Total: 45
The absence of comprehensive situational awareness information poses a significant challenge for humanitarian organizations during their response efforts. We present Flood Insights, an end-to-end system that ingests data from multiple non-traditional data sources such as remote sensing, social sensing, and geospatial data. We employ state-of-the-art natural language processing and computer vision models to identify flood exposure, ground-level damage and flood reports, and most importantly, urgent needs of affected people. We deploy and test the system during a recent real-world catastrophe, the 2022 Pakistan floods, to surface critical situational and damage information at the district level. We validated the system's effectiveness through geographic regression analysis using official ground-truth data, showcasing its strong performance and explanatory power. Moreover, the system was commended by the United Nations Development Programme stationed in Pakistan, as well as local authorities, for pinpointing hard-hit districts and enhancing disaster response.
In the realm of business automation, digital assistants/chatbots are emerging as the primary method for making automation software accessible to users in various business sectors. Access to automation primarily occurs through APIs and RPAs. To effectively convert APIs and RPAs into chatbots on a larger scale, it is crucial to establish an automated process for generating data and training models that can recognize user intentions, identify questions for conversational slot filling, and provide recommendations for subsequent actions. In this paper, we present a technique for enhancing and generating natural language conversational artifacts from API specifications using large language models (LLMs). The goal is to utilize LLMs in the "build" phase to assist humans in creating skills for digital assistants. As a result, the system doesn't need to rely on LLMs during conversations with business users, leading to efficient deployment. Experimental results highlight the effectiveness of our proposed approach. Our system is deployed in the IBM Watson Orchestrate product for general availability.
This article focuses on the development and evaluation of Small-sized Czech sentence embedding models. Small models are important components for real-time industry applications in resource-constrained environments. Given the limited availability of labeled Czech data, alternative approaches, including pre-training, knowledge distillation, and unsupervised contrastive fine-tuning, are investigated. Comprehensive intrinsic and extrinsic analyses are conducted, showcasing the competitive performance of our models compared to significantly larger counterparts, with approximately 8 times smaller size and 5 times faster speed than conventional Base-sized models. To promote cooperation and reproducibility, both the models and the evaluation pipeline are made publicly accessible. Ultimately, this article presents practical applications of the developed sentence embedding models in Seznam.cz, the Czech search engine. These models have effectively replaced previous counterparts, enhancing the overall search experience for instance, in organic search, featured snippets, and image search. This transition has yielded improved performance.
More than ever, air transport players (i.e., airline and airport companies) in an intensely competitive climate need to benefit from a carefully optimized management of airport resources to improve the quality of service and control the induced costs. In this paper, we investigate the Airport Check-in Desk Assignment Problem. We propose a Constraint Programming (CP) model for this problem, and present some promising experimental results from data coming from ADP (Aéroport de Paris). Our works are deployed in a preprod environment since 1 year.
One of the most crucial capabilities in the commercial sector is a personalized prediction of a customer's next purchase. We present a novel method of creating a commerce intelligence engine that caters to multiple merchants intended for the UB Platform, managed by e-payment company Harex InfoTech. To cultivate this intelligence, we utilized payment receipt data and created a Natural Language Processing (NLP)-based commerce model using a Transformer to accommodate multinational and merchant trade. Our model, called General Commerce Intelligence (GCI), provides a range of services for merchants, including product recommendations, product brainstorming, product bundling, event promotions, collaborative marketing, target marketing, and demand fore-casting etc. To bolster user privacy and foster sustainable business collaboration, especially among micro-, small-, and medium-sized enterprises (MSMEs), the GCI model was trained through federated learning, especially with glocalization. This study delves into the structure, development, and assessment of GCI, showcasing its transformative capacity to implement User Centric AI and re-shape the global commerce landscape to benefit MSMEs.
In the field of finance, the underwriting process is an essential step in evaluating every loan application. During this stage, the borrowers' creditworthiness and ability to repay the loan are assessed to ultimately decide whether to approve the loan application. One of the core components of underwriting is credit scoring, in which the probability of default is estimated. As such, there has been significant progress in enhancing the predictive accuracy of credit scoring models through the use of machine learning, but there still exists a need to ultimately construct an approval rule that takes into consideration additional criteria beyond the score itself. This construction process is traditionally done manually to ensure that the approval rule remains interpretable to humans. In this paper, we outline an automated system for optimizing a rule-based system for approving loan applications, which has been deployed at Hyundai Capital Services (HCS). The main challenge lay in creating a high-quality rule base that is simultaneously simple enough to be interpretable by risk analysts as well as customers, since the approval decision should be accountable. We addressed this challenge through principled submodular optimization. The deployment of our system has led to a 14% annual growth in the volume of loan services at HCS, while maintaining the target bad rate, and has resulted in the approval of customers who might have otherwise been rejected.
Over the past decade, significant advances have been made in the field of image search for e-commerce applications. Traditional image-to-image retrieval models, which focus solely on image details such as texture, tend to overlook useful semantic information contained within the images. As a result, the retrieved products might possess similar image details, but fail to fulfil the user's search goals. Moreover, the use of image-to-image retrieval models for products containing multiple images results in significant online product feature storage overhead and complex mapping implementations. In this paper, we report the design and deployment of the proposed Multi-modal Item Embedding Model (MIEM) to address these limitations. It is capable of utilizing both textual information and multiple images about a product to construct meaningful product features. By leveraging semantic information from images, MIEM effectively supplements the image search process, improving the overall accuracy of retrieval results. MIEM has become an integral part of the Shopee image search platform. Since its deployment in March 2023, it has achieved a remarkable 9.90% increase in terms of clicks per user and a 4.23% boost in terms of orders per user for the image search feature on the Shopee e-commerce platform.
Azure Core workload insights have time-series data with different metric units. Faults or Anomalies are observed in these time-series data owing to faults observed with respect to metric name, resources region, dimensions, and its dimension value associated with the data. For Azure Core, an important task is to highlight faults or anomalies to the user on a dashboard that they can perceive easily. The number of anomalies reported should be highly significant and in a limited number, e.g., 5-20 anomalies reported per hour. The reported anomalies will have significant user perception and high reconstruction error in any time-series forecasting model. Hence, our task is to automatically identify 'high significant anomalies' and their associated information for user perception.
Visual interpretation is extremely important in human geography as the primary technique for geographers to use photograph data in identifying, classifying, and quantifying geographic and topological objects or regions. However, it is also time-consuming and requires overwhelming manual effort from professional geographers. This paper describes our interdisciplinary team's efforts in integrating computer vision models with geographers' visual image interpretation process to reduce their workload in interpreting images. Focusing on the dune segmentation task, we proposed an approach featuring a deep dune segmentation model to identify dunes and label their ranges in an automated way. By developing a tool to connect our model with ArcGIS, one of the most popular workbenches for visual interpretation, geographers can further refine the automatically-generated dune segmentation on images without learning any CV or deep learning techniques. Our approach thus realized a non-invasive change to geographers' visual interpretation routines, reducing their manual efforts while incurring minimal interruptions to their work routines and tools they are familiar with. Deployment with a leading Chinese geography research institution demonstrated the potential of our approach in supporting geographers in researching and solving drylands desertification.
Automating the processing of health insurance claims to achieve "Straight-Through Processing" is one of the holy grails that all insurance companies aim to achieve. One of the major impediments to this automation is the difficulty in establishing the relationship between the underwriting exclusions that a policy has and the incoming claim's diagnosis information. Typically, policy underwriting exclusions are captured in free-text such as "Respiratory illnesses are excluded due to a pre-existing asthma condition". A medical claim coming from a hospital would have the diagnosis represented using the International Classification of Disease (ICD) codes from the World Health Organization. The complex and labour-intensive task of establishing the relationship between free-text underwriting exclusions in health insurance policies and medical diagnosis codes from health insurance claims is critical towards determining if a claim should be rejected due to underwriting exclusions. In this work, we present a novel framework that leverages both explicit and implicit domain knowledge present in medical ontologies and pre-trained language models respectively, to effectively establish the relationship between free-text describing medical conditions present in underwriting exclusions and the ICD-10CM diagnosis codes in health insurance claims. Termed KAMEL (Knowledge Aware Medical Entity Linkage), our proposed framework addresses the limitations faced by prior approaches when evaluated on real-world health insurance claims data. Our proposed framework have been deployed in several multi-national health insurance providers to automate their health insurance claims.
This paper introduces the design, development, and deployment of a Virtual Driving Instructor (VDI) for enhanced driver education. The VDI provides personalized, real-time feedback to students in a driving simulator, addressing some of the limitations of traditional driver instruction. Employing a hybrid AI system, the VDI combines rule-based agents, learning-based agents, knowledge graphs, and Bayesian networks to assess and monitor student performance in a comprehensive manner. Implemented in multiple simulators at a driving school in Norway, the system aims to leverage AI and driving simulation to improve both the learning experience and the efficiency of instruction. Initial feedback from students has been largely positive, highlighting the effectiveness of this integration while also pointing to areas for further improvement. This work marks a significant stride in infusing technology into driver education, offering a scalable and efficient approach to instruction.
Social insurance benefits qualification assessment is an important task to ensure that retirees enjoy their benefits according to the regulations. It also plays a key role in curbing social security frauds. In this paper, we report the deployment of the Intelligent Benefit Certification and Analysis (IBCA) platform, an AI-empowered platform for verifying the status of retirees to ensure proper dispursement of funds in Shandong province, China. Based on an improved Gated Recurrent Unit (GRU) neural network, IBCA aggregates missing value interpolation, temporal information, and global and local feature extraction to perform accurate retiree survival rate prediction. Based on the predicted results, a reliability assessment mechanism based on Variational Auto-Encoder (VAE) and Monte-Carlo Dropout (MC Dropout) is executed to perform reliability assessment. Deployed since November 2019, the IBCA platform has been adopted by 12 cities across the Shandong province, handling over 50 terabytes of data. It has empowered human resources and social services, civil affairs, and health care institutions to collaboratively provide high-quality public services. Under the IBCA platform, the efficiency of resources utilization as well as the accuracy of benefit qualification assessment have been significantly improved. It has helped Dareway Software Co. Ltd earn over RMB 50 million of revenue.
Gas usage estimation plays a critical role in various aspects of the power generation and delivery business, including budgeting, resource planning, and environmental preservation. Federated Learning (FL) has demonstrated its potential in enhancing the accuracy and reliability of gas usage estimation by enabling distributedly owned data to be leveraged, while ensuring privacy and confidentiality. However, to effectively motivate stakeholders to contribute their high-quality local data and computational resources for this purpose, incentive mechanism design is key. In this paper, we report our experience designing and deploying the Hierarchical FL Incentive mechanism for Gas usage estimation (HiFi-Gas) system. It is designed to cater to the unique structure of gas companies and their affiliated heating stations. HiFi-Gas provides effective incentivization in a hierarchical federated learning framework that consists of a horizontal federated learning (HFL) component for effective collaboration among gas companies and multiple vertical federated learning (VFL) components for the gas company and its affiliated heating stations. To motivate active participation and ensure fairness among gas companies and heating stations, we incorporate a multi-dimensional contribution-aware reward distribution function that considers both data quality and model contributions. Since its deployment in the ENN Group in December 2022, HiFi-Gas has successfully provided incentives for gas companies and heating stations to actively participate in FL training, resulting in more than 12% higher average gas usage estimation accuracy and substantial gas procurement cost savings. This implementation marks the first successful deployment of a hierarchical FL incentive approach in the energy industry.
Building teams and promoting collaboration are two very common business activities. An example of these are seen in the TeamingForFunding problem, where research institutions and researchers are interested to identify collaborative opportunities when applying to funding agencies in response to latter's calls for proposals. We describe a novel deployed system to recommend teams using a variety of AI methods, such that (1) each team achieves the highest possible skill coverage that is demanded by the opportunity, and (2) the workload of distributing the opportunities is balanced amongst the candidate members. We address these questions by extracting skills latent in open data of proposal calls (demand) and researcher profiles (supply), normalizing them using taxonomies, and creating efficient algorithms that match demand to supply. We create teams to maximize goodness along a novel metric balancing short- and long-term objectives. We validate the success of our algorithms (1) quantitatively, by evaluating the recommended teams using a goodness score and find that more informed methods lead to recommendations of smaller number of teams but higher goodness, and (2) qualitatively, by conducting a large-scale user study at a college-wide level, and demonstrate that users overall found the tool very useful and relevant. Lastly, we evaluate our system in two diverse settings in US and India (of researchers and proposal calls) to establish generality of our approach, and deploy it at a major US university for routine use.
Traditional business processes such as loan processing, order processing, or procurement have a series of steps that are pre-defined at design and executed by enterprise systems. Recent advancements in new-age businesses, however, focus on having adaptive and ad-hoc processes by stitching together a set of functions or steps enabled through autonomous agents. Further, to enable business users to execute a flexible set of steps, there have been works on providing a conversational interface to interact and execute automation. Often, it is necessary to guide the user through the set of possible steps in the process (or workflow). Existing work on recommending the next agent to run relies on historical data. However, with changing workflows and new automation constantly getting added, it is important to provide recommendations without historical data. Additionally, hand-crafted recommendation rules do not scale. The adaptive workflow being a combination of structured and unstructured information, makes it harder to mine. Hence, in this work, we leverage Large Language Models (LLMs) to combine process knowledge with the meta-data of agents to discover NBAs specifically at cold-start. We propose a multi-stage approach that uses existing process knowledge and agent meta-data information to prompt LLM and recommend meaningful next best agent (NBA) based on user utterances.
Currently, students acquire driving skills by practicing in actual traffic conditions and through direct interactions with an instructor. While one-on-one interactions could be tailored to a student’s learning style and skill level, making them effective for learning, one-on-one interactions are also inefficient, potentially costly, and not standardized with limitations on which traffic situation can be safely taught. For these exact reasons Way AS has developed and commercially deployed a virtual driving instructor that educates students in high-fidelity simulators. In this paper, we present a module, the Lesson generator, that extends the virtual driving instructor to generate personalized lessons for individual students with the goal to practice in a focused and deliberately fashion the skills that need practice for the students to become proficient drivers. A case study is presented, and the path to deployment is discussed.
Advanced Air Mobility (AAM) introduces a new, efficient mode of transportation with the use of vehicle autonomy and electrified aircraft to provide increasingly autonomous transportation between previously underserved markets. Safe and efficient navigation of low altitude aircraft through highly dense environments requires the integration of a multitude of complex observations, such as surveillance, knowledge of vehicle dynamics, and weather. The processing and reasoning on these observations pose challenges due to the various sources of uncertainty in the information while ensuring cooperation with a variable number of aircraft in the airspace. These challenges coupled with the requirement to make safety-critical decisions in real-time rule out the use of conventional separation assurance techniques. We present a decentralized reinforcement learning framework to provide autonomous self-separation capabilities within AAM corridors with the use of speed and vertical maneuvers. The problem is formulated as a Markov Decision Process and solved by developing a novel extension to the sample-efficient, off-policy soft actor-critic (SAC) algorithm. We introduce the use of attention networks for variable-length observation processing and a distributed computing architecture to achieve high training sample throughput as compared to existing approaches. A comprehensive numerical study shows that the proposed framework can ensure safe and efficient separation of aircraft in high density, dynamic environments with various sources of uncertainty.
In neural memory decoding, a concept being mentally recalled is identified using brain data. Recently, the feasibility of neural memory decoding with EEG data has been demonstrated. Here we propose a new application – neural information retrieval – that uses neural memory decoding to allow a document to be retrieved merely by thinking about it. In this paper we describe neural memory decoding, define the application of neural information retrieval, present experimental results related to the practicality of the application, and discuss issues of deployment and data privacy.
Chronological and Hierarchical Reasoning Over Naturally Occurring Schemas (CHRONOS) is a system that combines language model-based natural language processing with symbolic knowledge representations to analyze and make predictions about newsworthy events. CHRONOS consists of an event-centric information extraction pipeline and a complex event schema instantiation and prediction system. Resulting predictions are detailed with arguments, event types from Wikidata, schema-based justifications, and source document provenance. We evaluate our system by its ability to capture the structure of unseen events described in news articles and make plausible predictions as judged by human annotators.
Electronic theses and dissertations (ETDs) have been proposed, advocated, and generated for more than 25 years. Although ETDs are hosted by commercial or institutional digital library repositories, they are still an understudied type of scholarly big data, partially because they are usually longer than conference and journal papers. Segmenting ETDs will allow researchers to study sectional content. Readers can navigate to particular pages of interest, to discover and explore the content buried in these long documents. Most existing frameworks on document page classification are designed for classifying general documents, and perform poorly on ETDs. In this paper, we propose ETDPC. Its backbone is a two-stream multimodal model with a cross-attention network to classify ETD pages into 13 categories. To overcome the challenge of imbalanced labeled samples, we augmented data for minority categories and employed a hierarchical classifier. ETDPC outperforms the state-of-the-art models in all categories, achieving an F1 of 0.84 -- 0.96 for 9 out of 13 categories. We also demonstrated its data efficiency. The code and data can be found on GitHub (https://github.com/lamps-lab/ETDMiner/tree/master/etd_segmentation).
Fire Departments conduct inspections to prevent fires but it is unclear how to best allocate their limited inspection resources across the properties in a city. Currently, they use their intuition and experience to decide on which properties to inspect and lack a data-driven approach that could lead to a more principled use of inspection resources. The main contribution of this paper is to investigate such an approach, based on machine learning for predicting a fire risk score for properties in a city based on historical fire-incident data. These scores can then be used to help prioritize inspection resources toward higher-risk properties. We present a case study using data from a South Dakota fire department which contains information about properties in a city along with records of fire in- incidents. We use this data consisting of more than 72,000 properties to train a machine learning model to predict fire risk and evaluate its ability to rank the fire risk of properties in the city. We conduct and analyze experiments with variations of XG-Boost, which is an algorithm well-suited to the challenges in application, including missing data and a highly-skewed class distribution. Our evaluation of the model-generated rankings, based on ranking metrics, shows that the model significantly outperforms random rankings and other natural baselines. We also analyze the feature importance computed for the models, which provides further insight into the model behavior. This model has been integrated into an interface for displaying the rankings across a city and is ready for beta testing.
Long-term and high-dose prescription opioid use places individuals at risk for opioid misuse, opioid use disorder (OUD), and overdose. Existing methods for monitoring opioid use and detecting misuse rely on self-reports, which are prone to reporting bias, and toxicology testing, which may be infeasible in outpatient settings. Although wearable technologies for monitoring day-to-day health metrics have gained significant traction in recent years due to their ease of use, flexibility, and advancements in sensor technology, their application within the opioid use space remains underexplored. In the current work, we demonstrate that oral opioid administrations can be detected using physiological signals collected from a wrist sensor. More importantly, we show that models informed by opioid pharmacokinetics increase reliability in predicting the timing of opioid administrations. Forty-two individuals who were prescribed opioids as a part of their medical treatment in-hospital and after discharge were enrolled. Participants wore a wrist sensor throughout the study, while opioid administrations were tracked using electronic medical records and self-reports. We collected 1,983 hours of sensor data containing 187 opioid administrations from the inpatient setting and 927 hours of sensor data containing 40 opioid administrations from the outpatient setting. We demonstrate that a self-supervised pre-trained model, capable of learning the canonical time series of plasma concentration of the drug derived from opioid pharmacokinetics, can reliably detect opioid administration in both settings. Our work suggests the potential of pharmacokinetic-informed, data-driven models to objectively detect opioid use in daily life.
AI's widespread integration has led to neural networks (NN) deployment on edge and similar limited-resource platforms for safety-critical scenarios. Yet, NN's fragility raises concerns about reliable inference. Moreover, constrained platforms demand compact networks. This study introduces VeriCompress, a tool that automates the search and training of compressed models with robustness guarantees. These models are well-suited for safety-critical applications and adhere to predefined architecture and size limitations, making them deployable on resource-restricted platforms. The method trains models 2-3 times faster than the state-of-the-art approaches, surpassing them by average accuracy and robustness gains of 15.1 and 9.8 percentage points, respectively. When deployed on a resource-restricted generic platform, these models require 5-8 times less memory and 2-4 times less inference time than models used in verified robustness literature. Our comprehensive evaluation across various model architectures and datasets, including MNIST, CIFAR, SVHN, and a relevant pedestrian detection dataset, showcases VeriCompress's capacity to identify compressed verified robust models with reduced computation overhead compared to current standards. This underscores its potential as a valuable tool for end users, such as developers of safety-critical applications on edge or Internet of Things platforms, empowering them to create suitable models for safety-critical, resource-constrained platforms in their respective domains.
Digital mental health (DMH) interventions, such as text-message-based lessons and activities, offer immense potential for accessible mental health support. While these interventions can be effective, real-world experimental testing can further enhance their design and impact. Adaptive experimentation, utilizing algorithms like Thompson Sampling for (contextual) multi-armed bandit (MAB) problems, can lead to continuous improvement and personalization. However, it remains unclear when these algorithms can simultaneously increase user experience rewards and facilitate appropriate data collection for social-behavioral scientists to analyze with sufficient statistical confidence. Although a growing body of research addresses the practical and statistical aspects of MAB and other adaptive algorithms, further exploration is needed to assess their impact across diverse real-world contexts. This paper presents a software system developed over two years that allows text-messaging intervention components to be adapted using bandit and other algorithms while collecting data for side-by-side comparison with traditional uniform random non-adaptive experiments. We evaluate the system by deploying a text-message-based DMH intervention to 1100 users, recruited through a large mental health non-profit organization, and share the path forward for deploying this system at scale. This system not only enables applications in mental health but could also serve as a model testbed for adaptive experimentation algorithms in other domains.
Harnessing the wide-spread availability of cell phones, many nonprofits have launched mobile health (mHealth) programs to deliver information via voice or text to beneficiaries in underserved communities, with maternal and infant health being a key area of such mHealth programs. Unfortunately, dwindling listenership is a major challenge, requiring targeted interventions using limited resources. This paper focuses on Kilkari, the world's largest mHealth program for maternal and child care -- with over 3 million active subscribers at a time -- launched by India's Ministry of Health and Family Welfare (MoHFW) and run by the non-profit ARMMAN. We present a system called CHAHAK that aims to reduce automated dropouts as well as boost engagement with the program through the strategic allocation of interventions to beneficiaries. Past work in a similar domain has focused on a much smaller scale mHealth program and used markovian restless multiarmed bandits to optimize a single limited intervention resource. However this paper demonstrates the challenges in adopting a markovian approach in Kilkari; therefore CHAHAK instead relies on non-markovian time-series restless bandits, and optimizes a layered set of multiple interventions to improve listenership. We use real Kilkari data from the Odisha state in India to show CHAHAK's effectiveness in harnessing multiple interventions to boost listenership, benefiting marginalized communities. When deployed CHAHAK will assist the largest maternal mHealth program to date.