highest average accuracy in the testing portion using the KNN classification technique.

Keywords: batch process monitoring, chocolate conching, dynamic time warping, reference set distribution, variable duration

Procedia PDF Downloads 144

Authors: Zachary Pan

Abstract:

Our general mission is to solve the problem of classifying images into different body part types and deciding if each of them is healthy or not. However, for now, we will determine healthiness for only one-sixth of the body parts, specifically the chest. We will detect pneumonia in X-ray scans of those chest images. With this type of AI, doctors can use it as a second opinion when they are taking CT or X-ray scans of their patients. Another ad-vantage of using this machine learning classifier is that it has no human weaknesses like fatigue. The overall ap-proach to this problem is to split the problem into two parts: first, classify the image, then determine if it is healthy. In order to classify the image into a specific body part class, the body parts dataset must be split into test and training sets. We can then use many models, like neural networks or logistic regression models, and fit them using the training set. Now, using the test set, we can obtain a realistic accuracy the models will have on images in the real world since these testing images have never been seen by the models before. In order to increase this testing accuracy, we can also apply many complex algorithms to the models, like multiplicative weight update. For the second part of the problem, to determine if the body part is healthy, we can have another dataset consisting of healthy and non-healthy images of the specific body part and once again split that into the test and training sets. We then use another neural network to train on those training set images and use the testing set to figure out its accuracy. We will do this process only for the chest images. A major conclusion reached is that convolutional neural networks are the most reliable and accurate at image classification. In classifying the images, the logistic regression model, the neural network, neural networks with multiplicative weight update, neural networks with the black box algorithm, and the convolutional neural network achieved 96.83 percent accuracy, 97.33 percent accuracy, 97.83 percent accuracy, 96.67 percent accuracy, and 98.83 percent accuracy, respectively. On the other hand, the overall accuracy of the model that de-termines if the images are healthy or not is around 78.37 percent accuracy.

Keywords: body part, healthcare, machine learning, neural networks

Procedia PDF Downloads 73

Authors: Nádia Pereira, Paula Ferreira, Sofia Francisco, Sofia Oliveira, Sidclay Souza, Paula Paulino, Ana Margarida Veiga Simão

Abstract:

Social media has progressed into a platform for hate speech among its users, and thus, there is an increasing need to develop automatic detection classifiers of offense and conflicts to help decrease the prevalence of such incidents. Online communication can be used to intentionally harm someone, which is why such classifiers could be essential in social networks. A possible application of these classifiers is the automatic detection of cyberbullying. Even though identifying the aggressive language used in online interactions could be important to build cyberbullying datasets, there are other criteria that must be considered. Being able to capture the language, which is indicative of the intent to harm others in a specific context of online interaction is fundamental. Offense and hate speech may be the foundation of online conflicts, which have become commonly used in social media and are an emergent research focus in machine learning and natural language processing. This study presents two Portuguese language offense-related datasets which serve as examples for future research and extend the study of the topic. The first is similar to other offense detection related datasets and is entitled Aggressiveness dataset. The second is a novelty because of the use of the history of the interaction between users and is entitled the Conflicts/Attacks dataset. Both datasets were developed in different phases. Firstly, we performed a content analysis of verbal aggression witnessed by adolescents in situations of cyberbullying. Secondly, we computed frequency analyses from the previous phase to gather lexical and linguistic cues used to identify potentially aggressive conflicts and attacks which were posted on Twitter. Thirdly, thorough annotation of real tweets was performed byindependent postgraduate educational psychologists with experience in cyberbullying research. Lastly, we benchmarked these datasets with other machine learning classifiers.

Keywords: aggression, classifiers, cyberbullying, datasets, hate speech, machine learning

Procedia PDF Downloads 202

Authors: Martha C. Orazulume, Jibril D. Jiya

Abstract:

Flexible satellites are equipped with various appendages which vibrate under the influence of any excitation and make the attitude of the satellite to be unstable. Therefore, the system must be able to adjust to balance the effect of these appendages in order to point accurately and satisfactorily which is one of the most important problems in satellite design. Proportional Integral Derivative (PID) Controller is simple to design and computationally efficient to implement which is used to stabilize the effect of these flexible appendages. However, manual turning of the PID is time consuming, waste energy and money. Particle Swarm Optimization (PSO) is used to tune the parameters of PID Controller. Simulation results obtained show that PSO tuned PID Controller is able to re-orient the spacecraft attitude as well as dampen the effect of mechanical resonance and yields better performance when compared with manually tuned PID Controller.

Keywords: Attitude Control, Flexible Satellite, Particle Swarm Optimization, PID Controller and Optimization

Procedia PDF Downloads 367

Authors: Ermias A. Tegegn, Million Meshesha

Abstract:

Human Immunodeficiency Virus and Acquired Immunodeficiency Syndrome (HIV/AIDS) is a major cause of death for most African countries. Ethiopia is one of the seriously affected countries in sub Saharan Africa. Previously in Ethiopia, having HIV/AIDS was almost equivalent to a death sentence. With the introduction of Antiretroviral Therapy (ART), HIV/AIDS has become chronic, but manageable disease. The study focused on a data mining technique to predict future living status of HIV/AIDS patients at the time of drug regimen change when the patients become toxic to the currently taking ART drug combination. The data is taken from University of Gondar Hospital ART program database. Hybrid methodology is followed to explore the application of data mining on ART program dataset. Data cleaning, handling missing values and data transformation were used for preprocessing the data. WEKA 3.7.9 data mining tools, classification algorithms, and expertise are utilized as means to address the research problem. By using four different classification algorithms, (i.e., J48 Classifier, PART rule induction, Naïve Bayes and Neural network) and by adjusting their parameters thirty-two models were built on the pre-processed University of Gondar ART program dataset. The performances of the models were evaluated using the standard metrics of accuracy, precision, recall, and F-measure. The most effective model to predict the status of HIV patients with drug regimen substitution is pruned J48 decision tree with a classification accuracy of 98.01%. This study extracts interesting attributes such as Ever taking Cotrim, Ever taking TbRx, CD4 count, Age, Weight, and Gender so as to predict the status of drug regimen substitution. The outcome of this study can be used as an assistant tool for the clinician to help them make more appropriate drug regimen substitution. Future research directions are forwarded to come up with an applicable system in the area of the study.

Keywords: HIV drug regimen, data mining, hybrid methodology, predictive model

Procedia PDF Downloads 116

Authors: Shanlong Lu, Jiming Jin, Xiaochun Wang

Abstract:

The Tibetan Plateau has the largest number of inland lakes with the highest elevation on the planet. These massive and large lakes are mostly in natural state and are less affected by human activities. Their shrinking or expansion can truly reflect regional climate and environmental changes and are sensitive indicators of global climate change. However, due to the sparsely populated nature of the plateau and the poor natural conditions, it is difficult to effectively obtain the change data of the lake, which has affected people's understanding of the temporal and spatial processes of lake water changes and their influencing factors. By using the MODIS (Moderate Resolution Imaging Spectroradiometer) MOD09Q1 surface reflectance images as basic data, this study produced the 8-day lake water surface data set of the Tibetan Plateau from 2000 to 2012 at 250 m spatial resolution, with a lake water surface extraction method of combined with lake water surface boundary buffer analyzing and lake by lake segmentation threshold determining. Then based on the dataset, the lake water surface variations and their influencing factors were analyzed, by using 4 typical natural geographical zones of Eastern Qinghai and Qilian, Southern Qinghai, Qiangtang, and Southern Tibet, and the watersheds of the top 10 lakes of Qinghai, Siling Co, Namco, Zhari NamCo, Tangra Yumco, Ngoring, UlanUla, Yamdrok Tso, Har and Gyaring as the analysis units. The accuracy analysis indicate that compared with water surface data of the 134 sample lakes extracted from the 30 m Landsat TM (Thematic Mapper ) images, the average overall accuracy of the lake water surface data set is 91.81% with average commission and omission error of 3.26% and 5.38%; the results also show strong linear (R2=0.9991) correlation with the global MODIS water mask dataset with overall accuracy of 86.30%; and the lake area difference between the Second National Lake Survey and this study is only 4.74%, respectively. This study provides reliable dataset for the lake change research of the plateau in the recent decade. The change trends and influencing factors analysis indicate that the total water surface area of lakes in the plateau showed overall increases, but only lakes with areas larger than 10 km2 had statistically significant increases. Furthermore, lakes with area larger than 100 km2 experienced an abrupt change in 2005. In addition, the annual average precipitation of Southern Tibet and Southern Qinghai experienced significant increasing and decreasing trends, and corresponding abrupt changes in 2004 and 2006, respectively. The annual average temperature of Southern Tibet and Qiangtang showed a significant increasing trend with an abrupt change in 2004. The major reason for the lake water surface variation in Eastern Qinghai and Qilian, Southern Qinghai and Southern Tibet is the changes of precipitation, and that for Qiangtang is the temperature variations.

Keywords: lake water surface variation, MODIS MOD09Q1, remote sensing, Tibetan Plateau

Procedia PDF Downloads 209

Authors: Reeta Devi, Hitender Kumar Tyagi, Dinesh Kumar

Abstract:

In present scenario, cardiovascular problems are growing challenge for researchers and physiologists. As heart disease have no geographic, gender or socioeconomic specific reasons; detecting cardiac irregularities at early stage followed by quick and correct treatment is very important. Electrocardiogram is the finest tool for continuous monitoring of heart activity. Heart rate variability (HRV) is used to measure naturally occurring oscillations between consecutive cardiac cycles. Analysis of this variability is carried out using time domain, frequency domain and non-linear parameters. This paper presents HRV analysis of the online dataset for normal sinus rhythm (taken as healthy subject) and sudden cardiac death (SCD subject) using all three methods computing values for parameters like standard deviation of node to node intervals (SDNN), square root of mean of the sequences of difference between adjacent RR intervals (RMSSD), mean of R to R intervals (mean RR) in time domain, very low-frequency (VLF), low-frequency (LF), high frequency (HF) and ratio of low to high frequency (LF/HF ratio) in frequency domain and Poincare plot for non linear analysis. To differentiate HRV of healthy subject from subject died with SCD, k –nearest neighbor (k-NN) classifier has been used because of its high accuracy. Results show highly reduced values for all stated parameters for SCD subjects as compared to healthy ones. As the dataset used for SCD patients is recording of their ECG signal one hour prior to their death, it is therefore, verified with an accuracy of 95% that proposed algorithm can identify mortality risk of a patient one hour before its death. The identification of a patient’s mortality risk at such an early stage may prevent him/her meeting sudden death if in-time and right treatment is given by the doctor.

Keywords: early stage prediction, heart rate variability, linear and non-linear analysis, sudden cardiac death

Procedia PDF Downloads 321

Authors: Cher Leng Lee

Abstract:

The existence of multiple first-person pronouns (1PPs) in classical Chinese is an issue that has not been resolved despite linguists using the grammatical perspective. This paper proposes pragmatics as a viable solution. There is also a lack of research exploring the evolving usage patterns of 1PPs within the historical context of Chinese language use. Such research can help us comprehend the changes and developments of these linguistic elements. To fill these research gaps, we use the diachronic pragmatics approach to contrast the functions of Chinese 1PPs in three representative texts from three different historical periods: The Analects (The Spring and Autumn Period), The Grand Scribe’s Records (Grand Records) (Qin and Han Period), and A New Account of Tales of the World (New Account) (The Wei, Jin and Southern and Northern Period). The 1PPs of these texts are manually identified and classified according to the pragmatic functions in the given contexts to observe their historical changes, understand the factors that contribute to these changes, and provide possible answers to the development of how wo became the only 1PP in today’s spoken Mandarin.

Keywords: historical, Chinese, pronouns, pragmatics

Procedia PDF Downloads 27