Jonathan Carrero, Ismael Rodriguez, Fernando Rubio
When some resources are to be distributed among a set of agents following egalitarian social welfare, the goal is to maximize the utility of the agent whose utility turns out to be minimal. In this context, agents can have an incentive to lie about their actual preferences, so that more valuable resources are assigned to them. In this paper we analyze this situation, and we present a practical study where genetic algorithms are used to assess the benefits of lying under different situations.
Collaborative group projects are integral to computer science education, fostering teamwork, problem-solving, and industry-relevant skills. However, assessing individual contributions within group settings remains challenging. Traditional approaches, including equal grade distribution and subjective peer evaluations, often lack fairness, objectivity, and scalability, particularly in large classrooms. We propose TRACE, a semi-automated AI-assisted framework for assessing collaborative software projects that evaluates both project quality and individual contributions using repository mining, communication analytics, and AI-assisted analytics. A pilot deployment in a software engineering course demonstrated high alignment with instructor assessments, increased student satisfaction, and reduced instructor grading effort. The results suggest that AI-assisted analytics can improve the transparency and scalability of collaborative project assessment in computer science education.
Lisan Al Amin, Md. Ismail Hossain, Thanh Thi Nguyen
et al.
Recent advances in deepfake technology have created increasingly convincing synthetic media that poses significant challenges to information integrity and social trust. While current detection methods show promise, their underlying mechanisms remain poorly understood, and the large sizes of their models make them challenging to deploy in resource-limited environments. This study investigates the application of the Lottery Ticket Hypothesis (LTH) to deepfake detection, aiming to identify the key features crucial for recognizing deepfakes. We examine how neural networks can be efficiently pruned while maintaining high detection accuracy. Through extensive experiments with MesoNet, CNN-5, and ResNet-18 architectures on the OpenForensic and FaceForensics++ datasets, we find that deepfake detection networks contain winning tickets, i.e., subnetworks, that preserve performance even at substantial sparsity levels. Our results indicate that MesoNet retains 56.2% accuracy at 80% sparsity on the OpenForensic dataset, with only 3,000 parameters, which is about 90% of its baseline accuracy (62.6%). The results also show that our proposed LTH-based iterative magnitude pruning approach consistently outperforms one-shot pruning methods. Using Grad-CAM visualization, we analyze how pruned networks maintain their focus on critical facial regions for deepfake detection. Additionally, we demonstrate the transferability of winning tickets across datasets, suggesting potential for efficient, deployable deepfake detection systems.
Perception systems in autonomous driving rely on sensors such as LiDAR and cameras to perceive the 3D environment. However, due to occlusions and data sparsity, these sensors often fail to capture complete information. Semantic Occupancy Prediction (SOP) addresses this challenge by inferring both occupancy and semantics of unobserved regions. Existing transformer-based SOP methods lack explicit modeling of spatial structure in attention computation, resulting in limited geometric awareness and poor performance in sparse or occluded areas. To this end, we propose Spatially-aware Window Attention (SWA), a novel mechanism that incorporates local spatial context into attention. SWA significantly improves scene completion and achieves state-of-the-art results on LiDAR-based SOP benchmarks. We further validate its generality by integrating SWA into a camera-based SOP pipeline, where it also yields consistent gains across modalities.
Thanh Thi Nguyen, Quoc Viet Hung Nguyen, Jonathan Kua
et al.
Enabling multiple autonomous machines to perform reliably requires the development of efficient cooperative control algorithms. This paper presents a survey of algorithms that have been developed for controlling and coordinating autonomous machines in complex environments. We especially focus on task allocation methods using computational intelligence (CI) and deep reinforcement learning (RL). The advantages and disadvantages of the surveyed methods are analysed thoroughly. We also propose and discuss in detail various future research directions that shed light on how to improve existing algorithms or create new methods to enhance the employability and performance of autonomous machines in real-world applications. The findings indicate that CI and deep RL methods provide viable approaches to addressing complex task allocation problems in dynamic and uncertain environments. The recent development of deep RL has greatly contributed to the literature on controlling and coordinating autonomous machines, and it has become a growing trend in this area. It is envisaged that this paper will provide researchers and engineers with a comprehensive overview of progress in machine learning research related to autonomous machines. It also highlights underexplored areas, identifies emerging methodologies, and suggests new avenues for exploration in future research within this domain.
Soft sensing of hard-to-measure variables is often crucial in industrial processes. Current practices rely heavily on conventional modeling techniques that show success in improving accuracy. However, they overlook the non-linear nature, dynamics characteristics, and non-Euclidean dependencies between complex process variables. To tackle these challenges, we present a framework known as a Knowledge discovery graph Attention Network for effective Soft sensing (KANS). Unlike the existing deep learning soft sensor models, KANS can discover the intrinsic correlations and irregular relationships between the multivariate industrial processes without a predefined topology. First, an unsupervised graph structure learning method is introduced, incorporating the cosine similarity between different sensor embedding to capture the correlations between sensors. Next, we present a graph attention-based representation learning that can compute the multivariate data parallelly to enhance the model in learning complex sensor nodes and edges. To fully explore KANS, knowledge discovery analysis has also been conducted to demonstrate the interpretability of the model. Experimental results demonstrate that KANS significantly outperforms all the baselines and state-of-the-art methods in soft sensing performance. Furthermore, the analysis shows that KANS can find sensors closely related to different process variables without domain knowledge, significantly improving soft sensing accuracy.
The minimum cost of job assignment (Min-JA) is one of the practical NP-hard problems to manage the optimization in science-and-engineering applications. Formally, the optimal solution of the Min-JA can be computed by the branch-and-bound (BnB) algorithm (with the efficient predictor) in O(n!), n = problem size, and O(n3) in the best case but that best case hardly occurs. Currently, metaheuristic algorithms, such as genetic algorithms (GA) and swarm-optimization algorithms, are extensively studied, for polynomial-time solutions. Recently, unbiased filtering (in search-space reduction) could solve some NP-hard problems, such as 0/1-knapsack and multiple 0/1-knapsacks with Latin square (LS) of m-capacity ranking, for the ideal solutions in polynomial time. To solve the Min-JA problem, we propose the adaptive unbiased-filtering (AU-filtering) in O(n3) with a new hybrid (search-space) reduction (of the indirect metaheuristic strategy and the exact BnB). Innovation-and-contribution of our AU-filtering is achieved through three main steps: 1. find 9 + n effective job-orders for the good initial solutions (by the indirect assignment with UP: unbiased predictor), 2. improve top 9-solutions by the indirect improvement of the significant job-orders (by Latin square of n permutations plus n complex mod-functions), and 3. classify objects (from three of the best solutions) for AU-filtering (on large n) with deep-reduction (on smaller n’) and repeat (1)-(3) until n’ < 6, the exact BnB is applied. In experiments, the proposed AU-filtering was evaluated by a simulation study, where its ideal results outperformed the best results of the hybrid swarm-GA algorithm on a variety of 2D datasets (n ≤ 1000).
ABSTRACT Active object detection (AOD) is a crucial task in the field of robotics. A key challenge in household environments for AOD is that the target object is often undetectable due to partial occlusion, which leads to the failure of traditional methods. To address the occlusion problem, this paper first proposes a novel occlusion handling method based on the large multimodal model (LMM). The method utilises an LMM to detect and analyse input RGB images and generates adjustment actions to progressively eliminate occlusion. After the occlusion is handled, an improved AOD method based on a deep Q‐learning network (DQN) is used to complete the task. We introduce an attention mechanism to process image features, enabling the model to focus on critical regions of the input images. Additionally, a new reward function is proposed that comprehensively considers the bounding box of the target object and the robot's distance to the object, along with the actions performed by the robot. Experiments on the dataset and in real‐world scenarios validate the effectiveness of the proposed method in performing AOD tasks under partial occlusion.
The purpose of this study is to explore the mediating role of organizational trust in the impact of social sustainability on organizational resilience. Using a sample of 441 employees in the energy sector in Istanbul, a structured questionnaire was applied to measure employees' organizational resilience, organizational trust and perceived social sustainability activities. Data analysis was carried out with SPSS and AMOS 24 programs. Factor analysis and structural equation modeling were used in the study. The data analysis based on path modelling confirms the mediating role of organizational trust in the effect of social sustainability on organizational resilience. The findings show that all social sustainability variables significantly affect all organizational trust dimensions, and organizational trust dimensions significantly affect organizational resilience dimensions. Accordingly, organizational trust dimensions and all social sustainability dimensions have a full mediating variable role in the effect of organizational trust dimensions on organizational resilience dimensions. Future research is important to gain a deeper understanding of the relationships between social sustainability, organizational resilience and organizational trust. In particular, studies in specific sectors or cultural contexts can help us better understand how these relationships may vary and how they may shape organizations' strategies.
Aditya Kapoor, Vartika Sengar, Nijil George
et al.
Tracking of inventory and rearrangement of misplaced items are some of the most labor-intensive tasks in a retail environment. While there have been attempts at using vision-based techniques for these tasks, they mostly use planogram compliance for detection of any anomalies, a technique that has been found lacking in robustness and scalability. Moreover, existing systems rely on human intervention to perform corrective actions after detection. In this paper, we present Co-AD, a Concept-based Anomaly Detection approach using a Vision Transformer (ViT) that is able to flag misplaced objects without using a prior knowledge base such as a planogram. It uses an auto-encoder architecture followed by outlier detection in the latent space. Co-AD has a peak success rate of 89.90% on anomaly detection image sets of retail objects drawn from the RP2K dataset, compared to 80.81% on the best-performing baseline of a standard ViT auto-encoder. To demonstrate its utility, we describe a robotic mobile manipulation pipeline to autonomously correct the anomalies flagged by Co-AD. This work is ultimately aimed towards developing autonomous mobile robot solutions that reduce the need for human intervention in retail store management.
Collaborative 3D object detection, with its improved interaction advantage among multiple agents, has been widely explored in autonomous driving. However, existing collaborative 3D object detectors in a fully supervised paradigm heavily rely on large-scale annotated 3D bounding boxes, which is labor-intensive and time-consuming. To tackle this issue, we propose a sparsely supervised collaborative 3D object detection framework SSC3OD, which only requires each agent to randomly label one object in the scene. Specifically, this model consists of two novel components, i.e., the pillar-based masked autoencoder (Pillar-MAE) and the instance mining module. The Pillar-MAE module aims to reason over high-level semantics in a self-supervised manner, and the instance mining module generates high-quality pseudo labels for collaborative detectors online. By introducing these simple yet effective mechanisms, the proposed SSC3OD can alleviate the adverse impacts of incomplete annotations. We generate sparse labels based on collaborative perception datasets to evaluate our method. Extensive experiments on three large-scale datasets reveal that our proposed SSC3OD can effectively improve the performance of sparsely supervised collaborative 3D object detectors.
Bastian Pätzold, Andre Rochow, Michael Schreiber
et al.
Haptic perception is highly important for immersive teleoperation of robots, especially for accomplishing manipulation tasks. We propose a low-cost haptic sensing and rendering system, which is capable of detecting and displaying surface roughness. As the robot fingertip moves across a surface of interest, two microphones capture sound coupled directly through the fingertip and through the air, respectively. A learning-based detector system analyzes the data in real time and gives roughness estimates with both high temporal resolution and low latency. Finally, an audio-based vibrational actuator displays the result to the human operator. We demonstrate the effectiveness of our system through lab experiments and our winning entry in the ANA Avatar XPRIZE competition finals, where briefly trained judges solved a roughness-based selection task even without additional vision feedback. We publish our dataset used for training and evaluation together with our trained models to enable reproducibility of results.
Paulo R. Lisboa de Almeida, Jeovane Honório Alves, Luiz S. Oliveira
et al.
Smart-parking solutions use sensors, cameras, and data analysis to improve parking efficiency and reduce traffic congestion. Computer vision-based methods have been used extensively in recent years to tackle the problem of parking lot management, but most of the works assume that the parking spots are manually labeled, impacting the cost and feasibility of deployment. To fill this gap, this work presents an automatic parking space detection method, which receives a sequence of images of a parking lot and returns a list of coordinates identifying the detected parking spaces. The proposed method employs instance segmentation to identify cars and, using vehicle occurrence, generate a heat map of parking spaces. The results using twelve different subsets from the PKLot and CNRPark-EXT parking lot datasets show that the method achieved an AP25 score up to 95.60\% and AP50 score up to 79.90\%.
Recent advancements in legged locomotion research have made legged robots a preferred choice for navigating challenging terrains when compared to their wheeled counterparts. This paper presents a novel locomotion policy, trained using Deep Reinforcement Learning, for a quadrupedal robot equipped with an additional prismatic joint between the knee and foot of each leg. The training is performed in NVIDIA Isaac Gym simulation environment. Our study investigates the impact of these joints on maintaining the quadruped's desired height and following commanded velocities while traversing challenging terrains. We provide comparison results, based on a Cost of Transport (CoT) metric, between quadrupeds with and without prismatic joints. The learned policy is evaluated on a set of challenging terrains using the CoT metric in simulation. Our results demonstrate that the added degrees of actuation offer the locomotion policy more flexibility to use the extra joints to traverse terrains that would be deemed infeasible or prohibitively expensive for the conventional quadrupedal design, resulting in significantly improved efficiency.
Kritsanavis Chongsrid, Leon Wirz, Sasikan Sukhor
et al.
Hydrocephalus is a condition with an abnormal cerebrospinal fluid (CSF) accumulation in the brain's ventricles resulting in ventricular enlargement. One of the most common surgical treatments for hydrocephalus is the ventriculoperitoneal (VP) Shunt operation. A freehand technique using surface anatomy ventricular catheter placement has been widely used in VP Shunt operations because of its simplicity and low cost. However, this technique trades off with moderate accuracy. To improve accuracy, most existing freehand techniques involved using tools or software to manually measure distances and/or drilling angles from CT or MRI slides. In this work, we developed the first fully automated system VP shunt entry area recommender (VPSEAR) for a pre-planned freehand placement. The program with a user- interface took the patient's CT slides, calculated a circular entry site on a skull, and reported a unique circular entry region. The program integrated several mathematical knowledge and 3-D data processing techniques to ensure high accuracy and acceptable running time. We tested the invented programs on a collection of CT slices of 15 patients with 30 head sides and evaluated the system's accuracy against the traditional Keen's method using 3D Slicer software. We achieved an average accuracy of 95.33% using five internal points evaluation, with accuracy improvement over Keen's method up to 40.33%. The program running time was less than 15 min per head side.
Max Talanov, Jordi Vallverdu, Andrew Adamatzky
et al.
This work is dedicated to the review and perspective of the new direction that we call "Neuropunk revolution" resembling the cultural phenomenon of cyberpunk. This new phenomenon has its foundations in advances in neuromorphic technologies including memristive and bio-plausible simulations, BCI, and neurointerfaces as well as unconventional approaches to AI and computing in general. We present the review of the current state-of-the-art and our vision of near future development of scientific approaches and future technologies. We call the "Neuropunk revolution" the set of trends that in our view provide the necessary background for the new generation of approaches technologies to integrate the cybernetic objects with biological tissues in close loop system as well as robotic systems inspired by the biological processes again integrated with biological objects. We see bio-plausible simulations implemented by digital computers or spiking networks memristive hardware as promising bridge or middleware between digital and (neuro)biological domains.