Search results for: content independent features

Authors: Shuo Liu, Dan Liu

Abstract:

In the field of named entity recognition, most of the research has been conducted around simple entities. However, for nested named entities, which still contain entities within entities, it has been difficult to identify them accurately due to their boundary ambiguity. In this paper, a hierarchical recognition model is constructed based on the grammatical structure and semantic features of Chinese text for boundary calculation based on lexical features. The analysis is carried out at different levels in terms of granularity, semantics, and lexicality, respectively, avoiding repetitive work to reduce computational effort and using the semantic features of words to calculate the boundaries of entities to improve the accuracy of the recognition work. The results of the experiments carried out on web-based microblogging data show that the model achieves an accuracy of 86.33% and an F1 value of 89.27% in recognizing nested named entities, making up for the shortcomings of some previous recognition models and improving the efficiency of recognition of nested named entities.

Keywords: coarse-grained, nested named entity, Chinese natural language processing, word embedding, T-SNE dimensionality reduction algorithm

Procedia PDF Downloads 97

Authors: José A. Menezes, Giordano Cabral, Bruno T. Gomes

Abstract:

Choosing good features is an essential part of machine learning. Recent techniques aim to automate this process. For instance, feature learning intends to learn the transformation of raw data into a useful representation to machine learning tasks. In automatic audio classification tasks, this is interesting since the audio, usually complex information, needs to be transformed into a computationally convenient input to process. Another technique tries to generate features by searching a feature space. Genetic algorithms, for instance, have being used to generate audio features by combining or modifying them. We find this approach particularly interesting and, despite the undeniable advances of feature learning approaches, we wanted to take a step forward in the use of genetic algorithms to find audio features, combining them with more conventional methods, like PCA, and inserting search control mechanisms, such as constraints over a confusion matrix. This work presents the results obtained on particular audio classification problems.

Keywords: feature generation, feature learning, genetic algorithm, music information retrieval

Procedia PDF Downloads 400

Authors: A.Assariotakis, P. Vahamidis, P. Tarantilis, G. Economou

Abstract:

Greece, due to its geographical location and the particular climatic conditions, presents high biodiversity of Medicinal and Aromatic Plants. Among them, the genus Origanum not only presents a wide distribution, but it also has great economic importance. After extensive surveys in Ikaria Island (Greece), 3 species of the genus Origanum were identified, namely, Origanum vulgare ssp. hirtum (Greek oregano), Origanum onites (Turkish oregano) and Origanum x intercedens (hybrid), a naturally occurring hybrid between O. hirtum and O. onites. The purpose of this study was to determine their morphological as well as their temporal variability in essential oil yield and composition under field conditions. For this reason, a plantation of each species was created using vegetative propagation and was established at the experimental field of the Agricultural University of Athens (A.U.A.). From the establishment year and for the following two years (3 years of observations), several observations were taken during each growing season with the purpose of identifying the morphological differences among the studied species. Each year collected plant (at bloom stage) material was air-dried at room temperature in the shade. The essential oil content was determined by hydrodistillation using a Clevenger-type apparatus. The chemical composition of essential oils was investigated by Gas Chromatography-Mass Spectrometry (GC – MS). Significant differences were observed among the three oregano species in terms of plant height, leaf size, inflorescence features, as well as concerning their biological cycle. O. intercedens inflorescence presented more similarities with O. hirtum than with O. onites. It was found that calyx morphology could serve as a clear distinction feature between O. intercedens and O. hirtum. The calyx in O. hirtum presents five isometric teeth whereas in O. intercedens two high and three shorter. Essential oil content was significantly affected by genotype and year. O. hirtum presented higher essential oil content than the other two species during the first year of cultivation, however during the second year the hybrid (O. intercedens) recorded the highest values. Carvacrol, p-cymene and γ-terpinene were the main essential oil constituents of the three studied species. In O. hirtum carvacrol content varied from 84,28 - 93,35%, in O. onites from 86,97 - 91,89%, whereas in O. intercedens it was recorded the highest carvacrol content, namely from 89,25 - 97,23%.

Keywords: variability, oregano biotypes, essential oil, carvacrol

Procedia PDF Downloads 107

Authors: E. Oluwasola, E. Bamidele, E. Ogunbusola

Abstract:

Enriched “aadun” was produced from maize with, supplemented with cray fish and beans. Sodium chloride (Nacl) was also added to the product which acts as preservatives. The produced enriched “aadun” was compared with commercial “aadun” organoleptically the result of the sensory evaluation carried out on the product showed that there is a statistical significant difference between the mouth feel of enriched and commercial “aadun” at 0.05 level of significance (t=5.499, P<0.05) Similarly, the mean difference between enriched and commercial “aadun” in terms of aroma (t=4.403, P<0.05), taste (t=4.592, P<0.05) colour (t=2.788, P<0.05) and general acceptability (t=3.894, P<0.05) is statistically significant at 95% confidence level in each case, therefore, it is clearly revealed that product 321 (Enriched “aadun”) is more acceptable and significant better than product 432 (commercial “aadun”) in all the attributes evaluated. The proximate analysis using standard methods of analysis was carried out which include the moisture content, ash and protein content for both the enriched aadun and commercial aadun the result showed moisture content 9%, ash 6.2%, protein 19.6% and 12.9% moisture content, 4%ash content, 8.75% protein for the commercial and improved aadun respectively.

Keywords: aadun, enriched, maize, supplemented

Procedia PDF Downloads 528

Authors: S. Obregon-Cano, R. Moreno-Rojas, E. Cartea-Gonzalez, A. De Haro-Bailon

Abstract:

The potential of near-infrared spectroscopy (NIRS) for screening the total glucosinolate (t-GSL) content, and also, the aliphatic glucosinolates gluconapin (GNA), progoitrin (PRO) and glucobrassicanapin (GBN) in turnip greens and turnip tops was assessed. This crop is grown for edible leaves and stems for human consumption. The reference values for glucosinolates, as they were obtained by high performance liquid chromatography on the vegetable samples, were regressed against different spectral transformations by modified partial least-squares (MPLS) regression (calibration set of samples n= 350). The resulting models were satisfactory, with calibration coefficient values from 0.72 (GBN) to 0.98 (tGSL). The predictive ability of the equations obtained was tested using a set of samples (n=70) independent of the calibration set. The determination coefficients and prediction errors (SEP) obtained in the external validation were: GNA=0.94 (SEP=3.49); PRO=0.41 (SEP=1.08); GBN=0.55 (SEP=0.60); tGSL=0.96 (SEP=3.28). These results show that the equations developed for total glucosinolates, as well as for gluconapin can be used for screening these compounds in the leaves and stems of this species. In addition, the progoitrin and glucobrassicanapin equations obtained can be used to identify those samples with high, medium and low contents. The calibration equations obtained were accurate enough for a fast, non-destructive and reliable analysis of the content in GNA and tGSL directly from NIR spectra. The equations for PRO and GBN can be employed to identify samples with high, medium and low contents.

Keywords: brassica rapa, glucosinolates, gluconapin, NIRS, turnip greens

Procedia PDF Downloads 116

Authors: Naser Safdarian, Nader Jafarnia Dabanloo

Abstract:

In this paper we used four features i.e. Q-wave integral, QRS complex integral, T-wave integral and total integral as extracted feature from normal and patient ECG signals to detection and localization of myocardial infarction (MI) in left ventricle of heart. In our research we focused on detection and localization of MI in standard ECG. We use the Q-wave integral and T-wave integral because this feature is important impression in detection of MI. We used some pattern recognition method such as Artificial Neural Network (ANN) to detect and localize the MI. Because these methods have good accuracy for classification of normal and abnormal signals. We used one type of Radial Basis Function (RBF) that called Probabilistic Neural Network (PNN) because of its nonlinearity property, and used other classifier such as k-Nearest Neighbors (KNN), Multilayer Perceptron (MLP) and Naive Bayes Classification. We used PhysioNet database as our training and test data. We reached over 80% for accuracy in test data for localization and over 95% for detection of MI. Main advantages of our method are simplicity and its good accuracy. Also we can improve accuracy of classification by adding more features in this method. A simple method based on using only four features which extracted from standard ECG is presented which has good accuracy in MI localization.

Keywords: ECG signal processing, myocardial infarction, features extraction, pattern recognition

Procedia PDF Downloads 429

Authors: Khader S. Al-Aidmat, Venus W. Samawi

Abstract:

Blurred vision in the misty atmosphere is essential problem which needs to be resolved. To solve this problem, we developed a technique to restore foggy degraded image from its original version using Back-propagation neural network (BP-NN). The suggested technique is based on mapping between foggy scene and its corresponding original scene. Seven different approaches are suggested based on type of features used in image restoration. Features are extracted from spatial and spatial-frequency domain (using DCT). Each of these approaches comes with its own BP-NN architecture depending on type and number of used features. The weight matrix resulted from training each BP-NN represents a fog filter. The performance of these filters are evaluated empirically (using PSNR), and perceptually. By comparing the performance of these filters, the effective features that suits BP-NN technique for restoring foggy images is recognized. This system proved its effectiveness and success in restoring moderate foggy images.

Keywords: artificial neural network, discrete cosine transform, feed forward neural network, foggy image restoration

Procedia PDF Downloads 361

Authors: Nuchanat Handumrongkul, Suwaree Yordchim, Anantachai Aeka

Abstract:

Despite four years of study in the tourism industry, the Bachelor’s graduates cannot perform their jobs as experienced tour guides. This research aimed to develop French teaching and studying for Tourism with two main purposes: to analyze ‘Moves’ used in oral presentations at tourist attractions; and to study content in guiding presentations or 'Guide Speak'. The study employed audio recording of these presentations as an interview method in authentic situations, having four tour guides as respondents and information providers. The data was analyzed via moves and content analysis. The results found that there were eight moves used; namely: welcoming, introducing oneself, drawing someone’s attention, giving information, explaining, highlighting, persuading, and saying goodbye. In terms of content, the information being presented covered the outstanding characteristics of the places and well-integrated with other related content. The findings were used as guidelines for curriculum development; in particular, the core content and the presentation forming the basis for students to meet the standard requirements of the labor-market and professional schemes.

Keywords: moves, guiding presentation, french, tourism

Procedia PDF Downloads 215

Authors: Chieh-Fu Chang, Wan-Hsin Hsieh

Abstract:

We have proposed a novel scheme— iterative word-extension (IWE) to enhance the cliff effect of Reed-Solomon codes regarding the error performance at a specific Eb/N0. The scheme can be readily extended to block codes and the important properties of IWE are further investigated here. In order to select proper block codes specifying the desired cliff Eb/N0, the associated features of IWE are explored. These properties and features grant IWE ability to enhance security regarding the received Eb/N0 in physical layer so that IWE scheme can cooperate with the traditional presentation layer approach — cryptography, to meet the secure requirements in diverse applications. The features and feasibility of IWE scheme in satellite communication are finally discussed.

Keywords: security, IWE, cliff effect, space communications

Procedia PDF Downloads 391

Authors: Umme Hani, Mohammed Rahmatulla, Mohammed Ghazwani, Ali Alqahtani, Yahya Alhamhoom

Abstract:

Background and introduction: Neratinib is a potent anticancer drug used for the treatment of breast cancer. It is poorly soluble at higher pH, which tends to minimize the therapeutic effects in the lower gastrointestinal tract (GIT) leading to poor bioavailability. An attempt has been made to prepare and develop a gastro-retentive system of Neratinib to improve the drug bioavailability in the GIT by enhancing the gastric retention time. Materials and methods: In the present study a three-factor at two-level (23) factorial design based optimization was used to inspect the effects of three independent variables (factors) such as sodium alginate (A), sodium bicarbonate (B) and sodium citrate (C) on the dependent variables like in vitro gelation, in vitro floating, water uptake and percentage drug release. Results: All the formulations showed pH in the range 6.7 ±0.25 to 7.4 ±0.24, percentage drug content was observed to be 96.3±0.27 to 99.5 ±0.28%, in vitro gelation observed as gelation immediate remains for an extended period. Percentage of water uptake was in the range between 9.01±0.15 to 31.01±0.25%, floating lag time was estimated form 7±0.39 to 57±0.36 sec. F4 and F5 showed floating even after 12hrs. All formulations showed a release of around 90% drug release within 12hr. It was observed that the selected independent variables affect the dependent variables. Conclusion: The developed system may be a promising and alternative approach to augment gastric retention of drugs and enhances the therapeutic efficacy of the drug.

Keywords: neratinib, 2³ factorial design, sodium alginate, floating, in situ gelling system

Procedia PDF Downloads 121

Authors: Skyler Kim

Abstract:

An early diagnosis of leukemia has always been a challenge to doctors and hematologists. On a worldwide basis, it was reported that there were approximately 350,000 new cases in 2012, and diagnosing leukemia was time-consuming and inefficient because of an endemic shortage of flow cytometry equipment in current clinical practice. As the number of medical diagnosis tools increased and a large volume of high-quality data was produced, there was an urgent need for more advanced data analysis methods. One of these methods was the AI approach. This approach has become a major trend in recent years, and several research groups have been working on developing these diagnostic models. However, designing and implementing a leukemia diagnostic system in real clinical environments based on a deep learning approach with larger sets remains complex. Leukemia is a major hematological malignancy that results in mortality and morbidity throughout different ages. We decided to select acute lymphocytic leukemia to develop our diagnostic system since acute lymphocytic leukemia is the most common type of leukemia, accounting for 74% of all children diagnosed with leukemia. The results from this development work can be applied to all other types of leukemia. To develop our model, the Kaggle dataset was used, which consists of 15135 total images, 8491 of these are images of abnormal cells, and 5398 images are normal. In this paper, we design and implement a leukemia diagnostic system in a real clinical environment based on deep learning approaches with larger sets. The proposed diagnostic system has the function of detecting and classifying leukemia. Different from other AI approaches, we explore hybrid architectures to improve the current performance. First, we developed two independent convolutional neural network models: VGG19 and ResNet50. Then, using both VGG19 and ResNet50, we developed a hybrid deep learning architecture employing transfer learning techniques to extract features from each input image. In our approach, fusing the features from specific abstraction layers can be deemed as auxiliary features and lead to further improvement of the classification accuracy. In this approach, features extracted from the lower levels are combined into higher dimension feature maps to help improve the discriminative capability of intermediate features and also overcome the problem of network gradient vanishing or exploding. By comparing VGG19 and ResNet50 and the proposed hybrid model, we concluded that the hybrid model had a significant advantage in accuracy. The detailed results of each model’s performance and their pros and cons will be presented in the conference.

Keywords: acute lymphoblastic leukemia, hybrid model, leukemia diagnostic system, machine learning

Procedia PDF Downloads 160

Authors: M. Alsull

Abstract:

In this study, Tetraselmis sp. and Chlorella sp. isolated from Penang National Park coastal waters, Malaysia, and cultivated under combined various laboratory conditions (temperature, light and nitrogen limitation and starvation). Growth rate, dry weight, chlorophyll a content, total lipids content and total carbohydrates content were estimated at mid-exponential growth phase. Tetraselmis sp. and Chlorella sp. showed remarkably decrease in growth rate, chlorophyll a content and dry weight when maintained under nitrogen limitation and starvation conditions, as well as when grown under 12:12 h light, dark regime conditions. Chlorella sp. showed ability to counter the fluctuation in temperature with no significant effects on the measured parameters; in contrast, Tetraselmis sp. showed a decrease in growth rate, chlorophyll a content and dry weight when grown under 15±1˚C temperature. Cultures maintained under nitrogen full concentration, and 24 h light regime showed decrease in total lipids content, compared with 12:12 h light, dark cycle regime, in the two tested species.

Keywords: microalgae, biochemical composition, temperature, light, nitrogen limitation

Procedia PDF Downloads 265

Authors: Vesna Kirandziska, Nevena Ackovska, Ana Madevska Bogdanova

Abstract:

The problem of emotion recognition is a challenging problem. It is still an open problem from the aspect of both intelligent systems and psychology. In this paper, both voice features and facial features are used for building an emotion recognition system. A Support Vector Machine classifiers are built by using raw data from video recordings. In this paper, the results obtained for the emotion recognition are given, and a discussion about the validity and the expressiveness of different emotions is presented. A comparison between the classifiers build from facial data only, voice data only and from the combination of both data is made here. The need for a better combination of the information from facial expression and voice data is argued.

Keywords: emotion recognition, facial recognition, signal processing, machine learning

Procedia PDF Downloads 290

Authors: C. Lanzerstorfer, M. Hinterberger

Abstract:

The iron content of the ore used is crucial for the productivity and coke consumption rate in blast furnace pig iron production. Therefore, most iron ore deposits are processed in beneficiation plants to increase the iron content and remove impurities. In several comminution stages, the particle size of the ore is reduced to ensure that the iron oxides are physically liberated from the gangue. Subsequently, physical separation processes are applied to concentrate the iron ore. The fine-grained ore concentrates produced need to be transported, stored, and processed. For smooth operation of these processes, the flow properties of the material are crucial. The flowability of powders depends on several properties of the material: grain size, grain size distribution, grain shape, and moisture content of the material. The flowability of powders can be measured using ring shear testers. In this study, the influence of the moisture content on the flowability for the Krivoy Rog magnetite iron ore concentrate was investigated. Dry iron ore concentrate was mixed with varying amounts of water to produce samples with a moisture content in the range of 0.2 to 12.2%. The flowability of the samples was investigated using a Schulze ring shear tester. At all measured values of the normal stress (1.0 kPa – 20 kPa), the flowability decreased significantly from dry ore to a moisture content of approximately 3-5%. At higher moisture contents, the flowability was nearly constant, while at the maximum moisture content the flowability improved for high values of the normal stress only. The results also showed an improving flowability with increasing consolidation stress for all moisture content levels investigated. The wall friction angle of the dust with carbon steel (S235JR), and an ultra-high molecule low-pressure polyethylene (Robalon) was also investigated. The wall friction angle increased significantly from dry ore to a moisture content of approximately 3%. For higher moisture content levels, the wall friction angles were nearly constant. Generally, the wall friction angle was approximately 4° lower at the higher wall normal stress.

Keywords: iron ore concentrate, flowability, moisture content, wall friction angle

Procedia PDF Downloads 292

Authors: Narmina Mammadova

Abstract:

In modern linguistics, the comparative study of languages is becoming increasingly popular, the typology and comparison of languages that have different structures is expanding and deepening. Of particular interest is the study of phraseological units, which makes it possible to identify the specific features of the compared languages in all their national identity. This paper gives a brief analysis of the comparative study of somatic phraseological units (SFU) of the Spanish and Turkish languages with the component "hand" in the semantic aspect; identification of equivalents, analogs and non-equivalent units, as well as a description of methods of translation of non-equivalent somatic phraseological units. Comparative study of the phraseology of unrelated languages is of particular relevance since it allows us to identify both general, universal features and differential and specific features characteristic of a particular language. Based on the results of the generalization of the study, it can be assumed that phraseological units containing a somatic component have a high interlingual phraseological activity, which contributes to an increase in the degree of interlingual equivalence.

Keywords: Linguoculturology, Turkish, Spanish, language picture of the world, phraseological units, semantic microfield

Procedia PDF Downloads 167

Authors: Jessemyn Modiini, Timothy Lynar, Elena Sitnikova

Abstract:

We present a novel enhanced compartmental model for malware spread analysis in cyber security. This paper applies cyber security data features to epidemiological compartmental models to model the infectious potential of malware. Compartmental models are most efficient for calculating the infectious potential of a disease. In this paper, we discuss and profile epidemiologically relevant data features from a Domain Name System (DNS) dataset. We then apply these features to epidemiological compartmental models to network traffic features. This paper demonstrates how epidemiological principles can be applied to the novel analysis of key cybersecurity behaviours and trends and provides insight into threat modelling above that of kill-chain analysis. In applying deterministic compartmental models to a cyber security use case, the authors analyse the deficiencies and provide an enhanced stochastic model for cyber epidemiology. This enhanced compartmental model (SUEICRN model) is contrasted with the traditional SEIR model to demonstrate its efficacy.

Keywords: cybersecurity, epidemiology, cyber epidemiology, malware

Procedia PDF Downloads 83

Authors: Souvik Phadikar, Nidul Sinha, Rajdeep Ghosh

Abstract:

In brainwaves research using electroencephalogram (EEG) signals, finding the most relevant and effective feature set for identification of activities in the human brain is a big challenge till today because of the random nature of the signals. The feature extraction method is a key issue to solve this problem. Finding those features that prove to give distinctive pictures for different activities and similar for the same activities is very difficult, especially for the number of activities. The performance of a classifier accuracy depends on this quality of feature set. Further, more number of features result in high computational complexity and less number of features compromise with the lower performance. In this paper, a novel idea of the selection of optimal feature set using a heuristically optimized deep autoencoder is presented. Using various feature extraction methods, a vast number of features are extracted from the EEG signals and fed to the autoencoder deep neural network. The autoencoder encodes the input features into a small set of codes. To avoid the gradient vanish problem and normalization of the dataset, a meta-heuristic search algorithm is used to minimize the mean square error (MSE) between encoder input and decoder output. To reduce the feature set into a smaller one, 4 hidden layers are considered in the autoencoder network; hence it is called Heuristically Optimized Deep Autoencoder (HO-DAE). In this method, no features are rejected; all the features are combined into the response of responses of the hidden layer. The results reveal that higher accuracy can be achieved using optimal reduced features. The proposed HO-DAE is also compared with the regular autoencoder to test the performance of both. The performance of the proposed method is validated and compared with the other two methods recently reported in the literature, which reveals that the proposed method is far better than the other two methods in terms of classification accuracy.

Keywords: autoencoder, brainwave signal analysis, electroencephalogram, feature extraction, feature selection, optimization

Procedia PDF Downloads 92

Authors: Ning Kang, Marius Doornenbal

Abstract:

Funding is a very important – if not crucial – resource for research projects. Usually, funding organizations will publish a description of the funded research to describe the scope of the funding award. Logically, we would expect research outcomes to align with this funding award. For that reason, we might be able to predict future research topics based on present funding award data. That said, it remains to be shown if and how future research topics can be predicted by using the funding information. In this paper, we extract funding project information and their generated paper abstracts from the Gateway to Research database as a group, and use the papers from the same domains and publication years in the Scopus database as a baseline comparison group. We annotate both the project awards and the papers resulting from the funded projects with linguistic features (noun phrases), and then calculate tf-idf and cosine similarity between these two set of features. We show that the cosine similarity between the project-generated papers group is bigger than the project-baseline group, and also that these two groups of similarities are significantly different. Based on this result, we conclude that the funding information actually correlates with the content of future research output for the funded project on the topical level. How funding really changes the course of science or of scientific careers remains an elusive question.

Keywords: natural language processing, noun phrase, tf-idf, cosine similarity

Procedia PDF Downloads 217

Authors: Miloš Matúš, Peter Križan, Ľubomír Šooš, Juraj Beniak

Abstract:

The moisture content of densified biomass is a limiting parameter influencing the quality of this solid biofuel. It influences its calorific value, density, mechanical strength and dimensional stability as well as affecting its production process. This paper deals with experimental research into the effect of moisture content of the densified material on the final quality of biofuel in the form of logs (briquettes or pellets). Experiments based on the single-axis densification of the spruce sawdust were carried out with a hydraulic piston press (piston and die), where the densified logs were produced at room temperature. The effect of moisture content on the qualitative properties of the logs, including density, change of moisture, expansion and physical changes, and compressive and impact resistance were studied. The results show the moisture ranges required for producing good-quality logs. The experiments were evaluated and the moisture content of the tested material was optimized to achieve the optimum value for the best quality of the solid biofuel. The dense logs also have high-energy content per unit volume. The research results could be used to develop and optimize industrial technologies and machinery for biomass densification to achieve high quality solid biofuel.

Keywords: biomass, briquettes, densification, fuel quality, moisture content, density

Procedia PDF Downloads 397

Authors: Pratik Gandhi, Kavitha Chandra, Charles Thompson

Abstract:

A computational model of the acoustic room impulse response between transmitters and receivers located in an enclosed cavity under the influence of frequency-dependent reflection coefficients of the walls is presented. The characteristic features of the impulse responses that differentiate these results from frequency-independent reflecting surfaces are discussed. The image-source model is derived from the first principle solution to Green's function of the acoustic wave equation. The post-processing of the computed impulse response with a band-pass filter to better represents the response of a loud-speaker is demonstrated.

Keywords: acoustic room impulse response, frequency dependent reflection coefficients, Green's function, image model

Procedia PDF Downloads 192

Authors: Xingyu Gao, Qiang Wu

Abstract:

Patents play a crucial role in protecting innovation and intellectual property. Early prediction of the impact of artificial intelligence (AI) patents helps researchers and companies allocate resources and make better decisions. Understanding the key factors that influence patent impact can assist researchers in gaining a better understanding of the evolution of AI technology and innovation trends. Therefore, identifying highly impactful patents early and providing support for them holds immeasurable value in accelerating technological progress, reducing research and development costs, and mitigating market positioning risks. Despite the extensive research on AI patents, accurately predicting their early impact remains a challenge. Traditional methods often consider only single factors or simple combinations, failing to comprehensively and accurately reflect the actual impact of patents. This paper utilized the artificial intelligence patent database from the United States Patent and Trademark Office and the Len.org patent retrieval platform to obtain specific information on 35,708 AI patents. Using six machine learning models, namely Multiple Linear Regression, Random Forest Regression, XGBoost Regression, LightGBM Regression, Support Vector Machine Regression, and K-Nearest Neighbors Regression, and using early indicators of patents as features, the paper comprehensively predicted the impact of patents from three aspects: technical, social, and economic. These aspects include the technical leadership of patents, the number of citations they receive, and their shared value. The SHAP (Shapley Additive exPlanations) metric was used to explain the predictions of the best model, quantifying the contribution of each feature to the model's predictions. The experimental results on the AI patent dataset indicate that, for all three target variables, LightGBM regression shows the best predictive performance. Specifically, patent novelty has the greatest impact on predicting the technical impact of patents and has a positive effect. Additionally, the number of owners, the number of backward citations, and the number of independent claims are all crucial and have a positive influence on predicting technical impact. In predicting the social impact of patents, the number of applicants is considered the most critical input variable, but it has a negative impact on social impact. At the same time, the number of independent claims, the number of owners, and the number of backward citations are also important predictive factors, and they have a positive effect on social impact. For predicting the economic impact of patents, the number of independent claims is considered the most important factor and has a positive impact on economic impact. The number of owners, the number of sibling countries or regions, and the size of the extended patent family also have a positive influence on economic impact. The study primarily relies on data from the United States Patent and Trademark Office for artificial intelligence patents. Future research could consider more comprehensive data sources, including artificial intelligence patent data, from a global perspective. While the study takes into account various factors, there may still be other important features not considered. In the future, factors such as patent implementation and market applications may be considered as they could have an impact on the influence of patents.

Keywords: patent influence, interpretable machine learning, predictive models, SHAP

Procedia PDF Downloads 18

Authors: Jing Yuan, Hongwei Yang

Abstract:

This paper aims to understand U.S. middle school students’ mathematics achievements by examining relevant student and school-level predictors. Through a variance component analysis, the study first identifies evidence supporting the use of multilevel modeling. Then, a multilevel analysis is performed under Bayesian statistical inference where prior information is incorporated into the modeling process. During the analysis, independent variables are entered sequentially in the order of theoretical importance to create a hierarchy of models. By evaluating each model using Bayesian fit indices, a best-fit and most parsimonious model is selected where Bayesian statistical inference is performed for the purpose of result interpretation and discussion. The primary dataset for Bayesian modeling is derived from the Program for International Student Assessment (PISA) in 2012 with a secondary PISA dataset from 2003 analyzed under the traditional ordinary least squares method to provide the information needed to specify informative priors for a subset of the model parameters. The dependent variable is a composite measure of mathematics literacy, calculated from an exploratory factor analysis of all five PISA 2012 mathematics achievement plausible values for which multiple evidences are found supporting data unidimensionality. The independent variables include demographics variables and content-specific variables: mathematics efficacy, teacher-student ratio, proportion of girls in the school, etc. Finally, the entire analysis is performed using the MCMCpack and MCMCglmm packages in R.

Keywords: Bayesian multilevel modeling, mathematics education, PISA, multilevel

Procedia PDF Downloads 303

Authors: S. Njoumi, L. Ben Haj Said, M. J. Amiot, S. Bellagha

Abstract:

The main objective of this research was to establish the kinetics of variation of total polyphenol content (TPC) and total flavonoid content (TFC) in Tunisian Corchorus olitorius powder and in a traditional home cooked-meal (Molokheiya) when using stewing and stir-frying as cooking methods, but also to compare the effect of these two common cooking practices on water content, TPC, TFC and color. The L*, a* and b* coordinates values of the Molokheiya varied from 24.955±0.039 to 21.301±0.036, from -1.556±0.048 to 0.23±0.026 and from 5.675±0.052 to 6.313±0.103 when using stewing and from 21.328±0.025 to 20.56±0.021, from -1.093± 0.011to 0.121±0.007 and from 5.708±0.020 to 6.263±0.007 when using stir-frying, respectively. TPC and TFC increased during cooking. TPC of Molokheiya varied from 29.852±0.866 mg GAE/100 g to 220.416±0.519 mg GAE/100 g after 150 min of stewing and from 25.257±0.259 mg GAE/100 g to 208.897 ±0.173 mg GAE/100 g using stir-frying method during 150 min. TFC of Molokheiya varied from 48.229±1.47 mg QE/100 g to 843.802±1.841 mg QE/100 g when using stewing and from 37.031± 0.368 mg QE/100 g to 775.312±0.736 mg QE/100 g when using stir-frying. Kinetics followed similar curves in all cases but resulted in different final TPC and TFC. The shape of the kinetics curves suggests zero-order kinetics. The mathematical relations and the numerical approach used to model the kinetics of polyphenol and flavonoid contents in Molokheiya are described.

Keywords: Corchorus olitorius, Molokheiya, phenolic compounds, kinetic

Procedia PDF Downloads 327

Authors: Adilah Shariff, Nurhidayah Mohamed Noor, Alexander Lau, Muhammad Azwan Mohd Ali

Abstract:

Biomass such as corn and cassava wastes if left to decay will release significant quantities of greenhouse gases (GHG) including carbon dioxide and methane. The biomass wastes can be converted into biochar via thermochemical process such as slow pyrolysis. This approach can reduce the biomass wastes as well as preserve its carbon content. Biochar has the potential to be used as a carbon sequester and soil amendment. The aim of this study is to investigate the characteristics of the corn cob, cassava stem, and cassava rhizome in order to identify their potential as pyrolysis feedstocks for biochar production. This was achieved by using the proximate and elemental analyses as well as calorific value and lignocellulosic determination. The second objective is to investigate the effect of pyrolysis temperature on the biochar produced. A fixed bed slow pyrolysis reactor was used to pyrolyze the corn cob, cassava stem, and cassava rhizome. The pyrolysis temperatures were varied between 400 °C and 600 °C, while the heating rate and the holding time were fixed at 5 °C/min and 1 hour, respectively. Corn cob, cassava stem, and cassava rhizome were found to be suitable feedstocks for pyrolysis process because they contained a high percentage of volatile matter more than 80 mf wt.%. All the three feedstocks contained low nitrogen and sulphur content less than 1 mf wt.%. Therefore, during the pyrolysis process, the feedstocks give off very low rate of GHG such as nitrogen oxides and sulphur oxides. Independent of the types of biomass, the percentage of biochar yield is inversely proportional to the pyrolysis temperature. The highest biochar yield for each studied temperature is from slow pyrolysis of cassava rhizome as the feedstock contained the highest percentage of ash compared to the other two feedstocks. The percentage of fixed carbon in all the biochars increased as the pyrolysis temperature increased. The increment of pyrolysis temperature from 400 °C to 600 °C increased the fixed carbon of corn cob biochar, cassava stem biochar and cassava rhizome biochar by 26.35%, 10.98%, and 6.20% respectively. Irrespective of the pyrolysis temperature, all the biochars produced were found to contain more than 60 mf wt.% fixed carbon content, much higher than its feedstocks.

Keywords: biochar, biomass, cassava wastes, corn cob, pyrolysis

Procedia PDF Downloads 271

Authors: Tsegay Giday Woldu, Haibin Zhang, Xin Zhang, Yemane Hailu Fissuh

Abstract:

It is well known that nonlinear conjugate gradient method is one of the widely used first order methods to solve large scale unconstrained smooth optimization problems. Because of the low memory requirement, attractive theoretical features, practical computational efficiency and nice convergence properties, nonlinear conjugate gradient methods have a special role for solving large scale unconstrained optimization problems. Large scale optimization problems are with important applications in practical and scientific world. However, nonlinear conjugate gradient methods have restricted information about the curvature of the objective function and they are likely less efficient and robust compared to some second order algorithms. To overcome these drawbacks, the new modified nonlinear conjugate gradient method is presented. The noticeable features of our work are that the new search direction possesses the sufficient descent property independent of any line search and it belongs to a trust region. Under mild assumptions and standard Wolfe line search technique, the global convergence property of the proposed algorithm is established. Furthermore, to test the practical computational performance of our new algorithm, numerical experiments are provided and implemented on the set of some large dimensional unconstrained problems. The numerical results show that the proposed algorithm is an efficient and robust compared with other similar algorithms.

Keywords: conjugate gradient method, global convergence, large scale optimization, sufficient descent property

Procedia PDF Downloads 168

Authors: Lina Najafian, Hamidreza Vakilifard

Abstract:

The present study focused on the relationship between the quality of accruals and non-systematic risk. The independent study variables included the ability of accruals, the information content of accruals, and amount of discretionary accruals considered as accruals quality measures. The dependent variable was non-systematic risk based on the Fama and French Three Factor model (FFTFM) and the capital asset pricing model (CAPM). The control variables were firm size, financial leverage, stock return, cash flow fluctuations, and book-to-market ratio. The data collection method was based on library research and document mining including financial statements. Multiple regression analysis was used to analyze the data. The study results showed that there is a significant direct relationship between financial leverage and discretionary accruals and non-systematic risk based on FFTFM and CAPM. There is also a significant direct relationship between the ability of accruals, information content of accruals, firm size, and stock return and non-systematic based on both models. It was also found that there is no relationship between book-to-market ratio and cash flow fluctuations and non-systematic risk.

Keywords: accruals quality, non-systematic risk, CAPM, FFTFM

Procedia PDF Downloads 137

Authors: Yalong Jiang, Zheru Chi

Abstract:

In this paper, we study the factors which determine the capacity of a Convolutional Neural Network (CNN) model and propose the ways to evaluate and adjust the capacity of a CNN model for best matching to a specific pattern recognition task. Firstly, a scheme is proposed to adjust the number of independent functional units within a CNN model to make it be better fitted to a task. Secondly, the number of independent functional units in the capsule network is adjusted to fit it to the training dataset. Thirdly, a method based on Bayesian GAN is proposed to enrich the variances in the current dataset to increase its complexity. Experimental results on the PASCAL VOC 2010 Person Part dataset and the MNIST dataset show that, in both conventional CNN models and capsule networks, the number of independent functional units is an important factor that determines the capacity of a network model. By adjusting the number of functional units, the capacity of a model can better match the complexity of a dataset.

Keywords: CNN, convolutional neural network, capsule network, capacity optimization, character recognition, data augmentation, semantic segmentation

Procedia PDF Downloads 122

Authors: Michael Steve Lopez Bernabe

Abstract:

Political news coverage of tabloid sheets as one of the print media molds or influences public opinions and perceptions. In this study, Critical Discourse Analysis was employed to 30 political news taken from major tabloid sheets in the Philippines in order to determine the linguistics features and other features characterizing the political news in tabloids such as discursive styles, news topics or contexts, journalistic roles and news sources. The political underpinnings through framing were also explored in the study. The results revealed that the linguistics features of the news coverage include moods and modalities (morphology), passivity and transitivity, nominalization, appositives and embedding (syntax), and pre-modifications, the use of verbs and omissions (grammatical features). The discursive features were direct or indirect speech; cohesion; endophora and classifications. In terms of news sources were politicians, experts, and journalists; and the tabloid perform the journalistic roles such as an intervention, watchdog, loyal-facilitator, service, infotainment and civic. The news was also evident of different political underpinnings such as game or strategic framing, conflict framing, human interest framing, attrition of responsibility framing, morality framing, economic consequences framing and issue framing.

Keywords: critical discourse analysis, political news, applied linguistics, Philippines, tabloid sheets

Procedia PDF Downloads 12

Authors: Moh Rizaldi, Ali Abdurachman, Indra Perwira

Abstract:

The biggest demonstration after the 1998 reforms that took place in Indonesia for several days at the end of 2019 did not eliminate the intention of the People’s Representative Council (Dewan Perwakilan Rakyat or DPR) and the President to enact the law 19 of 2019 (KPK law). There is a central issue to be highlighted, namely whether the change is intended to strengthen or even weaken the KPK. To achieve this goal, the Analysis focuses on two agency principles namely the independent principle and the control principle as seen from three things namely the legal substance, legal structure, and legal culture. The research method is normative with conceptual, historical and statute approaches. The argument from this writing is that KPK Law has cut most of the KPK's authority as a result the KPK has become symbolic or toothless in combating corruption.

Keywords: control, independent, KPK, law no. 19 of 2019

Procedia PDF Downloads 101

Authors: Bahar Basturk, Secil Celik Erbas, Sevket Can Sarikaya

Abstract:

Composites combining the particulates and polymer components have attracted great interest in various application areas such as packaging, furniture, electronics and automotive industries. For strengthening the plastic matrices, the utilization of natural fillers instead of traditional reinforcement materials has received increased attention. The properties of natural filler based polymer composites (NFPC) may be improved by applying proper surface modification techniques to the powder phase of the structures. In this study, acorn powder-epoxy and pine corn powder-epoxy composites containing up to 45% weight percent particulates were prepared by casting method. Alkali treatment and acetylation techniques were carried out to the natural particulates for investigating their influences under mechanical forces. The effects of filler type and content on the tensile properties of the composites were compared with neat epoxy. According to the quasi-static tensile tests, the pine cone based composites showed slightly higher rigidity and strength properties compared to the acorn reinforced samples. Furthermore, the structures independent of powder type and surface modification technique, showed higher tensile properties with increasing the particle content.

Keywords: natural fillers, polymer composites, surface modifications, tensile properties

Procedia PDF Downloads 439