Search results for: sparse Bayesian learning

Authors: Khaled M. Alhawiti

Abstract:

Reading capability is a major segment of language competency. On the other hand, discovering topical writings at a fitting level for outside and second language learners is a test for educators. We address this issue utilizing natural language preparing innovation to survey reading level and streamline content. In the connection of outside and second-language learning, existing measures of reading level are not appropriate to this errand. Related work has demonstrated the profit of utilizing measurable language preparing procedures; we expand these thoughts and incorporate other potential peculiarities to measure intelligibility. In the first piece of this examination, we join characteristics from measurable language models, customary reading level measures and other language preparing apparatuses to deliver a finer technique for recognizing reading level. We examine the execution of human annotators and assess results for our finders concerning human appraisals. A key commitment is that our identifiers are trainable; with preparing and test information from the same space, our finders beat more general reading level instruments (Flesch-Kincaid and Lexile). Trainability will permit execution to be tuned to address the needs of specific gatherings or understudies.

Keywords: natural language processing, trainability, syntactic simplification tools, education

Procedia PDF Downloads 490

Authors: Promise Ekpo Osaine, Daniel Melesse

Abstract:

Image captioning is an active area of research in the multi-modal artificial intelligence (AI) community as it connects vision and language understanding, especially in settings where it is required that a model understands the content shown in an image and generates semantically and grammatically correct descriptions. In this project, we followed a standard approach to a deep learning-based image captioning model, injecting architecture for the encoder-decoder setup, where the encoder extracts image features, and the decoder generates a sequence of words that represents the image content. As such, we investigated image encoders, which are ResNet101, InceptionResNetV2, EfficientNetB7, EfficientNetV2M, and CLIP. As a caption generation structure, we explored long short-term memory (LSTM). The CLIP-LSTM model demonstrated superior performance compared to the encoder-decoder models, achieving a BLEU-1 score of 0.904 and a BLEU-4 score of 0.640. Additionally, among the CNN-LSTM models, EfficientNetV2M-LSTM exhibited the highest performance with a BLEU-1 score of 0.896 and a BLEU-4 score of 0.586 while using a single-layer LSTM.

Keywords: multi-modal AI systems, image captioning, encoder, decoder, BLUE score

Procedia PDF Downloads 78

Authors: Engku Haliza Engku Ibrahim, Isarji Sarudin, Ainon Jariah Muhamad

Abstract:

It is generally agreed that many factors contribute to one’s reading comprehension and there is consensus that vocabulary size one of the main factors. This study explores the relationship between second language learners’ vocabulary size and their reading comprehension scores. 130 Malay pre-university students of a public university participated in this study. They were students of an intensive English language programme doing preparatory English courses to pursue bachelors degree in English. A quantitative research method was employed based on the Vocabulary Levels Test by Nation (1990) and the reading comprehension score of the in-house English Proficiency Test. A review of the literature indicates that a somewhat positive correlation is to be expected though findings of this study can only be explicated once the final analysis has been carried out. This is an ongoing study and it is anticipated that results of this research will be finalized in the near future. The findings will help provide beneficial implications for the prediction of reading comprehension performance. It also has implications for the teaching of vocabulary in the ESL context. A better understanding of the relationship between vocabulary size and reading comprehension scores will enhance teachers’ and students’ awareness of the importance of vocabulary acquisition in the L2 classroom.

Keywords: vocabulary size, vocabulary learning, reading comprehension, ESL

Procedia PDF Downloads 452

Authors: Muhammad Akram, Qamar Naseem, Imtiaz Ahmad

Abstract:

The purpose of this study was to correlate students’ perceptions of teacher effectiveness with their academic achievement in English and Mathematics at the secondary level (grade 9th) based on five national professional standards for teacher evaluation in Pakistan (subject matter knowledge, instructional planning and strategies, assessment, learning environment, effective communication. A Students’ Perceptions of Teacher Effectiveness Questionnaire (SPTEQ) was developed by the researchers to collect data from 2009 students from forty public girls and boys high/ higher secondary schools in district Khanewal, Pakistan. The overall reliability of the SPTEQ was α=.86. The study found a significant positive relationship among all the five factors of teacher effectiveness construct. The study also showed significant, positive relationship between teacher effectiveness factors and students’ achievement in English and mathematics. No significant differences were found between male and female students’ perceptions about their English teacher effectiveness. The implications include students’ personal attachments with their teachers that might convince them to overrate their teachers.

Keywords: communication, students’ achievement, teacher effectiveness, teaching strategies, teaching strategies

Procedia PDF Downloads 301

Authors: Li Qingjian, Li Ke, He Chun, Huang Yong

Abstract:

In this paper, the method of combining the Pohl Seidman's deep belief network with the self-organizing neural network is proposed to classify the target. This method is mainly aimed at the high nonlinearity of the hyperspectral image, the high sample dimension and the difficulty in designing the classifier. The main feature of original data is extracted by deep belief network. In the process of extracting features, adding known labels samples to fine tune the network, enriching the main characteristics. Then, the extracted feature vectors are classified into the self-organizing neural network. This method can effectively reduce the dimensions of data in the spectrum dimension in the preservation of large amounts of raw data information, to solve the traditional clustering and the long training time when labeled samples less deep learning algorithm for training problems, improve the classification accuracy and robustness. Through the data simulation, the results show that the proposed network structure can get a higher classification precision in the case of a small number of known label samples.

Keywords: DBN, SOM, pattern classification, hyperspectral, data compression

Procedia PDF Downloads 341

Authors: Iván García-Magariño, Javier Bravo-Agapito, Marta López-Fernández

Abstract:

Online judges have proven their utility in partial auto-evaluation of programming short exercises in the last decades. UnitJudge online judge has the advantage of facilitating the evaluation of separate units to provide more segregate and meaningful feedback to students in complex exercises and practices. This paper discusses the use of UnitUdge in advanced Java object-oriented programming exercises and web development practices. This later usage has been proposed by means of the Selenium Java library and classes to provide the web address. Consequently, UnitJudge is an online judge system that can be applied in several subjects, and therefore, many other students would take advantage of self-testing their exercises. This paper presents the experiments with a Java programming exercise for learning Java object-oriented classes with a generic type. Considering 10 students who voluntarily used UnitJudge, 80% successfully learned this concept, passing the judge exercise with correct results.

Keywords: online judges, programming skills, computer science education, auto-evaluation

Procedia PDF Downloads 101

Authors: P. S. Jagadeesh Kumar, Tracy Lin Huan, Rebecca K. Rossi, Yanmin Yuan, Xianpei Li

Abstract:

The fiscal growth of any country hinges on the prudent administration of water resources. The river Yamuna and Ganga are measured as the life line of India as it affords the needs for life to endure. Earth observation over remote sensing images permits the precise description and identification of ingredients on the superficial from space and airborne platforms. Multiple and heterogeneous image sources are accessible for the same geographical section; multispectral, hyperspectral, radar, multitemporal, and multiangular images. In this paper, a taxonomical learning of the fluvial geomorphological features of river Yamuna and Ganga over doon valley using color fusion of multispectral remote sensing images was performed. Experimental results exhibited that the segmentation based colorization technique stranded on pattern recognition, and color mapping fashioned more colorful and truthful colorized images for geomorphological feature extraction.

Keywords: color fusion, geomorphology, fluvial processes, multispectral images, pattern recognition

Procedia PDF Downloads 306

Authors: Wei-Jong Yang, Wei-Hau Du, Pau-Choo Chang, Jar-Ferr Yang, Pi-Hsia Hung

Abstract:

The demands of smart visual thing recognition in various devices have been increased rapidly for daily smart production, living and learning systems in recent years. This paper proposed a visual thing recognition system, which combines binary scale-invariant feature transform (SIFT), bag of words model (BoW), and support vector machine (SVM) by using color information. Since the traditional SIFT features and SVM classifiers only use the gray information, color information is still an important feature for visual thing recognition. With color-based SIFT features and SVM, we can discard unreliable matching pairs and increase the robustness of matching tasks. The experimental results show that the proposed object recognition system with color-assistant SIFT SVM classifier achieves higher recognition rate than that with the traditional gray SIFT and SVM classification in various situations.

Keywords: color moments, visual thing recognition system, SIFT, color SIFT

Procedia PDF Downloads 471

Authors: Amanda Burrell, Tonia Gary, David Wright, Kumara Ward

Abstract:

This paper explores the concept of academic identity as it relates to the lecture, in particular, the digitized lecture delivered to a camera, in the absence of a student audience. Many academics have the performance aspect of the role thrust upon them with little or no training. For the purpose of this study, we look at the performance of the academic identity and examine tailored film presence coaching for its contributions toward academic identity, specifically in relation to feelings of self-confidence and diminishment of discomfort or stage fright. The case is articulated through the lens of scholar-practitioners, using expert facilitated participatory action research. It demonstrates in our sample of experienced academics, all reported some feelings of uncertainty about presenting lectures to camera prior to coaching. We share how power poses and reframing fear, produced improvements in the ease and competency of all participants. We share exactly how this insight could be adapted for self-coaching by any academic when called to present to a camera and consider the relationship between this and academic identity.

Keywords: academic identity, digitized lecture, embodied learning, performance coaching

Procedia PDF Downloads 337

Authors: Ms. Hema Ramachandran, Dr. N. Vasudevan

Abstract:

Accurate estimation of the battery State of Charge (SOC) is essential for optimizing the range and performance of modern electric vehicles. This paper focuses on analysing historical driving data from electric buses, with an emphasis on feature extraction and data preprocessing of driving conditions. By selecting relevant parameters, a set of characteristic variables tailored to specific driving scenarios is established. A battery SOC prediction model based on a combination a bidirectional long short-term memory (LSTM) architecture and a standard fully connected neural network (FCNN) is then proposed, where various hyperparameters are identified and fine-tuned to enhance prediction accuracy. The results indicate that with optimized hyperparameters, the prediction achieves a Root Mean Square Error (RMSE) of 1.98% and a Mean Absolute Error (MAE) of 1.72%. This approach is expected to improve the efficiency of battery management systems and battery utilization in electric vehicles.

Keywords: long short-term memory (lstm), battery health monitoring, data-driven models, battery charge-discharge cycles, adaptive soc estimation, voltage and current sensing

Procedia PDF Downloads 8

Authors: Madhu Babu Cherukuri, Tamoghna Ghosh

Abstract:

Factory supply chain management spends billions of dollars every year to procure and manage equipment spare parts. Due to technology -and processes changes some of these spares become obsolete/dead inventory. Factories have huge dead inventory worth millions of dollars accumulating over time. This is due to lack of a scientific methodology to identify them and send the inventory back to the suppliers on a timely basis. The standard approach followed across industries to deal with this is: if a part is not used for a set pre-defined period of time it is declared dead. This leads to accumulation of dead parts over time and these parts cannot be sold back to the suppliers as it is too late as per contract agreement. Our main idea is the time period for identifying a part as dead cannot be a fixed pre-defined duration across all parts. Rather, it should depend on various properties of the part like historical consumption pattern, type of part, how many machines it is being used in, whether it- is a preventive maintenance part etc. We have designed a predictive algorithm which predicts part obsolescence well in advance with reasonable accuracy and which can help save millions.

Keywords: obsolete inventory, machine learning, big data, supply chain analytics, dead inventory

Procedia PDF Downloads 319

Authors: Mohd Aderi Che Noh, Tuan Rahayu Tuan Lasan

Abstract:

Higher order thinking skills (HOTS) is an important skill in the Malaysian education system to produce a knowledgeable generation, able to think critically and creatively in order to face the challenges in the future. Educational challenges of the 21st century require that all students to have the HOTS. Therefore, this study aims to identify the level of knowledge, attitude and readiness of students towards HOTS. The respondents were 127 form four students from schools in the Federal Territory of Putrajaya. This study is quantitative survey using a questionnaire to collect data. Data were analyzed using Statistical Package for the Social Sciences (SPSS) 23.0. The results showed that knowledge, attitudes and readiness of students towards HOTS lam were at a high level. Inferential analysis showed that there was a significant relationship between knowledge with attitude and readiness towards HOTS. This study provides information to the schools and teachers to improve the teaching and learning to increase students HOTS and fulfilling the hope of Ministry of Education to produce human capital who can be globally competitive.

Keywords: high order thinking skills, teaching, education, Malaysia

Procedia PDF Downloads 212

Authors: Tomas Kos

Abstract:

An increasing body of research has explored patterns of interaction and peer support among young learners. Although some studies suggest that young learners can collaborate and support each other, other studies indicate that young learners may lack the ability to work together and support one another when interacting on classroom tasks. Moreover, despite the claims that peer collaboration is conducive to learning, studies have not paid enough attention to the “how” to enhance peer collaboration on classroom tasks. To fill this gap, this “how-to” article proposes that teaching young learners how to work together is a powerful pedagogical tool that can greatly improve collaborative behavior and a sense of mutuality among young learners. This article will pay particular attention to primary schools and the context of English as a foreign language. It will first review literature related to patterns of interaction and peer support conducted in the cognitive and sociocultural framework. It will then address what it actually means to collaborate. At the heart of the article, it will discuss some practical pedagogical ideas for language teachers, which entail teaching collaborative principles and strategies that will help their students to support each other and engage in communication with each other.

Keywords: young learners, peer collaboration, peer interaction, peer support, patterns of interaction

Procedia PDF Downloads 157

Authors: LiRen Kang, LingXia Li, KaiKai Liu, Yue Jin, ZengShan Tian

Abstract:

With the widespread adoption of 5G technology in the Internet of Things (IoT), indoor localization methods based on 5G signals have gradually become a research hotspot. However, traditional methods often perform poorly in multipath interference and signal attenuation environments. To address these challenges, this paper proposes an innovative fingerprint localization method that utilizes the multiple synchronization signal block (SSB) beam features of 5G signals combined with generative adversarial networks (GANs) for interpolation. Our method incorporates a ray tracing model as an auxiliary, integrating signal propagation models to enhance the interpolation process. We precisely extract the multiple SSB beam features from 5G signals; in the localization stage, deep learning neural networks (DNN) are used for localization. Field tests show that localization errors of less than 1.5 meters can be achieved within about 200 square meters of indoor environment. Our method represents a 56.7% improvement compared to traditional methods that use received signal strength (RSS) as a single feature.

Keywords: 5G NR, fingerprint localization, generative adversarial networks, Internet of Things, indoor localization systems

Procedia PDF Downloads 7

Authors: Marie-Josée Morneau

Abstract:

A literacy-based approach, centred on the use of the language of instruction as a cognitive tool, can increase the L2 communication skills of French immersion students. Academic subject areas such as science and mathematics offer an authentic language learning context where students can become more proficient speakers while using specific vocabulary and language structures to learn, interact and communicate their reasoning, when provided the opportunities and guidance to do so. In this Canadian quasi-experimental study, the effects of teaching specific language elements during mathematic classes through literacy-based activities in Early French Immersion programming were compared between two Grade 7/8 groups: the experimental group, which received literacy-based teaching for a 6-week period, and the control group, which received regular teaching instruction. The results showed that the participants from the experimental group made more progress in their mathematical communication skills, which suggests that targeting L2 language as a cognitive tool can be beneficial to immersion learners who learn mathematic concepts and remind us that all L2 teachers are language teachers.

Keywords: mathematics, French immersion, literacy-based, oral communication, L2

Procedia PDF Downloads 76

Authors: Eunice Tan

Abstract:

The purpose of this presentation is to look at an alternative to the approach and methodologies of working with a child with special needs. The strength-based approach to education embodies a paradigm shift. It is a strategy to move away from a deficit-based methodology which inadvertently may lead to an extensive list of things that the child cannot do or is unable to do. Today, many parents of individuals with special needs are focused on the individual’s deficits rather than on his or her strengths. Even when parents recognise and identify their child’s savant strengths to be valuable and wish to develop their abilities, they face the challenge that there are insufficient programs committed to supporting the development and improvement of such abilities. What is a strength-based approach in education? A strength-based approach in education focuses on students' positive qualities and contributions to class instead of the skills and abilities they may not have. Many schools are focused on the child’s special educational needs rather than the whole child. Parents interviewed have said that they have to engage external tutors to help hone in on their child’s interests and strengths. The strength-based approach to writing statements encourages educators to find out: • What a child can do • What a child can do when he or she is given educational support • Learning more about children with special needs and their strengths and talents will broaden our understanding of how we can help them with language acquisition, social skills, as well as self-help and independence skills.

Keywords: special needs, strengths, and talents, alternative educational approach, strength based approach

Procedia PDF Downloads 289

Authors: Atuhurra Jesse, N'guessan Yves-Roland Douha, Pabitra Lenka

Abstract:

The detection of diseases within plants has attracted a lot of attention from computer vision enthusiasts. Despite the progress made to detect diseases in many plants, there remains a research gap to train image classifiers to detect the cacao swollen shoot virus disease or CSSVD for short, pertinent to cacao plants. This gap has mainly been due to the unavailability of high quality labeled training data. Moreover, institutions have been hesitant to share their data related to CSSVD. To fill these gaps, image classifiers to detect CSSVD-infected cacao plants are presented in this study. The classifiers are based on VGG16, ResNet50 and Vision Transformer (ViT). The image classifiers are evaluated on a recently released and publicly accessible KaraAgroAI Cocoa dataset. The best performing image classifier, based on ResNet50, achieves 95.39\% precision, 93.75\% recall, 94.34\% F1-score and 94\% accuracy on only 20 epochs. There is a +9.75\% improvement in recall when compared to previous works. These results indicate that the image classifiers learn to identify cacao plants infected with CSSVD.

Keywords: CSSVD, image classification, ResNet50, vision transformer, KaraAgroAI cocoa dataset

Procedia PDF Downloads 104

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

Abstract:

The most aggressive form of brain tumor is called glioma. Glioma is kind of tumor that arises from glial tissue of the brain and occurs quite often. A fully automatic 2D-CNN model for brain tumor segmentation is presented in this paper. We performed pre-processing steps to remove noise and intensity variances using N4ITK and standard intensity correction, respectively. We used Keras open-source library with Theano as backend for fast implementation of CNN model. In addition, we used BRATS 2015 MRI dataset to evaluate our proposed model. Furthermore, we have used SimpleITK open-source library in our proposed model to analyze images. Moreover, we have extracted random 2D patches for proposed 2D-CNN model for efficient brain segmentation. Extracting 2D patched instead of 3D due to less dimensional information present in 2D which helps us in reducing computational time. Dice Similarity Coefficient (DSC) is used as performance measure for the evaluation of the proposed method. Our method achieved DSC score of 0.77 for complete, 0.76 for core, 0.77 for enhanced tumor regions. However, these results are comparable with methods already implemented 2D CNN architecture.

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

Procedia PDF Downloads 183

Authors: Duygu Dere, Mert Ergeneci, Kaan Gokcesu

Abstract:

Google Trends data has gained increasing popularity in the applications of behavioral finance, decision science and risk management. Because of Google’s wide range of use, the Trends statistics provide significant information about the investor sentiment and intention, which can be used as decisive factors for corporate and risk management fields. However, an anomaly, a significant increase or decrease, in a certain query cannot be detected by the state of the art applications of computation due to the random baseline noise of the Trends data, which is modelled as an Additive white Gaussian noise (AWGN). Since through time, the baseline noise power shows a gradual change an adaptive thresholding method is required to track and learn the baseline noise for a correct classification. To this end, we introduce an online method to classify meaningful deviations in Google Trends data. Through extensive experiments, we demonstrate that our method can successfully classify various anomalies for plenty of different data.

Keywords: adaptive data processing, behavioral finance , convex optimization, online learning, soft minimum thresholding

Procedia PDF Downloads 169

Authors: Junqi Zou

Abstract:

As one of the world’s most tech-ready countries, Singapore has initiated the Smart Nation plan to harness the full power and potential of digital technologies to transform the way people live and work, through the more efficient government and business processes, to make the economy more productive. The key evolutions of digital technology transformation in healthcare and the increasing deployment of Internet of Things (IoTs), Big Data, AI/cognitive, Robotic Process Automation (RPA), Electronic Health Record Systems (EHR), Electronic Medical Record Systems (EMR), Warehouse Management System (WMS in the most recent decade have significantly stepped up the move towards an information-driven healthcare ecosystem. The advances in information technology not only bring benefits to patients but also act as a key force in changing management accounting in healthcare sector. The aim of this study is to investigate the impacts of digital technology transformation on Singapore’s healthcare sector from a management accounting perspective. Adopting a Balanced Scorecard (BSC) analysis approach, this paper conducted an exploratory case study of a newly launched Singapore public hospital, which has been recognized as amongst the most digitally advanced healthcare facilities in Asia-Pacific region. Specifically, this study gains insights on how the new technology is changing healthcare organizations’ management accounting from four perspectives under the Balanced Scorecard approach, 1) Financial Perspective, 2) Customer (Patient) Perspective, 3) Internal Processes Perspective, and 4) Learning and Growth Perspective. Based on a thorough review of archival records from the government and public, and the interview reports with the hospital’s CIO, this study finds the improvements from all the four perspectives under the Balanced Scorecard framework as follows: 1) Learning and Growth Perspective: The Government (Ministry of Health) works with the hospital to open up multiple training pathways to health professionals that upgrade and develops new IT skills among the healthcare workforce to support the transformation of healthcare services. 2) Internal Process Perspective: The hospital achieved digital transformation through Project OneCare to integrate clinical, operational, and administrative information systems (e.g., EHR, EMR, WMS, EPIB, RTLS) that enable the seamless flow of data and the implementation of JIT system to help the hospital operate more effectively and efficiently. 3) Customer Perspective: The fully integrated EMR suite enhances the patient’s experiences by achieving the 5 Rights (Right Patient, Right Data, Right Device, Right Entry and Right Time). 4) Financial Perspective: Cost savings are achieved from improved inventory management and effective supply chain management. The use of process automation also results in a reduction of manpower costs and logistics cost. To summarize, these improvements identified under the Balanced Scorecard framework confirm the success of utilizing the integration of advanced ICT to enhance healthcare organization’s customer service, productivity efficiency, and cost savings. Moreover, the Big Data generated from this integrated EMR system can be particularly useful in aiding management control system to optimize decision making and strategic planning. To conclude, the new digital technology transformation has moved the usefulness of management accounting to both financial and non-financial dimensions with new heights in the area of healthcare management.

Keywords: balanced scorecard, digital technology transformation, healthcare ecosystem, integrated information system

Procedia PDF Downloads 162

Authors: Hyunbin Choi, Jihyeon Noh, Changwon Lim

Abstract:

In this paper, we propose SiamMask++, an architecture that performs layer-wise aggregation and depth-wise cross-correlation and introduce multi-RPN module and multi-MASK module to improve EAO (Expected Average Overlap), a representative performance evaluation metric for Visual Object Tracking (VOT) challenge. The proposed architecture, SiamMask++, has two versions, namely, bi_SiamMask++, which satisfies the real time (56fps) on systems equipped with GPUs (Titan XP), and rf_SiamMask++, which combines mask refinement modules for EAO improvements. Tests are performed on VOT2016, VOT2018 and VOT2019, the representative datasets of Visual Object Tracking tasks labeled as rotated bounding boxes. SiamMask++ perform better than SiamMask on all the three datasets tested. SiamMask++ is achieved performance of 62.6% accuracy, 26.2% robustness and 39.8% EAO, especially on the VOT2018 dataset. Compared to SiamMask, this is an improvement of 4.18%, 37.17%, 23.99%, respectively. In addition, we do an experimental in-depth analysis of how much the introduction of features and multi modules extracted from the backbone affects the performance of our model in the VOT task.

Keywords: visual object tracking, video, deep learning, layer wise aggregation, Siamese network

Procedia PDF Downloads 163

Authors: Lule Basha, Eralda Gjika

Abstract:

The exchange rate is one of the most important economic variables, especially for a small, open economy such as Albania. Its effect is noticeable in one country's competitiveness, trade and current account, inflation, wages, domestic economic activity, and bank stability. This study investigates the fluctuation of Albania’s exchange rates using monthly average foreign currency, Euro (Eur) to Albanian Lek (ALL) exchange rate with a time span from January 2008 to June 2021, and the macroeconomic factors that have a significant effect on the exchange rate. Initially, the Random Forest Regression algorithm is constructed to understand the impact of economic variables on the behavior of monthly average foreign currencies exchange rates. Then the forecast of macro-economic indicators for 12 months was performed using time series models. The predicted values received are placed in the random forest model in order to obtain the average monthly forecast of the Euro to Albanian Lek (ALL) exchange rate for the period July 2021 to June 2022.

Keywords: exchange rate, random forest, time series, machine learning, prediction

Procedia PDF Downloads 104

Authors: Botirjon Kosimov

Abstract:

This work sheds light on the reforms towards the independence of the judiciary in Uzbekistan, as well as issues of further ensuring judicial independence in the country based on international values, particularly the legal practice of the United States. In every democratic state infringed human rights are reinstated and violated laws are protected by the help of justice based on the strict principle of judicial independence. The realization of this principle in Uzbekistan has been paid much attention since the proclamation of its independence. In the country, a series of reforms have been implemented in the field of the judiciary in order to actualize the principle of judicial independence. Uzbekistan has been reforming the judiciary considering both international and national values and practice of foreign countries. While forming a democratic state based on civil society, Uzbekistan shares practice with the most developed countries in the world. The United States of America can be a clear example which is worth learning how to establish and ensure an independent judiciary. It seems that although Uzbekistan has reformed the judiciary efficiently, it should further reform considering the legal practice of the United States.

Keywords: dependent judges, independent judges, judicial independence, judicial reforms, judicial life tenure, obstacles to judicial independence

Procedia PDF Downloads 266

Authors: Nadia Masood Khan, Muhammad Salman Khan, Gul Muhammad Khan

Abstract:

Cardiologists perform cardiac auscultation to detect abnormalities in heart sounds. Since accurate auscultation is a crucial first step in screening patients with heart diseases, there is a need to develop computer-aided detection/diagnosis (CAD) systems to assist cardiologists in interpreting heart sounds and provide second opinions. In this paper different algorithms are implemented for automated heart sound classification using unsegmented phonocardiogram (PCG) signals. Support vector machine (SVM), artificial neural network (ANN) and cartesian genetic programming evolved artificial neural network (CGPANN) without the application of any segmentation algorithm has been explored in this study. The signals are first pre-processed to remove any unwanted frequencies. Both time and frequency domain features are then extracted for training the different models. The different algorithms are tested in multiple scenarios and their strengths and weaknesses are discussed. Results indicate that SVM outperforms the rest with an accuracy of 73.64%.

Keywords: pattern recognition, machine learning, computer aided diagnosis, heart sound classification, and feature extraction

Procedia PDF Downloads 264

Authors: Jaspreet Singh, Gurvinder Singh, Prabhsimran Singh, Rajinder Singh, Prithvipal Singh, Karanjeet Singh Kahlon, Ravinder Singh Sawhney

Abstract:

Morphological evaluation of Indian languages is one of the burgeoning fields in the area of Natural Language Processing (NLP). The evaluation of a language is an eminent task in the era of information retrieval and text mining. The extraction and classification of knowledge from text can be exploited for sentiment analysis and morphological evaluation. This study coalesce morphological evaluation and sentiment analysis for the task of classification of farmer suicide cases reported in Punjab state of India. The pre-processing of Punjabi text involves morphological evaluation and normalization of Punjabi word tokens followed by the training of proposed model using deep learning classification on Punjabi language text extracted from online Punjabi news reports. The class-wise accuracies of sentiment prediction for four negatively oriented classes of farmer suicide cases are 93.85%, 88.53%, 83.3%, and 95.45% respectively. The overall accuracy of sentiment classification obtained using proposed framework on 275 Punjabi text documents is found to be 90.29%.

Keywords: deep neural network, farmer suicides, morphological processing, punjabi text, sentiment analysis

Procedia PDF Downloads 328

Authors: Turuganti Venkateswarlu, Jagadeesh Anmala

Abstract:

Excessive runoffs from various non-point source land uses, and other point sources are rapidly contaminating the water quality of streams in the Upper Green River watershed, Kentucky, USA. It is essential to maintain the stream water quality as the river basin is one of the major freshwater sources in this province. It is also important to understand the water quality parameters (WQPs) quantitatively and qualitatively along with their important features as stream water is sensitive to climatic events and land-use practices. In this paper, a model was developed for predicting one of the significant WQPs, Fecal Coliform (FC) from precipitation, temperature, urban land use factor (ULUF), agricultural land use factor (ALUF), and forest land-use factor (FLUF) using Random Forest (RF) algorithm. The RF model, a novel ensemble learning algorithm, can even find out advanced feature importance characteristics from the given model inputs for different combinations. This model’s outcomes showed a good correlation between FC and climate events and land use factors (R2 = 0.94) and precipitation and temperature are the primary influencing factors for FC.

Keywords: water quality, land use factors, random forest, fecal coliform

Procedia PDF Downloads 198

Authors: Eftah Bte. Moh Hj Abdullah, Izazol Binti Idris, Abd Aziz Bin Abd Shukor

Abstract:

This study aims to identify the understanding expectations of school administrators concerning school assessment. The researcher utilized a qualitative descriptive study on 19 administrators from three secondary schools in the North Kinta district. The respondents had been interviewed on their understanding expectations of school assessment using the focus group discussion method. Overall findings showed that the administrators’ understanding expectations of school assessment was weak; especially in terms of content focus, articulation across age and grade, transparency and fairness, as well as the pedagogical implications. Findings from interviews indicated that administrators explained their understanding expectations of school assessment from the aspect of school management, and not from the aspect of instructional leadership or specifically as assessment leaders. The study implications from the administrators’ understanding expectations may hint at the difficulty of the administrators to function as assessment leaders, in order to reduce their focus as manager, and move towards their primary role in the process of teaching and learning. The administrator, as assessment leaders, would be able to reach assessment goals via collaboration in identifying and listing teacher assessment competencies, how to construct assessment capacity, how to interpret assessment correctly, the use of assessment and how to use assessment information to communicate confidently and effectively to the public.

Keywords: assessment leaders, assessment goals, instructional leadership, understanding expectation of assessment

Procedia PDF Downloads 459

Authors: V. Saccà, A. Sarica, F. Novellino, S. Barone, T. Tallarico, E. Filippelli, A. Granata, P. Valentino, A. Quattrone

Abstract:

The work aim was to evaluate how well Random Forest (RF) and Support Vector Machine (SVM) algorithms could support the early diagnosis of Multiple Sclerosis (MS) from resting-state functional connectivity data. In particular, we wanted to explore the ability in distinguishing between controls and patients of mean signals extracted from ICA components corresponding to 15 well-known networks. Eighteen patients with early-MS (mean-age 37.42±8.11, 9 females) were recruited according to McDonald and Polman, and matched for demographic variables with 19 healthy controls (mean-age 37.55±14.76, 10 females). MRI was acquired by a 3T scanner with 8-channel head coil: (a)whole-brain T1-weighted; (b)conventional T2-weighted; (c)resting-state functional MRI (rsFMRI), 200 volumes. Estimated total lesion load (ml) and number of lesions were calculated using LST-toolbox from the corrected T1 and FLAIR. All rsFMRIs were pre-processed using tools from the FMRIB's Software Library as follows: (1) discarding of the first 5 volumes to remove T1 equilibrium effects, (2) skull-stripping of images, (3) motion and slice-time correction, (4) denoising with high-pass temporal filter (128s), (5) spatial smoothing with a Gaussian kernel of FWHM 8mm. No statistical significant differences (t-test, p < 0.05) were found between the two groups in the mean Euclidian distance and the mean Euler angle. WM and CSF signal together with 6 motion parameters were regressed out from the time series. We applied an independent component analysis (ICA) with the GIFT-toolbox using the Infomax approach with number of components=21. Fifteen mean components were visually identified by two experts. The resulting z-score maps were thresholded and binarized to extract the mean signal of the 15 networks for each subject. Statistical and machine learning analysis were then conducted on this dataset composed of 37 rows (subjects) and 15 features (mean signal in the network) with R language. The dataset was randomly splitted into training (75%) and test sets and two different classifiers were trained: RF and RBF-SVM. We used the intrinsic feature selection of RF, based on the Gini index, and recursive feature elimination (rfe) for the SVM, to obtain a rank of the most predictive variables. Thus, we built two new classifiers only on the most important features and we evaluated the accuracies (with and without feature selection) on test-set. The classifiers, trained on all the features, showed very poor accuracies on training (RF:58.62%, SVM:65.52%) and test sets (RF:62.5%, SVM:50%). Interestingly, when feature selection by RF and rfe-SVM were performed, the most important variable was the sensori-motor network I in both cases. Indeed, with only this network, RF and SVM classifiers reached an accuracy of 87.5% on test-set. More interestingly, the only misclassified patient resulted to have the lowest value of lesion volume. We showed that, with two different classification algorithms and feature selection approaches, the best discriminant network between controls and early MS, was the sensori-motor I. Similar importance values were obtained for the sensori-motor II, cerebellum and working memory networks. These findings, in according to the early manifestation of motor/sensorial deficits in MS, could represent an encouraging step toward the translation to the clinical diagnosis and prognosis.

Keywords: feature selection, machine learning, multiple sclerosis, random forest, support vector machine

Procedia PDF Downloads 241

Authors: Lina S. Calucag

Abstract:

Integration of research and teaching in higher education can provide valuable ways of enhancing the student learning experience, but establishing such integrative links can be complex and problematic, given different practices and levels of understanding. This study contributes to the pedagogical literature in drawing on findings from students’ survey exploring perceptions of research-informed teaching to examine how links between research and teaching can be suitably strengthened. The study employed a descriptive research design limited to the undergraduate students taking thesis/capstone courses in the tertiary levels private or public colleges and universities across the globe as respondents of the study. The findings noted that the students’ responses from different disciplines: engineering, science, education, business-related, and computer on the nexus between research and teaching is remarkable in fostering student expectations of research-informed teaching approaches. Students’ expectations on research-led, research-oriented, research-based, and research-tutored are enablers in linking research and teaching. It is recommended that experimental studies should be conducted using the four different research-informed teaching approaches in the classroom, namely: research-led, research-oriented, research-based, and research-tutored.

Keywords: research-led, research-informed teaching, research-oriented teaching, research-tutored, research-based

Procedia PDF Downloads 164

Authors: S. Gordon

Abstract:

Dual language immersion is growing fast in language teaching today. This study provides an overview and evaluation of the different models of Dual language immersion programs in US K-12 schools. First, the paper provides a brief current literature review on the theory of Dual Language Immersion (DLI) in Second Language Acquisition (SLA) studies. Second, examples of several types of DLI language teaching models in US K-12 public schools are presented (including 50/50 models, 90/10 models, etc.). Third, we focus on the unique example of DLI education in the state of Utah, a successful, growing program in K-12 schools that includes: French, Chinese, Spanish, and Portuguese. The project investigates the theory and practice particularly of the case of public elementary and secondary school children that study half their school day in the L1 and the other half in the chosen L2, from kindergarten (age 5-6) through high school (age 17-18). Finally, the project takes the observations of Utah French DLI elementary through secondary programs as a case study. To conclude, we look at the principal challenges, pedagogical objectives and outcomes, and important implications for other US states and other countries (such as France currently) that are in the process of developing similar language learning programs.

Keywords: dual language immersion, second language acquisition, language teaching, pedagogy, teaching, French

Procedia PDF Downloads 179