An innovative clustering technique for unsupervized learning in the context of remotely sensed earth resources data analysis

A new clustering technique, based on the concept of immediato neighbourhood, with a novel capability to self-learn the number of clusters expected in the unsupervized environment, has been developed. The method compares favourably with other clustering schemes based on distance measures, both in terms of conceptual innovations and computational economy. Test implementation of the scheme using C-l flight line training sample data in a simulated unsupervized mode has brought out the efficacy of the technique. The technique can easily be implemented as a front end to established pattern classification systems with supervized learning capabilities to derive unified learning systems capable of operating in both supervized and unsupervized environments. This makes the technique an attractive proposition in the context of remotely sensed earth resources data analysis wherein it is essential to have such a unified learning system capability.

Assessment of crop insect damage using unmanned aerial systems: A machine learning approach

Agricultural pests are responsible for millions of dollars in crop losses and management costs every year. In order to implement optimal site-specific treatments and reduce control costs, new methods to accurately monitor and assess pest damage need to be investigated. In this paper we explore the combination of unmanned aerial vehicles (UAV), remote sensing and machine learning techniques as a promising technology to address this challenge. The deployment of UAVs as a sensor platform is a rapidly growing field of study for biosecurity and precision agriculture applications. In this experiment, a data collection campaign is performed over a sorghum crop severely damaged by white grubs (Coleoptera: Scarabaeidae). The larvae of these scarab beetles feed on the roots of plants, which in turn impairs root exploration of the soil profile. In the field, crop health status could be classified according to three levels: bare soil where plants were decimated, transition zones of reduced plant density and healthy canopy areas. In this study, we describe the UAV platform deployed to collect high-resolution RGB imagery as well as the image processing pipeline implemented to create an orthoimage. An unsupervised machine learning approach is formulated in order to create a meaningful partition of the image into each of the crop levels. The aim of the approach is to simplify the image analysis step by minimizing user input requirements and avoiding the manual data labeling necessary in supervised learning approaches. The implemented algorithm is based on the K-means clustering algorithm. In order to control high-frequency components present in the feature space, a neighbourhood-oriented parameter is introduced by applying Gaussian convolution kernels prior to K-means. The outcome of this approach is a soft K-means algorithm similar to the EM algorithm for Gaussian mixture models. The results show the algorithm delivers decision boundaries that consistently classify the field into three clusters, one for each crop health level. The methodology presented in this paper represents a venue for further research towards automated crop damage assessments and biosecurity surveillance.

Learning experiences in a giant interactive environment: Insights from The Cube

In November 2012, Queensland University of Technology in Australia launched a giant interactive learning environment known as The Cube. This article reports a phenomenographic investigation into visitors’ different experiences of learning in The Cube. At present very little is known about people’s learning experience in spaces featuring large interactive screens. We observed many visitors to The Cube and interviewed 26 people. Our analysis identified critical variation across the visitors’ experience of learning in The Cube. The findings are discussed as the learning strategy (in terms of Absorption, Exploration, Isolation and Collaboration); and the content learned (in terms of Technology, Skills and Topics). Other findings presented here are dimensions of the learning strategy and the content learned, with differing perspectives on each dimension. These outcomes provide early insights into the potential of giant interactive environments to enhance learning approaches and guide the design of innovative learning spaces in higher education.

Enhancing the learning experiences through Industry-Based Learning from Indonesian university perspective

This paper investigates how students’ learning experience can be enhanced by participating in the Industry-Based Learning (IBL) program. In this program, the university students coming into the industry to experience how the business is run. The students’ learning media is now not coming from the textbooks or the lecturers but from learning by doing. This new learning experience could be very interesting for students but at the same time could also be challenging. The research involves interviewing a number of students from the IBL programs, the academic staff from the participated university who has experience in supervising students and the employees of the industry who supported and supervised the students in their work placements. The research findings offer useful insights and create new knowledge in the field of education and learning. The research contributes to the existing knowledge by providing a new understanding of the topic as it applied to the Indonesian context.

Realisation of University-Industry Collaboration through Industry-Based Learning at Indonesian Higher Education

The collaboration between universities and industries has become increasingly important for the development of Science and Technology. This is particularly more prominent in the Science Technology Engineering and Mathematics (STEM) disciplines. Literature suggest that the key element of University-Industry Partnership (UIP) is the exchange of knowledge that is mutually beneficial for both parties. One real example of the collaborations is Industry-Based Learning (IBL) in which university students are coming into industries to experience and learn how the skills and knowledge acquired in the classroom are implemented in work places. This paper investigate how the University-Industry Collaboration program is implemented though Industry-Based Learning (IBL) at Indonesian Universities. The research findings offer useful insights and create a new knowledge in the field of STEM education and collaborative learning. The research will contribute to existing knowledge by providing empirical understanding of this topic. The outcomes can be used to improve the quality of University-Industry Partnership programs at Indonesian Universities and inform Indonesian higher education authorities and their industrial partners of an alternative approach to enhance their IBL programs.

Older Australians: Structural barriers to learning in later life

Learning in older age is associated with a wide range of benefits including increases in skills, social interactions, self-satisfaction, coping ability, enjoyment, and resilience to age-related changes in the brain. It is also recognized as being a fundamental component of active ageing and if active ageing objectives are to be met for the growing ageing population, barriers to learning for this group need to be fully understood so that they can be properly addressed. This paper reports on findings from a study aimed at determining the degree that structural factors deter older people aged 55 years and older from engaging in learning activities relative to other factors, based on survey (n=421) and interview (n=40) data. Quantitative and qualitative analyses revealed that factors related to educational institutions as well as infrastructure were commonly cited as barriers to participation in learning. The implications of these and other findings are discussed.

Ageing and learning in Australia: Arguing an evidence base for informed and equitable policy

Given Australia’s population ageing and predicted impacts related to health, productivity, equity and enhancing quality of life outcomes for senior Australians, lifelong learning has been identified as a pathway for addressing the risks associated with an ageing population. To date Australian governments have paid little attention to addressing these needs and thus, there is an urgent need for policy development for lifelong learning as a national priority. The purpose of this article is to explore the current lifelong learning context in Australia and to propose a set of factors that are most likely to impact learning in later years.

Ageing and learning as conceptualized by senior adults in two cultures: Hong Kong and Australia

This paper is about a study aimed to understand what successful ageing and later life learning mean to older adults in two cultures: Hong Kong and Australia. Findings from the study were reported in this paper to shed light on: (1) the meaning of ageing and learning as conceptualized by elders in Hong Kong and Australia; (2) the reasons for participation in later life learning, as well as, barriers for non-participation; (3) their learning interests and instructional preferences, and finally (4) the correlation between learning and successful ageing, and between learning and other well-being variables, including health, happiness and satisfaction of elders in Hong Kong and Australia. Two large samples of elders from Hong Kong (n=519) and Queensland, Australia (n=421) participated in the study. Within group analysis of the data from the two locations indicated that there are more similarities, rather than differences, between elders in Hong Kong and Australia with respect to background characteristics, meanings of ageing and learning, reasons for participation, barriers for non-participation, learning interests and instructional preferences.

Learning dynamic prices in multiseller electronic retail markets with price sensitive customers, stochastic demands, and inventory replenishments

In this paper, we use reinforcement learning (RL) as a tool to study price dynamics in an electronic retail market consisting of two competing sellers, and price sensitive and lead time sensitive customers. Sellers, offering identical products, compete on price to satisfy stochastically arriving demands (customers), and follow standard inventory control and replenishment policies to manage their inventories. In such a generalized setting, RL techniques have not previously been applied. We consider two representative cases: 1) no information case, were none of the sellers has any information about customer queue levels, inventory levels, or prices at the competitors; and 2) partial information case, where every seller has information about the customer queue levels and inventory levels of the competitors. Sellers employ automated pricing agents, or pricebots, which use RL-based pricing algorithms to reset the prices at random intervals based on factors such as number of back orders, inventory levels, and replenishment lead times, with the objective of maximizing discounted cumulative profit. In the no information case, we show that a seller who uses Q-learning outperforms a seller who uses derivative following (DF). In the partial information case, we model the problem as a Markovian game and use actor-critic based RL to learn dynamic prices. We believe our approach to solving these problems is a new and promising way of setting dynamic prices in multiseller environments with stochastic demands, price sensitive customers, and inventory replenishments.

Psychologically-Based and Content-Oriented Experience in Entertainment Virtual Environments

In daily life, rich experiences evolve in every environmental and social interaction. Because experience has a strong impact on how people behave, scholars in different fields are interested in understanding what constitutes an experience. Yet even if interest in conscious experience is on the increase, there is no consensus on how such experience should be studied. Whatever approach is taken, the subjective and psychologically multidimensional nature of experience should be respected. This study endeavours to understand and evaluate conscious experiences. First I intro-duce a theoretical approach to psychologically-based and content-oriented experience. In the experiential cycle presented here, classical psychology and orienting-environmental content are connected. This generic approach is applicable to any human-environment interaction. Here I apply the approach to entertainment virtual environments (VEs) such as digital games and develop a framework with the potential for studying experiences in VEs. The development of the methodological framework included subjective and objective data from experiences in the Cave Automatic Virtual Environment (CAVE) and with numerous digital games (N=2,414). The final framework consisted of fifteen factor-analytically formed subcomponents of the sense of presence, involvement and flow. Together, these show the multidimensional experiential profile of VEs. The results present general experiential laws of VEs and show that the interface of a VE is related to (physical) presence, which psychologically means attention, perception and the cognitively evaluated realness and spatiality of the VE. The narrative of the VE elicits (social) presence and involvement and affects emotional outcomes. Psychologically, these outcomes are related to social cognition, motivation and emotion. The mechanics of a VE affect the cognitive evaluations and emotional outcomes related to flow. In addition, at the very least, user background, prior experience and use context affect the experiential variation. VEs are part of many peoples lives and many different outcomes are related to them, such as enjoyment, learning and addiction, depending on who is making the evalua-tion. This makes VEs societally important and psychologically fruitful to study. The approach and framework presented here contribute to our understanding of experiences in general and VEs in particular. The research can provide VE developers with a state-of-the art method (www.eveqgp.fi) that can be utilized whenever new product and service concepts are designed, prototyped and tested.

Reinforcement learning applications in dynamic pricing of retail markets

In this paper, we investigate the use of reinforcement learning (RL) techniques to the problem of determining dynamic prices in an electronic retail market. As representative models, we consider a single seller market and a two seller market, and formulate the dynamic pricing problem in a setting that easily generalizes to markets with more than two sellers. We first formulate the single seller dynamic pricing problem in the RL framework and solve the problem using the Q-learning algorithm through simulation. Next we model the two seller dynamic pricing problem as a Markovian game and formulate the problem in the RL framework. We solve this problem using actor-critic algorithms through simulation. We believe our approach to solving these problems is a promising way of setting dynamic prices in multi-agent environments. We illustrate the methodology with two illustrative examples of typical retail markets.

Learning and using taxonomies for visual and olfactory classification

Humans are able of distinguishing more than 5000 visual categories even in complex environments using a variety of different visual systems all working in tandem. We seem to be capable of distinguishing thousands of different odors as well. In the machine learning community, many commonly used multi-class classifiers do not scale well to such large numbers of categories. This thesis demonstrates a method of automatically creating application-specific taxonomies to aid in scaling classification algorithms to more than 100 cate- gories using both visual and olfactory data. The visual data consists of images collected online and pollen slides scanned under a microscope. The olfactory data was acquired by constructing a small portable sniffing apparatus which draws air over 10 carbon black polymer composite sensors. We investigate performance when classifying 256 visual categories, 8 or more species of pollen and 130 olfactory categories sampled from common household items and a standardized scratch-and-sniff test. Taxonomies are employed in a divide-and-conquer classification framework which improves classification time while allowing the end user to trade performance for specificity as needed. Before classification can even take place, the pollen counter and electronic nose must filter out a high volume of background “clutter” to detect the categories of interest. In the case of pollen this is done with an efficient cascade of classifiers that rule out most non-pollen before invoking slower multi-class classifiers. In the case of the electronic nose, much of the extraneous noise encountered in outdoor environments can be filtered using a sniffing strategy which preferentially samples the visensor response at frequencies that are relatively immune to background contributions from ambient water vapor. This combination of efficient background rejection with scalable classification algorithms is tested in detail for three separate projects: 1) the Caltech-256 Image Dataset, 2) the Caltech Automated Pollen Identification and Counting System (CAPICS) and 3) a portable electronic nose specially constructed for outdoor use.

Structure learning in a sensorimotor association task.

Learning is often understood as an organism's gradual acquisition of the association between a given sensory stimulus and the correct motor response. Mathematically, this corresponds to regressing a mapping between the set of observations and the set of actions. Recently, however, it has been shown both in cognitive and motor neuroscience that humans are not only able to learn particular stimulus-response mappings, but are also able to extract abstract structural invariants that facilitate generalization to novel tasks. Here we show how such structure learning can enhance facilitation in a sensorimotor association task performed by human subjects. Using regression and reinforcement learning models we show that the observed facilitation cannot be explained by these basic models of learning stimulus-response associations. We show, however, that the observed data can be explained by a hierarchical Bayesian model that performs structure learning. In line with previous results from cognitive tasks, this suggests that hierarchical Bayesian inference might provide a common framework to explain both the learning of specific stimulus-response associations and the learning of abstract structures that are shared by different task environments.

Structure learning in action.

'Learning to learn' phenomena have been widely investigated in cognition, perception and more recently also in action. During concept learning tasks, for example, it has been suggested that characteristic features are abstracted from a set of examples with the consequence that learning of similar tasks is facilitated-a process termed 'learning to learn'. From a computational point of view such an extraction of invariants can be regarded as learning of an underlying structure. Here we review the evidence for structure learning as a 'learning to learn' mechanism, especially in sensorimotor control where the motor system has to adapt to variable environments. We review studies demonstrating that common features of variable environments are extracted during sensorimotor learning and exploited for efficient adaptation in novel tasks. We conclude that structure learning plays a fundamental role in skill learning and may underlie the unsurpassed flexibility and adaptability of the motor system.

Measuring stiffness during arm movements in various dynamic environments

The technique presented in this paper enables a simple, accurate and unbiased measurement of hand stiffness during human arm movements. Using a computer-controlled mechanical interface, the hand is shifted relative to a prediction of the undisturbed trajectory. Stiffness is then computed as the restoring force divided by the position amplitude of the perturbation. A precise prediction algorithm insures the measurement quality. We used this technique to measure stiffness in free movements and after adaptation to a linear velocity dependent force field. The subjects compensated for the external force by co-contracting muscles selectively. The stiffness geometry changed with learning and stiffness tended to increase in the direction of the external force.