Search results for: synthetic dataset

Authors: Anshika Kankane, Dongshik Kang

Abstract:

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

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

Procedia PDF Downloads 101

Authors: Dita Mayasari, Zahrina Mardina, Riki Siswanto, Agresta Ifada, Ova Oktavina, Prihartini Widiyanti

Abstract:

Heart failure is a serious major health problem with high number of mortality per year. Bypass is one of the solutions that has often been taken. Natural vascular graft (xenograft) as the substitute in bypass is inconvenient due to ethic problems and the risk of infection transmission caused by the usage of another species transgenic vascular. Nowadays, synthetic materials have been fabricated from polymers. The aim of this research is to make a synthetic vascular graft with great physical strength, high biocompatibility, and good affordability. The method of this research was mixing PLGA and collagen by magnetic stirrer. This composite were shaped by spinneret with water as coagulant. Then it was coated by chitosan with 3 variations of weight (1 gram, 2 grams, and 3 grams) to increase hemo and cytocompatibility, proliferation, and cell attachment in order for the vascular graft candidates to be more biocompatible. Mechanical strength for each variation was 5,306 MPa (chitosan 1 gram), 3,433 MPa (chitosan 2 grams) and 3,745 MPa (chitosan 3 grams). All the tensile values were higher than human vascular tensile strength. Toxicity test showed that the living cells in all variations were more than 60% in number, thus the vascular graft is not toxic.

Keywords: chitosan, collagen, PLGA, spinneret

Procedia PDF Downloads 393

Authors: T. O. Babarinde

Abstract:

Interest in natural refrigerants, such as hydrocarbons has been renewed in recent years because of the environmental problems associated with synthetic chlorofluorocarbon (CFC) and hydro-chlorofluorocarbon (HCFC) refrigerants. Due to the depletion of ozone-layer and global warming effects, synthetic refrigerants are being gradually phased out in accordance with the international protocols that aim to protect the environment. In this work, a refrigerator designed to work with R134a was used for this experiment, Liquefied Petroleum Gas (LPG) which consists of commercial propane and butane in a single evaporator domestic refrigerator with a total volume of 62 litres. In this experiment, type K thermocouples with their probes were used to measure the temperatures of four major components (evaporator, compressor, condenser and expansion device) of the refrigeration system. Also the system was instrumented with two pressure gauges at the inlet and outlet of the compressor for measuring the suction and discharged pressures. Four sets of experiments were carried out using different charges and the charges were measured with a digital charging scale. Thermodynamic properties of the LPG refrigerant were determined. The results obtained showed that the design temperature and pull-down time set by International Standard Organisation (ISO) for refrigerator was achieved using LPG charge of 60g. The system COP increases with 14.6% and the power consumption reduced with 9.8% when compared with R134a. Therefore, LPG can replace R134a in domestic refrigerator.

Keywords: domestic refrigerator, experimental, R290/R600, R134a

Procedia PDF Downloads 428

Authors: Burak Bal

Abstract:

Mechanical characterization tests might come with a remarkable cost of time and money for both companies and academics. The inquiry to transform laboratory experiments to the computational media is getting a trend; accordingly, the literature supplies many analytical ways to explain the mechanics of deformation. In our work, we focused on the crystal plasticity finite element modeling (CPFEM) analysis on various materials in various crystal structures to predict the stress-strain curve without tensile tests. For FEM analysis, which we used in this study was ABAQUS, a standard user-defined material subroutine (UMAT) was prepared. The geometry of a specimen was created via DREAM 3D software with the inputs of Euler angles taken by Electron Back-Scattered Diffraction (EBSD) technique as orientation, or misorientation angles. The synthetic crystal created with DREAM 3D is also meshed in a way the grains inside the crystal meshed separately, and the computer can realize interaction of inter, and intra grain structures. The mechanical deformation parameters obtained from the literature put into the Fortran based UMAT code to describe how material will response to the load applied from specific direction. The mechanical response of a synthetic crystal created with DREAM 3D agrees well with the material response in the literature.

Keywords: crystal plasticity finite element modeling, ABAQUS, Dream.3D, microstructure

Procedia PDF Downloads 148

Authors: V. K. Srivastava

Abstract:

The chemistry of compounds containing transition metals bound to sulfur containing ligands has been actively studied. Interest in these compounds arises from the identification of the biological importance of iron-sulfur containing proteins as well as the unusual behaviour of several types of synthetic metal-sulfur complexes. Metal complexes (C₆H₅)₄P)₂ Pt(Mos₄)₂, (C₆H₅)₄P)₂ Pd(MoS₄)₂, (C₆H₅)₄P)₂ Ni(MoS₄)₂ of bioinorganic relevance were investigated. The complexes [M(M'S₄)₂]²⁻ were prepared with high yield and purity as salts of the variety of organic cations. The diamagnetism and spectroscopic properties of these complexes confirmed that their structures are essentially equivalent with two bidentate M'S₄²⁻ ligands coordinated to the central d⁸ metal in a square planer geometry. The interaction of the complexes with CT-DNA was studied. Results showed that metal complexes increased DNA's relative viscosity and quench the fluorescence intensity of EB bound to DNA. In antimicrobial activities, all complexes showed good antimicrobial activity higher than ligand against gram positive, gram negative bacteria and fungi. The antitumor properties have been tested in vitro against two tumor human cell lines, Hela (derived from cervical cancer) and MCF-7 (derived from breast cancer) using metabolic activity tests. Result showed that the complexes are promising chemotherapeutic alternatives in the search of anticancer agents.

Keywords: anti cancer, biocidal, DNA binding, spectra

Procedia PDF Downloads 157

Authors: Sajeeha Ansar, Asad Ali Safi, Sheikh Ziauddin, Ahmad R. Shahid, Faraz Ahsan

Abstract:

Gliomas are most challenging and aggressive type of tumors which appear in different sizes, locations, and scattered boundaries. CNN is most efficient deep learning approach with outstanding capability of solving image analysis problems. A fully automatic deep learning based 2D-CNN model for brain tumor segmentation is presented in this paper. We used small convolution filters (3 x 3) to make architecture deeper. We increased convolutional layers for efficient learning of complex features from large dataset. We achieved better results by pushing convolutional layers up to 16 layers for HGG model. We achieved reliable and accurate results through fine-tuning among dataset and hyper-parameters. Pre-processing of this model includes generation of brain pipeline, intensity normalization, bias correction and data augmentation. We used the BRATS-2015, and Dice Similarity Coefficient (DSC) is used as performance measure for the evaluation of the proposed method. Our method achieved DSC score of 0.81 for complete, 0.79 for core, 0.80 for enhanced tumor regions. However, these results are comparable with methods already implemented 2D CNN architecture.

Keywords: brain tumor segmentation, convolutional neural networks, deep learning, HGG

Procedia PDF Downloads 251

Authors: Mandeep Kataria, Ankita Thakur

Abstract:

Glycyrrhiza glabra grows in the sub- tropical and warm temperate regions of the world, in Mediterranean countries and China, America, Europe, Asia and Australia. It grows in areas with sunny, dry and hot climates. It has numerous medicinal properties like it is used to cure Peptic Ulcers, Canker sores, Eczema, Indigestion and Upper Respiratory Infections. Biosynthetic methods such as plant extract have emerged as a simple and viable alternative to more complex chemical synthetic procedures to obtain nanomaterials. Extract from plant may act both as reducing and capping agents in silver nanoparticles synthesis. In the present work, Green Silver nanoparticles were successfully formulated from bioreduction of silver nitrate solutions using Glycyrrhiza glabra root extract. These Green Silver nanoparticles have been appropriately characterized using Visible spectroscopy, colour change. The Antimicrobial activity was done by Agar disc diffusion assay. AgNPs were developed by using aqueous root extract of Glycyrrhiza glabra, which acts as a reducing as well as stabilizing agent. The green synthetic method is a fast, low cost and eco-friendly process in the field of nanotechnology. The study revealed that the green-synthesized silver nanoparticle provides a promising approach for antimicrobial activity.

Keywords: Glycyrrhiza glabra, nanoparticles, antimicrobial activity, aqueous extract

Procedia PDF Downloads 120

Authors: Billel Kenidra, Mohamed Benmohammed

Abstract:

Data mining technique used in the field of clustering is a subject of active research and assists in biological pattern recognition and extraction of new knowledge from raw data. Clustering means the act of partitioning an unlabeled dataset into groups of similar objects. Each group, called a cluster, consists of objects that are similar between themselves and dissimilar to objects of other groups. Several clustering methods are based on partitional clustering. This category attempts to directly decompose the dataset into a set of disjoint clusters leading to an integer number of clusters that optimizes a given criterion function. The criterion function may emphasize a local or a global structure of the data, and its optimization is an iterative relocation procedure. The K-Means algorithm is one of the most widely used partitional clustering techniques. Since K-Means is extremely sensitive to the initial choice of centers and a poor choice of centers may lead to a local optimum that is quite inferior to the global optimum, we propose a strategy to initiate K-Means centers. The improved K-Means algorithm is compared with the original K-Means, and the results prove how the efficiency has been significantly improved.

Keywords: microarray data mining, biological pattern recognition, partitional clustering, k-means algorithm, centroid initialization

Procedia PDF Downloads 187

Authors: Conor Blunt, Mariluz del Pino-de Elias, Grace Cott, Saoirse Tracy, Rainer Melzer

Abstract:

The European Green Deal announced in 2021 details agricultural chemical pesticide use and synthetic fertilizer application to be reduced by 50% and 20% by 2030. Increasing and maintaining expected yields under these ambitious goals has strained the agricultural sector. This intergovernmental plan has identified plant biostimulants as one potential input to facilitate this new phase of sustainable agriculture; these products are defined as microorganisms or substances that can stimulate soil and plant functioning to enhance crop nutrient use efficiency, quality and tolerance to abiotic stresses. Spring barley is Ireland’s most widely sown tillage crop, and grain destined for malting commands the most significant market price. Heavy erratic rainfall is forecasted in Ireland’s climate future, and barley is particularly susceptible to waterlogging. Recent findings suggest that plant receptivity to biostimulants may depend on the level of stress inflicted on crops to elicit an assisted plant response. In this study, three biostimulants of different genesis (seaweed, protein hydrolysate and bacteria) are applied to ‘RGT Planet’ malting barley fertilized at three different rates (0 kg/ha, 40 kg/ha, 75 kg/ha) of calcium ammonium nitrogen (27% N) under non-stressed and waterlogged conditions. This 4x3x2 factorial trial design was planted in a completed randomized block with one plant per experimental unit. Leaf gas exchange data and key agronomic and grain quality parameters were analyzed via ANOVA. No penalty on productivity was evident on plants receiving 40 kg/ha of N and bio stimulant compared to 75 kg/ha of N treatments. The main effects of nitrogen application and waterlogging provided the most significant variation in the dataset.

Keywords: biostimulant, Barley, malting, NUE, waterlogging

Procedia PDF Downloads 72

Authors: Mouli Banga, Chaya Ravindra

Abstract:

Wound classification is a crucial step in wound diagnosis. An effective classifier can aid wound specialists in identifying wound types with reduced financial and time investments, facilitating the determination of optimal treatment procedures. This study presents a deep neural network-based classifier that leverages wound images and their corresponding locations to categorize wounds into various classes, such as diabetic, pressure, surgical, and venous ulcers. By incorporating a developed body map, the process of tagging wound locations is significantly enhanced, providing healthcare specialists with a more efficient tool for wound analysis. We conducted a comparative analysis between two prominent convolutional neural network models, ResNet50 and MobileNetV2, utilizing a dataset of 730 images. Our findings reveal that the RestNet50 outperforms MovileNetV2, achieving an accuracy of approximately 90%, compared to MobileNetV2’s 83%. This disparity highlights the superior capability of ResNet50 in the context of this dataset. The results underscore the potential of integrating deep learning with spatial data to improve the precision and efficiency of wound diagnosis, ultimately contributing to better patient outcomes and reducing healthcare costs.

Keywords: wound classification, MobileNetV2, ResNet50, multimodel

Procedia PDF Downloads 25

Authors: Semeh Ben Salem, Sami Naouali, Moetez Sallami

Abstract:

Clustering is a well known data mining technique used in pattern recognition and information retrieval. The initial dataset to be clustered can either contain categorical or numeric data. Each type of data has its own specific clustering algorithm. In this context, two algorithms are proposed: the k-means for clustering numeric datasets and the k-modes for categorical datasets. The main encountered problem in data mining applications is clustering categorical dataset so relevant in the datasets. One main issue to achieve the clustering process on categorical values is to transform the categorical attributes into numeric measures and directly apply the k-means algorithm instead the k-modes. In this paper, it is proposed to experiment an approach based on the previous issue by transforming the categorical values into numeric ones using the relative frequency of each modality in the attributes. The proposed approach is compared with a previously method based on transforming the categorical datasets into binary values. The scalability and accuracy of the two methods are experimented. The obtained results show that our proposed method outperforms the binary method in all cases.

Keywords: clustering, unsupervised learning, pattern recognition, categorical datasets, knowledge discovery, k-means

Procedia PDF Downloads 255

Authors: D. P. N. De Silva, N. P. P. Liyanage

Abstract:

Zebrafish (Danio rerio) in the family Cyprinidae, is a tropical freshwater fish widely used as a model organism in scientific research. Use of effective and economical anaesthetic is very important when handling fish. Clove oil (active ingredient: eugenol) was identified as a natural product which is safer and economical compared to synthetic chemicals like methanesulfonate (MS-222). Therefore, the aim of this study was to identify the most effective dosage of clove oil solution as an anaesthetic on mature Zebrafish. Clove oil solution was prepared by mixing pure clove oil with 94% ethanol at a ratio of 1:9 respectively. From that solution, different volumes were selected as (0.4 ml, 0.6 ml and 0.8 ml) and dissolved in one liter of conditioned water (dosages : 0.4 ml/L, 0.6 ml/L and 0.8 ml/L). Water quality parameters (pH, temperature and conductivity) were measured before and after adding clove oil solution. Mature Zebrafish with similar standard length (2.76 ± 0.1 cm) and weight (0.524 ± 0.1 g) were selected for this experiment. Time taken for loss of equilibrium (initiation phase) and complete loss of movements including opercular movement (anaesthetic phase) were measured. To detect the efficacy on anaesthetic recovery, time taken to begin opercular movements (initiation of recovery phase) until swimming (post anaesthetic phase) were observed. The results obtained were analyzed according to the analysis of variance (ANOVA) and Tukeys’ method using SPSS version 17.0 at 95% confidence interval (p<0.5). According to the results, there was no significant difference at the initiation phase of anaesthesia in all three doses though the time taken was varied from 0.14 to 0.41 minutes. Mean value of the time taken to complete the anaesthetic phase at 0.4 ml/L dosage was significantly different with 0.6 ml/L and 0.8 ml/L dosages independently (p=0.01). There was no significant difference among recovery times at all dosages but 0.8 ml/L dosage took longer time compared to 0.6 ml/L dosage. The water quality parameters (pH and temperature) were stable throughout the experiment except conductivity, which increased with the higher dosage. In conclusion, the best dosage need to anaesthetize Zebrafish using clove oil solution was 0.6 ml/L due to its fast initiation of anaesthesia and quick recovery compared to the other two dosages. Therefore clove oil can be used as a good substitute for synthetic anaesthetics because of its efficacy at a lower dosage with higher safety at a low cost.

Keywords: anaesthetics, clove oil, zebrafish, Cyprinidae

Procedia PDF Downloads 713

Authors: Monireh Ahmadi Bani, Adel Khorramrouz, Lalenoor Morvarid, Bagheri Mahtab

Abstract:

Background:- Foot disorders are common in musculoskeletal problems. Plantar pressure distribution measurement is one the most important part of foot disorders diagnosis for quantitative analysis. However, the association of plantar pressure and foot disorders is not clear. With the growth of dataset and machine learning methods, the relationship between foot disorders and plantar pressures can be detected. Significance of the study:- The purpose of this study was to predict the probability of common foot disorders based on peak plantar pressure distribution and center of pressure during walking. Methodologies:- 2323 participants were assessed in a foot therapy clinic between 2015 and 2021. Foot disorders were diagnosed by an experienced physician and then they were asked to walk on a force plate scanner. After the data preprocessing, due to the difference in walking time and foot size, we normalized the samples based on time and foot size. Some of force plate variables were selected as input to a deep neural network (DNN), and the probability of any each foot disorder was measured. In next step, we used support vector machine (SVM) and run dataset for each foot disorder (classification of yes or no). We compared DNN and SVM for foot disorders prediction based on plantar pressure distributions and center of pressure. Findings:- The results demonstrated that the accuracy of deep learning architecture is sufficient for most clinical and research applications in the study population. In addition, the SVM approach has more accuracy for predictions, enabling applications for foot disorders diagnosis. The detection accuracy was 71% by the deep learning algorithm and 78% by the SVM algorithm. Moreover, when we worked with peak plantar pressure distribution, it was more accurate than center of pressure dataset. Conclusion:- Both algorithms- deep learning and SVM will help therapist and patients to improve the data pool and enhance foot disorders prediction with less expense and error after removing some restrictions properly.

Keywords: deep neural network, foot disorder, plantar pressure, support vector machine

Procedia PDF Downloads 341

Authors: Seini G. Kaufusi

Abstract:

Background. Physician-assisted death (PAD) has and continues to be a controversial issue in the U.S. Dying with dignity statutes exists in 9 U.S. jurisdictions that permit competent adults diagnosed with a terminal illness and given a prognosis of 6 month or less to live to request medication to hasten death. Robust advocacy for and against PAD influences policy, and opinions vary. Aim. This study aims to explore the association between race and the attitudes toward physician-assisted death in the U.S. Methods. Data for this study derives from the General Social Survey (GSS) dataset, a national survey conducted by the National Opinion Research Center (NORC) that focuses on the opinions and values of American’s. A cross-sectional design and probability sample from the 2018 data set was used to randomly select respondents. Results. The results indicated that race is significantly associated with attitudes towards physician-assisted death. The level of significance suggests a strong positive association, and the direction indicated that Black and Other racial groups have higher rates of positive decision about PAD. Conclusion. Although attitudes towards PAD varied, Black and other racial groups had favorable decisions for PAD. Further research is crucial in the continuous debate on PAD and understanding the influences of predictors for or against PAD.

Keywords: attitudes, euthanasia, physician-assisted death, race

Procedia PDF Downloads 160

Authors: Shah Rucksana Akhter Urme

Abstract:

Agriculture is the main source of food for human consumption and feeding the world huge population, the pressure of food supply is increasing day by day. Undoubtedly, quality strain, improved plantation, farming technology, synthetic fertilizer, readily available irrigation, insecticides and harvesting technology are the main factors those to meet up the huge demand of food consumption all over the world. However, depended on this limited resources and excess amount of consuming lands, water, fertilizers leads to the end of the resources and severe climate effects has been left for our future generation. Agriculture is the most responsible to global warming, emitting more greenhouse gases than all other vehicles largely from nitrous oxide released by from fertilized fields, and carbon dioxide from the cutting of rain forests to grow crops . Farming is the thirstiest user of our precious water supplies and a major polluter, as runoff from fertilizers disrupts fragile lakes, rivers, and coastal ecosystems across the globe which accelerates the loss of biodiversity, crucial habitat and a major driver of wildlife extinction. It is needless to say that we have to more concern on how we can save the nutrients of the soil, storage of the water and avoid excessive depends on synthetic fertilizer and insecticides. In this case, eco- friendly cultivation could be a potential alternative solution to minimize effects of agriculture in our environment. The objective of this review paper is about organic cultivation following in particular biotechnological process focused on bio-fertilizer and bio-pesticides. Intense practice of chemical pesticides, insecticides has severe effect on both in human life and biodiversity. This cultivation process introduces farmer an alternative way which is nonhazardous, cost effective and ecofriendly. Organic fertilizer such as tea residue, ashes might be the best alternative to synthetic fertilizer those play important role in increasing soil nutrient and fertility. Ashes contain different essential and non-essential mineral contents that are required for plant growth. Organic pesticide such as neem spray is beneficial for crop as it is toxic for pest and insects. Recycled and composted crop wastes and animal manures, crop rotation, green manures and legumes etc. are suitable for soil fertility which is free from hazardous chemicals practice. Finally water hyacinth and algae are potential source of nutrients even alternative to soil for cultivation along with storage of water for continuous supply. Inorganic practice of agriculture, consuming fruits and vegetables becomes a threat for both human life and eco-system and synthetic fertilizer and pesticides are responsible for it. Farmers that practice eco-friendly farming have to implement steps to protect the environment, particularly by severely limiting the use of pesticides and avoiding the use of synthetic chemical fertilizers, which are necessary for organic systems to experience reduced environmental harm and health risk.

Keywords: organic farming, biopesticides, organic nutrients, water storage, global warming

Procedia PDF Downloads 54

Authors: Daniel M. Wolff, Patricia Gray, Rafael de la Parra Venegas

Abstract:

An unsupervised machine listening system is constructed and applied to a dataset of 17,195 30-second marine hydrophone recordings. The system is then heuristically supplemented with anecdotal listening, contextual recording information, and supervised learning techniques to reduce the number of false positives. Features for classification are assembled by extracting the following data from each of the audio files: the spectral centroid, root-mean-squared values for each frequency band of a 10-octave filter bank, and mel-frequency cepstral coefficients in 5-second frames. In this way both time- and frequency-domain information are contained in the features to be passed to a clustering algorithm. Classification is performed using the k-means algorithm and then a k-nearest neighbors search. Different values of k are experimented with, in addition to different combinations of the available feature sets. Hypothesized class labels are 'primarily anthrophony' and 'primarily biophony', where the best class result conforming to the former label has 104 members after heuristic pruning. This demonstrates how a large audio dataset has been made more tractable with machine learning techniques, forming the foundation of a framework designed to acoustically monitor and gauge biological and anthropogenic activity in a marine environment.

Keywords: anthrophony, hydrophone, k-means, machine learning

Procedia PDF Downloads 166

Authors: Lavanya Srinivasan

Abstract:

Biometric identification is to identify unique features in a person like fingerprints, iris, ear, and voice recognition that need the subject's permission and physical contact. Gait biometric is used to identify the unique gait of the person by extracting moving features. The main advantage of gait biometric to identify the gait of a person at a distance, without any physical contact. In this work, the gait biometric is used for person re-identification. The person walking naturally compared with the same person walking with bag, coat, and case recorded using longwave infrared, short wave infrared, medium wave infrared, and visible cameras. The videos are recorded in rural and in urban environments. The pre-processing technique includes human identified using YOLO, background subtraction, silhouettes extraction, and synthesis Gait Entropy Image by averaging the silhouettes. The moving features are extracted from the Gait Entropy Energy Image. The extracted features are dimensionality reduced by the principal component analysis and recognised using different classifiers. The comparative results with the different classifier show that linear discriminant analysis outperforms other classifiers with 95.8% for visible in the rural dataset and 94.8% for longwave infrared in the urban dataset.

Keywords: biometric, gait, silhouettes, YOLO

Procedia PDF Downloads 170

Authors: Hsin-Yang Wang, K. M. A. Salam, Ying-Jia Lin, Daniel Tan, Tzu-Hsuan Chou, Hung-Yu Kao

Abstract:

Detecting user intent from natural language expression has a wide variety of use cases in different natural language processing applications. Recently few-shot training has a spike of usage on commercial domains. Due to the lack of significant sample features, the downstream task performance has been limited or leads to an unstable result across different domains. As a state-of-the-art method, the pre-trained BERT model gathering the sentence-level information from a large text corpus shows improvement on several NLP benchmarks. In this research, we are proposing a method to change multi-class classification tasks into binary classification tasks, then use the confidence score to rank the results. As a language model, BERT performs well on sequence data. In our experiment, we change the objective from predicting labels into finding the relations between words in sequence data. Our proposed method achieved 71.0% accuracy in the internal intent detection dataset and 63.9% accuracy in the HuffPost dataset. Acknowledgment: This work was supported by NCKU-B109-K003, which is the collaboration between National Cheng Kung University, Taiwan, and SoftBank Corp., Tokyo.

Keywords: OSML, BERT, text classification, one shot

Procedia PDF Downloads 94

Authors: Vinay P., Srinivas K. S.

Abstract:

Low Light Image Enhancement is of utmost impor- tance in computer vision based tasks. Applications include vision systems for autonomous driving, night vision devices for defence systems, low light object detection tasks. Many of the existing deep learning methods are resource intensive during the inference step and take considerable time for processing. The algorithm should take considerably less than 41 milliseconds in order to process a real-time video feed with 24 frames per second and should be even less for a video with 30 or 60 frames per second. The paper presents a fast and efficient solution which has two main advantages, it has the potential to be used for a real-time video feed, and it can be used in low compute environments because of the lightweight nature. The proposed solution is a pipeline of three steps, the first one is the use of a simple function to map input RGB values to output RGB values, the second is to balance the colors and the final step is to adjust the contrast of the image. Hence a custom dataset is carefully prepared using images taken in low and bright lighting conditions. The preparation of the dataset, the proposed model, the processing time are discussed in detail and the quality of the enhanced images using different methods is shown.

Keywords: low light image enhancement, real-time video, computer vision, machine learning

Procedia PDF Downloads 197

Authors: Ikram Kamal, Mohamed Blaghen

Abstract:

Petroleum hydrocarbons are serious problems and global pollutants in the environment due to their toxicity, carcinogenicity and persistent organic pollutant properties. One of the approaches to enhance biodegradation of petroleum hydrocarbons is to use biosurfactant. Biosurfactants are amphiphilic biomolecules produced as metabolic by-products from microorganisms they received considerable attention in the field of environmental remediation processes such as bioremediation. Biosurfactants have been considered as a desirable alternative to synthetic surfactants in various applications particularly in the environmental field. In comparison with their synthetic counterparts, biosurfactants have been reported to be less toxic, biodegradable and persistent. In this study we have investigated the potential of bacterial strains collected aseptically from the lagoon Marchika (water and soil) in Nador, Morocco; for the production of biosurfactants. This study also aimed to optimize the biosurfactant production process by changing the variables that influence the type and amount of biosurfactant produced by these microorganisms such as: carbon sources and also other physical and chemical parameters such as temperature and pH. Emulsification index, methylene blue test and thin layer chromatography (TLC) revealed the ability of strains used in this study to produce compounds that could emulsify gasoline. In addition, a HPLC/MS was used to separate and identify different biosurfactants purified.

Keywords: petroleum hydrocarbons, biosurfactants, biodegradation, lagoon marchika, emulsification index

Procedia PDF Downloads 257

Authors: Cyrus Addy, Venkata Sriram Siddhardh Nadendla, Kwame Awuah-Offei

Abstract:

Surface robots in modern underground mine rescue operations suffer from several limitations in enabling a prompt self-rescue. Therefore, the possibility of designing and deploying in-mine robots to expedite miner self-rescue can have a transformative impact on miner safety. These in-mine robots for miner self-rescue can be envisioned to carry out diverse tasks such as object detection, autonomous navigation, and payload delivery. Specifically, this paper investigates the challenges in the design of object detection algorithms for in-mine robots using thermal images, especially to detect people in real-time. A total of 125 thermal images were collected in the Missouri S&T Experimental Mine with the help of student volunteers using the FLIR TG 297 infrared camera, which were pre-processed into training and validation datasets with 100 and 25 images, respectively. Three state-of-the-art, pre-trained real-time object detection models, namely YOLOv5, YOLO-FIRI, and YOLOv8, were considered and re-trained using transfer learning techniques on the training dataset. On the validation dataset, the re-trained YOLOv8 outperforms the re-trained versions of both YOLOv5, and YOLO-FIRI.

Keywords: miner self-rescue, object detection, underground mine, YOLO

Procedia PDF Downloads 77

Authors: Mikheil Kalmakhelidze

Abstract:

Record linkage (RL) problem has become more and more important in recent years due to the growing interest towards big data analysis. The problem can be formulated in a very simple way: Given two entries a and b of a database, decide whether they represent the same object or not. There are two classical deterministic and probabilistic ways of solving the RL problem. Using simple Bayes classifier in many cases produces useful results but sometimes they show to be poor. In recent years several successful approaches have been made towards solving specific RL problems by neural network algorithms including single layer perception, multilayer back propagation network etc. In our work, we model the RL problem for specific dataset of student applications in fuzzy description logic (FDL) where linkage of specific pair (a,b) depends on the truth value of corresponding formula A(a,b) in a canonical FDL model. As a main result, we build neural network for deciding truth value of FDL formulas in a canonical model and thus link RL problem to machine learning. We apply the approach to dataset with 10000 entries and also compare to classical RL solving approaches. The results show to be more accurate than standard probabilistic approach.

Keywords: description logic, fuzzy logic, neural networks, record linkage

Procedia PDF Downloads 271

Authors: Mehran Asadi, Afrand Agah

Abstract:

In data mining, partitioning is used as a fundamental tool for classification. With the help of partitioning, we study the structure of data, which allows us to envision decision rules, which can be applied to classification trees. In this research, we used online social network dataset and all of its attributes (e.g., Node features, labels, etc.) to determine what constitutes an above average chance of being a divergent node. We used the R statistical computing language to conduct the analyses in this report. The data were found on the UC Irvine Machine Learning Repository. This research introduces the basic concepts of classification in online social networks. In this work, we utilize overfitting and describe different approaches for evaluation and performance comparison of different classification methods. In classification, the main objective is to categorize different items and assign them into different groups based on their properties and similarities. In data mining, recursive partitioning is being utilized to probe the structure of a data set, which allow us to envision decision rules and apply them to classify data into several groups. Estimating densities is hard, especially in high dimensions, with limited data. Of course, we do not know the densities, but we could estimate them using classical techniques. First, we calculated the correlation matrix of the dataset to see if any predictors are highly correlated with one another. By calculating the correlation coefficients for the predictor variables, we see that density is strongly correlated with transitivity. We initialized a data frame to easily compare the quality of the result classification methods and utilized decision trees (with k-fold cross validation to prune the tree). The method performed on this dataset is decision trees. Decision tree is a non-parametric classification method, which uses a set of rules to predict that each observation belongs to the most commonly occurring class label of the training data. Our method aggregates many decision trees to create an optimized model that is not susceptible to overfitting. When using a decision tree, however, it is important to use cross-validation to prune the tree in order to narrow it down to the most important variables.

Keywords: online social networks, data mining, social cloud computing, interaction and collaboration

Procedia PDF Downloads 153

Authors: Deniz Peksen

Abstract:

This thesis aims to predict trend movement of closing price of stock and to maximize portfolio by utilizing the predictions. In this context, the study aims to define a stock portfolio strategy from models created by using Logistic Regression, Gradient Boosting and Random Forest. Recently, predicting the trend of stock price has gained a significance role in making buy and sell decisions and generating returns with investment strategies formed by machine learning basis decisions. There are plenty of studies in the literature on the prediction of stock prices in capital markets using machine learning methods but most of them focus on closing prices instead of the direction of price trend. Our study differs from literature in terms of target definition. Ours is a classification problem which is focusing on the market trend in next 20 trading days. To predict trend direction, fourteen years of data were used for training. Following three years were used for validation. Finally, last three years were used for testing. Training data are between 2002-06-18 and 2016-12-30 Validation data are between 2017-01-02 and 2019-12-31 Testing data are between 2020-01-02 and 2022-03-17 We determine Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate as benchmarks which we should outperform. We compared our machine learning basis portfolio return on test data with return of Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate. We assessed our model performance with the help of roc-auc score and lift charts. We use logistic regression, Gradient Boosting and Random Forest with grid search approach to fine-tune hyper-parameters. As a result of the empirical study, the existence of uptrend and downtrend of five stocks could not be predicted by the models. When we use these predictions to define buy and sell decisions in order to generate model-based-portfolio, model-based-portfolio fails in test dataset. It was found that Model-based buy and sell decisions generated a stock portfolio strategy whose returns can not outperform non-model portfolio strategies on test dataset. We found that any effort for predicting the trend which is formulated on stock price is a challenge. We found same results as Random Walk Theory claims which says that stock price or price changes are unpredictable. Our model iterations failed on test dataset. Although, we built up several good models on validation dataset, we failed on test dataset. We implemented Random Forest, Gradient Boosting and Logistic Regression. We discovered that complex models did not provide advantage or additional performance while comparing them with Logistic Regression. More complexity did not lead us to reach better performance. Using a complex model is not an answer to figure out the stock-related prediction problem. Our approach was to predict the trend instead of the price. This approach converted our problem into classification. However, this label approach does not lead us to solve the stock prediction problem and deny or refute the accuracy of the Random Walk Theory for the stock price.

Keywords: stock prediction, portfolio optimization, data science, machine learning

Procedia PDF Downloads 77

Authors: I. R. Keke, C. S. Nwigwe, O. S. Nwanjo, A. S. Egeruoh

Abstract:

An experiment was carried out at Urban Farm and Fisheries Nigeria Ltd, Owerri Imo State South East Nigeria between February and June 2014 to induce Brood stock of Heterobranchus longifilis (mean wt 1.3kg) in concrete tanks (1.0 x 2.0 x 1.5m) in dimension using a synthetic hormone (Ovaprim) and pituitary extract from Heterobranchus longifilis. Brood stock males were selected as pituitary donors and their weights matched those of females to be injected at 1ml/kg body weight of Fish. Ovaprim, was injected at 0.5ml/kg body weight of female fish. A latency period of 12 hours was allowed after injection of the Brood stock females before stripping the egg and incubation at 23 °C. While incubating the eggs, samples were drawn and the rate of fertilization was determined. Hatching occurred within 33 hours and hatchability rate (%) was determined by counting the active hatchings. The result showed that Ovaprim injected Brood stock eggs fertilized up to 80% while the pituitary from the Heterobranchus longifilis had low fertilization and hatching success 20%. Ovaprim is imported and costly, so more effort is required to enhance the procedures for homoplastic hypophysation.

Keywords: heterobranchus longifilis, ovaprim, hypophysation, latency period, pituitary

Procedia PDF Downloads 209

Authors: Fei Gao, Rodolfo C. Raga Jr.

Abstract:

This research proposal will ascertain the major risk factors for diabetes and to design a predictive model for risk assessment. The project aims to improve diabetes early detection and management by utilizing data science techniques, which may improve patient outcomes and healthcare efficiency. The phase relation values of each attribute were used to analyze and choose the attributes that might influence the examiner's survival probability using Diabetes Health Indicators Dataset from Kaggle’s data as the research data. We compare and evaluate eight machine learning algorithms. Our investigation begins with comprehensive data preprocessing, including feature engineering and dimensionality reduction, aimed at enhancing data quality. The dataset, comprising health indicators and medical data, serves as a foundation for training and testing these algorithms. A rigorous cross-validation process is applied, and we assess their performance using five key metrics like accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC). After analyzing the data characteristics, investigate their impact on the likelihood of diabetes and develop corresponding risk indicators.

Keywords: diabetes, risk factors, predictive model, risk assessment, data science techniques, early detection, data analysis, Kaggle

Procedia PDF Downloads 71

Authors: Jean-Pierre Dubois, Jihad S. Daba, H. Karam, J. Abdallah

Abstract:

Tsunami early detection and warning systems have proved to be of ultimate importance, especially after the destructive tsunami that hit Japan in March 2012. Such systems are crucial to inform the authorities of any risk of a tsunami and of the degree of its danger in order to make the right decision and notify the public of the actions they need to take to save their lives. The purpose of this research is to enhance existing tsunami detection and warning systems. We first propose an automated and miniaturized model of an early tsunami detection and warning system. The model for the operation of a tsunami warning system is simulated using the data acquisition toolbox of Matlab and measurements acquired from specified internet pages due to the lack of the required real-life sensors, both seismic and hydrologic, and building a graphical user interface for the system. In the second phase of this work, we implement various satellite image filtering schemes to enhance the acquired synthetic aperture radar images of the tsunami affected region that are masked by speckle noise. This enables us to conduct a post-tsunami damage extent study and calculate the percentage damage. We conclude by proposing improvements to the existing telecommunication infrastructure of existing warning tsunami systems using a migration to IP-based networks and fiber optics links.

Keywords: detection, GIS, GSN, GTS, GPS, speckle noise, synthetic aperture radar, tsunami, wiener filter

Procedia PDF Downloads 387

Authors: M. D. H. Beg, John O. Akindoyo, Suriati Ghazali, Nitthiyah Jeyaratnam

Abstract:

Over the period of time, several approaches have been undertaken to mitigate the challenges associated with bone regeneration. This includes but not limited to xenografts, allografts, autografts as well as artificial substitutions like bioceramics, synthetic cements and metals. The former three techniques often come along with peculiar limitation and problems such as morbidity, availability, disease transmission, collateral site damage or absolute rejection by the body as the case may be. Synthetic routes remain the only feasible alternative option for treatment of bone defects. Hydroxyapatite (HA) is very compatible and suitable for this application. However, most of the common methods for HA synthesis are either expensive, complicated or environmentally unfriendly. Interestingly, extraction of HA from bio-wastes have been perceived not only to be cost effective, but also environment friendly. In this research, HA was synthesized from bio-waste: namely bovine bones through three different methods which are hydrothermal chemical processes, ultrasound assisted synthesis and ordinary calcination techniques. Structure and property analysis of the HA was carried out through different characterization techniques such as TGA, FTIR, and XRD. All the methods applied were able to produce HA with similar compositional properties to biomaterials found in human calcified tissues. Calcination process was however observed to be more efficient as it eliminated all the organic components from the produced HA. The HA synthesized is unique for its minimal cost and environmental friendliness. It is also perceived to be suitable for tissue and bone engineering applications.

Keywords: hydroxyapatite, bone, calcination, biowaste

Procedia PDF Downloads 243

Authors: Hsin Lee, Hsuan Lee

Abstract:

Legal artificial intelligence (LegalAI) has been increasing applications within legal systems, propelled by advancements in natural language processing (NLP). Compared with general documents, legal case documents are typically long text sequences with intrinsic logical structures. Most existing language models have difficulty understanding the long-distance dependencies between different structures. Another unique challenge is that while the Judiciary of Taiwan has released legal judgments from various levels of courts over the years, there remains a significant obstacle in the lack of labeled datasets. This deficiency makes it difficult to train models with strong generalization capabilities, as well as accurately evaluate model performance. To date, models in Taiwan have yet to be specifically trained on judgment data. Given these challenges, this research proposes a Longformer-based pre-trained language model explicitly devised for retrieving similar judgments in Taiwanese legal documents. This model is trained on a self-constructed dataset, which this research has independently labeled to measure judgment similarities, thereby addressing a void left by the lack of an existing labeled dataset for Taiwanese judgments. This research adopts strategies such as early stopping and gradient clipping to prevent overfitting and manage gradient explosion, respectively, thereby enhancing the model's performance. The model in this research is evaluated using both the dataset and the Average Entropy of Offense-charged Clustering (AEOC) metric, which utilizes the notion of similar case scenarios within the same type of legal cases. Our experimental results illustrate our model's significant advancements in handling similarity comparisons within extensive legal judgments. By enabling more efficient retrieval and analysis of legal case documents, our model holds the potential to facilitate legal research, aid legal decision-making, and contribute to the further development of LegalAI in Taiwan.

Keywords: legal artificial intelligence, computation and language, language model, Taiwanese legal cases

Procedia PDF Downloads 68

Authors: Niousha Bagheri Khulenjani, Mohammad Saniee Abadeh

Abstract:

Learning from very big datasets is a significant problem for most present data mining and machine learning algorithms. MicroRNA (miRNA) is one of the important big genomic and non-coding datasets presenting the genome sequences. In this paper, a hybrid method for the classification of the miRNA data is proposed. Due to the variety of cancers and high number of genes, analyzing the miRNA dataset has been a challenging problem for researchers. The number of features corresponding to the number of samples is high and the data suffer from being imbalanced. The feature selection method has been used to select features having more ability to distinguish classes and eliminating obscures features. Afterward, a Convolutional Neural Network (CNN) classifier for classification of cancer types is utilized, which employs a Genetic Algorithm to highlight optimized hyper-parameters of CNN. In order to make the process of classification by CNN faster, Graphics Processing Unit (GPU) is recommended for calculating the mathematic equation in a parallel way. The proposed method is tested on a real-world dataset with 8,129 patients, 29 different types of tumors, and 1,046 miRNA biomarkers, taken from The Cancer Genome Atlas (TCGA) database.

Keywords: cancer classification, feature selection, deep learning, genetic algorithm

Procedia PDF Downloads 108