We have adapted an expert system of medical diagnosis for use by low to mid-level health workers in remote and rural locations. Key to the successful deployment of this expert system is the rapid adaptation of the database and clinical interface for use in specific regions and by varying user skill.

Development is fundamentally about understanding people, their motivations, behaviors and reactions. We have two primary means of understanding people — observing what they do, and what they say. As the AI4D community has noted, people's increased use of mobile devices has led to a wealth of new data relevant to these topics. We are on the cusp of developing incredibly powerful tools that can help us understand how human beings migrate, transact and acquire wealth. This could have a large impact on how we determine policies and allocate resources. Most of this analysis has tended to focus on what people do — where they go, who they talk to, what they buy, etc. I argue that what people say is an equally rich source of development data, often containing information that cannot be obtained from people's actions, such as their needs, hopes and aspirations. Voice is the most natural form of communication, especially for people who speak a non-mainstream language, and/or have marginal literacy skills.  These are often exactly those populations who are most disenfranchised, and therefore most need their voices to be heard.

Although the various VA methods do Challenges for Global Health (Varmus et al. 2003) have not predict causes of deaths with vague symptoms as helped to reinforce the need for evidence-based global accurately as laboratory diagnostics can, verbal autopsy health priorities. Accurate health metrics and improved can predict causes of death with distinct symptoms with statistics can provide crucial decision-making inputs that some degree of accuracy (WHO 2007). For some areas of enable more efficient allocation of scarce financial the world verbal autopsies provide the only information resources towards the most pressing health needs (Murray about mortality currently available. Provided they can and Frenk 2008). Mortality statistics are a widely-used match or improve upon the accuracy of physician-coded resource for setting spending priorities, but out of 192 VA and expert algorithms, data-driven methods should be countries worldwide, only 23 have high-quality death used because they require less time from doctors or registration data, and 75 have no cause-specific mortality medical experts, and may provide valid reproducible fraction information at all (King and Lu 2008).

Local information access (LIA) programs tap into existing public health data flows, and present data in simple and useful ways to ground staff. LIAs hold great potential for improving rural health systems in developing regions; benefits include more evidence-based decision making and optimizations at a local scale, as well as improved service delivery and data quality. Our fledgling LIA program in rural Uganda currently provides clinicians with a small set of static data visualizations for discussion. To increase the program’s effectiveness, we want to automatically identify relevant data visualizations. We propose an adaptive tool that learns from local clinicians’ decision-making processes to predict and generate visualizations that show actionable anomalies.

Community health worker programs provide healthcare to those living outside the financial and physical reach of the standard health infrastructure. These programs are particularly prevalent in low resource regions. Frequently such programs involve community health workers making household visits across a significant geographical area. We suggest that this problem can be posed as a formal routing and scheduling problem, and to use techniques developed from solving the travelling salesman problem with time windows. In addition, household visits can generate a series of future follow up visits, a feature not often handled in the combinatorial scheduling and routing literature. We present the basic problem and outline potential research directions.

But whereas in the general Rwandan populace males tend Despite the increasing ubiquity of mobile phones in the developing to be much better educated (76.3% of males are literate, but world, remarkably little is known about the structure only 64.7% of females), among mobile phone users it is the and demographics of the mobile phone market. While a women who achieve higher levels of education: the median few qualitative studies have detailed social norms of phone woman completes secondary school, while the median man use in specific communities (Donner 2007; Burrell 2009), does not (t 4.79). Table 1 shows a few statistics on asset and a handful of quantitative researchers have begun to analyze ownership, with associated sampling error.

Data mining and machine learning technologies for business applications have evolved over the past two decades, and are regularly applied in contemporary organizations to everything from manufacturing to online advertising in fields ranging from health care to motor racing. Unfortunately, data mining techniques are not applied as often to problems in the developing world. Despite the fact that some industries, such as banks, airlines, courts, and telecommunications firms, necessitate data storage as part of their business process. We argue that data mining could be used to reduce infrastructure inefficiencies, which is one of the largest problems faced by Africa. We demonstrate that we can potentially reduce the infrastructure inefficiency of the Ethiopian telecommunications industry by ranking customers according to their likelihood of nonpayment using a data mining approach.

This position paper describes how the nascent area of AI for development can learn from the challenges and successes of its parents: artificial intelligence and information and communication technologies for development (ICT4D). AI suffered from overly ambitious beginnings and years of stumbling before finding its footing, and achieving impactful ICT4D has been an equally challenging endeavor. We describe the history and challenges of both AI and ICT4D research, and present three broad suggestions for AI-for-development researchers: (1) that they spend as much time as possible with the kind of site or the organization they are hoping to impact; (2) that they be ambitious but humble in their goals and expectations; and (3) that they put AI in the service of existing, well-intented, competent development organizations.

With the increased availability of rich behavioral data sets, we present a novel combination of tools to analyze to analyze this information.  Using criminal offense records as an example, we employ cross-correlation measures, eigenvalue spectrum analysis, and results from random matrix theory to identify spatiotemporal patterns.  Finally, with multivariate autoregressive models, we demonstrate a possible source of structure within the data.

Traffic monitoring systems usually make assumptions about the movement of vehicles, such as that they drive in dedicated lanes, and that those lanes rarely include non-vehicle clutter. Urban settings within developing countries often present extremely chaotic traffic scenarios which make these assumptions unrealistic. We show how a standard approach to traffic monitoring can be made more robust by using probabilistic inference, and in such a way that we bypass the need for vehicle segmentation. Instead of tracking individual vehicles but treat a lane of traffic as a fluid and estimate the rate of flow. Our modelling of uncertainty allows us to accurately monitor traffic flow even in the presence of substantial clutter.