Hong Xie

The use of sensors for monitoring livestock has opened up new possibilities for the management of livestock in extensive grazing systems. The work presented in this paper aimed to develop a model for predicting the metabolisable energy intake (MEI) of sheep by using temperature, pitch angle, roll angle, distance, speed, and grazing time data obtained directly from wearable sensors on the sheep. A Deep Belief Network (DBN) algorithm was used to predict MEI, which to our knowledge, has not been attempted previously. The results demonstrated that the DBN method could predict the MEI for sheep using sensor data alone. The mean square error (MSE) values of 4.46 and 20.65 have been achieved using the DBN model for training and testing datasets, respectively. We also evaluated the influential sensor data variables, i.e., distance and pitch angle, for predicting the MEI. Our study demonstrates that the application of machine learning techniques directly to on-animal sensor data presents a substantial opportunity to interpret biological interactions in grazing systems directly from sensor data. We expect that further development and refinement of this technology will catalyse a step-change in extensive livestock management, as wearable sensors become widely used by livestock producers.

Feature Selection (FS) methods have been studied extensively in the literature, and there are a crucial component in machine learning techniques. However, unsupervised text feature selection has not been well studied in document clustering problems. Feature selection could be modelled as an optimization problem due to the large number of possible solutions that might be valid. In this paper, a memetic method that combines Differential Evolution (DE) with Simulated Annealing (SA) for unsupervised FS was proposed. Due to the use of only two values indicating the existence or absence of the feature, a binary version of differential evolution is used. A dichotomous DE was used for the purpose of the binary version, and the proposed method is named Dichotomous Differential Evolution Simulated Annealing (DDESA). This method uses dichotomous mutation instead of using the standard mutation DE to be more effective for binary purposes. The Mean Absolute Distance (MAD) filter was used as the feature subset internal evaluation measure in this paper. The proposed method was compared with other state-of-the-art methods including the standard DE combined with SA, which is named DESA in this paper, using five benchmark datasets. The F-micro, F-macro (F-scores) and Average Distance of Document to Cluster (ADDC) measures were utilized as the evaluation measures. The Reduction Rate (RR) was also used as an evaluation measure. Test results showed that the proposed DDESA outperformed the other tested methods in performing the unsupervised text feature selection.

One of the fundamental tasks in the management of livestock is to understand their behaviour and use this information to increase livestock productivity and welfare. Developing new and improved methods to classify livestock behaviour based on their daily activities can greatly improve livestock management. In this paper, we propose the use of a hierarchical machine learning method to classify livestock behaviours. We first classify the livestock behaviours into two main behavioural categories. Each of the two categories is then broken down at the next level into more specific behavioural categories. We have tested the proposed methodology using two commonly used classifiers, Random Forest, Support Vector Machine and a newer approach involving Deep Belief Networks. Our results show that the proposed hierarchical classification technique works better than the conventional approach. The experimental studies also show that Deep Belief Networks perform better than the Random Forest and Support Vector Machine for most cases.

An Adaptive Crossover Memetic Differential Harmony Search (ACMDHS) method was developed for optimizing document clustering in this paper. Due to the complexity of the documents available today, the allocation of the centroid of the document clusters and finding the optimum clusters in the search space are more complex to deal with. One of the possible enhancements on the document clustering is the use of Harmony Search (HS) algorithm to optimize the search. As HS is highly dependent on its control parameters, a differential version of HS was introduced. In the modified version of HS, the Band Width parameter (BW) has been replaced by another pitch adjustment technique due to the sensitivity of the BW parameter. Thus, the Differential Evolution (DE) mutation was used instead. In this paper the DE crossover was also used with the Differential HS for further search space exploitation, the produced global search is named Crossover DHS (CDHS). Moreover, DE crossover (Cr) and mutation (F) probabilities are dynamically tuned through generations. The Memetic optimization was used to enhance the local search capability of CDHS. The proposed ACMDHS was compared to other document clustering techniques using HS, DHS, and K-means methods. It was also compared to its other two variants which are the Memetic DHS (MDHS) and the Crossover Memetic Differential Harmony Search (CMDHS). Moreover, two state-of-the-art clustering methods were also considered in comparisons, the Chaotic Gradient Artificial Bee Colony (CGABC) and the Differential Evolution Memetic Clustering (DEMC). From the experimental results, it was shown that CMDHS variant (the non-adaptive version of ACMDHS) and ACMDHS were highly competitive while both CMDHS and ACMDHS were superior to all other methods.

Deep learning techniques have shown to perform well in Question Answering (QA) tasks. We present a framework that combines Memory Network (MN) and Reinforcement Learning (Q-learning) to perform QA, termed Reinforced MN (R-MN). We investigate the proposed framework by the use of Long Short Term Memory Network (LSTM) and Dynamic Memory Network (DMN). We call them Reinforced LSTM (R-LSTM) and Reinforced DMN (R-DMN), respectively. The input text sequence and question are passed to both MN and Q-Learning. The output of the MN is then fed to Q-Learning as a second input for refinement. The R-MN is trained end-to-end. We evaluated R-MNs on the bAbI 1 K QA dataset for all of the 20 tasks. We achieve superior performance when compared to conventional method of RL, LSTM and the state of the art technique, DMN. Using only half of the training data, both R-LSTM and R-DMN achieved all of the bAbI tasks with high accuracies. The experimental results demonstrated that the proposed framework of combining MN and Q-learning enhances the QA tasks while using less training data.

In this paper, we present a semantic parser using a knowledgebase. Instead of relying on filtering the concepts extracted from the knowledgebase, we use all the concepts to create the parser. A simple search is conducted on ConceptNet for the words in the input sentence. In this paper, two proposed techniques are used to extract concepts from the ConceptNet 5. The reason for proposing two techniques in this paper is to address the issue of removing the supervision and training process. The first approach extracts all concepts from ConceptNet 5 for each input word. The extracted concepts are used to search again in ConceptNet 5, which creates multiple levels of search results. This deep concept structure creates a multi-level search to create the semantic parse result. The second approach follows the same first step of extracting concepts using the input text. However, the extracted concepts are passed through a relationship check and then used for the second level search. Concepts are drawn from 2 levels of searching in ConceptNet. The extracted concepts are used to create the parser. Furthermore, we use the initial concepts extracted to search again in ConceptNet. The parser we created is tested on Free917, Stanford Sentiment dataset and the WebQ. We achieve recall of 93.82%, 94.91% for Stanford Sentiment dataset, accuracy of 77.1%, 79.2% for Free917 and 26.5%, 38.2% for WebQ respectively for the two approaches. This shows state-of-the-art results compared to other methods for each datasets.

In this paper, a document clustering method with a hybrid feature selection method is proposed. The proposed hybrid feature selection method integrates a Genetic-based wrapper method with ranking filter. The method is named Memetic Algorithm-Feature Selection (MA-FS). In this paper, MA-FS is combined with K-means and Spherical K-means (SK-means) clustering methods to perform document clustering. For the purpose of comparison, another unsupervised feature selection method, Feature Selection Genetic Text Clustering (FSGATC), is used. Two real-world criminal report document sets were used along with two popular benchmark datasets which are Reuters and 20newsgroup, were used in the comparisons. F-Micro, F-Macro and Average Distance of Document to Cluster (ADDC) measures were used for evaluation. The test results showed that the MA-FS method has outperformed the FSGATC method. It has also outperformed the results after using the entire feature space (ALL).

In this paper, we propose a Memetic-based clustering method that improves the partitioning of document clustering. Our proposed method is named as Differential Evolution Memetic Clustering (DEMC). Differential Evolution (DE) is used for the selection of the best set of cluster centres (centroids) while the Chaotic Logistic Search (CLS) is used to enhance the best set of solutions found by DE. For the purpose of comparison, the DEMC is compared with the basic DE, Differential Evolution Simulated Annealing (DESA) and the Differential Evolution K-Means (DEKM) methods as well as the traditional partitioning clustering using the K-means. The DEMC is also compared with the recently proposed Chaotic Gradient Artificial Bee Colony (CGABC) document clustering method. The reuters-21578, a pair of the 20-news group, classic 3 and TDT benchmark collection (TDT5) along with real-world six-event-crimes datasets are used in the experiments in this paper. The results showed that the proposed DEMC outperformed the other methods in terms of the convergence rate measured by the fitness function (ADDC) and the compactness of the resulted clusters measured by the F-macro and F-micro measures.

It is challenging to ensure security and to minimize economic impacts due to cyber-attacks because of the heavy reliance on ICT in different organizations and this paper presents an approach to estimate the cost of cyber security in public and private sector organizations. The paper also describes an approach for selecting the type of cyber security improvements to ensure that organizational goals are achieved. Different types of cyber-attacks and the subsequent impacts of these attacks are considered. A Value Analysis method is proposed to support the decision-making process by determining the priorities of deployment of various cyber security technologies. The proposed method is based on security costs related to and the losses due to attacks. Examples are provided in the paper to illustrate the proposed approach.

Current screen-reader program used by the blind people to access the Internet inflicts navigation restrictions since the blind users can only perceive the content in serial mode. The serialized access using screen-reader program restricts the blind users from having the multi-dimensional effects required to fully understand the page layout. We believe that by accessing web pages using bi-modal interaction, a blind user would be able to perceive a two-dimensional perspective of a web page in his or her mental model. The purpose of this st udy is to investigate the differences in the mental models created by blind people from a two-dimensional web page using two different means: one using a screen-reader only and the other using a touch screen with audio feedback. Ten blind people and thirty sighted blindfolded participants participated in this study. This study employed within-subjects repeated measures experiments together with observations, verbal protocols and semi-structured questionnaires to achieve the objectives of the study. Besides, the influence of user’s spatial ability on the user’s performance was investigated using Tactual Performance Test (TPT). The study revealed that using touch screen with audio feedback; the blind people achieved more accurate orientation. However, the accuracy seems to be affected by page complexity. In addition, investigation of blind users’ spatial ability on users’ sense of position revealed that using touch screen with audio feedback, blind participants with lower spatial ability took longer time to locate information. Therefore, users’ spatial ability plays an important determinant for the Web navigability using touch screen with audio feedback.