The challenging task in educational institutions is to maximize the high performance of students and minimize the failure rate of poor-performing students. An effective method to leverage this task is to know student learning patterns with highly influencing factors and get an early prediction of student learning outcomes at the timely stage for setting up policies for improvement. Educational data mining (EDM) is an emerging disciplinary field of data mining, statistics, and machine learning concerned with extracting useful knowledge and information for the sake of improvement and development in the education environment. The study is of this work is to propose techniques in EDM and integrate it into a web-based system for predicting poor-performing students. A comparative study of prediction models is conducted. Subsequently, high performing models are developed to get higher performance. The hybrid random forest (Hybrid RF) produces the most successful classification. For the context of intervention and improving the learning outcomes, a feature selection method MICHI, which is the combination of mutual information (MI) and chi-square (CHI) algorithms based on the ranked feature scores, is introduced to select a dominant feature set that improves the performance of prediction and uses the obtained dominant set as information for intervention. By using the proposed techniques of EDM, an academic performance prediction system (APPS) is subsequently developed for educational stockholders to get an early prediction of student learning outcomes for timely intervention. Experimental outcomes and evaluation surveys report the effectiveness and usefulness of the developed system. The system is used to help educational stakeholders and related individuals for intervening and improving student performance.
The use of deep learning for species identification in camera trap images has revolutionised our ability to study, conserve and monitor species in a highly efficient and unobtrusive manner, with state-of-the-art models achieving accuracies surpassing the accuracy of manual human classification. The high imbalance of camera trap datasets, however, results in poor accuracies for minority (rare or endangered) species due to their relative insignificance to the overall model accuracy. This paper investigates the use of Focal Loss, in comparison to the traditional Cross Entropy Loss function, to improve the identification of minority species in the “255 Bird Species” dataset from Kaggle. The results show that, although Focal Loss slightly decreased the accuracy of the majority species, it was able to increase the F1-score by 0.06 and improve the identification of the bottom two, five and ten (minority) species by 37.5%, 15.7% and 10.8%, respectively, as well as resulting in an improved overall accuracy of 2.96%.
Fake news detection research is still in the early stage as this is a relatively new phenomenon in the interest raised by society. Machine learning helps to solve complex problems and to build AI systems nowadays and especially in those cases where we have tacit knowledge or the knowledge that is not known. We used machine learning algorithms and for identification of fake news; we applied three classifiers; Passive Aggressive, Naïve Bayes, and Support Vector Machine. Simple classification is not completely correct in fake news detection because classification methods are not specialized for fake news. With the integration of machine learning and text-based processing, we can detect fake news and build classifiers that can classify the news data. Text classification mainly focuses on extracting various features of text and after that incorporating those features into classification. The big challenge in this area is the lack of an efficient way to differentiate between fake and non-fake due to the unavailability of corpora. We applied three different machine learning classifiers on two publicly available datasets. Experimental analysis based on the existing dataset indicates a very encouraging and improved performance.
Following a review of various approaches that are utilized for classifying the tail behavior of a distribution, an easily implementable methodology that relies on an arctangent transformation is presented. The classification criterion is actually based on the difference between two specific quantiles of the transformed distribution. The resulting categories enable one to classify distributional tails as distinctly short, short, nearly medium, medium, extended medium and somewhat long, providing that at least two moments exist. Distributions possessing a single moment are said to be long tailed while those failing to have any finite moments are classified as having an extremely long tail. Several illustrative examples will be presented.
In the field of machine learning, the ensemble has been employed as a common methodology to improve the performance upon multiple base classifiers. However, the true predictions are often canceled out by the false ones during consensus due to a phenomenon called “curse of correlation” which is represented as the strong interferences among the predictions produced by the base classifiers. In addition, the existing practices are still not able to effectively mitigate the problem of imbalanced classification. Based on the analysis on our experiment results, we conclude that the two problems are caused by some inherent deficiencies in the approach of consensus. Therefore, we create an enhanced ensemble algorithm which adopts a designed rank-based chain-mode consensus to overcome the two problems. In order to evaluate the proposed ensemble algorithm, we employ a well-known benchmark data set NSL-KDD (the improved version of dataset KDDCup99 produced by University of New Brunswick) to make comparisons between the proposed and 8 common ensemble algorithms. Particularly, each compared ensemble classifier uses the same 22 base classifiers, so that the differences in terms of the improvements toward the accuracy and reliability upon the base classifiers can be truly revealed. As a result, the proposed rank-based chain-mode consensus is proved to be a more effective ensemble solution than the traditional consensus approach, which outperforms the 8 ensemble algorithms by 20% on almost all compared metrices which include accuracy, precision, recall, F1-score and area under receiver operating characteristic curve.
Speech to text in Malay language is a system that converts Malay speech into text. The Malay language recognition system is still limited, thus, this paper aims to investigate the performance of ten Malay words obtained from the online Malay news. The methodology consists of three stages, which are preprocessing, feature extraction, and speech classification. In preprocessing stage, the speech samples are filtered using pre emphasis. After that, feature extraction method is applied to the samples using Mel Frequency Cepstrum Coefficient (MFCC). Lastly, speech classification is performed using Feedforward Neural Network (FFNN). The accuracy of the classification is further investigated based on the hidden layer size. From experimentation, the classifier with 40 hidden neurons shows the highest classification rate which is 94%.
A major challenge in medical studies, especially those that are longitudinal, is the problem of missing measurements which hinders the effective application of many machine learning algorithms. Furthermore, recent Alzheimer's Disease studies have focused on the delineation of Early Mild Cognitive Impairment (EMCI) and Late Mild Cognitive Impairment (LMCI) from cognitively normal controls (CN) which is essential for developing effective and early treatment methods. To address the aforementioned challenges, this paper explores the potential of using the eXtreme Gradient Boosting (XGBoost) algorithm in handling missing values in multiclass classification. We seek a generalized classification scheme where all prodromal stages of the disease are considered simultaneously in the classification and decision-making processes. Given the large number of subjects (1631) included in this study and in the presence of almost 28% missing values, we investigated the performance of XGBoost on the classification of the four classes of AD, NC, EMCI, and LMCI. Using 10-fold cross validation technique, XGBoost is shown to outperform other state-of-the-art classification algorithms by 3% in terms of accuracy and F-score. Our model achieved an accuracy of 80.52%, a precision of 80.62% and recall of 80.51%, supporting the more natural and promising multiclass classification.
Geotechnical engineers face many problematic soils upon construction and they have the choice for replacing these soils with more appropriate soils or attempting to improve the engineering properties of the soil through a suitable soil stabilization technique. Mostly, improving soils is environmental, easier and more economical than other solutions. Stabilization soils technique is applied by introducing a cementing agent or by injecting a substance to fill the pore volume. Chemical stabilizers are divided into two groups: traditional agents such as cement or lime and non-traditional agents such as polymers. This paper studies the effect of epoxy additives on the compression strength of four types of soil and then compares with the effect of cement on the compression strength for the same soils. Overall, the epoxy additives are more effective in increasing the strength for different types of soils regardless its classification. On the other hand, there was no clear relation between studied parameters liquid limit, passing No.200, unit weight and between the strength of samples for different types of soils.
Hand gesture recognition is a technique used to locate, detect, and recognize a hand gesture. Detection and recognition are concepts of Artificial Intelligence (AI). AI concepts are applicable in Human Computer Interaction (HCI), Expert systems (ES), etc. Hand gesture recognition can be used in sign language interpretation. Sign language is a visual communication tool. This tool is used mostly by deaf societies and those with speech disorder. Communication barriers exist when societies with speech disorder interact with others. This research aims to build a hand recognition system for Lesotho’s Sesotho and English language interpretation. The system will help to bridge the communication problems encountered by the mentioned societies. The system has various processing modules. The modules consist of a hand detection engine, image processing engine, feature extraction, and sign recognition. Detection is a process of identifying an object. The proposed system uses Canny pruning Haar and Haarcascade detection algorithms. Canny pruning implements the Canny edge detection. This is an optimal image processing algorithm. It is used to detect edges of an object. The system employs a skin detection algorithm. The skin detection performs background subtraction, computes the convex hull, and the centroid to assist in the detection process. Recognition is a process of gesture classification. Template matching classifies each hand gesture in real-time. The system was tested using various experiments. The results obtained show that time, distance, and light are factors that affect the rate of detection and ultimately recognition. Detection rate is directly proportional to the distance of the hand from the camera. Different lighting conditions were considered. The more the light intensity, the faster the detection rate. Based on the results obtained from this research, the applied methodologies are efficient and provide a plausible solution towards a light-weight, inexpensive system which can be used for sign language interpretation.
This paper presents a road vehicle detection approach for the intelligent transportation system. This approach mainly uses low-cost magnetic sensor and associated data collection system to collect magnetic signals. This system can measure the magnetic field changing, and it also can detect and count vehicles. We extend Mel Frequency Cepstral Coefficients to analyze vehicle magnetic signals. Vehicle type features are extracted using representation of cepstrum, frame energy, and gap cepstrum of magnetic signals. We design a 2-dimensional map algorithm using Vector Quantization to classify vehicle magnetic features to four typical types of vehicles in Australian suburbs: sedan, VAN, truck, and bus. Experiments results show that our approach achieves a high level of accuracy for vehicle detection and classification.
Data mining has, over recent years, seen big advances because of the spread of internet, which generates everyday a tremendous volume of data, and also the immense advances in technologies which facilitate the analysis of these data. In particular, classification techniques are a subdomain of Data Mining which determines in which group each data instance is related within a given dataset. It is used to classify data into different classes according to desired criteria. Generally, a classification technique is either statistical or machine learning. Each type of these techniques has its own limits. Nowadays, current data are becoming increasingly heterogeneous; consequently, current classification techniques are encountering many difficulties. This paper defines new measure functions to quantify the resemblance between instances and then combines them in a new approach which is different from actual algorithms by its reliability computations. Results of the proposed approach exceeded most common classification techniques with an f-measure exceeding 97% on the IRIS Dataset.
The aim of this paper is the comparison of three different methods, in order to produce fuzzy tolerance relations for rainfall data classification. More specifically, the three methods are correlation coefficient, cosine amplitude and max-min method. The data were obtained from seven rainfall stations in the region of central Greece and refers to 20-year time series of monthly rainfall height average. Three methods were used to express these data as a fuzzy relation. This specific fuzzy tolerance relation is reformed into an equivalence relation with max-min composition for all three methods. From the equivalence relation, the rainfall stations were categorized and classified according to the degree of confidence. The classification shows the similarities among the rainfall stations. Stations with high similarity can be utilized in water resource management scenarios interchangeably or to augment data from one to another. Due to the complexity of calculations, it is important to find out which of the methods is computationally simpler and needs fewer compositions in order to give reliable results.
Character recognition is the process of converting a text image file into editable and searchable text file. Feature Extraction is the heart of any character recognition system. The character recognition rate may be low or high depending on the extracted features. In the proposed paper, 25 features for one character are used in character recognition. Basically, there are three steps of character recognition such as character segmentation, feature extraction and classification. In segmentation step, horizontal cropping method is used for line segmentation and vertical cropping method is used for character segmentation. In the Feature extraction step, features are extracted in two ways. The first way is that the 8 features are extracted from the entire input character using eight direction chain code frequency extraction. The second way is that the input character is divided into 16 blocks. For each block, although 8 feature values are obtained through eight-direction chain code frequency extraction method, we define the sum of these 8 feature values as a feature for one block. Therefore, 16 features are extracted from that 16 blocks in the second way. We use the number of holes feature to cluster the similar characters. We can recognize the almost Myanmar common characters with various font sizes by using these features. All these 25 features are used in both training part and testing part. In the classification step, the characters are classified by matching the all features of input character with already trained features of characters.
In this study, an application was carried out to determine the Volcanic Soils by using remote sensing. The study area was located on the Golcuk formation in Isparta-Turkey. The thermal bands of Landsat 7 image were used for processing. The implementation of the climate model that was based on the water index was used in ERDAS Imagine software together with pixel based image classification. Soil Moisture Index (SMI) was modeled by using the surface temperature (Ts) which was obtained from thermal bands and vegetation index (NDVI) derived from Landsat 7. Surface moisture values were grouped and classified by using scoring system. Thematic layers were compared together with the field studies. Consequently, different moisture levels for volcanic soils were indicator for determination and separation. Those thermal wavelengths are preferable bands for separation of volcanic soils using moisture and temperature models.
The commercial nuclear power reactor in South Korea, Kori Unit 1, which was a 587 MWe pressurized water reactor that started operation since 1978, was permanently shut down in June 2017 without an additional operating license extension. The Kori 1 Unit is scheduled to become the nuclear power unit to enter the decommissioning phase. In this study, the preliminary evaluation of the decommissioning wastes for the Kori Unit 1 was performed based on the following series of process: firstly, the plant inventory is investigated based on various documents (i.e., equipment/ component list, construction records, general arrangement drawings). Secondly, the radiological conditions of systems, structures and components (SSCs) are established to estimate the amount of radioactive waste by waste classification. Third, the waste management strategies for Kori Unit 1 including waste packaging are established. Forth, selection of the proper decontamination and dismantling (D&D) technologies is made considering the various factors. Finally, the amount of decommissioning waste by classification for Kori 1 is estimated using the DeCAT program, which was developed by KEPCO-E&C for a decommissioning cost estimation. The preliminary evaluation results have shown that the expected amounts of decommissioning wastes were less than about 2% and 8% of the total wastes generated (i.e., sum of clean wastes and radwastes) before/after waste processing, respectively, and it was found that the majority of contaminated material was carbon or alloy steel and stainless steel. In addition, within the range of availability of information, the results of the evaluation were compared with the results from the various decommissioning experiences data or international/national decommissioning study. The comparison results have shown that the radioactive waste amount from Kori Unit 1 decommissioning were much less than those from the plants decommissioned in U.S. and were comparable to those from the plants in Europe. This result comes from the difference of disposal cost and clearance criteria (i.e., free release level) between U.S. and non-U.S. The preliminary evaluation performed using the methodology established in this study will be useful as a important information in establishing the decommissioning planning for the decommissioning schedule and waste management strategy establishment including the transportation, packaging, handling, and disposal of radioactive wastes.
The aim of paper is to analyze business models of bancassurance in Italy for life business. The life insurance business is very developed in the Italian market and banks branches have 80% of the market share. Given its maturity, the life insurance market needs to consolidate its organizational form to allow for the development of non-life business, which nowadays collects few premiums but represents a great opportunity to enlarge the market share of bancassurance using its strength in the distribution channel while the market share of independent agents is decreasing. Starting with the main business model of bancassurance for life business, this paper will analyze the performances of life companies in the Italian market by balance sheet indicators and by main discriminant variables of business models. The study will observe trends from 2013 to 2015 for the Italian market by exploiting a database managed by Associazione Nazionale delle Imprese di Assicurazione (ANIA). The applied approach is based on a bottom-up analysis starting with variables and indicators to define business models’ classification. The statistical classification algorithm proposed by Ward is employed to design business models’ profiles. Results from the analysis will be a representation of the main business models built by their profile related to indicators. In that way, an unsupervised analysis is developed that has the limit of its judgmental dimension based on research opinion, but it is possible to obtain a design of effective business models.
Sentiment analysis and opinion mining have become emerging topics of research in recent years but most of the work is focused on data in the English language. A comprehensive research and analysis are essential which considers multiple languages, machine translation techniques, and different classifiers. This paper presents, a comparative analysis of different approaches for multilingual sentiment analysis. These approaches are divided into two parts: one using classification of text without language translation and second using the translation of testing data to a target language, such as English, before classification. The presented research and results are useful for understanding whether machine translation should be used for multilingual sentiment analysis or building language specific sentiment classification systems is a better approach. The effects of language translation techniques, features, and accuracy of various classifiers for multilingual sentiment analysis is also discussed in this study.