In this work, we show that a late fusion approach to multimodality in sign language recognition improves the overall ability of the model in comparison to the singular approaches of image ...classification (88.14%) and Leap Motion data classification (72.73%). With a large synchronous dataset of 18 BSL gestures collected from multiple subjects, two deep neural networks are benchmarked and compared to derive a best topology for each. The Vision model is implemented by a Convolutional Neural Network and optimised Artificial Neural Network, and the Leap Motion model is implemented by an evolutionary search of Artificial Neural Network topology. Next, the two best networks are fused for synchronised processing, which results in a better overall result (94.44%) as complementary features are learnt in addition to the original task. The hypothesis is further supported by application of the three models to a set of completely unseen data where a multimodality approach achieves the best results relative to the single sensor method. When transfer learning with the weights trained via British Sign Language, all three models outperform standard random weight distribution when classifying American Sign Language (ASL), and the best model overall for ASL classification was the transfer learning multimodality approach, which scored 82.55% accuracy.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
In this work we present a three-stage Machine Learning strategy to country-level risk classification based on countries that are reporting COVID-19 information. A K% binning discretisation (K = 25) ...is used to create four risk groups of countries based on the risk of transmission (coronavirus cases per million population), risk of mortality (coronavirus deaths per million population), and risk of inability to test (coronavirus tests per million population). The four risk groups produced by K% binning are labelled as 'low', 'medium-low', 'medium-high', and 'high'. Coronavirus-related data are then removed and the attributes for prediction of the three types of risk are given as the geopolitical and demographic data describing each country. Thus, the calculation of class label is based on coronavirus data but the input attributes are country-level information regardless of coronavirus data. The three four-class classification problems are then explored and benchmarked through leave-one-country-out cross validation to find the strongest model, producing a Stack of Gradient Boosting and Decision Tree algorithms for risk of transmission, a Stack of Support Vector Machine and Extra Trees for risk of mortality, and a Gradient Boosting algorithm for the risk of inability to test. It is noted that high risk for inability to test is often coupled with low risks for transmission and mortality, therefore the risk of inability to test should be interpreted first, before consideration is given to the predicted transmission and mortality risks. Finally, the approach is applied to more recent risk levels to data from September 2020 and weaker results are noted due to the growth of international collaboration detracting useful knowledge from country-level attributes which suggests that similar machine learning approaches are more useful prior to situations later unfolding.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
In this paper, the problem of semantic place categorization in mobile robotics is addressed by considering a time-based probabilistic approach called dynamic Bayesian mixture model (DBMM), which is ...an improved variation of the dynamic Bayesian network. More specifically, multi-class semantic classification is performed by a DBMM composed of a mixture of heterogeneous base classifiers, using geometrical features computed from 2D laserscanner data, where the sensor is mounted on-board a moving robot operating indoors. Besides its capability to combine different probabilistic classifiers, the DBMM approach also incorporates time-based (
dynamic
) inferences in the form of previous class-conditional probabilities and priors. Extensive experiments were carried out on publicly available benchmark datasets, highlighting the influence of the number of time-slices and the effect of additive smoothing on the classification performance of the proposed approach. Reported results, under different scenarios and conditions, show the effectiveness and competitive performance of the DBMM.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OBVAL, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
In this work, we show the success of unsupervised transfer learning between Electroencephalographic (brainwave) classification and Electromyographic (muscular wave) domains with both MLP and CNN ...methods. To achieve this, signals are measured from both the brain and forearm muscles and EMG data is gathered from a 4-class gesture classification experiment via the Myo Armband, and a 3-class mental state EEG dataset is acquired via the Muse EEG Headband. A hyperheuristic multi-objective evolutionary search method is used to find the best network hyperparameters. We then use this optimised topology of deep neural network to classify both EMG and EEG signals, attaining results of 84.76% and 62.37% accuracy, respectively. Next, when pre-trained weights from the EMG classification model are used for initial distribution rather than random weight initialisation for EEG classification, 93.82%(+29.95) accuracy is reached. When EEG pre-trained weights are used for initial weight distribution for EMG, 85.12% (+0.36) accuracy is achieved. When the EMG network attempts to classify EEG, it outperforms the EEG network even without any training (+30.25% to 82.39% at epoch 0), and similarly the EEG network attempting to classify EMG data outperforms the EMG network (+2.38% at epoch 0). All transfer networks achieve higher pre-training abilities, curves, and asymptotes, indicating that knowledge transfer is possible between the two signal domains. In a second experiment with CNN transfer learning, the same datasets are projected as 2D images and the same learning process is carried out. In the CNN experiment, EMG to EEG transfer learning is found to be successful but not vice-versa, although EEG to EMG transfer learning did exhibit a higher starting classification accuracy. The significance of this work is due to the successful transfer of ability between models trained on two different biological signal domains, reducing the need for building more computationally complex models in future research.
In this work we present the Chatbot Interaction with Artificial Intelligence (CI-AI) framework as an approach to the training of a transformer based chatbot-like architecture for task classification ...with a focus on natural human interaction with a machine as opposed to interfaces, code, or formal commands. The intelligent system augments human-sourced data via artificial paraphrasing in order to generate a large set of training data for further classical, attention, and language transformation-based learning approaches for Natural Language Processing (NLP). Human beings are asked to paraphrase commands and questions for task identification for further execution of algorithms as skills. The commands and questions are split into training and validation sets. A total of 483 responses were recorded. Secondly, the training set is paraphrased by the T5 model in order to augment it with further data. Seven state-of-the-art transformer-based text classification algorithms (BERT, DistilBERT, RoBERTa, DistilRoBERTa, XLM, XLM-RoBERTa, and XLNet) are benchmarked for both sets after fine-tuning on the training data for two epochs. We find that all models are improved when training data is augmented by the T5 model, with an average increase of classification accuracy by 4.01%. The best result was the RoBERTa model trained on T5 augmented data which achieved 98.96% classification accuracy. Finally, we found that an ensemble of the five best-performing transformer models via Logistic Regression of output label predictions led to an accuracy of 99.59% on the dataset of human responses. A highly-performing model allows the intelligent system to interpret human commands at the social-interaction level through a chatbot-like interface (e.g. “Robot, can we have a conversation?”) and allows for better accessibility to AI by non-technical users.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Recent advances in the availability of computational resources allow for more sophisticated approaches to speech recognition than ever before. This study considers Artificial Neural Network and ...Hidden Markov Model methods of classification for Human Speech Recognition through Diphthong Vowel sounds in the English Phonetic Alphabet rather than the classical approach of the classification of whole words and phrases, with a specific focus on both single and multi-objective evolutionary optimisation of bioinspired classification methods. A set of audio clips are recorded by subjects from the United Kingdom and Mexico and the recordings are transformed into a static dataset of statistics by way of their Mel-Frequency Cepstral Coefficients (MFCC) at sliding window length of 200ms as well as a reshaped MFCC timeseries format for forecast-based models. An deep neural network with evolutionary optimised topology achieves 90.77% phoneme classification accuracy in comparison to the best HMM that achieves 86.23% accuracy with 150 hidden units, when only accuracy is considered in a single-objective optimisation approach. The obtained solutions are far more complex than the HMM taking around 248 seconds to train on powerful hardware versus 160 for the HMM. A multi-objective approach is explored due to this. In the multi-objective approaches of scalarisation presented, within which real-time resource usage is also considered towards solution fitness, far more optimal solutions are produced which train far quicker than the forecast approach (69 seconds) with classification ability retained (86.73%). Weightings towards either maximising accuracy or reducing resource usage from 0.1 to 0.9 are suggested depending on the resources available, since many future IoT devices and autonomous robots may have limited access to cloud resources at a premium in comparison to the GPU used in this experiment.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
This study suggests a new approach to EEG data classification by exploring the idea of using evolutionary computation to both select useful discriminative EEG features and optimise the topology of ...Artificial Neural Networks. An evolutionary algorithm is applied to select the most informative features from an initial set of 2550 EEG statistical features. Optimisation of a Multilayer Perceptron (MLP) is performed with an evolutionary approach before classification to estimate the best hyperparameters of the network. Deep learning and tuning with Long Short-Term Memory (LSTM) are also explored, and Adaptive Boosting of the two types of models is tested for each problem. Three experiments are provided for comparison using different classifiers: one for attention state classification, one for emotional sentiment classification, and a third experiment in which the goal is to guess the number a subject is thinking of. The obtained results show that an Adaptive Boosted LSTM can achieve an accuracy of 84.44%, 97.06%, and 9.94% on the attentional, emotional, and number datasets, respectively. An evolutionary-optimised MLP achieves results close to the Adaptive Boosted LSTM for the two first experiments and significantly higher for the number-guessing experiment with an Adaptive Boosted DEvo MLP reaching 31.35%, while being significantly quicker to train and classify. In particular, the accuracy of the nonboosted DEvo MLP was of 79.81%, 96.11%, and 27.07% in the same benchmarks. Two datasets for the experiments were gathered using a Muse EEG headband with four electrodes corresponding to TP9, AF7, AF8, and TP10 locations of the international EEG placement standard. The EEG MindBigData digits dataset was gathered from the TP9, FP1, FP2, and TP10 locations.
In this work, we argue that the implications of pseudorandom and quantum-random number generators (PRNG and QRNG) inexplicably affect the performances and behaviours of various machine learning ...models that require a random input. These implications are yet to be explored in soft computing until this work. We use a CPU and a QPU to generate random numbers for multiple machine learning techniques. Random numbers are employed in the random initial weight distributions of dense and convolutional neural networks, in which results show a profound difference in learning patterns for the two. In 50 dense neural networks (25 PRNG/25 QRNG), QRNG increases over PRNG for accent classification at + 0.1%, and QRNG exceeded PRNG for mental state EEG classification by + 2.82%. In 50 convolutional neural networks (25 PRNG/25 QRNG), the MNIST and CIFAR-10 problems are benchmarked, and in MNIST the QRNG experiences a higher starting accuracy than the PRNG but ultimately only exceeds it by 0.02%. In CIFAR-10, the QRNG outperforms PRNG by + 0.92%. The
n
-random split of a Random Tree is enhanced towards and new Quantum Random Tree (QRT) model, which has differing classification abilities to its classical counterpart, 200 trees are trained and compared (100 PRNG/100 QRNG). Using the accent and EEG classification data sets, a QRT seemed inferior to a RT as it performed on average worse by − 0.12%. This pattern is also seen in the EEG classification problem, where a QRT performs worse than a RT by − 0.28%. Finally, the QRT is ensembled into a Quantum Random Forest (QRF), which also has a noticeable effect when compared to the standard Random Forest (RF). Ten to 100 ensembles of trees are benchmarked for the accent and EEG classification problems. In accent classification, the best RF (100 RT) outperforms the best QRF (100 QRF) by 0.14% accuracy. In EEG classification, the best RF (100 RT) outperforms the best QRF (100 QRT) by 0.08% but is extremely more complex, requiring twice the amount of trees in committee. All differences are observed to be situationally positive or negative and thus are likely data dependent in their observed functional behaviour.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OBVAL, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
In this study, we present a transfer learning method for gesture classification via an inductive and supervised transductive approach with an electromyographic dataset gathered via the Myo armband. A ...ternary gesture classification problem is presented by states of
’thumbs up’
,
’thumbs down’
, and
’relax’
in order to communicate in the affirmative or negative in a non-verbal fashion to a machine. Of the nine statistical learning paradigms benchmarked over 10-fold cross validation (with three methods of feature selection), an ensemble of Random Forest and Support Vector Machine through voting achieves the best score of 91.74% with a rule-based feature selection method. When new subjects are considered, this machine learning approach fails to generalise new data, and thus the processes of Inductive and Supervised Transductive Transfer Learning are introduced with a short calibration exercise (15 s). Failure of generalisation shows that 5 s of data per-class is the strongest for classification (versus one through seven seconds) with only an accuracy of 55%, but when a short 5 s per class calibration task is introduced via the suggested transfer method, a Random Forest can then classify unseen data from the calibrated subject at an accuracy of around 97%, outperforming the 83% accuracy boasted by the proprietary Myo system. Finally, a preliminary application is presented through social interaction with a humanoid Pepper robot, where the use of our approach and a most-common-class metaclassifier achieves 100% accuracy for all trials of a ‘20 Questions’ game.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
The novelty of this study consists of the exploration of multiple new approaches of data pre-processing of brainwave signals, wherein statistical features are extracted and then formatted as visual ...images based on the order in which dimensionality reduction algorithms select them. This data is then treated as visual input for 2D and 3D convolutional neural networks (CNNs) which then further extract 'features of features'.
Statistical features derived from three electroencephalography (EEG) datasets are presented in visual space and processed in 2D and 3D space as pixels and voxels respectively. Three datasets are benchmarked, mental attention states and emotional valences from the four TP9, AF7, AF8 and TP10 10-20 electrodes and an eye state data from 64 electrodes. Seven hundred twenty-nine features are selected through three methods of selection in order to form 27 × 27 images and 9 × 9 × 9 cubes from the same datasets. CNNs engineered for the 2D and 3D preprocessing representations learn to convolve useful graphical features from the data.
A 70/30 split method shows that the strongest methods for classification accuracy of feature selection are One Rule for attention state and Relative Entropy for emotional state both in 2D. In the eye state dataset 3D space is best, selected by Symmetrical Uncertainty. Finally, 10-fold cross validation is used to train best topologies. Final best 10-fold results are 97.03% for attention state (2D CNN), 98.4% for Emotional State (3D CNN), and 97.96% for Eye State (3D CNN).
The findings of the framework presented by this work show that CNNs can successfully convolve useful features from a set of pre-computed statistical temporal features from raw EEG waves. The high performance of K-fold validated algorithms argue that the features learnt by the CNNs hold useful knowledge for classification in addition to the pre-computed features.