Art Machine Learning Techniques Research Articles

Enhanced Approaches for Safeguarding Communication Channels from Illicit Messages

This research project presents a comprehensive strategy aimed at mitigating the pervasive threat of human trafficking through the innovative application of machine learning methodologies. The primary objective revolves around the development and deployment of sophisticated algorithms to identify and intercept human trafficking- related communications. Leveraging the power of Support Vector Machine (SVM) classification, the system meticulously scrutinizes textual data streams, flagging messages indicative of trafficking activities for further investigation. Moreover, our approach extends beyond mere message analysis by incorporating cutting-edge Utilize Convolutional Neural Network (CNN) models for performing facial recognition, age estimation, and gender identification. By harnessing the rich visual information embedded in images and videos, the system enhances its capability to identify potential victims and perpetrators with unprecedented accuracy and efficiency. A pivotal component of our solution is the seamless integration of an alert mechanism facilitated by a Simple Mail Transfer Protocol (SMTP) server. This critical feature ensures that pertinent authorities are promptly notified upon the detection of suspicious activities, enabling swift and decisive intervention. Through this amalgamation of advanced technological frameworks, our research endeavors to empower law enforcement agencies and humanitarian organizations in their tireless efforts to combat the heinous crime of human trafficking. In essence, this research represents a significant stride towards the realization of a technologically fortified defense against the exploitation of vulnerable individuals. By amalgamating state-of-the- art machine learning techniques with real-time alert systems, we aspire to create a formidable deterrent against the perpetrators of this egregious crime, thereby Ensuring the protection of human dignity and advocating for social justice.

EmoMatchSpanishDB: study of speech emotion recognition machine learning models in a new Spanish elicited database

In this paper we present a new speech emotion dataset on Spanish. The database is created using an elicited approach and is composed by fifty non-actors expressing the Ekman’s six basic emotions of anger, disgust, fear, happiness, sadness, and surprise, plus neutral tone. This article describes how this database has been created from the recording step to the performed crowdsourcing perception test step. The crowdsourcing has facilitated to statistically validate the emotion of each collected audio sample and also to filter noisy data samples. Hence we obtained two datasets EmoSpanishDB and EmoMatchSpanishDB. The first includes those recorded audios that had consensus during the crowdsourcing process. The second selects from EmoSpanishDB only those audios whose emotion also matches with the originally elicited. Last, we present a baseline comparative study between different state of the art machine learning techniques in terms of accuracy, precision, and recall for both datasets. The results obtained for EmoMatchSpanishDB improves the ones obtained for EmoSpanishDB and thereof, we recommend to follow the methodology that was used for the creation of emotional databases.

State of the Art Machine Learning Techniques for Detecting Fake News

The social media has significantly changed how we communicate and exchange information throughout time. Along with it comes the issue of fake news' quick spread, which may have detrimental effects on both people and society. Fake news has been surfacing often and in enormous quantities online for a variety of political and economic goals. To increase the appeal of their publications, fake news publishers employ a number of stylistic strategies, one of which is stirring up readers' emotions. To increase the appeal of their publications, fake news publishers employ a number of stylistic strategies, one of which is stirring up the feelings of readers. As an outcome, it is now extremely difficult to analyses bogus news so that the creators may verify it through data processing channels without misleading the public. It is necessary to implement a system for fact-checking claims, especially those that receive thousands of views and likes before being disputed and disproved by reliable sources. Numerous machine learning algorithms have been applied to accurately identify and categories bogus news. A ML classifier was used in this investigation to determine if news was phony or authentic. On the dataset, the proposed model and other benchmark methods are assessed using the best characteristics. Results from the classification show that our suggested model (CNNs) performs better than the current models with a precision of 98.13%.

1-D convolution neural network based leak detection, location and size estimation in smart water grid

ABSTRACT Water is one of the essential natural resources for survival, but the water transportation system faces significant challenges because of huge water loss due to leaky pipeline systems. An IoT based novel SWG prototype has been developed and reported in this work. The SWG comprises sensors and devices that can continuously and remotely monitor the pressure, temperature, flow, pH, turbidity, etc., of the water being transported. Moreover, a novel 1-D CNN model has been developed by creating an artificial leak on the pipeline that takes input data points as a chunk of 5-minute time series to the network and gives output in leak detection, location and size estimation simultaneously. Further, the developed model is compared with other state of the art machine learning techniques and the proposed model is found better in terms of accuracy which is 94.32%, 91.91% and 89.85% for leak detection, size estimation and location respectively.

Listen to the noise – Demonstrating an end to end multi-platform and multilingual sentiment analysis approach

This paper demonstrates a holistic approach for conducting multi-platform and multilingual sentiment analysis of a main stream football club in the United Arab Emirates. The paper reports first iterations of the research project which anticipates to build an automated sentiment analysis system for football clubs to detect and prevent a potential social media crisis at an early stage. The article illustrates a schematic of how state of the art machine learning algorithms, methods and techniques can be put together to provide a basis for automated data collection, classification, sentiment analysis and visual reporting. The article also presents that the time-consuming and costly process of human text labelling can be effectively replaced by lexicon-based sentiment analysis. This paper reports the complete process from data collection to visual reports to discuss challenges and opportunities associated with design and development of such artefacts.

Assistive Devices Analysis for Visually Impaired Persons: A Review on Taxonomy

Visually impaired persons (VIPs) comprise a significant portion of the population and they are present in all corners of the world. In recent times, the technology proved its presence in every domain of life and innovative devices are assisting humans in all fields especially, artificial intelligence has dominated and outperformed the rest of the trades. VIPs need assistance in performing daily life tasks like object/obstacle detection and recognition, navigation, and mobility, particularly in indoor and outdoor environments. Moreover, the protection and safety of these people are of prime concern. Several devices and applications have been developed for the assistance of VIPs. Firstly, these devices take input from the surrounding environment through different sensors e.g. infrared radiation, ultrasonic, imagery sensor, etc. In the second stage, state of the art machine learning techniques process these signals and extract useful information. Finally, feedback is provided to the user through auditory and/or vibratory means. It is observed that most of the existing devices are constrained in their abilities. The paper presents a comprehensive comparative analysis of the state-of-the-art assistive devices for VIPs. These techniques are categorized based on their functionality and working principles. The main attributes, challenges, and limitations of these techniques have also been highlighted. Moreover, a score-based quantitative analysis of these devices is performed to highlight their feature enrichment capability for each category. It may help to select an appropriate device for a particular scenario.

Applied Machine Learning for Games: A Graduate School Course

The game industry is moving into an era where old-style game engines are being replaced by re-engineered systems with embedded machine learning technologies for the operation, analysis and understanding of game play. In this paper, we describe our machine learning course designed for graduate students interested in applying recent advances of deep learning and reinforcement learning towards gaming. This course serves as a bridge to foster interdisciplinary collaboration among graduate schools and does not require prior experience designing or building games. Graduate students enrolled in this course apply different fields of machine learning techniques such as computer vision, natural language processing, computer graphics, human computer interaction, robotics and data analysis to solve open challenges in gaming. Student projects cover use-cases such as training AI-bots in gaming benchmark environments and competitions, understanding human decision patterns in gaming, and creating intelligent non-playable characters or environments to foster engaging gameplay. Projects demos can help students open doors for an industry career, aim for publications, or lay the foundations of a future product. Our students gained hands-on experience in applying state of the art machine learning techniques to solve real-life problems in gaming.

Landslide susceptibility assessment and mapping using state-of-the art machine learning techniques

Landslides pose a serious risk to human life and the natural environment. Here, we compare machine learning algorithms including the generalized linear model (GLM), mixture discriminant analysis (MDA), boosted regression tree (BRT), and functional discriminant analysis (FDA) to evaluate the landslide exposure regions in Fars Province, comprising an area of approximately 7% of Iran. Initially, an aggregate of 179 historical landslide occurrences was prepared and partitioned. Subsequently, ten landslide conditioning factors (LCFs) were generated. The partial least squares algorithm was utilized to assess the significance of the LCFs with the help of a training dataset which indicated that distance from road had the maximum significance in forecasting landslides, followed by altitude (Al), lithological units, and slope degree. Finally, the LSMs generated using BRT, GLM, MDA, and FDA were validated and compared using cut-off reliant and independent validation measures. The results of the validation metrics showed that GLM and BRT had an AUC of 0.908, while FDA and MDA had AUCs of 0.858 and 0.821, respectively. The results from our case study can be utilized to develop strategies and plans to minimize the loss of human lives and the natural environment.

Optimized Predictive Framework for Healthcare Through Deep Learning

Smart healthcare integrates an advanced wave of information technology using smart devices to collect health-related medical science data. Such data usually exist in unstructured, noisy, incomplete, and heterogeneous forms. Annotating these limitations remains an open challenge in deep learning to classify health conditions. In this paper, a long short-term memory (LSTM) based health condition prediction framework is proposed to rectify imbalanced and noisy data and transform it into a useful form to predict accurate health conditions. The imbalanced and scarce data is normalized through coding to gain consistency for accurate results using synthetic minority oversampling technique. The proposed model is optimized and fine-tuned in an end to end manner to select ideal parameters using tree parzen estimator to build a probabilistic model. The patient’s medication is pigeonholed to plot the diabetic condition’s risk factor through an algorithm to classify blood glucose metrics using a modern surveillance error grid method. The proposed model can efficiently train, validate, and test noisy data by obtaining consistent results around 90% over the state of the art machine and deep learning techniques and overcoming the insufficiency in training data through transfer learning. The overall results of the proposed model are further tested with secondary datasets to verify model sustainability.

Prediction of the Remaining Useful Life of Aircraft Systems via Web Interface

In this work a web-based tool is presented for the simulation of a Prognostics and Health Management (PHM) system used for exploring and testing different machine learning experimental scenarios with the goal of predicting the Remaining Useful Life (RUL) of aircraft systems. With this tool, the user can select a set of options like the datasets to use, its size, the machine learning method to apply for the RUL prediction and the metrics used for comparing the results. The proposed datasets correspond to public data extracted from a model which aims to simulate a Turbofan Engine dataset of an aircraft. Also, three different State of the Art machine learning techniques are made available to be applied and tested: a Similarity-based, a Neural Network-based and an Extrapolation-based approach. The results obtained by the different approaches can be graphically compared in the web interface. As the methods are executed remotely, the user incurs no computational costs, which constitutes an advantage of using this tool. This web tool aims to be a user-friendly interface used for simulating online experiments regarding the RUL prediction.

Classification of Plant leaf diseases: A Deep Learning Method

For the continuous existence of human life, agriculture plays a vital role due to the dependency of lives of people on it for production of food. In order to meet high production rate, precision farming is required. Presently, substantial developments attained “in the field of image processing and recognition” which has being a foremost challenge earlier in the practice of Precision farming. The reduction in the growth, quality and quantity of plants is due to expansion of plant diseases.The survey literature confers various plant leaf diseases and their detections during different phases through various state of art machine and deep learning techniques. The particular emphasis in this paper is on detection and classification of plant “leaf diseases” through deep “convolutional neural networks algorithms.

“Super-efficient gradient estimation technique,” Recent advances in efficient adjoint sensitivity analysis and its application in metamaterial design

Computer-aided design (CAD) tools in electromagnetics allow accurate modeling of the preferred responses. We can adjust a desired response by conducting an optimization algorithm. This requisite the gradient estimation of structures with respect to potentially N number of optimizable parameters. In conventional gradient estimation methods, the number of required simulations scales linearly with N. Adjoint variable method (AVM) is an extremely efficient sensitivity analysis method that estimates the gradients with respect to the all N parameters by conducting only 2 simulations, regardless of N. We have developed AVM method for gradient analysis of anisotropic and dispersive anisotropic structures. Then, we applied it in wideband inversely invisibility cloak design for 2-D and 3-D structures at optical and microwave frequency regions. In those examples, our algorithm accelerates the gradient estimation over 1400 and 12 500 times per iteration, respectively, compared to the conventional methods. This advanced optimization based metamaterial cloak design to 3-D arbitrary shape objects and optical frequency region which was not feasible before. For the next step, we are planning to extend this efficient gradient estimation algorithm to the state of the art machine learning techniques and recently introduced continuous neural networks such as neural ordinary differential equations (ODE-Net).

Multi-Hazard Exposure Mapping Using Machine Learning Techniques: A Case Study from Iran

Mountainous areas are highly prone to a variety of nature-triggered disasters, which often cause disabling harm, death, destruction, and damage. In this work, an attempt was made to develop an accurate multi-hazard exposure map for a mountainous area (Asara watershed, Iran), based on state-of-the art machine learning techniques. Hazard modeling for avalanches, rockfalls, and floods was performed using three state-of-the-art models—support vector machine (SVM), boosted regression tree (BRT), and generalized additive model (GAM). Topo-hydrological and geo-environmental factors were used as predictors in the models. A flood dataset (n = 133 flood events) was applied, which had been prepared using Sentinel-1-based processing and ground-based information. In addition, snow avalanche (n = 58) and rockfall (n = 101) data sets were used. The data set of each hazard type was randomly divided to two groups: Training (70%) and validation (30%). Model performance was evaluated by the true skill score (TSS) and the area under receiver operating characteristic curve (AUC) criteria. Using an exposure map, the multi-hazard map was converted into a multi-hazard exposure map. According to both validation methods, the SVM model showed the highest accuracy for avalanches (AUC = 92.4%, TSS = 0.72) and rockfalls (AUC = 93.7%, TSS = 0.81), while BRT demonstrated the best performance for flood hazards (AUC = 94.2%, TSS = 0.80). Overall, multi-hazard exposure modeling revealed that valleys and areas close to the Chalous Road, one of the most important roads in Iran, were associated with high and very high levels of risk. The proposed multi-hazard exposure framework can be helpful in supporting decision making on mountain social-ecological systems facing multiple hazards.

Presentation Slides: Forecasting Using NNS

Presentation slides highlighting the forecasting technique NNS.ARMA using nonlinear nonparametric statistics in the R-package NNS. Explains the determination of seasonality using the coefficient of variance of subset series and the implementation of both linear and nonlinear regressions on the component series. Examples comparing performance against traditional ARMA methods as well as state of the art machine learning techniques.

Optimisation of hybrid energy systems for maritime vessels

The decarbonisation agenda in maritime transport requires that asset owners and operators adopt greener technologies within their existing and new vessels. The primary drivers within this agenda relate to improved environmental metrics, efficient energy performance, and improved asset management. However, the integration of new technologies always presents technical and financial risks. Here, utilising energy and environmental monitoring from real vessels, the authors propose an energy system optimisation architecture, hybrid fusion energy management system (HyFES), that optimises the key performance indicators of energy performance, reduction of diesel engine nitrogen oxide (NOx), and particulate matter (PM), and prognostic state of health assessment of energy storage technologies. Using state of the art machine-learning techniques, the authors are able to determine the on-board lithium-ion and lead acid batteries' state of health with accuracy > 8 and 4%, respectively. Dependent on the mode of operation, optimisation of energy performance indicates fuel saving of between 70 and 80% for the vessel operator. Future research will focus on the integration of more assets into the optimisation architecture and increased vessel journey use cases.

Validating Deep Neural Networks for Online Decoding of Motor Imagery Movements from EEG Signals.

Non-invasive, electroencephalography (EEG)-based brain-computer interfaces (BCIs) on motor imagery movements translate the subject’s motor intention into control signals through classifying the EEG patterns caused by different imagination tasks, e.g., hand movements. This type of BCI has been widely studied and used as an alternative mode of communication and environmental control for disabled patients, such as those suffering from a brainstem stroke or a spinal cord injury (SCI). Notwithstanding the success of traditional machine learning methods in classifying EEG signals, these methods still rely on hand-crafted features. The extraction of such features is a difficult task due to the high non-stationarity of EEG signals, which is a major cause by the stagnating progress in classification performance. Remarkable advances in deep learning methods allow end-to-end learning without any feature engineering, which could benefit BCI motor imagery applications. We developed three deep learning models: (1) A long short-term memory (LSTM); (2) a spectrogram-based convolutional neural network model (CNN); and (3) a recurrent convolutional neural network (RCNN), for decoding motor imagery movements directly from raw EEG signals without (any manual) feature engineering. Results were evaluated on our own publicly available, EEG data collected from 20 subjects and on an existing dataset known as 2b EEG dataset from “BCI Competition IV”. Overall, better classification performance was achieved with deep learning models compared to state-of-the art machine learning techniques, which could chart a route ahead for developing new robust techniques for EEG signal decoding. We underpin this point by demonstrating the successful real-time control of a robotic arm using our CNN based BCI.

Design of an Interactive Biomedical Text Mining Framework to Recognize Real-Time Drug Entities Using Machine Learning Algorithms

Drug Named Entity Recognition (DNER) is the process of identifying drug names from unstructured biomedical text. Most of the research works in this area make use of the available benchmark biomedical corpus to train and test the DNER system. In this paper, we propose an interactive biomedical text mining framework to access the scientific abstracts online, to pre-process and to extract drug entity through state – of – art machine learning techniques. This framework facilitates recognizing new drug names from real time biomedical abstracts from PubMed as well as from existing benchmark test datasets.

A Hybrid Intelligence System Based on Relevance Vector Machines and Imperialist Competitive Optimization for Modelling Forest Fire Danger Using GIS

This article proposes and verifies a novel intelligence approach for modelling forest fire danger, namely ICA-RVM, developed based on Relevance Vector Machine (RVM) and Imperialist Competitive Algorithm (ICA), state-of-the art machine learning techniques that have not been investigated for forest fire danger modeling. RVM is used to establish a prediction model that computes probability of fire danger, whereas ICA is adopted to optimize the prediction model. The tropical forest at Gia Lai province, Central Highland (Vietnam), was used as a case study. Area under the curve (AUC) and statistical measures were used to assess the model performance. The result showed that the proposed model achieves high performances; AUC is 0.842 and 0.793 on the training dataset and the validation dataset, respectively. Compared to two benchmarks, Random Forests and Support Vector Machine, the proposed model performs better. Therefore, the propose ICA-RVM is a valid alternative system for forest fire danger modeling.

Automatic classification of cancer cells in multispectral microscopic images of lymph node samples.

Histopathological analysis is crucial for the diagnosis of a large number of cancer types. A lot of progress has been made in the development of molecular based assays, but many of the cases still require the careful analysis of the stained tissue under a bright-field microscope and its analysis. This procedure is costly and time-consuming. We present a novel method for classification of cancer cells in lymph node images. It is based on the measurement of the spectral image of hematoxylin and eosin stained sample under the microscope and the analysis of the acquired data using state of the art machine learning techniques. The method is based on the analysis of the spectral information of the cells as well as their morphological properties. A large number of descriptors is extracted for each cell location, which are used to train a supervised classifier which discriminates between normal and cancer cells. We show that a reliable analysis can be made with detection rate (recall) of 81%-100% for the cancer class.

A novel ontology and machine learning driven hybrid cardiovascular clinical prognosis as a complex adaptive clinical system

Abstract Purpose This multidisciplinary industrial research project sets out to develop a hybrid clinical decision support mechanism (inspired by ontology and machine learning driven techniques) by combining evidence, extrapolated through legacy patient data to facilitate cardiovascular preventative care. Methods The proposed cardiovascular clinical decision support framework comprises of two novel key components: (1) Ontology driven clinical risk assessment and recommendation system (ODCRARS) (2) Machine learning driven prognostic system (MLDPS). State of the art machine learning and feature selection methods are utilised for the prognostic modelling purposes. The ODCRARS is a knowledge-based system which is based on clinical expert’s knowledge, encoded in the form of clinical rules engine to carry out cardiac risk assessment for various cardiovascular diseases. The MLDPS is a non knowledge-based/data driven system which is developed using state of the art machine learning and feature selection techniques applied on real patient datasets. Clinical case studies in the RACPC, heart disease and breast cancer domains are considered for the development and clinical validation purposes. For the purpose of this paper, clinical case study in the RACPC/chest pain domain will be discussed in detail from the development and validation perspective. Results The proposed clinical decision support framework is validated through clinical case studies in the cardiovascular domain. This paper demonstrates an effective cardiovascular decision support mechanism for handling inaccuracies in the clinical risk assessment of chest pain patients and help clinicians effectively distinguish acute angina/cardiac chest pain patients from those with other causes of chest pain. Conclusion The new clinical models, having been evaluated in clinical practice, resulted in very good predictive power, demonstrating general performance improvement over benchmark multivariate statistical classifiers. Various chest pain risk assessment prototypes have been developed and deployed online for further clinical trials.