Hearings of witnesses and defendants play a crucial role when reaching court trial decisions. Given the high-stakes nature of trial outcomes, developing computational models that assist the decision-making process is an important research venue. In this paper, we address the identification of deception in real-life trial data. We use a dataset consisting of videos collected from public court trials. We explore the use of verbal and non-verbal modalities to build a multimodal deception detection system that aims to discriminate between truthful and deceptive statements provided by defendants and witnesses. In particular, three complementary modalities (visual, acoustic and linguistic) are evaluated for the classification of deception at the subject level. The final classifier is obtained by combining the three modalities via score-level classification, achieving 83.05% accuracy in subject-level deceit detection. To place our results in perspective, we present a human deception detection study where we evaluate the human capability of detecting deception using different modalities and compare the results to the developed system. The results show that our system outperforms the average non-expert human capability of identifying deceit.
In this paper, we investigated various physiological indicators on their ability to identify distracted and drowsy driving. In particular, four physiological signals are being tested: blood volume pulse (BVP), respiration, skin conductance and skin temperature. Data were collected from 45 participants, under a simulated driving scenario, through different times of the day and during their engagement on a variety of physical and cognitive distractors. We explore several statistical features extracted from those signals and their efficiency to discriminate between the presence or not of each of the two conditions. To that end, we evaluate three traditional classifiers (Random Forests, KNN and SVM), which have been extensively applied by the related literature and we compare their performance against a deep CNN-LSTM network that learns spatio-temporal physiological representations. In addition, we explore the potential of learning multiple conditions in parallel using a single machine learning model, and we discuss how such a problem could be formulated and what are the benefits and disadvantages of the different approaches. Overall, our findings indicate that information related to the BVP data, especially features that describe patterns with respect to the inter-beat-intervals (IBI), are highly associates with both targeted conditions. In addition, features related to the respiratory behavior of the driver can be indicative of drowsiness, while being less associated with distractions. Moreover, spatio-temporal deep methods seem to have a clear advantage against traditional classifiers on detecting both driver conditions. Our experiments show, that even though learning both conditions jointly can not compete directly to individual, task-specific CNN-LSTM models, deep multitask learning approaches have a great potential towards that end as they offer the second best performance on both tasks against all other evaluated alternatives in terms of sensitivity, specificity and the area under the receiver operating characteristic curve (AUC).
There is a recent trend of research and applications of Cyber-Physical Systems (CPS) in manufacturing to enhance human-robot collaboration and production. In this paper, we propose a CPS framework for personalized Human-Robot Collaboration and Training to promote safe human-robot collaboration in manufacturing environments. We propose a human-centric CPS approach that focuses on multimodal human behavior monitoring and assessment, to promote human worker safety and enable human training in Human-Robot Collaboration tasks. We present the architecture of our proposed system, our experimental testbed and our proposed methods for multimodal physiological sensing, human state monitoring and interactive robot adaptation, to enable personalized interaction.
The laser-based, non-destructive, front heating/front detection type transient thermo-reflectance (TTR) method was adapted to measure soft materials, and it was subsequently deployed to measure the thermal properties of a couple of popular Thermal Interface Materials (TIM) used in the microelectronics industry. Both the thermal conductivity of the TIM layer and the interface thermal resistance between the TIM and the solid substrate can be measured. A special fixture was built that enables precise control of the applied pressure on the TIM, in the range 0 to 4000 kPa and above. As a result, the TTR measurement system can be used to extract the variation of the above mentioned TIM thermal properties with the applied pressure. Our results show that the interface thermal resistance decreases with the applied pressure until about 800 kPa after which it stays constant. The values are relatively small, suggesting very good thermal interface resistance. Overall it was found that compared to other systems, such as the those described by standard ASTM D5470, the laser based method used here possesses unique characteristics that makes it is better suited for measuring the interface thermal resistance in TIM films.
13 August 2025 in International Journal of Heat and Mass Transfer