Search

The top priority of a Housing and Homelessness System of Care (HHSC) is to connect people experiencing homelessness to supportive housing. An HHSC typically consists of many agencies serving the same population. Information technology platforms differ in type and quality between agencies, so their data are usually isolated from one agency to another. Larger agencies may have sufficient data to train and test artificial intelligence (AI) tools but smaller agencies typically do not. To address this gap, we introduce a Federated Learning (FL) approach enabling all agencies to train a predictive model collaboratively without sharing their sensitive data. We demonstrate how FL can be used within an HHSC to provide all agencies equitable access to quality AI and further assist human decision-makers in the allocation of resources within HHSC. This is achieved while preserving the privacy of the people within the data by not sharing identifying information between agencies without their consent. Our experimental results using real-world HHSC data from Calgary, Alberta, demonstrate that our FL approach offers comparable performance with the idealized scenario of training the predictive model with data fully shared and linked between agencies., Comment: Accepted at the 2024 AAAI/ACM Conference on AI, Ethics, and Society (AIES)

Machine learning models benefit when allowed to learn from temporal trends in time-stamped administrative data. These trends can be represented by dividing a model's observation window into time segments or bins. Model training time and performance can be improved by representing each feature with a different time resolution. However, this causes the time bin size hyperparameter search space to grow exponentially with the number of features. The contribution of this paper is to propose a computationally efficient time series analysis to investigate binning (TAIB) technique that determines which subset of data features benefit the most from time bin size hyperparameter tuning. This technique is demonstrated using hospital and housing/homelessness administrative data sets. The results show that TAIB leads to models that are not only more efficient to train but can perform better than models that default to representing all features with the same time bin size.

This paper investigates how COVID-19 disrupted emergency housing shelter access patterns in Calgary, Canada and what aspects of these changes persist to the present day. This analysis will utilize aggregated shelter access data for over 40,000 individuals from seven major urban shelters dating from 2018 to the present. A graph theoretic approach will be used to examine the journeys of individuals between shelters before, during and after the COVID-19 lockdown period. This approach treats shelters as nodes in a graph and a person's transition between shelter as an arrow or edge between nodes. This perspective is used to create both timeline and network diagrams that visualize shelter use and the flow of people between shelters. Statistical results are also presented that illustrate the differences between the cohorts of people who only used shelter pre/post-lockdown, people who stayed in shelter during lockdown and people who used shelter for the first time during lockdown. The results demonstrate not only how a complex system of care responded to the pandemic but also the characteristics of the people most likely to continue to rely on that system during an emergency.

The Simplified Access Metric (SAM) is a new approach for characterizing emergency shelter access patterns as a measure of shelter client vulnerability. The goal of SAM is to provide shelter operators with an intuitive way to understand access patterns that can be implemented by non-technical staff using spreadsheet operations. Client data from a large North American shelter will be used to demonstrate that SAM produces similar results to traditional transitional, episodic and chronic client cluster analysis. Since SAM requires less data than cluster analysis, it is also able to generate a real time picture of how shelter access patterns are affected by external factors. Timelines generated from nine years of shelter client data using SAM demonstrate the impact of Housing First programming and the COVID-19 lockdown on how people access shelter. Finally, SAM allows shelter staff to move beyond assigning transitional, episodic and chronic labels and instead use the "soft" output of SAM directly as a measure of vulnerability.

This paper uses rule search techniques for the early identification of emergency homeless shelter clients who are at risk of becoming long term or chronic shelter users. Using a data set from a major North American shelter containing 12 years of service interactions with over 40,000 individuals, the optimized pruning for unordered search (OPUS) algorithm is used to develop rules that are both intuitive and effective. The rules are evaluated within a framework compatible with the real-time delivery of a housing program meant to transition high risk clients to supportive housing. Results demonstrate that the median time to identification of clients at risk of chronic shelter use drops from 297 days to 162 days when the methods in this paper are applied., Comment: Ideas incorporated into other publications

This paper investigates how to best compare algorithms for predicting chronic homelessness for the purpose of identifying good candidates for housing programs. Predictive methods can rapidly refer potentially chronic shelter users to housing but also sometimes incorrectly identify individuals who will not become chronic (false positives). We use shelter access histories to demonstrate that these false positives are often still good candidates for housing. Using this approach, we compare a simple threshold method for predicting chronic homelessness to the more complex logistic regression and neural network algorithms. While traditional binary classification performance metrics show that the machine learning algorithms perform better than the threshold technique, an examination of the shelter access histories of the cohorts identified by the three algorithms show that they select groups with very similar characteristics. This has important implications for resource constrained not-for-profit organizations since the threshold technique can be implemented using much simpler information technology infrastructure than the machine learning algorithms.

This paper presents the results of the first multi- antenna propagation measurement campaign to be conducted at an operating petroleum refining facility. The measurement equipment transmits pseudo-random noise test signals from two antennas at a 2.47 GHz carrier with a signal bandwidth of approximately 25 MHz. The measurement data is analyzed to extract path loss exponent, shadowing distribution, fading distribution, coherence bandwidth and antenna correlation. The results reveal an environment where large scale attenuation is relatively mild, fading is severe and good performance is expected from both antenna and frequency diversity.

Unmanned aerial vehicles, or drones, have the potential to significantly reduce the cost and time of making last-mile deliveries and responding to emergencies. Despite this potential, little work has gone into developing vehicle routing problems (VRPs) specifically for drone delivery scenarios. Existing VRPs are insufficient for planning drone deliveries: either multiple trips to the depot are not permitted, leading to solutions with excess drones, or the effect of battery and payload weight on energy consumption is not considered, leading to costly or infeasible routes. We propose two multi-trip VRPs for drone delivery that address both issues. One minimizes costs subject to a delivery time limit, while the other minimizes the overall delivery time subject to a budget constraint. We mathematically derive and experimentally validate an energy consumption model for multirotor drones, demonstrating that energy consumption varies approximately linearly with payload and battery weight. We use this approximation to derive mixed integer linear programs for our VRPs. We propose a cost function that considers our energy consumption model and drone reuse, and apply it in a simulated annealing (SA) heuristic for finding sub-optimal solutions to practical scenarios. To assist drone delivery practitioners with balancing cost and delivery time, the SA heuristic is used to show that the minimum cost has an inverse exponential relationship with the delivery time limit, and the minimum overall delivery time has an inverse exponential relationship with the budget. Numerical results confirm the importance of reusing drones and optimizing battery size in drone delivery VRPs., Comment: 16 pages, 10 figures, 6 tables, 6 algorithms. Accepted by IEEE Transactions on Systems, Man, and Cybernetics: Systems

This radio channel measurement campaign characterizes the propagation conditions experienced in a dense urban environment over fixed backhaul links between wireless devices that are mounted on utility or traffic light poles. The measurements characterize the 2x1 multiple input single output channel in the 2.45 GHz band for both spatially separated omni antennas and cross polarized directional antennas. Results presented include both small and large scale channel statistics, antenna correlation coefficient values and the off-broadside rejection achieved with the directional antennas.

Minimizing the cost of deploying and operating a Wireless Sensor Network (WSN) involves deciding how to partition a budget between competing expenses such as node hardware, energy, and labor. Most commercial network operators account for interest rates in their budgeting exercises, providing a financial incentive to defer some costs until a later time. In this paper, we propose a net present cost (NPC) model for WSN capital and operating expenses that accounts for interest rates. Our model optimizes the number, size, and spacing between expenditures in order to minimize the NPC required for the network to achieve a desired operational lifetime. In general this optimization problem is non-convex, but if the spacing between expenditures is linearly proportional to the size of the expenditures, and the number of maintenance cycles is known in advance, the problem becomes convex and can be solved to global optimality. If non-deferrable recurring costs are low, then evenly spacing the expenditures can provide near-optimal results. With the provided models and methods, network operators can now derive a payment schedule to minimize NPC while accounting for various operational parameters. The numerical examples show substantial cost benefits under practical assumptions., Comment: 14 pages, 9 figures, 2 algorithms. Accepted by IEEE Transactions on Network and Service Management