17 items found

Blog Posts (4)

  • Can AI Learn Faster from Children?

    Modeling human behavior remains an immensely challenging task. However, such models are necessary. For example, to build completely driverless cars, the autonomous "AI driver" must be able to safely engage the human driver when necessary. The necessary AI-human engagement requires the AI to have a model of the human driver. Although a driving behavior is actually rather limited in comparison to the full scope of human behavior, it is still challenging to capture in a model, and is the subject of active research. Our projects and research indicate that we are developing a Human Digital Twin (HDT), which, of course, requires a model of the human it supports. However, we will begin with capturing simpler versions of human behavior: children's behavior! For example, in the case of the Patient-Human Digital Twin, the beginning is with Neonatology, where the measured parameters are limited in contrast to an adult patient, the medical history is considerably shorter, and the intervention possibilities are somewhat limited. As a result, we anticipate that the models will be simpler and more reliable.  The same concept underpins the TwinUp app, which predicts child abuse risk. Because children's habits, routines, and movement profiles are limited, the model necessary for the app to predict abuse is also limited, and thus the predictability is more reliable. With more data, use cases, and models, the goal is to gradually expand the Human Digital Twin initital models to capture more complex behaviors and eventually maturing them to capture more aspects of a person's life in the same way that children gradually develop their concepts and skills over many years.

  • Child Protection through Prediction

    One of the risks a child might face is abuse, which can happen in many different ways and in all different kinds of social groups, cultures, and countries. Every parent wants their kids to be safe and accordingly there are many apps that provide parents with various possibilities to connect to their children, manage their digital interactions or monitor their locations, or get alerts if their kids are out of specific zones. On the other hand, risk management and mitigation are heavily reliant on assigning a level of probability—a prediction—to the incidents that an organization wants to limit or avoid, such as accidents, losses, or project failures. In comparison, to provide successful child protection, a parent must gain insights into the risks they believe are relevant to their child and an early assessment of the child's level of risk exposure to mitigate risks before they occur. This is the primary goal of our TwinUp app: to learn a child's social interactions and routines, apply a community-specific abuse risk profile to predict a risk score to various child activities. Based on the score, the TwinUp app then can inform the child, parents, or caregivers of potential high-risk circumstances to mitigate the situation. In addition, the TwinUp app provides a digital network that connects a child's device to what we call "persons of trust" at the many places a child frequents to speed up mitigation and assistance when needed. It should be said that the TwinUp app doesn't need any data that other child protection apps don't already use.

  • The Challenge with Smart Apps

    Business intelligence (BI) provides insights on four levels: descriptive (what happened), diagnostic (why did happen), predictive (what will happen) and prescriptive (how to make it happen). The most crucial point to remember is that each level builds on the one before it. For example, a prescriptive task to determine the pricing for a service or product which would improve sales by 15%, is contingent on accurate sales volume predictions, which are based on knowledge (diagnostic) of what factors influence sales and consumer purchasing decisions, which is contingent on access to previous sales numbers. There is a challenge, however, with many intelligent mobile apps that prescribe actions to their users to reach some goals (for example, fitness, health or financial goals): they struggle with the second level, the diagnostic, and accordingly, their recommendations are not as effective as might be expected by the users. To "prescribe" training or diet regimes, a fitness or health app needs reliable diagnostic about why did a user achieve or miss their target. One way of providing this diagnostic is to rely on assumptions learned across multiple users which are then refined using user input via questionnaires. The problem with that technique is that it is tedious, and the users may be unaware of factors influencing their behavior and choices. Another technique for providing a more reliable diagnostic of users is to collect a broader range of user interactions across different aspects of their lives and rely on these interactions to learn user-specific patterns and preferences. Such user-specific patterns would reveal insights into the user's lifestyle and commitments, which might then be used by an app to enhance Its diagnostic and provide more effective recommendations. This is what the Information Digital Twin (IDT) is attempting to accomplish: observe user digital interactions, learn their specific routines, infer and classify their interaction preferences, and provide the user—and other apps, if desired—with a better insights Into the user's lifestyle and thus enable the users to achieving their goals more effectively. Our assumption is that many aspects of our lives are revealed through our digital interactions. Which app (or application) categories we use, how often, for how long, when, where, and in what order we use them—regardless of content—can reveal insights about a person's mood, lifestyle, and preferences, and enable accurate and personalized assumptions about why-type questions.

View All

Pages (13)

  • Information Digital Twin | SEMARX

    The Social AI Platform Digital Transformation with Information Digital Twins How to get there? ... use Information Digital Twins! The Social AI Platform uses a new type of digital twins - the Information Digital Twin (IDT) - to enable public and commercial organizations to automate complex people-based scenarios and decisions. Simultaneously , the Social AI Platform enables people to automate their complex social and professional transactions according to their personal preferences, lifestyle and objectives. ​ The Social AI Platform is not just a solution, rather, It's a technology framework to manage and automate many types of processes involving people, machines, and organizations. ​ The Social AI Platform places the active agent of a scenario - whether human or machine - at the center of all decisions. As a result, process coordination and optimization reflect each agent's unique choices and preferences, which is critical for achieving adaptation and social resilience. Healthcare Digital Twins How patient-specific digital twins, Patient Human Digital Twin (HDT), can reduce the risks of ICU patients by continuously monitoring them predicting potential critical events , and alerting medical personnel. The critical events predictions provide the medical staff with sufficient time to further examine the unfolding situation and mitigate potential risks, thus improving treatment effectiveness and reducing patients' risks. ​ The Patient HDT can be provided as a service to patients to keep monitoring their risks even after they leave the hospital. Healthcare Use Case Wellbeing Digital Twins How a personal digital twins (the TwinUp app) can reduce children's risk of abuse by monitoring their social interactions, predicting potential abuse events, alerting them to change their behavior, or involving their caregivers to intervene and mitigate an abuse event before it happens, thereby reducing abuse in a community and ensuring children's safety. ​ The TwinUp creates a digital safety network for its users that links them with people they trust so they may get support whenever needed. ​ Because the TwinUp can predict a wide range of events, it can assist individuals in avoiding undesired encounters and ensure their safety. Human Wellbeing Use Case SC Digital Twins How a Shipment Digital Twin (DT) monitors a shipment's progress through the supply chain, predicting shipment-specific delays , and alerting operators with mitigation options to minimize delays and ensuring delivery timeframes and costs. ​ The Shipment DT is a virtual instance that is terminated after the shipment has been completed. However, the predictions and risk assessments from several Shipment DTs are aggregated to improve SC-level predictions for events like delays or costs ​ Shipment DTs may be selectively aggregated to create Container DTs, Vessel DTs, or complete SC DTs. Shipment Digital Twin Use Case Human-Machine Digital Twins How to use a combination of Human and Information Digital Twins to coordinate complex human-machine interactions toward a common goal. Each digital twin keeps track of its user interactions, whether human or machine, predicts deviations from task objectives, and alerts their user or other team members so they can alter their actions accordingly, resulting in better overall team collaboration and goal achievement. ​ Over time, the models of the various digital twins may be combined seamlessly to define more general, role-specific data-based models (e.g., driver, pilot, or operator.) Such models are then used to establish trust between humans and machines and automate their complex interactions. Human-Machine Teaming Use Case Why is the Social AI Platform Different? Based on a Reference Model The platform's defining characteristic is its use of a central model from which all linked digital twins are primed and into which they all update their predictions, so enabling a collective intelligence Universal Use Cases The platform is capable of managing and automating a wide range of complex scenarios , regardless of domain Users Driven The platform learns from its users. Each action or choice made by a user affects the information used by all other users, resulting in significantly faster learning and adaptation to changes The Information Digital Twin (IDT) The Social AI Platform's central component is a universal type of digital twins, the Information Digital Twin (IDT). ​ The IDT enables its user to predict their environment , and-if desired-be predictable by others around them, which is the basis for effective collaboration and automation. ​ The IDT learns its user preferences and automates some of their digital interactions. Thus, the IDT significantly boosts individuals' capacity to connect with society while freeing more of their attention to focus on their personal wellbeing. ​ Depending on the domain or use case, the Information Digital Twin (IDT) can be deployed as a mobile or desktop application that connects people to the platform, in which case it is referred to as a Human Digital Twin (HDT). The IDT can also be deployed as a standalone device equipped with sensors and actuators to integrate robots or other types of agents into the platform ( read more! ). AI SCENARIOS

  • The Human Digital Twin | SEMARX

    The Human Digital Twin (HDT) Digital Life and Human Wellbeing The Human Digital Twin (HDT) is an AI-based mobile application which helps its user to manage, optimize and automate their digital interactions according to their preferences and interests, thus enabling them to manage their lives in a balanced and healthy manner. ​ The AI scenarios we envision show how the HDT can help their users to manage and automate various digital interactions simultaneously and thus enable them achieving their goals in an effective and balanced manner. Automating Digital Interactions and Choices The HDT takes care of many of its users' digital decisions, giving them more time and focus to spend on creative and social activities. ​ The HDT provides the same features of the more general agent, the Information Digital Twin (IDT) , which we use to enable various types of digital twins for industrial and commercial use cases . Ensuring Users Long-Term Interests In its most advanced form, the Human Digital Twin (HDT) provides its users with best-action recommendations (for example, regarding health-related choices) to ensure they preserve their long-term interests in the face of a rapidly changing and complex world. HDT Short Survey As with many new technologies, the potential and impact of the Human Digital Twin (HDT) are yet to be seen. We believe, however, that digital twins of humans-in the form of our HDT or other similar technologies-will sooner or later become a common, everyday technology, just like aero planes, or mobile phones. ​ The HDT survey, and its results should provide an indication of how people interested in the HDT technology also see the potential, impact, and also the time line for maturing the HDT technology. ​ Current Human Digital Twin (HDT) Use Cases We are developing the HDT in two use cases: Patients-HDT , which assists neonatology ICU patients, and Children-HDT (the TwinUp app), which assures children's safety and minimizes their risk of abuse. Both use cases focus on children because we believe modeling and forecasting risks for children are more achievable due to their less complex nature and behavior. ​ Different aspects of the architecture and use of the HDT are discussed in multiple research papers . HDT Conference Video TECHNOLOGY

  • Copy of Human Wellbeing | SEMARX

    Protecting Vulnerable People "Child maltreatment is a global problem with serious life-long consequences," the World Health Organization states. Almost every second child endures some form of abuse during childhood or adolescence in some parts of the world. The difficulty in identifying child abuse is that children frequently are unable to identify an interaction as abusive; if they do, they withhold information out of fear and shame; and that abuse occurs from both known and unknown individuals to the child. There are numerous mobile applications that inform parents of their children's whereabouts, receive notifications about their precise location, access their devices remotely, enable children to quickly contact parents, trusted individuals, or authorities if they feel threatened; however, our IDT-based app, the TwinUp (in development), aims to predict possible abuse events , thereby reducing the chances of children from getting into an abusive situation in the first place. Help Children Avoid Abusive Events Child abuse situations vary significantly by neighborhood, culture, or country. Thus, the TwinUp app is pre-loaded with a community-specific abuse risk profile. The abuse risk profile is based on a Reference Events Model (REM) that considers a variety of factors relating to abuse incidents and how children respond to abuse experiences in a specific environment. A parent or caregiver configures the TwinUp for their child by providing basic background information and designating individuals in the child's environment as persons of trust with whom the TwinUp can communicate when within range of the child. ​ The TwinUp learns the child's routines, provides estimates for deviations from that routine, and finally projects an abuse risk score . When the anticipated risk score exceeds a reference value (calculated by the TwinUp from the REM), the TwinUp can initiate a series of steps based on the parents' initial configuration to minimize the possibility of an abuse events. ​ With time and the use of the TwinUp by many parents in a community, the app's prediction accuracy will improve accordingly. The TwinUp FAQ Help Women Avoid Abusive Events As with the TwinUp for children protection, the TwinUp for women's safety learns its user's behavior patterns and, based on a community risk profile established in a Reference Events Model (REM), assigns risk levels to various daily situations. ​ On the one hand, an adult's life is more complex and diversified than that of a child; on the other, this complexity provides the TwinUp with additional data and digital interactions to learn the user patterns and sentiments. ​ Similar to the TwinUp for children, a critical component of maintaining safety for adults is maintaining a digital network of trusted individuals and friends. Another consideration is determining a person's overall sentiment based on their digital interactions. This enables the TwinUp to assess its user's stress levels and rely on it to predict risk, as stressed individuals may be less aware of the ramifications of particular choices. ​ Based on the projected risk score, the TwinUp can notify their user to raise their awareness or recommend that they vary their routines and become unexpected, thus minimizing the likelihood of critical encounters. How is the TwinUp App Different? There are many apps for protecting children and keeping women safe that give detailed, real-time information about where a child is and what is going on around them. ​ However, as with any risk, the key is to find ways to lessen it. We thus think a safety solution should focus on: predicting risky situations in advance so that the child and the parents have time to act BEFORE something bad happens. Long-Term Vision Protecting children or adults from abuse is a necessary first step toward supporting them in other aspects of their lives, such as predicting and lowering stress, predicting and managing addictions, or improving care for children with disabilities. Children Wellbeing White Paper

View All