Commenced in January 2007 | Frequency: Monthly | Edition: International | Paper Count: 360 |
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.
Bayesian Network (BN) is one of the most efficient classification methods. It is widely used in several fields (i.e., medical diagnostics, risk analysis, bioinformatics research). The BN is defined as a probabilistic graphical model that represents a formalism for reasoning under uncertainty. This classification method has a high-performance rate in the extraction of new knowledge from data. The construction of this model consists of two phases for structure learning and parameter learning. For solving this problem, the K2 algorithm is one of the representative data-driven algorithms, which is based on score and search approach. In addition, the integration of the expert's knowledge in the structure learning process allows the obtainment of the highest accuracy. In this paper, we propose a hybrid approach combining the improvement of the K2 algorithm called K2 algorithm for Parents and Children search (K2PC) and the expert-driven method for learning the structure of BN. The evaluation of the experimental results, using the well-known benchmarks, proves that our K2PC algorithm has better performance in terms of correct structure detection. The real application of our model shows its efficiency in the analysis of the phosphate laundry effluents' impact on the watershed in the Gafsa area (southwestern Tunisia).
The reason for conducting this research is to develop an algorithm that is capable of classifying news articles from the automobile industry, according to the competitive actions that they entail, with the use of Text Mining (TM) methods. It is needed to test how to properly preprocess the data for this research by preparing pipelines which fits each algorithm the best. The pipelines are tested along with nine different classification algorithms in the realm of regression, support vector machines, and neural networks. Preliminary testing for identifying the optimal pipelines and algorithms resulted in the selection of two algorithms with two different pipelines. The two algorithms are Logistic Regression (LR) and Artificial Neural Network (ANN). These algorithms are optimized further, where several parameters of each algorithm are tested. The best result is achieved with the ANN. The final model yields an accuracy of 0.79, a precision of 0.80, a recall of 0.78, and an F1 score of 0.76. By removing three of the classes that created noise, the final algorithm is capable of reaching an accuracy of 94%.
Traffic control has been one of the most common and irritating problems since the time automobiles have hit the roads. Problems like traffic congestion have led to a significant time burden around the world and one significant solution to these problems can be the proper implementation of the Intelligent Transport System (ITS). It involves the integration of various tools like smart sensors, artificial intelligence, position technologies and mobile data services to manage traffic flow, reduce congestion and enhance driver's ability to avoid accidents during adverse weather. Road and traffic signs’ recognition is an emerging field of research in ITS. Classification problem of traffic signs needs to be solved as it is a major step in our journey towards building semi-autonomous/autonomous driving systems. The purpose of this work focuses on implementing an approach to solve the problem of traffic sign classification by developing a Convolutional Neural Network (CNN) classifier using the GTSRB (German Traffic Sign Recognition Benchmark) dataset. Rather than using hand-crafted features, our model addresses the concern of exploding huge parameters and data method augmentations. Our model achieved an accuracy of around 97.6% which is comparable to various state-of-the-art architectures.
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.
Organizations, including governments, generate (big) data that are high in volume, velocity, veracity, and come from a variety of sources. Public Administrations are using (big) data, implementing base registries, and enforcing data sharing within the entire government to deliver (big) data related integrated services, provision of insights to users, and for good governance. Government (Big) data ecosystem actors represent distinct entities that provide data, consume data, manipulate data to offer paid services, and extend data services like data storage, hosting services to other actors. In this research work, we perform a systematic literature review. The key objectives of this paper are to propose a robust definition of government (big) data ecosystem and a classification of government (big) data ecosystem actors and their roles. We showcase a graphical view of actors, roles, and their relationship in the government (big) data ecosystem. We also discuss our research findings. We did not find too much published research articles about the government (big) data ecosystem, including its definition and classification of actors and their roles. Therefore, we lent ideas for the government (big) data ecosystem from numerous areas that include scientific research data, humanitarian data, open government data, industry data, in the literature.
Learning from very big datasets is a significant problem for most present data mining and machine learning algorithms. MicroRNA (miRNA) is one of the important big genomic and non-coding datasets presenting the genome sequences. In this paper, a hybrid method for the classification of the miRNA data is proposed. Due to the variety of cancers and high number of genes, analyzing the miRNA dataset has been a challenging problem for researchers. The number of features corresponding to the number of samples is high and the data suffer from being imbalanced. The feature selection method has been used to select features having more ability to distinguish classes and eliminating obscures features. Afterward, a Convolutional Neural Network (CNN) classifier for classification of cancer types is utilized, which employs a Genetic Algorithm to highlight optimized hyper-parameters of CNN. In order to make the process of classification by CNN faster, Graphics Processing Unit (GPU) is recommended for calculating the mathematic equation in a parallel way. The proposed method is tested on a real-world dataset with 8,129 patients, 29 different types of tumors, and 1,046 miRNA biomarkers, taken from The Cancer Genome Atlas (TCGA) database.
In this work, a training algorithm for probabilistic neural networks (PNN) is presented. The algorithm addresses one of the major drawbacks of PNN, which is the size of the hidden layer in the network. By using a cross-validation training algorithm, the number of hidden neurons is shrunk to a smaller number consisting of the most representative samples of the training set. This is done without affecting the overall architecture of the network. Performance of the network is compared against performance of standard PNN for different databases from the UCI database repository. Results show an important gain in network size and performance.
Cognitive decline and frailty is apparent in older adults leading to an increased likelihood of the risk of falling. Currently health care professionals have to make professional decisions regarding such risks, and hence make difficult decisions regarding the future welfare of the ageing population. This study uses health data from The Irish Longitudinal Study on Ageing (TILDA), focusing on adults over the age of 50 years, in order to analyse health risk factors and predict the likelihood of falls. This prediction is based on the use of machine learning algorithms whereby health risk factors are used as inputs to predict the likelihood of falling. Initial results show that health risk factors such as long-term health issues contribute to the number of falls. The identification of such health risk factors has the potential to inform health and social care professionals, older people and their family members in order to mitigate daily living risks.
In the 21st century, the disciplinary boundaries of past centuries that we often create through mainstream art historical classification, techniques and sources may have been eroded by visual culture, which seems to provide a more inclusive umbrella for the new ways artists go about the creative process and its resultant commodities. Over the past four decades, artists in Africa have resorted to new materials, techniques and themes which have affected our ways of research on these artists and their art. Frontline artists such as El Anatsui, Yinka Shonibare, Erasmus Onyishi are demonstrating that any material is just suitable for artistic expression. Most of times, these materials come with their own techniques/effects and visual syntax: a combination of materials compounds techniques, formal aesthetic indexes, halo effects, and iconography. This tends to challenge the categories and we lean on to view, think and talk about them. This renders our main stream art historical research methods inadequate, thus suggesting new discursive concepts, terms and theories. This paper proposed the Africanist eclectic methods derived from the dual framework of Masquerade Theory and What Comes Behind Six is More Than Seven. This paper shares thoughts/research on art historical methods, terminological re-alignments on classification/source data, presentational format and interpretation arising from the emergent trends in our subject. The outcome provides useful tools to mediate new thoughts and experiences in recent African art and visual culture.
Biological and chemical activities in carbonates are responsible for the complexity of the pore system. Primary porosity is generally of natural origin while secondary porosity is subject to chemical reactivity through diagenetic processes. To understand the integrated part of hydrocarbon exploration, it is necessary to understand the carbonate pore system. However, the current porosity classification scheme is limited to adequately predict the petrophysical properties of different reservoirs having various origins and depositional environments. Rock classification provides a descriptive method for explaining the lithofacies but makes no significant contribution to the application of porosity and permeability (poro-perm) correlation. The Central Luconia carbonate system (Malaysia) represents a good example of pore complexity (in terms of nature and origin) mainly related to diagenetic processes which have altered the original reservoir. For quantitative analysis, 32 high-resolution images of each thin section were taken using transmitted light microscopy. The quantification of grains, matrix, cement, and macroporosity (pore types) was achieved using a petrographic analysis of thin sections and FESEM images. The point counting technique was used to estimate the amount of macroporosity from thin section, which was then subtracted from the total porosity to derive the microporosity. The quantitative observation of thin sections revealed that the mouldic porosity (macroporosity) is the dominant porosity type present, whereas the microporosity seems to correspond to a sum of 40 to 50% of the total porosity. It has been proven that these Miocene carbonates contain a significant amount of microporosity, which significantly complicates the estimation and production of hydrocarbons. Neglecting its impact can increase uncertainty about estimating hydrocarbon reserves. Due to the diversity of geological parameters, the application of existing porosity classifications does not allow a better understanding of the poro-perm relationship. However, the classification can be improved by including the pore types and pore structures where they can be divided into macro- and microporosity. Such studies of microporosity identification/classification represent now a major concern in limestone reservoirs around the world.
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.
Machine Learning and Data Mining are the two important tools for extracting useful information and knowledge from large datasets. In machine learning, classification is a wildly used technique to predict qualitative variables and is generally preferred over regression from an operational point of view. Due to the enormous increase in air pollution in various countries especially China, Air Quality Classification has become one of the most important topics in air quality research and modelling. This study aims at introducing a hybrid classification model based on information theory and Support Vector Machine (SVM) using the air quality data of four cities in China namely Beijing, Guangzhou, Shanghai and Tianjin from Jan 1, 2014 to April 30, 2016. China's Ministry of Environmental Protection has classified the daily air quality into 6 levels namely Serious Pollution, Severe Pollution, Moderate Pollution, Light Pollution, Good and Excellent based on their respective Air Quality Index (AQI) values. Using the information theory, information gain (IG) is calculated and feature selection is done for both categorical features and continuous numeric features. Then SVM Machine Learning algorithm is implemented on the selected features with cross-validation. The final evaluation reveals that the IG and SVM hybrid model performs better than SVM (alone), Artificial Neural Network (ANN) and K-Nearest Neighbours (KNN) models in terms of accuracy as well as complexity.
Classification of high resolution polarimetric Synthetic Aperture Radar (PolSAR) images plays an important role in land cover and land use management. Recently, classification algorithms based on Bag of Visual Words (BOVW) model have attracted significant interest among scholars and researchers in and out of the field of remote sensing. In this paper, BOVW model with pixel based low-level features has been implemented to classify a subset of San Francisco bay PolSAR image, acquired by RADARSAR 2 in C-band. We have used segment-based decision-making strategy and compared the result with the result of traditional Support Vector Machine (SVM) classifier. 90.95% overall accuracy of the classification with the proposed algorithm has shown that the proposed algorithm is comparable with the state-of-the-art methods. In addition to increase in the classification accuracy, the proposed method has decreased undesirable speckle effect of SAR images.
Production of a global sedimentological seabed map has been initiated in 1995 to provide the necessary tool for searches of aircraft and boats lost at sea, to give sedimentary information for nautical charts, and to provide input data for acoustic propagation modelling. This original approach had already been initiated one century ago when the French hydrographic service and the University of Nancy had produced maps of the distribution of marine sediments of the French coasts and then sediment maps of the continental shelves of Europe and North America. The current map of the sediment of oceans presented was initiated with a UNESCO's general map of the deep ocean floor. This map was adapted using a unique sediment classification to present all types of sediments: from beaches to the deep seabed and from glacial deposits to tropical sediments. In order to allow good visualization and to be adapted to the different applications, only the granularity of sediments is represented. The published seabed maps are studied, if they present an interest, the nature of the seabed is extracted from them, the sediment classification is transcribed and the resulted map is integrated in the world map. Data come also from interpretations of Multibeam Echo Sounder (MES) imagery of large hydrographic surveys of deep-ocean. These allow a very high-quality mapping of areas that until then were represented as homogeneous. The third and principal source of data comes from the integration of regional maps produced specifically for this project. These regional maps are carried out using all the bathymetric and sedimentary data of a region. This step makes it possible to produce a regional synthesis map, with the realization of generalizations in the case of over-precise data. 86 regional maps of the Atlantic Ocean, the Mediterranean Sea, and the Indian Ocean have been produced and integrated into the world sedimentary map. This work is permanent and permits a digital version every two years, with the integration of some new maps. This article describes the choices made in terms of sediment classification, the scale of source data and the zonation of the variability of the quality. This map is the final step in a system comprising the Shom Sedimentary Database, enriched by more than one million punctual and surface items of data, and four series of coastal seabed maps at 1:10,000, 1:50,000, 1:200,000 and 1:1,000,000. This step by step approach makes it possible to take into account the progresses in knowledge made in the field of seabed characterization during the last decades. Thus, the arrival of new classification systems for seafloor has improved the recent seabed maps, and the compilation of these new maps with those previously published allows a gradual enrichment of the world sedimentary map. But there is still a lot of work to enhance some regions, which are still based on data acquired more than half a century ago.
Datasets or collections are becoming important assets by themselves and now they can be accepted as a primary intellectual output of a research. The quality and usage of the datasets depend mainly on the context under which they have been collected, processed, analyzed, validated, and interpreted. This paper aims to present a collection of program educational objectives mapped to student’s outcomes collected from self-study reports prepared by 32 engineering programs accredited by ABET. The manual mapping (classification) of this data is a notoriously tedious, time consuming process. In addition, it requires experts in the area, which are mostly not available. It has been shown the operational settings under which the collection has been produced. The collection has been cleansed, preprocessed, some features have been selected and preliminary exploratory data analysis has been performed so as to illustrate the properties and usefulness of the collection. At the end, the collection has been benchmarked using nine of the most widely used supervised multiclass classification techniques (Binary Relevance, Label Powerset, Classifier Chains, Pruned Sets, Random k-label sets, Ensemble of Classifier Chains, Ensemble of Pruned Sets, Multi-Label k-Nearest Neighbors and Back-Propagation Multi-Label Learning). The techniques have been compared to each other using five well-known measurements (Accuracy, Hamming Loss, Micro-F, Macro-F, and Macro-F). The Ensemble of Classifier Chains and Ensemble of Pruned Sets have achieved encouraging performance compared to other experimented multi-label classification methods. The Classifier Chains method has shown the worst performance. To recap, the benchmark has achieved promising results by utilizing preliminary exploratory data analysis performed on the collection, proposing new trends for research and providing a baseline for future studies.
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.