Search results for: labeled Petri nets

Authors: Xiaohan Bookman, Xiaoyan Zhu

Abstract:

Margin-Based Principle has been proposed for a long time, it has been proved that this principle could reduce the structural risk and improve the performance in both theoretical and practical aspects. Meanwhile, feed-forward neural network is a traditional classifier, which is very hot at present with a deeper architecture. However, the training algorithm of feed-forward neural network is developed and generated from Widrow-Hoff Principle that means to minimize the squared error. In this paper, we propose a new training algorithm for feed-forward neural networks based on Margin-Based Principle, which could effectively promote the accuracy and generalization ability of neural network classifiers with less labeled samples and flexible network. We have conducted experiments on four UCI open data sets and achieved good results as expected. In conclusion, our model could handle more sparse labeled and more high-dimension data set in a high accuracy while modification from old ANN method to our method is easy and almost free of work.

Keywords: Max-Margin Principle, Feed-Forward Neural Network, classifier, structural risk

Procedia PDF Downloads 346

Authors: Po-Chun Wang, Yan-Ru Lai, Sophia I. C. Lin, Alvin W. Y. Su

Abstract:

The Generative Theory of Tonal Music (GTTM) provides systematic approaches to recognizing local boundaries of music. The rules have been implemented in some automated melody segmentation algorithms. Besides, there are also deep learning methods with GTTM features applied to boundary detection tasks. However, these studies might face constraints such as a lack of or inconsistent label data. The GTTM database is currently the most widely used GTTM database, which includes manually labeled GTTM rules and local boundaries. Even so, we found some problems with these labels. They are sometimes discrepancies with GTTM rules. In addition, since it is labeled at different times by multiple musicians, they are not within the same scope in some cases. Therefore, in this paper, we examine this database with musicians from the aspect of classical music and relabel the scores. The relabeled database - GTTM Database v2.0 - will be released for academic research usage. Despite the experimental and statistical results showing that the relabeled database is more consistent, the improvement in boundary detection is not substantial. It seems that we need more clues than GTTM rules for boundary detection in the future.

Keywords: dataset, GTTM, local boundary, neural network

Procedia PDF Downloads 147

Authors: Hoa Thi Hoang, Stephan Sass, Michael U. Kumke

Abstract:

Concanavalin A (conA) is a protein has been widely used in sensor system based on its specific binding to α-D-Glucose or α-D-Manose. For glucose sensor using conA, either fluoresence based techniques with intensity based or lifetime based are used. In this research, liposomes made from phospholipids were used as a biomimetic membrane system. In a first step, novel building blocks containing perylene labeled glucose units were added to the system and used to decorate the surface of the liposomes. Upon the binding between rhodamine labeled con A to the glucose units at the biomimetic membrane surface, a Förster resonance energy transfer system can be formed which combines unique fluorescence properties of perylene (e.g., high fluorescence quantum yield, no triplet formation) and its high hydrophobicity for efficient anchoring in membranes to form a novel probe for the investigation of sugar-driven binding reactions at biomimetic surfaces. Two glucose-labeled perylene derivatives were synthesized with different spacer length between the perylene and glucose unit in order to probe the binding of conA. The binding interaction was fully characterized by using high-end fluorescence techniques. Steady-state and time-resolved fluorescence techniques (e.g., fluorescence depolarization) in combination with single-molecule fluorescence spectroscopy techniques (fluorescence correlation spectroscopy, FCS) were used to monitor the interaction with conA. Base on the fluorescence depolarization, the rotational correlation times and the alteration in the diffusion coefficient (determined by FCS) the binding of the conA to the liposomes carrying the probe was studied. Moreover, single pair FRET experiments using pulsed interleaved excitation are used to characterize in detail the binding of conA to the liposome on a single molecule level avoiding averaging out effects.

Keywords: concanavalin A, FRET, sensor, biomimetic membrane

Procedia PDF Downloads 307

Authors: Ying Zhao, Xingyan Bin

Abstract:

Semi-supervised clustering algorithms have been shown effective to improve clustering process with even limited supervision. However, semi-supervised hierarchical clustering remains challenging due to the complexities of expressing constraints for agglomerative clustering algorithms. This paper proposes novel semi-supervised agglomerative clustering algorithms to build a hierarchy based on a known reference tree. We prove that by enforcing distance constraints defined by a reference tree during the process of hierarchical clustering, the resultant tree is guaranteed to be consistent with the reference tree. We also propose a framework that allows the hierarchical tree generation be aware of levels of levels of the agglomerative tree under creation, so that metric weights can be learned and adopted at each level in a recursive fashion. The experimental evaluation shows that the additional cost of our contraint-based semi-supervised hierarchical clustering algorithm (HAC) is negligible, and our combined semi-supervised HAC algorithm outperforms the state-of-the-art algorithms on real-world datasets. The experiments also show that our proposed methods can improve clustering performance even with a small number of unevenly distributed labeled data.

Keywords: semi-supervised clustering, hierarchical agglomerative clustering, reference trees, distance constraints

Procedia PDF Downloads 548

Authors: Sarah A. Goodchild, Rachel Gao, Philip N. Bartlett

Abstract:

A novel detection approach using immobilized DNA probes labeled with Anthraquinone (AQ) as an electrochemically active reporter moiety has been successfully developed as a new, simple, reliable method for the detection of DNA. This method represents a step forward in DNA detection as it can discriminate between multiple nucleotide polymorphisms within target DNA strands without the need for any additional reagents, reporters or processes such as melting of DNA strands. The detection approach utilizes single-stranded DNA probes immobilized on gold surfaces labeled at the distal terminus with AQ. The effective immobilization has been monitored using techniques such as AC impedance and Raman spectroscopy. Simple voltammetry techniques (Differential Pulse Voltammetry, Cyclic Voltammetry) are then used to monitor the reduction potential of the AQ before and after the addition of complementary strand of target DNA. A reliable relationship between the shift in reduction potential and the number of base pair mismatch has been established and can be used to discriminate between DNA from highly related pathogenic organisms of clinical importance. This indicates that this approach may have great potential to be exploited within biosensor kits for detection and diagnosis of pathogenic organisms in Point of Care devices.

Keywords: Anthraquinone, discrimination, DNA detection, electrochemical biosensor

Procedia PDF Downloads 394

Authors: Mohit Gupta, Chialing Wei, Thomas Czerniawski

Abstract:

In this paper, we have built a neural network that can detect walls on 2D sheets and subsequently create a 3D model in Revit using Dynamo. The training set includes 3500 labeled images, and the detection algorithm used is YOLO. Typically, engineers/designers make concentrated efforts to convert 2D cad drawings to 3D models. This costs a considerable amount of time and human effort. This paper makes a contribution in automating the task of 3D walls modeling. 1. Detecting Walls in 2D cad and generating 3D pop-ups in Revit. 2. Saving designer his/her modeling time in drafting elements like walls from 2D cad to 3D representation. An object detection algorithm YOLO is used for wall detection and localization. The neural network is trained over 3500 labeled images of size 256x256x3. Then, Dynamo is interfaced with the output of the neural network to pop-up 3D walls in Revit. The research uses modern technological tools like deep learning and artificial intelligence to automate the process of generating 3D walls without needing humans to manually model them. Thus, contributes to saving time, human effort, and money.

Keywords: neural networks, Yolo, 2D to 3D transformation, CAD object detection

Procedia PDF Downloads 146

Authors: G. Pelozo, N. Quaranta

Abstract:

The assessment of environmental hazard and ecotoxicological potential of industrial wastes has become an issue of concern in many countries. Therefore, the aim of this work is to develop a methodology, adapting an Argentinian standard, which allows analyze the ecotoxicological effect of various metallurgical and steel wastes. Foundry sand, white mud, red mud, electric arc furnace dust, converter slag, among others, are the studied wastes. The species used to analyze the ecotoxicological effects of wastes is rye grass (Lolium Perenne). The choice of this kind lies, among other things, in its easy and rapid germination making it possible to develop the test in a few days. Moreover, since the processes involved are general for most seeds, the obtained results with this kind are representative, in general, of the effects on seeds or seedlings. Since the studied residues are solids, prior to performing the assay, an eluate is obtained by stirring for 2 hours and subsequent filtration of a solution of waste in water in a relationship of 1:4. This represents 100% of eluate from which two dilutions in water (25% and 50%) are prepared. A sample with untreated solid waste and water is also performed. The test is performed by placing two filter papers in a Petri dish that are saturated with 3.5ml of the prepared dilutions. After that 20 rye grass seeds are placed, and the Petri dishes are covered and the seeds are incubated for 120 hours at 24 °C. Reference controls are carried out by distilled water. Three replicates are performed for each concentration. Once the exposure period is finished, inhibiting elongation of the root is measured (IR). The results of this test show that all the studied wastes produce an unfavorable effect on the development of the seedlings, being the electric arc furnace dust which more affects the germination.

Keywords: ecotoxicity, industrial wastes, environmental hazard, seeds

Procedia PDF Downloads 403

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 73

Authors: Shrabani Ghosh

Abstract:

Automatic offensive language detection in social media has become a stirring task in today's NLP. Manual Offensive language detection is tedious and laborious work where automatic methods based on machine learning are only alternatives. Previous works have done sentiment analysis over social media in different ways such as supervised, semi-supervised, and unsupervised manner. Domain adaptation in a semi-supervised way has also been explored in NLP, where the source domain and the target domain are different. In domain adaptation, the source domain usually has a large amount of labeled data, while only a limited amount of labeled data is available in the target domain. Pretrained transformers like BERT, RoBERTa models are fine-tuned to perform text classification in an unsupervised manner to perform further pre-train masked language modeling (MLM) tasks. In previous work, hate speech detection has been explored in Gab.ai, which is a free speech platform described as a platform of extremist in varying degrees in online social media. In domain adaptation process, Twitter data is used as the source domain, and Gab data is used as the target domain. The performance of domain adaptation also depends on the cross-domain similarity. Different distance measure methods such as L2 distance, cosine distance, Maximum Mean Discrepancy (MMD), Fisher Linear Discriminant (FLD), and CORAL have been used to estimate domain similarity. Certainly, in-domain distances are small, and between-domain distances are expected to be large. The previous work finding shows that pretrain masked language model (MLM) fine-tuned with a mixture of posts of source and target domain gives higher accuracy. However, in-domain performance of the hate classifier on Twitter data accuracy is 71.78%, and out-of-domain performance of the hate classifier on Gab data goes down to 56.53%. Recently self-supervised learning got a lot of attention as it is more applicable when labeled data are scarce. Few works have already been explored to apply self-supervised learning on NLP tasks such as sentiment classification. Self-supervised language representation model ALBERTA focuses on modeling inter-sentence coherence and helps downstream tasks with multi-sentence inputs. Self-supervised attention learning approach shows better performance as it exploits extracted context word in the training process. In this work, a self-supervised attention mechanism has been proposed to detect hate speech on Gab.ai. This framework initially classifies the Gab dataset in an attention-based self-supervised manner. On the next step, a semi-supervised classifier trained on the combination of labeled data from the first step and unlabeled data. The performance of the proposed framework will be compared with the results described earlier and also with optimized outcomes obtained from different optimization techniques.

Keywords: attention learning, language model, offensive language detection, self-supervised learning

Procedia PDF Downloads 107

Authors: Justin Fu, Thomas Mazzuchi, Shahram Sarkani

Abstract:

A key factor in technological immaturity in defense weapons acquisition is lack of understanding critical integrations at the subsystem and component level. To address this shortfall, recent research in integration readiness level (IRL) combines with technology readiness level (TRL) to form a system readiness level (SRL). SRL can be enriched with more robust quantitative methods to provide the program manager a useful tool prior to committing to major weapons acquisition programs. This research harnesses previous mathematical models based on graph theory, Petri nets, and tropical algebra and proposes a modification of the desirable SRL mathematical properties such that a tightly integrated (multitude of interfaces) subsystem can display a lower SRL than an inherently less coupled subsystem. The synthesis of these methods informs an improved decision tool for the program manager to commit to expensive technology development. This research ties the separately developed manufacturing readiness level (MRL) into the network representation of the system and addresses shortfalls in previous frameworks, including the lack of integration weighting and the over-importance of a single extremely immature component. Tropical algebra (based on the minimum of a set of TRLs or IRLs) allows one low IRL or TRL value to diminish the SRL of the entire system, which may not be reflective of actuality if that component is not critical or tightly coupled. Integration connections can be weighted according to importance and readiness levels are modified to be a cardinal scale (based on an analytic hierarchy process). Integration arcs’ importance are dependent on the connected nodes and the additional integrations arcs connected to those nodes. Lack of integration is not represented by zero, but by a perfect integration maturity value. Naturally, the importance (or weight) of such an arc would be zero. To further explore the impact of grouping subsystems, a multi-objective genetic algorithm is then used to find various clusters or communities that can be optimized for the most representative subsystem SRL. This novel calculation is then benchmarked through simulation and using past defense acquisition program data, focusing on the newly introduced Middle Tier of Acquisition (rapidly field prototypes). The model remains a relatively simple, accessible tool, but at higher fidelity and validated with past data for the program manager to decide major defense acquisition program milestones.

Keywords: readiness, maturity, system, integration

Procedia PDF Downloads 98

Authors: K. Eryilmaz, G. Mercanoglu

Abstract:

Aim: Purification of the final product, which is the last step in the synthesis of lanthanide-labeled peptide compounds, can be accomplished by different methods. Among these methods, the two most commonly used methods are C18 solid phase extraction (SPE) and weak cation exchanger cartridge elution. SPE C18 solid phase extraction method yields high purity final product, while elution from the weak cation exchanger cartridge is pH dependent and ineffective in removing colloidal impurities. The aim of this work is to develop an additional purification method for the lanthanide-labeled peptide compound in cases where the desired radionuclidic and radiochemical purity of the final product can not be achieved because of pH problem or colloidal impurity. Material and Methods: For colloidal impurity formation, 3 mL of water for injection (WFI) was added to 30 mCi of 177LuCl3 solution and allowed to stand for 1 day. 177Lu-DOTATATE was synthesized using EZAG ML-EAZY module (10 mCi/mL). After synthesis, the final product was mixed with the colloidal impurity solution (total volume:13 mL, total activity: 40 mCi). The resulting mixture was trapped in SPE-C18 cartridge. The cartridge was washed with 10 ml saline to remove impurities to the waste vial. The product trapped in the cartridge was eluted with 2 ml of 50% ethanol and collected to the final product vial via passing through a 0.22μm filter. The final product was diluted with 10 mL of saline. Radiochemical purity before and after purification was analysed by HPLC method. (column: ACE C18-100A. 3µm. 150 x 3.0mm, mobile phase: Water-Acetonitrile-Trifluoro acetic acid (75:25:1), flow rate: 0.6 mL/min). Results: UV and radioactivity detector results in HPLC analysis showed that colloidal impurities were completely removed from the 177Lu-DOTATATE/ colloidal impurity mixture by purification method. Conclusion: The improved purification method can be used as an additional method to remove impurities that may result from the lanthanide-peptide synthesis in which the weak cation exchange purification technique is used as the last step. The purification of the final product and the GMP compliance (the final aseptic filtration and the sterile disposable system components) are two major advantages.

Keywords: lanthanide, peptide, labeling, purification, radionuclide, radiopharmaceutical, synthesis

Procedia PDF Downloads 164

Authors: Opara Monica, Suriani Ismail, Ahmad Iqmer Nashriq Mohd Nazan

Abstract:

The true magnitude of the mortality and morbidity attributable to malaria worldwide is, at best, a scientific guess, although it is not disputable that the greatest burden is in sub-Saharan Africa. Those at highest risk are children younger than 5 years and pregnant women, particularly primigravidae. Nationally, malaria remains the third leading cause of death and is still considered a major public health problem. Therefore, this study is aimed to assess the effectiveness of health education intervention on insecticide-treated net use and its practices among pregnant women attending antenatal clinics. Materials and Methods: This study will be an intervention study with two arms double parallel randomized controlled trial (blinded) to be conducted in 3 stages. The first stage will develop health belief model (HBM) program, while in the second stage, pregnant women will be recruited, assessed (baseline data), randomized into two arms of the study, and follow-up for six months. The third stage will evaluate the impact of the intervention on HBM and disseminate the findings. Data will be collected with the use of a structured questionnaire which will contain validated tools. The main outcome measurement will be the treatment effect using HBM, while data will be analysed using SPSS, version 22. Discussion: The study will contribute to the existing knowledge on hospital-based care programs for pregnant women in developing countries where the literature is scanty. It will generally give insight into the importance of HBM measurement in interventional studies on malaria and other related infectious diseases in this setting.

Keywords: malaria, health education, insecticide-treated nets, sub-Saharan Africa

Procedia PDF Downloads 125

Authors: Ergun Sakalar, Kubra Bilgic

Abstract:

In the last decades, real-time PCR has become a reliable tool preferred to use in many laboratories for pathogen detection. This technique allows for monitoring target amplification via fluorescent molecules besides admit of quantitative analysis by enabling of convert outcomes of thermal cycling to digital data. Sensitivity and traceability of real-time PCR are based on measuring of fluorescence that appears only when fluorescent reporter dye bound to specific target DNA.The fluorescent reporter systems developed for this purpose are divided into two groups. The first group consists of intercalator fluorescence dyes such as SYBR Green, EvaGreen which binds to double-stranded DNA. On the other hand, the second group includes fluorophore-labeled oligonucleotide probes that are separated into three subgroups due to differences in mechanism of action; initial primer-probes such as Cyclicons, Angler®, Amplifluor®, LUX™, Scorpions, and the second one hydrolysis probes like TaqMan, Snake assay, finally hybridization probes, for instance, Molecular Beacons, Hybprobe/FRET, HyBeacon™, MGB-Eclipse, ResonSense®, Yin-Yang, MGB-Pleiades. In addition nucleic acid analogues, an increase of probe affinity to target site is also employed with fluorescence-labeled probes. Consequently, abundant real-time PCR detection chemistries are chosen by researcher according to the field of application, mechanism of action, advantages, and proper structures of primer/probes.

Keywords: fluorescent dye, food safety, molecular probes, nucleic acid analogues

Procedia PDF Downloads 257

Authors: Akbar Esmaeili, Zahra Salarieh

Abstract:

Cerium oxide nanoparticles (nano-series) are used as catalysts in industrial applications due to their free radical scavenging properties. Given that free radicals play an essential role in the pathology of many neurological diseases, we investigated the use of nanocrystals as a potential therapeutic agent for oxidative damage. This project synthesized nano-series from a new and environmentally friendly bio-pathway. Investigation of cerium nitrate in culture medium containing inoculated Lactobacillus acidophilus strain before incubation produces nano-series. Loaded with glatiramer acetate (GA) was formed by coating carboxymethylcellulose (CMC) and CeO2. FE-SEM analysis showed nano-series in the 9-11 nm range, spherical shape, and uniform particle size distribution. Cubic nanoparticles containing anti-multiple sclerosis (anti-Ms) treatment called GA were used. Glycerol monostearate (GMS) was used as a fat base, and evening primrose extract was used as an anti-inflammatory in cubosomes. Design-Expert® software was used to study the effects of different formulation factors on the properties of GAloaded cubic dispersions. Thirty GA-labeled cubic dispersions were prepared with GA-labeled carboxymethylcellulose and evaluated in vitro. The results showed an average nano-series size of 89.02 and a zeta potential of -49.9. Cubosomes containing GA-CMC/CeO2 showed a stable release profile for 180 min. The results showed that cubosomes containing GA-CMC/CeO2 could be a promising drug carrier with normal release behavior.

Keywords: ciochemistry, biotechnology, molecular, biology

Procedia PDF Downloads 53

Authors: Ali S. Gargoum

Abstract:

Graphical modeling plays an important role in providing efficient probability calculations in high dimensional problems (computational efficiency). In this paper, we address one of such problems where we discuss fragmenting puff models and some distributional assumptions concerning models for the instantaneous, emission readings and for the fragmenting process. A graphical representation in terms of a junction tree of the conditional probability breakdown of puffs and puff fragments is proposed.

Keywords: graphical models, influence diagrams, junction trees, Bayesian nets

Procedia PDF Downloads 396

Authors: Kolja Them, Johannes Salamon, Harald Ittrich, Michael Kaul, Tobias Knopp

Abstract:

Superparamagnetic iron oxide nanoparticles (SPIONs) are nanoscale magnets which can be biologically functionalized for biomedical applications. Stem cell therapies to repair damaged tissue, magnetic fluid hyperthermia for cancer therapy and targeted drug delivery based on SPIONs are prominent examples where the visualization of a preferably low concentrated SPION distribution is essential. In 2005 a new method for tomographic SPION imaging has been introduced. The method named magnetic particle imaging (MPI) takes advantage of the nanoparticles magnetization change caused by an oscillating, external magnetic field and allows to directly image the time-dependent nanoparticle distribution. The SPION magnetization can be changed by the electron spin dynamics as well as by a mechanical rotation of the nanoparticle. In this work different calibration methods in MPI are investigated for image reconstruction of magnetically labeled stem cells. It is shown that a calibration using rotationally immobilized SPIONs provides a higher quality of stem cell images with fewer artifacts than a calibration using mobile SPIONs. The enhancement of the image quality and the reduction of artifacts enables the localization and identification of a smaller number of magnetically labeled stem cells. This is important for future medical applications where low concentrations of functionalized SPIONs interacting with biological matter have to be localized.

Keywords: biomedical imaging, iron oxide nanoparticles, magnetic particle imaging, stem cell imaging

Procedia PDF Downloads 465

Authors: Salma El Hajjami, Jamal Malki, Alain Bouju, Mohammed Berrada

Abstract:

With the expansion of machine learning and data mining in the context of Big Data analytics, the common problem that affects data is class imbalance. It refers to an imbalanced distribution of instances belonging to each class. This problem is present in many real world applications such as fraud detection, network intrusion detection, medical diagnostics, etc. In these cases, data instances labeled negatively are significantly more numerous than the instances labeled positively. When this difference is too large, the learning system may face difficulty when tackling this problem, since it is initially designed to work in relatively balanced class distribution scenarios. Another important problem, which usually accompanies these imbalanced data, is the overlapping instances between the two classes. It is commonly referred to as noise or overlapping data. In this article, we propose an approach called: One Side Behavioral Noise Reduction (OSBNR). This approach presents a way to deal with the problem of class imbalance in the presence of a high noise level. OSBNR is based on two steps. Firstly, a cluster analysis is applied to groups similar instances from the minority class into several behavior clusters. Secondly, we select and eliminate the instances of the majority class, considered as behavioral noise, which overlap with behavior clusters of the minority class. The results of experiments carried out on a representative public dataset confirm that the proposed approach is efficient for the treatment of class imbalances in the presence of noise.

Keywords: machine learning, imbalanced data, data mining, big data

Procedia PDF Downloads 132

Authors: Daniel Pinheiro Da Silva Junior, Aline Paes, Daniel De Oliveira, Christiano Lacerda Ghuerren, Marcio Duran

Abstract:

The Courts of Accounts are institutions responsible for overseeing and point out irregularities of Public Administration expenses. They have a high demand for processes to be analyzed, whose decisions must be grounded on severity laws. Despite the existing large amount of processes, there are several cases reporting similar subjects. Thus, previous decisions on already analyzed processes can be a precedent for current processes that refer to similar topics. Identifying similar topics is an open, yet essential task for identifying similarities between several processes. Since the actual amount of topics is considerably large, it is tedious and error-prone to identify topics using a pure manual approach. This paper presents a tool based on Machine Learning and Natural Language Processing to assists in building a labeled dataset. The tool relies on Topic Modelling with Latent Dirichlet Allocation to find the topics underlying a document followed by Jensen Shannon distance metric to generate a probability of similarity between documents pairs. Furthermore, in a case study with a corpus of decisions of the Rio de Janeiro State Court of Accounts, it was noted that data pre-processing plays an essential role in modeling relevant topics. Also, the combination of topic modeling and a calculated distance metric over document represented among generated topics has been proved useful in helping to construct a labeled base of similar and non-similar document pairs.

Keywords: courts of accounts, data labelling, document similarity, topic modeling

Procedia PDF Downloads 180

Authors: Shariful Islam, Sharun Akter Khushbu, S. M. Shaqib, Shahriar Sultan Ramit

Abstract:

In the construction sector, ensuring worker safety is of the utmost significance. In this study, a deep learning-based technique is presented for identifying safety gear worn by construction workers, such as helmets, goggles, jackets, gloves, and footwear. The suggested method precisely locates these safety items by using the YOLO v7 (You Only Look Once) object detection algorithm. The dataset utilized in this work consists of labeled images split into training, testing and validation sets. Each image has bounding box labels that indicate where the safety equipment is located within the image. The model is trained to identify and categorize the safety equipment based on the labeled dataset through an iterative training approach. We used custom dataset to train this model. Our trained model performed admirably well, with good precision, recall, and F1-score for safety equipment recognition. Also, the model's evaluation produced encouraging results, with a [email protected] score of 87.7%. The model performs effectively, making it possible to quickly identify safety equipment violations on building sites. A thorough evaluation of the outcomes reveals the model's advantages and points up potential areas for development. By offering an automatic and trustworthy method for safety equipment detection, this research contributes to the fields of computer vision and workplace safety. The proposed deep learning-based approach will increase safety compliance and reduce the risk of accidents in the construction industry.

Keywords: deep learning, safety equipment detection, YOLOv7, computer vision, workplace safety

Procedia PDF Downloads 68

Authors: Ali Bahkali, Rayan Yousef Booq, Mohammad Khiyami

Abstract:

Soil samples were collected from five different regions in the Kingdom of Saudi Arabia. Microbiological methods included dilution methods and pour plates to isolate and purify bacteria soil. The ability of isolates to develop biopolymer was investigated on petri dishes containing elements and substance concentrations stimulating developing biopolymer. Fluorescent stains, Nile red and Nile blue were used to stain the bacterial cells developing biopolymers. In addition, Sudan black was used to detect biopolymers in bacterial cells. The isolates which developed biopolymers were identified based on their gene sequence of 1 6sRNA and their ability to grow and synthesize PHAs on mineral medium supplemented with 1% dates molasses as the only carbon source under nitrogen limitation. During the study 293 bacterial isolates were isolated and detected. Through the initial survey on the petri dishes, 84 isolates showed the ability to develop biopolymers. These bacterial colonies developed a pink color due to accumulation of the biopolymers in the cells. Twenty-three isolates were able to grow on dates molasses, three strains of which showed the ability to accumulate biopolymers. These strains included Bacillus sp., Ralstonia sp. and Microbacterium sp. They were detected by Nile blue A stain with fluorescence microscopy (OLYMPUS IX 51). Among the isolated strains Ralstonia sp. was selected after its ability to grow on molasses dates in the presence of a limited nitrogen source was detected. The optimum conditions for formation of biopolymers by isolated strains were investigated. Conditions studied included, best incubation duration (2 days), temperature (30°C) and pH (7-8). The maximum PHB production was raised by 1% (v1v) when using concentrations of dates molasses 1, 2, 3, 4 and 5% in MSM. The best inoculated with 1% old inoculum (1= OD). The ideal extraction method of PHA and PHB proved to be 0.4% sodium hypochlorite solution, producing a quantity of polymer 98.79% of the cell's dry weight. The maximum PHB production was 1.79 g/L recorded by Ralstonia sp. after 48 h, while it was 1.40 g/L produced by R.eutropha ATCC 17697 after 48 h.

Keywords: bacteria forming polyhydroxyalkanoate, detection, molecular, Saudi Arabia

Procedia PDF Downloads 347

Authors: Sabri Sudirman, Yuan-Hua Hsu, Zwe-Ling Kong

Abstract:

Male reproductive dysfunction is predominantly due to insulin resistance and hyperglycemia result in inflammation and oxidative stress. Furthermore, nanotechnology provides an alternative approach to improve the bioavailability of natural active food ingredients. Therefore, the aim of this study were to investigate nanoencapsulated triterpenoids from petri-dish cultured Antrodia cinnamomea (PAC) nanoparticles whether it could increase the bioavailability; in addition, the anti-inflammatory and anti-oxidative effects could more effectively ameliorate the reproductive function of diabetic male rats. First, PAC encapsulated in chitosan-silica nanoparticles (Nano-PAC) were prepared by biosilicification method. Scanning electron micrographs confirm the average particle size is about 30 nm, and the encapsulation efficiency is 83.7% by HPLC. Diabetic male Sprague-Dawley rats were induced by high fat diet (40% kcal from fat) and streptozotocin (35 mg/kg). Nano-PAC was administered by oral gavage in three doses (4, 8 and 20 mg/kg) for 6 weeks. Besides, metformin (300 mg/kg) and nanoparticles (Nano) were treated as the positive and negative control respectively. Results indicated that 4 mg/kg Nano-PAC administration for 6 weeks improved hyperglycemia, insulin resistance, and also reduced advanced glycation end products in plasma. In addition, 8 mg/kg Nano-PAC ameliorated morphological of testicular seminiferous tubules, sperm morphology and motility, reactive oxygen species production and mitochondrial membrane potential. Moreover, 20 mg/kg Nano-PAC restored reproductive endocrine system function and increased KiSS-1 level in plasma. In plasma or testis anti-oxidant superoxide dismutase, glutathione peroxidase and catalase were increased whereas malondialdehyde, as well as pro-inflammatory cytokines tumor necrosis factor-α, interleukin-6, and interferon-gamma, decreased. Most importantly, 8 mg/kg Nano-PAC down-regulated the oxidative stress induced c-Jun N-terminal kinase (JNK) signaling pathway. Our study successfully nanoencapsulated PAC to form nanoparticles and low-dose Nano-PAC improved diabetes-induced hyperglycemia, inflammation and oxidative stress to ameliorate the reproductive function of diabetic male rats.

Keywords: Antrodia cinnamomea, diabetes mellitus, male reproduction, nanoparticles

Procedia PDF Downloads 222

Authors: Shuo Li, Yannick Coffinier, Chann Lagadec, Fabrizio Cleri, Katsuhiko Nishiguchi, Akira Fujiwara, Soo Hyeon Kim, Nicolas Clément

Abstract:

The need for single cell detection and analysis techniques has increased in the past decades because of the heterogeneity of individual living cells, which increases the complexity of the pathogenesis of malignant tumors. In the search for early cancer detection, high-precision medicine and therapy, the technologies most used today for sensitive detection of target analytes and monitoring the variation of these species are mainly including two types. One is based on the identification of molecular differences at the single-cell level, such as flow cytometry, fluorescence-activated cell sorting, next generation proteomics, lipidomic studies, another is based on capturing or detecting single tumor cells from fresh or fixed primary tumors and metastatic tissues, and rare circulating tumors cells (CTCs) from blood or bone marrow, for example, dielectrophoresis technique, microfluidic based microposts chip, electrochemical (EC) approach. Compared to other methods, EC sensors have the merits of easy operation, high sensitivity, and portability. However, despite various demonstrations of low limits of detection (LOD), including aptamer sensors, arrayed EC sensors for detecting single-cell have not been demonstrated. In this work, a new technique based on 20-nm-thick nanopillars array to support cells and keep them at ideal recognition distance for redox-labeled aptamers grafted on the surface. The key advantages of this technology are not only to suppress the false positive signal arising from the pressure exerted by all (including non-target) cells pushing on the aptamers by downward force but also to stabilize the aptamer at the ideal hairpin configuration thanks to a confinement effect. With the first implementation of this technique, a LOD of 13 cells (with5.4 μL of cell suspension) was estimated. In further, the nanosupported cell technology using redox-labeled aptasensors has been pushed forward and fully integrated into a single-cell electrochemical aptasensor array. To reach this goal, the LOD has been reduced by more than one order of magnitude by suppressing parasitic capacitive electrochemical signals by minimizing the sensor area and localizing the cells. Statistical analysis at the single-cell level is demonstrated for the recognition of cancer cells. The future of this technology is discussed, and the potential for scaling over millions of electrodes, thus pushing further integration at sub-cellular level, is highlighted. Despite several demonstrations of electrochemical devices with LOD of 1 cell/mL, the implementation of single-cell bioelectrochemical sensor arrays has remained elusive due to their challenging implementation at a large scale. Here, the introduced nanopillar array technology combined with redox-labeled aptamers targeting epithelial cell adhesion molecule (EpCAM) is perfectly suited for such implementation. Combining nanopillar arrays with microwells determined for single cell trapping directly on the sensor surface, single target cells are successfully detected and analyzed. This first implementation of a single-cell electrochemical aptasensor array based on Brownian-fluctuating redox species opens new opportunities for large-scale implementation and statistical analysis of early cancer diagnosis and cancer therapy in clinical settings.

Keywords: bioelectrochemistry, aptasensors, single-cell, nanopillars

Procedia PDF Downloads 118

Authors: Laura Rodríguez Amaya

Abstract:

The impact of natural disasters on food security can be devastating, especially in rural settings where livelihoods are closely tied to their productive assets. In hazards studies, absorptive capacity is seen as a threshold that impacts the degree of people’s recovery after a natural disaster. Increasing our understanding of households’ capacity to absorb natural disaster shocks can provide the international community with viable measurements for assessing at-risk communities’ resilience to food insecurities. The purpose of this study is to identify the most important factors in determining a household’s capacity to absorb the impact of a natural disaster. This is an empirical study conducted in six communities in Costa Rica affected by earthquakes. The Earthquake Impact Index was developed for the selection of the communities in this study. The households coded as total loss in the selected communities constituted the sampling frame from which the sample population was drawn. Because of the study area geographically dispersion over a large surface, the stratified clustered sampling hybrid technique was selected. Of the 302 households identified as total loss in the six communities, a total of 126 households were surveyed, constituting 42 percent of the sampling frame. A list of indicators compiled based on theoretical and exploratory grounds for the absorptive capacity construct served to guide the survey development. These indicators were included in the following variables: (1) use of informal safety nets, (2) Coping Strategy, (3) Physical Connectivity, and (4) Infrastructure Damage. A multivariate data analysis was conducted using Statistical Package for Social Sciences (SPSS). The results show that informal safety nets such as family and friends assistance exerted the greatest influence on the ability of households to absorb the impact of earthquakes. In conclusion, communities that experienced the highest environmental impact and human loss got disconnected from the social networks needed to absorb the shock’s impact. This resulted in higher levels of household food insecurity.

Keywords: absorptive capacity, earthquake, food security, rural

Procedia PDF Downloads 256

Authors: Vaishali Joshi, Pallav Joshi

Abstract:

Environment concern has become an important topic and continues to acquire more popularity in the coming scenario. We all are exposed to messages daily, which encourage us to involve in green behavior. Factors such as Global Warming, Climate change are creating a big buzz amongst the people. Realizing this, many firms/companies are adopting the bright way of making profit along with creating a brand image, by going green. These firms/companies persuade consumers to use purchase eco-friendly products for the benefit of the environment and the society. In such scenario, it becomes very essential for such firms/companies to approach the customers in a better way. In other words, we can say that marketing approach plays a crucial role for such firm/companies. Hence in this research study, we have tried to create a marketing approach for the firms/companies for selling the eco-friendly apparels. We have studied the hypothetical apparel brand who has taken a green initiative of making their products eco-friendly. We have named this hypothetical brand as “Go-Green”. By taking this hypothetical brand we have studied about how this brand can achieve better marketing approach. In particular, we have studied the four types of print advertisements of this brand as follows :(i) print advertisement showing only eco-friendly apparel (ii) print advertisement showing eco-friendly apparel labeled with eco-label (iii) print advertisement showing eco-friendly apparel along with information about the benefit of the featured apparel and (iv) print advertisement showing eco-friendly apparel with both eco-label and information about the benefit of the featured apparel. The conclusion of this research suggest that respondents more positively evaluate the print advertisement of eco-friendly apparel labeled with eco-labels and information about the benefit of the featured apparel, compared by other three print advertisement. Moreover, in this research study, we have studied environment knowledge, as the moderating factor affecting the consumer green purchase behavior.

Keywords: eco-friendly apparel, print advertisement, eco-label, environment knowledge

Procedia PDF Downloads 286

Authors: Ivan M. Taremwa, Scholastic Ashaba, Harriet O. Adrama, Carlrona Ayebazibwe, Daniel Omoding, Imelda Kemeza, Jane Yatuha, Thadeus Turuho, Noni E. MacDonald, Robert Hilliard

Abstract:

Background: The burden of malaria in Uganda remains unacceptably high, especially among children and pregnant women. To prevent malaria related complications, household possession and use of Insecticide Treated mosquito Nets (ITNs) has become a common practice in the country. Despite the availability of ITNs, the number of malaria cases has not gone down. We sought to explore knowledge, attitude, and behaviour towards the use of ITNs as a nightly malaria prevention strategy among pregnant women and children under five years of age in rural southwest Uganda. Materials and Methods: This was a community based, descriptive cross-sectional study, in which households with children under 5 years, and/or pregnant women were enrolled. We used a structured questionnaire to collect data on participants’ understanding of the causes, signs and symptoms of malaria; use of ITNs to prevent malaria; attitudes and behaviours towards the use of ITNs. We also conducted key informant interviews (KIIs) to get in-depth understanding of responses from the participants. We analysed quantitative data using STATA version 12. Qualitative findings from the KIIs were transcribed and translated, and manually analysed using thematic content analysis. Results: Of the 369 households enrolled, 98.6% (N=363) households had children under five. Most participants (41.2%, N=152) were in the 21-30 years of age category (mean age; 32.2). 98.6% (N=362) of the respondents considered ITNs a key malaria prevention strategy. The ITN possession rate was 84.0% (N=310), of these, 67.0% (N=205) consistently used them. 39% of the respondents did not have a positive attitude towards ITNs, as they considered more the perceived effects of ITNs. Conclusions: Although 84.0% of the respondents possessed ITNs, many were not consistently using them. There is need to engage all stakeholders (including cultural leaders, community health workers, religious leaders and the government) in the malaria prevention campaigns using ITNs through: a) government’s concerted effort to ensure universal access of good quality ITNs, b) end-user directed education to correct false beliefs and misinformation, c) telling the ITN success stories to improve on the usage.

Keywords: ITNs use, malaria, pregnant women, rural Uganda

Procedia PDF Downloads 357

Authors: Kiyanoush Ghalavand

Abstract:

Aquaculture production is inherently a risky business, and farmers face a variety of weather, pest, disease, inptut supply, and market related risks. There are many factors out farmers control and unpredictable. Insurance has an important role in aquaculture production and is a tool to support farmers against threats. Investigation of factors affecting aquaculture farmers' adoption of aquaculture insurance strategy was the objective of this study. The purpose of this study was determining the related factors to adoption of insurance by aquaculture farmers in Khuzestan province, Iran. The research design was a descriptive and correlation surveying method. Aquaculture farmers in Khuzestan province were the target population for this study. A random sample of aquaculture selected (N=1830, n =139). The main result of the study reveled that exist correlation between the level of education, knowledge about purpose of insurance, participation in extension course, visit with insurance organization, and contact with extension agents to the adoption of insurance by aquaculture farmers were significantly positive. By using Bartlett's test and KMO test, determine whether research variables are appropriate for factor analysis (Sig = 0.000, Bartlett test = 0.9724, KMO = 0.74). The number of factors was determined using a split plot, eigenvalue, and percent of variance. An examination of the items and their factors loadings was used to understand the nature of the nine factors. To reduce subjectivity, items with factor loading equal to or greater than 0.5 were considered most important when factors were labeled. The nine factors were labeled (1) Extension and education activities, (2) Economical characteristics, (3) Governmental support, (4) communicational channel, (5) local leaders, (6) Facilitate in given damage (7) Motivation establishing, (8) Given damage in appropriate methods and (9) Appropriate activities by insurance organization. The results obtained from the factors analysis reveal that the nine factors explain percentage75 of the variation of the adoption of insurance of the adoption of insurance by aquaculture farmers in Khuzestan province.

Keywords: aquaculture farmers, insurance, factorial analysis, Khuzestan province, risks

Procedia PDF Downloads 152

Authors: Natalia Alvarado, Myldred Hernandez-Gonzalez, Mary Laird, Madeline Phillips, Elizabeth Miller, Luis Mendez, Teresa Satterfield Linares

Abstract:

Objectives: Focusing on the reported levels of depressive symptoms from Hispanic individuals in the U.S. during the ongoing COVID-19 pandemic, we analyze the psychological effects of being labeled an ‘essential worker/trabajador(a) esencial.’ We situate this attribute within the complex context of how an individual’s mental health is linked to work status and his/her community’s attitude toward such a status. Method: 336 Spanish-speaking adults (Mage = 34.90; SD = 11.00; 46% female) living in the U.S. participated in a mixed-method study. Participants completed a self-report Spanish-language survey consisting of COVID-19 prompts (e.g., Soy un trabajador esencial durante la pandemia. I am an ‘essential worker’ during the pandemic), civic engagement scale (CES) attitudes (e.g., Me siento responsable de mi comunidad. I feel responsible for my community) and behaviors (e.g., Ayudo a los miembros de mi comunidad. I help members of my community), and the Center for Epidemiological Studies Depression Scale (e.g., Me sentía deprimido/a. I felt depressed). The survey was conducted several months into the pandemic and before the vaccine distribution. Results: Regression analyses show that being labeled an essential worker was correlated to CES attitudes (b= .28, p < .001) and higher CES behaviors (b= .32, p < .001). Essential worker status also reported higher levels of depressive symptoms (b= .17, p < .05). In addition, we found that CES attitudes and CES behaviors were related to higher levels of depressive symptoms (b= .11, p <.05, b = .22, p < .001, respectively). These findings suggest that those who are on the frontlines during the COVID-19 pandemic suffer higher levels of depressive symptoms, despite their affirming community attitudes and behaviors. Discussion: Hispanics/Latinxs make up 53% of the high-proximity employees who must work in person and in close contact with others; this is the highest rate of any racial or ethnic category. Moreover, 31% of Hispanics are classified as essential workers. Our outcomes show that those labeled as trabajadores esenciales convey attitudes of remaining strong and resilient for COVID-19 victims. They also express community attitudes and behaviors reflecting a sense of responsibility to continue working to help others during these unprecedented times. However, we also find that the pressure of maintaining basic needs for others exacerbates mental health challenges and stressors, as many essential workers are anxious and stressed about their physical and economic security. As a result, community attitudes do not protect from depressive symptoms as Hispanic essential workers are failing to balance everyone’s needs, including their own (e.g., physical exhaustion and psychological distress). We conclude with a discussion on alternatives to the phrase ‘essential worker’ and of incremental steps that can be taken to address pandemic-related mental health issues targeting US Hispanic workers.

Keywords: COVID-19, essential worker, mental health, race and ethnicity

Procedia PDF Downloads 129

Authors: Adel Khorramrouz, Monireh Ahmadi Bani, Ehsan Norouzi, Morvarid Lalenoor

Abstract:

Background: Plantar pressure distribution measurement has been used for a long time to assess foot disorders. Plantar pressure is an important component affecting the foot and ankle function and Changes in plantar pressure distribution could indicate various foot and ankle disorders. Morphologic and mechanical properties of the foot may be important factors affecting the plantar pressure distribution. Accurate and early measurement may help to reduce the prevalence of pes planus. With recent developments in technology, new techniques such as machine learning have been used to assist clinicians in predicting patients with foot disorders. Significance of the study: This study proposes a neural network learning-based flat foot classification methodology using static foot pressure distribution. Methodologies: Data were collected from 895 patients who were referred to a foot clinic due to foot disorders. Patients with pes planus were labeled by an experienced physician based on clinical examination. Then all subjects (with and without pes planus) were evaluated for static plantar pressures distribution. Patients who were diagnosed with the flat foot in both feet were included in the study. In the next step, the leg length was normalized and the network was trained for plantar pressure mapping images. Findings: From a total of 895 image data, 581 were labeled as pes planus. A computational neural network (CNN) ran to evaluate the performance of the proposed model. The prediction accuracy of the basic CNN-based model was performed and the prediction model was derived through the proposed methodology. In the basic CNN model, the training accuracy was 79.14%, and the test accuracy was 72.09%. Conclusion: This model can be easily and simply used by patients with pes planus and doctors to predict the classification of pes planus and prescreen for possible musculoskeletal disorders related to this condition. However, more models need to be considered and compared for higher accuracy.

Keywords: foot disorder, machine learning, neural network, pes planus

Procedia PDF Downloads 364

Authors: Patel P. Kailash, Patel M. Parimal

Abstract:

An investigation was conducted to study the different concentration of coal fly ash solution on morphological and biochemical parameters of Helianthus annuus L. The seeds of Helianthus annuus L. were placed in petri dishes in three replicates and allowed to grow for 16 days in different concentration of coal fly ash solution. Shoot length, root length and fresh weight, dry weight declined with increasing concentration of fly ash. Semidiluted and concentrated fly ash solution exhibited significant reduction in chlorophyll, protein,sugar and ascorbic acid. Concentration dependent changes were observed in most of parameters. Diluted solution of fly ash revealed the maximum increase morphological and biochemical changes of seedlings.

Keywords: Helianthus annuus L., protein, sugar, chlorophyll, coal fly ash

Procedia PDF Downloads 352

Authors: Jia-Lien Hsu, Chiung-Wen Chang

Abstract:

Research articles may follow a simple and succinct structure of organizational patterns, called move. For example, considering extended abstracts, we observe that an extended abstract usually consists of five moves, including Background, Aim, Method, Results, and Conclusion. As another example, when publishing articles in PubMed, authors are encouraged to provide a structured abstract, which is an abstract with distinct and labeled sections (e.g., Introduction, Methods, Results, Discussions) for rapid comprehension. This paper introduces a method for computational analysis of move structures (i.e., Background-Purpose-Method-Result-Conclusion) in abstracts and introductions of research documents, instead of manually time-consuming and labor-intensive analysis process. In our approach, sentences in a given abstract and introduction are automatically analyzed and labeled with a specific move (i.e., B-P-M-R-C in this paper) to reveal various rhetorical status. As a result, it is expected that the automatic analytical tool for move structures will facilitate non-native speakers or novice writers to be aware of appropriate move structures and internalize relevant knowledge to improve their writing. In this paper, we propose a Bayesian approach to determine move tags for research articles. The approach consists of two phases, training phase and testing phase. In the training phase, we build a Bayesian model based on a couple of given initial patterns and the corpus, a subset of CiteSeerX. In the beginning, the priori probability of Bayesian model solely relies on initial patterns. Subsequently, with respect to the corpus, we process each document one by one: extract features, determine tags, and update the Bayesian model iteratively. In the testing phase, we compare our results with tags which are manually assigned by the experts. In our experiments, the promising accuracy of the proposed approach reaches 56%.

Keywords: academic English writing, assisted writing, move tag analysis, Bayesian approach

Procedia PDF Downloads 332