Michael Lewis

Apple jam is a widely used all-season product. The quality of the jam is closely related to its sugar concentration, which affects its taste, texture, shelf life, and legal compliance with production requirements. Although traditional methods for measuring sugar, such as titration, enzymatic methods, and chromatography, are accurate, they are also invasive, destructive, and unsuitable for rapid screening. This study investigates a non-destructive and non-invasive alternative method that uses hyperspectral imaging (HSI) in combination with machine learning to estimate the sugar content in processed apple products. Eight cultivars were selected from the Central Asian region, recognized as the origin of apples and known for its rich diversity of apple cultivars. A total of 88 jam samples were prepared with sugar concentrations ranging from 25% to 75%. For each sample, several hyperspectral images were obtained using a visible-to-near-infrared (VNIR) camera. The acquired spectral data were then processed and analyzed using regression models, including the support vector machine (SVM), eXtreme gradient boosting (XGBoost), and a one-dimensional residual network (1D ResNet). Among them, ResNet achieved the highest prediction accuracy of R² = 0.948. The results highlight the potential of HSI and machine learning for a fast, accurate, and non-invasive assessment of the sugar content in processed foods.

Human-machine communication can be substantially enhanced by the inclusion of high-quality real-time recognition of spontaneous emotional expressions. However, successful recognition of such expressions can be negatively impacted by factors such as sudden variations of lighting, or intentional obfuscation. In addition, the presentation and meaning of emotional expressions can vary significantly, depending on external factors such as the environment within which the emotions are expressed, and the culture of the expressor. As an example, an emotion recognition model trained on a regionally-specific database, collected from North America, might fail to recognize standard emotional expressions from another region, such as East Asia. To address the problem of regional and cultural bias in emotion recognition from facial expressions, we propose a meta-model that fuses multiple emotional cues and features. The proposed approach integrates macro-expression, micro-expression, action level features and image features into a multi-cues emotion model (MCAM). The results show that the proposed meta-classifier (MCAM) reduces the bias factors and achieves successful emotion recognition in most of the evaluated scenarios. Additionally, we also identified certain cues and features of the data-sets that preclude the design of the perfect unbiased classifier.

Accurate modeling provides a means by which a complex problem can be examined for informed decision-making. We present a particle-based SEIR epidemic simulator as a tool to assess the impact of vaccination strategies on viral propagation and to model both sterilizing and effective immunization outcomes. The simulator includes modules to support contact tracing of the interactions amongst individuals as well as epidemiological testing of the general population. The simulator particles are distinguished by age, thus enabling a more accurate representation of the rates of infection and mortality in accordance with differential demographic susceptibilities and medical outcomes. Moreover, based on the age differentiation of particles the vaccination can be simulated based on the age group descending order or randomly across all age groups. The simulator can be calibrated by region of interest and variable vaccination strategies (i.e. random or prioritized by age) so as to enable locality-sensitive virus mitigation policy measures and resource allocation. The results described, based on the experience of the province of Lecco, Italy, indicate that the tool can be used to evaluate vaccination strategies in a way that incorporates local circumstances of viral propagation and demographic susceptibilities. Further, the simulator accounts for modeling the distinction between sterilizing immunization, in which immunized people are no longer contagious, and that of effective immunization, in which symptoms and mortality outcomes are diminished but individuals can still transmit the virus. The sterilizing-age-based vaccination scenario results in the least number of deaths compared to other scenarios. Furthermore, sterilizing immunity shows that random-all vaccination still results in a much smaller number of deaths across age groups 7-9 (ages 70 and above, i.e. age groups with the highest mortality rate) compared to the effective immunization scenario due to the herd immunity that stops further transmission of infection. As the vaccination rate increases, the mortality gap between the scenarios shrinks.

We present SpeakingFaces as a publicly-available large-scale multimodal dataset developed to support machine learning research in contexts that utilize a combination of thermal, visual, and audio data streams; examples include human–computer interaction, biometric authentication, recognition systems, domain transfer, and speech recognition. SpeakingFaces is comprised of aligned high-resolution thermal and visual spectra image streams of fully-framed faces synchronized with audio recordings of each subject speaking approximately 100 imperative phrases. Data were collected from 142 subjects, yielding over 13,000 instances of synchronized data (∼3.8 TB). For technical validation, we demonstrate two baseline examples. The first baseline shows classification by gender, utilizing different combinations of the three data streams in both clean and noisy environments. The second example consists of thermal-to-visual facial image translation, as an instance of domain transfer.

Accurate modeling provides a means by which a complex problem can be examined for informed decision-making. We present a particle-based SEIR epidemic simulator as a tool to assess the impact of vaccination strategies on viral propagation and to model both sterilizing and effective immunization outcomes. The simulator includes modules to support contact tracing of the interactions amongst individuals as well as epidemiological testing of the general population. The simulator particles are distinguished by age, thus enabling a more accurate representation of the rates of infection and mortality in accordance with differential demographic susceptibilities and medical outcomes. Moreover, thanks to the age differentiation of particles, the vaccination can be simulated based on the age group descending order or randomly across all age groups. The simulator can be calibrated by region of interest and variable vaccination strategies (i.e. random or prioritized by age) so as to enable locality-sensitive virus mitigation policy measures and resource allocation. The results described, based on the experience of the province of Lecco, Italy, indicate that the tool can be used to evaluate vaccination strategies in a way that incorporates local circumstances of viral propagation and demographic susceptibilities. Further, the simulator accounts for modeling the distinction between sterilizing immunization, in which immunized people are no longer contagious, and that of effective immunization, in which symptoms and mortality outcomes are diminished but individuals can still transmit the virus. The sterilizing-age-based vaccination scenario results in the least number of deaths compared to other scenarios. Furthermore, the results show that the vaccination of the most vulnerable portion of the population should be prioritized for the effective immunization case. As the vaccination rate increases, the mortality gap between the scenarios shrinks.

In this work, we present an open-source stochastic epidemic simulator calibrated with extant epidemic experience of COVID-19. The simulator models a country as a network representing each node as an administrative region. The transportation connections between the nodes are modeled as the edges of this network. Each node runs a Susceptible-Exposed-Infected-Recovered (SEIR) model and population transfer between the nodes is considered using the transportation networks which allows modeling of the geographic spread of the disease. The simulator incorporates information ranging from population demographics and mobility data to health care resource capacity, by region, with interactive controls of system variables to allow dynamic and interactive modeling of events. The single-node simulator was validated using the thoroughly reported data from Lombardy, Italy. Then, the epidemic situation in Kazakhstan as of 31 May 2020 was accurately recreated. Afterward, we simulated a number of scenarios for Kazakhstan with different sets of policies. We also demonstrate the effects of region-based policies such as transportation limitations between administrative units and the application of different policies for different regions based on the epidemic intensity and geographic location. The results show that the simulator can be used to estimate outcomes of policy options to inform deliberations on governmental interdiction policies.

In this work, we present an open-source stochastic epidemic simulator, calibrated with extant epidemic experience of COVID-19. Our simulator incorporates information ranging from population demographics and mobility data to health care resource capacity, by region, with interactive controls of system variables to allow dynamic and interactive modeling of events. The simulator can be generalized to model the propagation of any disease, in any territory, but for this experiment was customized to model the spread of COVID-19 in the Republic of Kazakhstan, and estimate outcomes of policy options to inform deliberations on governmental interdiction policies.