The representation of feature space is a crucial environment where data points get vectorized and embedded for subsequent modeling. Thus, the efficacy of machine learning (ML) algorithms is closely related to the quality of feature engineering. As one of the most important techniques, feature generation transforms raw data into an optimized feature space conducive to model training and further refines the space. Despite the advancements in automated feature engineering and feature generation, current methodologies often suffer from three fundamental issues: lack of explainability, limited applicability, and inflexible strategy. These shortcomings frequently hinder and limit the deployment of ML models across varied scenarios. Our research introduces a novel approach adopting large language models (LLMs) and feature-generating prompts to address these challenges. We propose a dynamic and adaptive feature generation method that enhances the interpretability of the feature generation process. Our approach broadens the applicability across various data types and tasks and offers advantages in terms of strategic flexibility. A broad range of experiments showcases that our approach is significantly superior to existing methods.

In this paper, we show that exploiting Generative Adversarial Networks (GANs) to transform nighttime images into daytime representation increases the robustness of pedestrian detection in low-light conditions. Our work aims at first learning the image translation to transfer the style from daytime images to nighttime images with unpaired GAN training. Second, we use our end-to-end trained GAN model to translate night images as a pre-processing step before feeding them into an object detector that is pre-trained on daytime images only. To demonstrate the effectiveness of our translation approach, we conducted experiments on two real-world pedestrian datasets using both one-stage and two-stage object detectors. Our results outperform the baseline in all experiments and show highly competitive detection performance compared with other GAN-based approaches while holding the most lightweight architecture. We believe that our approach is an effective pre-processing first step that helps in bridging the performance gap between day and night at no expense of re-training object detector networks with more night images.

This paper introduces EnGRMA, an Enhanced deep reinforcement learning-based Group Recommendation system with Multi-head Attention for varied group sizes.EnGRMA adapts its recommendation strategy according to group sizes, using individual member preferences in smaller groups through a weighted average method, and leveraging multihead attention to aggregate diverse opinions effectively in larger groups.This method helps model dynamic member-item interactions, enhancing the system's ability to deliver personalized recommendations.Our evaluation of the MovieLens-Rand dataset shows that EnGRMA not only outperforms GRMA and DRGR in Recall, NDCG, Precision, and F1 scores but also demonstrates superior performance in NDCG against AGREE.

Despite major advancements in state-of-the-art object detectors and low-light image enhancements, nighttime pedestrian detection remains a challenge. One commonly used solution to remedy this domain shift problem is re-training object detectors with extra nighttime scenes which is not only computationally expensive but also not generalizable. In this paper, we explore a new solution and aim to systematically analyze and understand the efficiency of a lightening algorithm on pedestrian detection in low-light conditions. In our analysis, we first explore the effect of normalizing image luminance based on the ground truth bounding boxes to adaptively adjust global image luminance and evaluate its effects on detection performance. Second, unlike general low-light image enhancements that rely on global or local image statistics, we design a pedestrian-luminance-aware lightening algorithm to automatically correct nighttime images luminance so that pedestrians can be more robustly detected. Through extensive experiments, our algorithm not only achieves competitive detection results compared to the baseline on two real-world nighttime datasets but also elevates the confidence score of detected pedestrians.

This virtual reality study was conducted to assess the impact of the appearance of virtual characters on the avoidance movement behavior of participants. Five experimental conditions were examined. Under each condition, one of the five different virtual characters (classified as mannequin, human, cartoon, robot, and zombie) was studied. Each participant had to experience only one condition and was asked to perform the collision avoidance tasks two times. During the walking task, the motion of participants was recorded. After finishing the collision avoidance segment of the study, a questionnaire that examined different concepts (emotional reactivity, emotional contagion, attentional allocation, behavioral independence, perceived skill, presence, immersion, virtual character realism, and virtual character unpleasantness) was distributed to the participants. Based on the collected measurements (avoidance movement behavior and self-reported ratings), we tried to understand the effects of the appearance of a virtual character on the avoidance movement behavior, and its possible correlation to subjective ratings. The results obtained from this study indicated that the appearance of the virtual characters did affect the avoidance movement behavior and also some of the examined concepts. Additionally, participant avoidance movement behavior correlates with some subjective ratings.

Successful robot path planning is challenging in the presence of visual occlusions and moving targets. Classical methods to solve this problem have used visioning and perception algorithms in addition to partially observable markov decision processes to aid in path planning for pursuit-evasion and robot tracking. We present a predictive path planning process that measures and utilizes the uncertainty present during robot motion planning. We develop a variant of subjective logic in combination with the Markov decision process (MDP) and provide a measure for belief, disbelief, and uncertainty in relation to feasible trajectories being generated. We then model the MDP to identify the best path planning method from a list of possible choices. Our results show a high percentage accuracy based on the closest acquired proximity between a target and a tracking robot and a simplified pursuer trajectory in comparison with related work.

Knowledge Base, represents facts about the world, often in some form of subsumption ontology, rather than implicitly, embedded in procedural code, the way a conventional computer program does. While there is a rapid growth in knowledge bases, it poses a challenge of retrieving information from them. Knowledge Base Question Answering is one of the promising approaches for extracting substantial knowledge from Knowledge Bases. Unlike web search, Question Answering over a knowledge base gives accurate and concise results, provided that natural language questions can be understood and mapped precisely to an answer in the knowledge base. However, some of the existing embedding-based methods for knowledge base question answering systems ignore the subtle correlation between the question and the Knowledge Base (e.g., entity types, relation paths, and context) and suffer from the Out Of Vocabulary problem. In this paper, we focused on using a pre-trained language model for the Knowledge Base Question Answering task. Firstly, we used Bert base uncased for the initial experiments. We further fine-tuned these embeddings with a two way attention mechanism from the knowledge base to the asked question and from the asked question to the knowledge base answer aspects. Our method is based on a simple Convolutional Neural Network architecture with a Multi-Head Attention mechanism to represent the asked question dynamically in multiple aspects. Our experimental results show the effectiveness and the superiority of the Bert pre-trained language model embeddings for question answering systems on knowledge bases over other well-known embedding methods.

This paper examines a common problem found in a number of virtual reality setups—mismatches between real and virtual environments. Specifically, this paper investigates whether the mismatching between a real and a virtual environment in terms of appearance and physical constraints can affect the arousal (electrodermal activity) and movement behavior in the participants. For this study, one baseline condition and four mismatch conditions that examine different mismatching types were developed and tested in a between-group study design. The participants were immersed in a virtual environment and were asked to walk in a direction given to them along a provided path. During that time, electrodermal activity and the walking motion of participants were captured to assess potential alterations in their arousal and movement behavior respectively. Results obtained from this study indicate significant differences in the electrodermal activity and movement behavior of participants, especially when walking in a virtual environment that is mismatched both in appearance and physical constraints. Even though to a lesser degree, evidence was also found that correlates electrodermal activity with movement behavior. Limitations and future research directions are discussed.

In recent years, deep learning methods are becoming more widely used; however, large quantities of labeled training data are required for most models. Labeling large datasets is tedious, expensive, and time consuming. Generating large labeled synthetic datasets, on the other hand, is easier and less expensive since annotations are available. But there is usually a large gap between the distribution of the synthetic and real data. In this paper, we propose a novel method based on Generative Adversarial Networks (GANs) to improve the realism of the synthetic images while preserving the annotation information. In our work the inputs of the GANs are synthetic images instead of random vectors. Furthermore, we describe how a perceptual loss can be utilized while introducing the basic features and techniques from adversarial networks for obtaining better results. We evaluate our approach for appearance-based gaze direction classification on the MPIIGaze dataset. The results show that our generated refined images are more realistic and better preserve the annotation information than the refined images generated by the state-of-the-art methods.

In this work, we have considered designing a highly efficient capacity-constrained overlay multicast protocol; it is designed specifically for an existing Chinese Remainder Theorem (CRT) - based structured P2P architecture [9]. Such an architecture has been the choice for its structural advantages over DHT-based architectures. It is worth mentioning its most important advantage from the viewpoint of speed of communication, that is its diameter, which is only 3 overlay hops. The protocol is not restricted to a single data source and it incorporates peer heterogeneity as well. We have also designed another any source capacity-constrained multicast protocol that incorporates the unique idea of transforming the multicast problem to a broadcast one [10]. We have compared analytically the performance of the two protocols; it has led to the observation that use of this unique idea [10] cannot take advantage of all structural advantages of a CRT-based system resulting in decrease in performance. However, the proposed multicast source discovery protocol has used this unique idea offering good performance.

A virtual reality study was conducted to understand participants' anxiety when immersed in a virtual reality trip with a self-driving car. Participants were placed as passengers in a virtual car, and they were seated in the co-driver seat. Five different conditions were developed and examined. For this experiment, the Anxiety Modality Questionnaire that captures the cognitive anxiety of participants was used. The obtained results indicated that the participants' level of anxiety for the partial awareness of the driver condition is influenced less than expected. Specifically, lower levels of anxiety were found when the driver is either fully or partially aware of the traffic and the behavior of the car, and higher anxiety levels were found when the driver is completely unaware.

The present study investigates users' movement behavior in a virtual environment when they attempted to avoid a virtual character. At each iteration of the experiment, four conditions (Self-Avatar LookAt, No Self-Avatar LookAt, Self-Avatar No LookAt, and No Self-Avatar No LookAt) were applied to examine users' movement behavior based on kinematic measures. During the experiment, 52 participants were asked to walk from a starting position to a target position. A virtual character was placed at the midpoint. Participants were asked to wear a head-mounted display throughout the task, and their locomotion was captured using a motion capture suit. We analyzed the captured trajectories of the participants' routes on four kinematic measures to explore whether the four experimental conditions influenced the paths they took. The results indicated that the Self-Avatar LookAt condition affected the path the participants chose more significantly than the other three conditions in terms of length, duration, and deviation, but not in terms of speed. Overall, the length and duration of the task, as well as the deviation of the trajectory from the straight line, were greater when a self-avatar represented participants. An additional effect on kinematic measures was found in the LookAt (Gaze) conditions. Implications for future research are discussed.

This paper compares two approaches for predicting air temperature from historical pressure, humidity, and temperature data gathered from meteorological sensors in Northwestern Nevada. We describe our data and our representation and compare a standard neural network against a deep learning network. Our empirical results indicate that a deep neural network with Stacked Denoising Auto-Encoders (SDAE) outperforms a standard multilayer feed forward network on this noisy time series prediction task. In addition, predicting air temperature from historical air temperature data alone can be improved by employing related weather variables like barometric pressure, humidity and wind speed data in the training process.

The ability to detect human actions or gestures is key for a wide range of applications that involve interactions between humans and robots. These actions are patterns that have a particular spatio-temporal structure. This paper presents an approach for encoding such patterns using spike-timing networks with axonal conductance delays. The proposed method brings the following contributions: first, it enables the encoding of patterns in an unsupervised manner. Second, it allows us to create models of specific patterns using a very small set of training samples, in contrast with standard pattern recognition approaches that typically require large amounts of training data. Based on these models, the method further enables classification of new patterns using a longest-common subsequence approach for matching between patterns of activated neurons. Third, the approach is invariant to scale and translation and thus it enables generalization across multiple scales and positions. Fourth, the approach also enables early recognition of patterns from only partial information about the pattern. The proposed method is validated on a set of gestures representing the digits from 0 to 9, extracted from video data of a human drawing the corresponding digits. The results are also compared with other state of the art pattern recognition algorithms.

This paper investigates three approaches to the problem of identity recognition in real-world unconstrained environments. We describe a new and challenging face recognition dataset captured in a laboratory environment with no strong constraints on lighting, motion, or subject pose, orientation, distance, or facial expression. We then evaluate three approaches to identity recognition on this new dataset. We find that a deep neural network with stacked denoising auto-encoders significantly outperforms a standard feedforward neural network and a baseline eigenfaces approach from the OpenCV library. Despite the 66 million plus parameters in the best trained deep network, it significantly outperforms the other two methods even on the relatively small number (relative to the number of deep network parameters) of 8,895 training samples. We believe our work adds to the growing empirical and theoretical evidence that deep networks provide a promising approach to unconstrained recognition problems.

In this paper, we propose a new approach for recognizing intentions of humans by observing their activities with an RGB-D camera. Activities and goals are modeled as a distributed network of inter-connected nodes in an Activation Spreading Network (ASN). Inspired by a formalism in hierarchical task networks, the structure of the network captures the hierarchical relationship between high-level goals and low-level activities that realize these goals. Our approach can detect intentions before they are realized and it can work in real-time. We also extend the formalism of ASNs to incorporate contextual information into intent recognition. A fully functioning system is developed for experimental evaluation. We implemented a robotic system that uses our intent recognition to naturally interact with the user. Our ASN based intent recognizer is tested against two different scenarios involving everyday activities performed by a subject, and our results show that the proposed approach is able to detect low-level activities and recognize high-level intentions effectively in real-time. Further analysis shows that contextual ASN is able to discriminate between otherwise ambiguous goals.