자연주의적 탐구조사(Naturalistic Inquiry)

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

https://link.springer.com/content/pdf/10.2307%2F3343168.pdf

Development as Freedom

The goal of this article is to review the state-of-the-art tracking methods, classify them into different categories, and identify new trends. Object tracking, in general, is a challenging problem. Difficulties in tracking objects can arise due to abrupt object motion, changing appearance patterns of both the object and the scene, nonrigid object structures, object-to-object and object-to-scene occlusions, and camera motion. Tracking is usually performed in the context of higher-level applications that require the location and/or shape of the object in every frame. Typically, assumptions are made to constrain the tracking problem in the context of a particular application. In this survey, we categorize the tracking methods on the basis of the object and motion representations used, provide detailed descriptions of representative methods in each category, and examine their pros and cons. Moreover, we discuss the important issues related to tracking including the use of appropriate image features, selection of motion models, and detection of objects.

/pdf/object-tracking-a-survey-3706dclxb5.pdf

Object tracking: A survey

In this paper, we propose a novel explicit image filter called guided filter. Derived from a local linear model, the guided filter computes the filtering output by considering the content of a guidance image, which can be the input image itself or another different image. The guided filter can be used as an edge-preserving smoothing operator like the popular bilateral filter [1], but it has better behaviors near edges. The guided filter is also a more generic concept beyond smoothing: It can transfer the structures of the guidance image to the filtering output, enabling new filtering applications like dehazing and guided feathering. Moreover, the guided filter naturally has a fast and nonapproximate linear time algorithm, regardless of the kernel size and the intensity range. Currently, it is one of the fastest edge-preserving filters. Experiments show that the guided filter is both effective and efficient in a great variety of computer vision and computer graphics applications, including edge-aware smoothing, detail enhancement, HDR compression, image matting/feathering, dehazing, joint upsampling, etc.

/pdf/guided-image-filtering-5atmpsksoa.pdf

Guided Image Filtering

Rural PC kiosks have become prominent recently as a way to impact socio-economic development through computing technology. Despite the significant backing these projects receive from governments and other large organizations, there are very few rigorous studies which measure their actual impact and utility. We have developed and deployed a software PC logging tool that allows us to gain exact quantitative insight into the usage statistics of kiosks on which the tool is installed. In field trials in Maharashtra and Uttar Pradesh, India, we collected over 120 days of software tool logging data from 13 separate kiosks, while we also questioned the kiosk operators during the same period. We show some evidence that the software based logging tool complements the existing survey based and other ethnographic approaches for data collection. We also show that the tool does a better job in gathering certain usage statistics as compared to questioning the kiosk operator.

Kiosk Usage Measurement using a Software Logging Tool

We examine the broad challenges facing a computer-based system to help match low-income domestic workers from an urban slum with potential middle-class employers in Bangalore, India. Due to the near impossibility of implementing such a system in one shot, we first implemented a paper-based system that provides the intended functionality but without a computer. This system proved a significant challenge in itself, and among the lessons learned are the crucial role of human intermediaries (necessary even in the final computer-based system), the importance of building skills among the domestic workers, the need for a strong value proposition for both employers and employees well above existing systems, and the requirement of technological literacy. We then show that these lessons are applicable to other scenarios where computing technology is applied to developingworld challenges, by analyzing corresponding issues in related work. Our broad conclusion is that computer-based systems to solve developing-world problems often require significant work above and beyond an implementation of the technology, with trustworthy human intermediaries playing a critical role.

/pdf/challenges-of-computerized-job-search-in-the-developing-2rqpl17yq0.pdf

Challenges of Computerized Job-Search in the Developing World

In resource-constrained classrooms in the developing world, it is common for several students to share each computer. Unfortunately, dominance behavior often naturally emerges in these situations, when one child monopolizes the mouse and keyboard. One way to mitigate this phenomenon is by providing each child with a mouse and a corresponding on-screen cursor so that everyone can interact. Though such multiple-mouse configurations reduce the possibility of total domination by one individual, they do not automatically eliminate dominance behavior completely. We propose the use of a design for small-group learning on shared computers based on enforced turn-taking in a split-screen, multiple-mouse environment. In an evaluation with 104 rural schoolchildren in India, we found that dominance behavior was indeed reduced through these design choices.

/pdf/reducing-dominance-in-multiple-mouse-learning-activities-2kd4ov84e7.pdf

Reducing dominance in multiple-mouse learning activities

We examine the broad challenges facing a computer-based system to help match low-income domestic workers from an urban slum with potential middle-class employers in Bangalore, India. Due to the near impossibility of implementing such a system in one shot, we first implemented a paper-based system that provides the intended functionality but without a computer. This system proved a significant challenge in itself, and among the lessons learned are the crucial role of human intermediaries (necessary even in the final computer-based system), the importance of building skills among the domestic workers, the need for a strong value proposition for both employers and employees well above existing systems, and the requirement of technological literacy. We then show that these lessons are applicable to other scenarios where computing technology is applied to developing-world challenges, by analyzing corresponding issues in related work. \ \ Our broad conclusion is that computer-based systems to solve developing-world problems often require significant work above and beyond an implementation of the technology, with trustworthy human intermediaries playing a critical role. \

/pdf/challenges-in-computerized-job-search-for-the-developing-3sk5vgafpa.pdf

Challenges in computerized job search for the developing world

In recent years there has been a growing body of work from the CHI communities that looks at designing for inclusivity and for the unique and specific constraints of diverse populations. This has included but is not limited to, work on designing within patriarchal contexts, designing around issues of gender and sexual orientation and designing around literacy. In tandem, local HCI initiatives such as ArabHCI [3] have emerged to address the misrepresentation of these populations in HCI research, highlighting the fact that Western originated design methods would require delicate adaptations to suit non-Western cultural contexts. With the same approach towards inclusivity and co-existence the aim of this workshop is to bring together HCI researchers and practitioners who engage in studies and interventions within Muslim majority communities around the world. The goal is to understand the Muslim identity and perceptions around it, the unique constraints and limitations within Muslim communities and to identify core issues and concerns within these populations. We will explore the following themes: refugees and islamophobia; Muslim feminism and Digital financial services.

Kentaro Toyama

Papers

Kiosk Usage Measurement using a Software Logging Tool

Challenges of Computerized Job-Search in the Developing World

Reducing dominance in multiple-mouse learning activities

Challenges in computerized job search for the developing world

IslamicHCI: Designing with and within Muslim Populations