In this study, we examined the effects of integrating data that contains divergent information, especially concerning anti-vaccination narratives, into the training of a GPT-2 language model. The model was fine-tuned using content sourced from anti-vaccination groups and channels on Telegram, aiming to analyze its ability to generate coherent and rationalized texts in comparison to a model pre-trained on OpenAI’s WebText dataset. The results demonstrate that fine-tuning a GPT-2 model with biased data leads the model to perpetuate these biases in its responses, albeit with a certain degree of rationalization. This finding underscores the importance of using high-quality and reliable data in training natural language processing models, highlighting the implications for information dissemination through these models. It also provides social scientists with a tool to explore and understand the complexities and challenges associated with public health misinformation via the use of language models, particularly in the context of vaccines.

A significant number of traffic accidents are attributed to poor traffic signalization, including issues related to speed bump signs, which are a crucial element in the driving context to regulate speed limits. In these circumstances, object detection associated with deep learning methodology is rapidly gaining momentum over the Advanced Driver-Assistance Systems (ADAS) context. It has already showed to be very efficient in helping the driver to achieve a safer experience. Exploring this technology, this article presents a mobile application that detects speed bump signs in real time using the smartphone’s back camera. The application generates sound and visual alerts for the driver to increase the chances of a proper reaction to the speed bump. Since mobile phone usually have limited computational capacities, this article leverages the use of a compact deep learning model trained using an artificially generated dataset. Results show that the final model is able to operate with the limited mobile resources available, while achieving a 90.8 percent Average Precision Score.

Stroke is a neurological syndrome that usually causes a loss of voluntary control of lower/upper body movements, making it difficult for affected individuals to perform Activities of Daily Living (ADLs). Brain-Computer Interfaces (BCIs) combined with robotic systems, such as Motorized Mini Exercise Bikes (MMEB), have enabled the rehabilitation of people with disabilities by decoding their actions and executing a motor task. However, Electroencephalography (EEG)-based BCIs are affected by the presence of physiological and non-physiological artifacts. Thus, movement discrimination using EEG become challenging, even in pedaling tasks, which have not been well explored in the literature. In this study, Common Spatial Patterns (CSP)-based methods were proposed to classify pedaling motor tasks. To address this, Filter Bank Common Spatial Patterns (FBCSP) and Filter Bank Common Spatial-Spectral Patterns (FBCSSP) were implemented with different spatial filtering configurations by varying the time segment with different filter bank combinations for the three methods to decode pedaling tasks. An in-house EEG dataset during pedaling tasks was registered for 8 participants. As results, the best configuration corresponds to a filter bank with two filters (8-19 Hz and 19-30 Hz) using a time window between 1.5 and 2.5 s after the cue and implementing two spatial filters, which provide accuracy of approximately 0.81, False Positive Rates lower than 0.19, andKappaindex of 0.61. This work implies that EEG oscillatory patterns during pedaling can be accurately classified using machine learning. Therefore, our method can be applied in the rehabilitation context, such as MMEB-based BCIs, in the future.

This work investigates the usage of a deep learning model to support breast diagnostics from mammographic image data [1]. We are collaborating as a beta-tester on the NYU Breast Cancer Classification Meta-repository. Medical images were obtained for testing from a Brazilian Federal Hospital - HUCFF and a database at IEN have been created for research continuity. The main objective is to evaluate a model that could improve radiologist clinical routine, a computational system (Figure 1) for breast cancer diagnostic for standardization and improvement of deep learning in breast cancer for data owners and developers that has the entire pipeline encapsulated in a Docker container [2]. It includes ready-to-use Docker images of screening mammography models.

Modern lane detection methods have achieved remarkable performances in complex real-world scenarios, but many have issues maintaining real-time efficiency, which is important for autonomous vehicles. In this work, we propose LaneATT: an anchor-based deep lane detection model, which, akin to other generic deep object detectors, uses the anchors for the feature pooling step. Since lanes follow a regular pattern and are highly correlated, we hypothesize that in some cases global information may be crucial to infer their positions, especially in conditions such as occlusion, missing lane markers, and others. Thus, this work proposes a novel anchor-based attention mechanism that aggregates global information. The model was evaluated extensively on three of the most widely used datasets in the literature. The results show that our method outperforms the current state-of-the-art methods showing both higher efficacy and efficiency. Moreover, an ablation study is performed along with a discussion on efficiency trade-off options that are useful in practice.

In this work, we present a visual global localization system based on Deep Neural Networks (DNNs) for self-driving cars, named DeepVGL (Deep Visual Global Localization). In training mode, DeepVGL is trained with images and associated poses from datasets built during the mapping process; and, in operating mode, DeepVGL receives images captured online and infers the global poses of the self-driving car. To assess the performance of DeepVGL, we carried out experiments using datasets collected by experimental self-driving cars on trips made over long periods of time, thus including significant changes in the environment, traffic volume and weather conditions, as well as different times of the day and seasons of the year. Experimental results show that DeepVGL is able to correctly locate the self-driving car up to 75% of the time for 0.2 m of accuracy and 96% of the time for 5 m of accuracy.

The localization of self-driving cars is needed for several tasks such as keeping maps updated, tracking objects, and planning. Localization algorithms often take advantage of maps for estimating the car pose. Since maintaining and using several maps is computationally expensive, it is important to analyze which type of map is more adequate for each application. In this work, we provide data for such analysis by comparing the accuracy of a particle filter localization when using occupancy, reflectivity, color, or semantic grid maps. To the best of our knowledge, such evaluation is missing in the literature. For building semantic and colour grid maps, point clouds from a Light Detection and Ranging (LiDAR) sensor are fused with images captured by a front-facing camera. Semantic information is extracted from images with a deep neural network. Experiments are performed in varied environments, under diverse conditions of illumination and traffic. Results show that occupancy grid maps lead to more accurate localization, followed by reflectivity grid maps. In most scenarios, the localization with semantic grid maps kept the position tracking without catastrophic losses, but with errors from 2 to 3 times bigger than the previous. Colour grid maps led to inaccurate and unstable localization even using a robust metric, the entropy correlation coefficient, for comparing online data and the map.

We present a path planner for unstructured urban environments (PPUE) for self-driving cars. PPUE receives initial and goal poses as input, as well as maps of the environment. It employs a hybrid A* algorithm with two heuristics for generating paths, which are smoothed using Conjugate Gradient optimization. Different from previous works, PPUE uses: (i) an obstacle distance grid-map, instead of an occupancy grid-map, for representing the environment; and (ii) an accurate but simple collision model of the car. We have examined PPUE’s performance experimentally in simulated and real world scenarios. Our results show that PPUE computes smooth and safe paths, which follow the kinematic constraints of the vehicle, fast enough for suitable real world operation. * Senior Member, IEEE

In this work, we present a novel strategy for correcting imperfections in occupancy grid maps called map decay. The objective of map decay is to correct invalid occupancy probabilities of map cells that are unobservable by sensors. The strategy was inspired by an analogy between the memory architecture believed to exist in the human brain and the maps maintained by an autonomous vehicle. It consists in merging sensory information obtained during runtime (online) with a priori data from a high-precision map constructed offline. In map decay, cells observed by sensors are updated using traditional occupancy grid mapping techniques and unobserved cells are adjusted so that their occupancy probabilities tend to the values found in the offline map. This strategy is grounded in the idea that the most precise information available about an unobservable cell is the value found in the high-precision offline map. Map decay was successfully tested and is still in use in the IARA autonomous vehicle from Universidade Federal do Espírito Santo.

As changes in external environments are inevitable, a lifelong mapping system is desirable for autonomous robots that aim at long-term operation. Capturing external environment changes into internal representations (for example, maps) is crucial for proper behavior and safety, especially in the case of autonomous vehicles. In this work, we propose a new large-scale mapping system for our autonomous vehicle or any other. The new mapping system is based on the Graph SLAM algorithm, with extensions to deal with the calibration of odometry directly in the optimization of the graph and to address map merging for long-term map maintenance. The mapping system can use sensor data from one or more robots to build and merge different types of occupancy grid maps. The system’s performance is evaluated in a series of experiments carried out with data captured in complex real-world scenarios. The experimental results indicate that the new large-scale mapping system can provide high-quality occupancy grid maps for later navigation and localization of autonomous vehicles that use occupancy grid maps.

We survey research on self-driving cars published in the literature focusing on autonomous cars developed since the DARPA challenges, which are equipped with an autonomy system that can be categorized as SAE level 3 or higher. The architecture of the autonomy system of self-driving cars is typically organized into the perception system and the decision-making system. The perception system is generally divided into many subsystems responsible for tasks such as self-driving-car localization, static obstacles mapping, moving obstacles detection and tracking, road mapping, traffic signalization detection and recognition, among others. The decision-making system is commonly partitioned as well into many subsystems responsible for tasks such as route planning, path planning, behavior selection, motion planning, and control. In this survey, we present the typical architecture of the autonomy system of self-driving cars. We also review research on relevant methods for perception and decision making. Furthermore, we present a detailed description of the architecture of the autonomy system of the self-driving car developed at the Universidade Federal do Espírito Santo (UFES), named Intelligent Autonomous Robotics Automobile (IARA). Finally, we list prominent self-driving car research platforms developed by academia and technology companies, and reported in the media.

One of the main factors that contributed to the large advances in autonomous driving is the advent of deep learning. For safer self-driving vehicles, one of the problems that has yet to be solved completely is lane detection. Since methods for this task have to work in real-time (+30 FPS), they not only have to be effective (i.e., have high accuracy) but they also have to be efficient (i.e., fast). In this work, we present a novel method for lane detection that uses as input an image from a forward-looking camera mounted in the vehicle and outputs polynomials representing each lane marking in the image, via deep polynomial regression. The proposed method is shown to be competitive with existing state-of-the-art methods in the TuSimple dataset while maintaining its efficiency (115 FPS). Additionally, extensive qualitative results on two additional public datasets are presented, alongside with limitations in the evaluation metrics used by recent works for lane detection. Finally, we provide source code and trained models that allow others to replicate all the results shown in this paper, which is surprisingly rare in state-of-the-art lane detection methods.

Companies created for money-laundering or as a means for taxevasion are harmful to the country's economy and society. This problem is usually tackled by governmental agencies by having officials to pore over companies' financial data and to single out those that exhibit fraudulent behavior. Such work tends to be slow-paced and tedious. This paper proposes a machine learning-based system capable of classifying whether a company is likely to be involved in fraud or not. Based on financial and tax data from various companies, four different classifiers – k-Nearest Neighbors, Random Forest, Support Vector Machine (SVM), and a Neural Network – were trained and then used to indicate fraud. The best-performing model achieved a macro-averaged F1-score of 92.98% with the Random Forest.

Natural Language Processing (NLP) has been receiving increasing attention in the past few years. In part, this is related to the huge flow of data being made available everyday on the internet, which increased the need for automatic tools capable of analyzing and extracting relevant information, especially from the text. In this context, text classification became one of the most studied tasks on the NLP domain. The objective is to assign predefined categories or labels to text or sentences. Important applications include sentence classification, sentiment analysis, spam detection, among many others. This work proposes an automatic system for product categorization using only their titles. The proposed system employs a state-of-the-art deep neural network as a tool to extract features from the titles to be used as input in different machine learning models. The system is evaluated in the large-scale Mercado Libre dataset, which has the common characteristics of real-world problems such as imbalanced classes, unreliable labels, besides having a large number of samples: 20,000,000 in total. The results showed that the proposed system was able to correctly categorize the products with a balanced accuracy of 86.57% on the local test split of the Mercado Libre dataset. It also surpassed the fourth place on the public rank of the MeLi Data Challenge with 91.19% of balanced accuracy, which represents less than 1% of the difference to the winner.

The reconstruction of shredded documents consists in arranging the pieces of paper (shreds) in order to reassemble the original aspect of such documents. This task is particularly relevant for supporting forensic investigation as documents may contain criminal evidence. As an alternative to the laborious and time-consuming manual process, several researchers have been investigating ways to perform automatic digital reconstruction. A central problem in automatic reconstruction of shredded documents is the pairwise compatibility evaluation of the shreds, notably for binary text documents. In this context, deep learning has enabled great progress for accurate reconstructions in the domain of mechanically-shredded documents. A sensitive issue, however, is that current deep model solutions require an inference whenever a pair of shreds has to be evaluated. This work proposes a scalable deep learning approach for measuring pairwise compatibility in which the number of inferences scales linearly (rather than quadratically) with the number of shreds. Instead of predicting compatibility directly, deep models are leveraged to asymmetrically project the raw shred content onto a common metric space in which distance is proportional to the compatibility. Experimental results show that our method has accuracy comparable to the state-of-the-art with a speed-up of about 22 times for a test instance with 505 shreds (20 mixed shredded-pages from different documents).

We propose an image-based real-time path planner for the self-driving car IARA, named DeepPath. DeepPath uses a CNN for inferring paths from images. During the self-driving car operation, DeepPath receives an image and the current car pose. Then, it sends the image to a CNN trained to infer a model of the path. After that, DeepPath generates the path in the IARA's coordinate system using the path model. Subsequently, given the current IARA's pose, DeepPath transforms each pose of the path in the IARA's coordinate system into another pose in the world coordinate system. Finally, it sends the path to the IARA's Behavior Selector subsystem, the next subsystem in the IARA's Decision-Making system. We evaluated the performance of DeepPath in real world scenarios. Our results showed that DeepPath is able to correctly generate paths for IARA that differ only slightly from those defined by humans.

•Paper shreds matching via self-supervised deep learning.•Training with simulated cuts is effective for real-shredded documents.•A new public dataset with 100 strip-shredded documents (2292 shreds).•Accurate (over 90% accuracy) reconstruction of 100 mixed shredded documents.

In general, proposed solutions for LiDAR-based localization used in autonomous cars require expensive sensors and computationally expensive mapping processes. Moreover, the global localization for autonomous driving is converging to the use of maps. Straightforward strategies to reduce the costs are to produce simpler sensors and use maps already available on the Internet. Here, an analysis is presented to show how simple can a LiDAR sensor be without degrading the localization accuracy that uses road and satellite maps together to globally pose the car. Three characteristics of the sensor are evaluated: the number of range readings, the amount of noise in the LiDAR readings, and the frame rate, with the aim of finding the minimum number of LiDAR lines, the maximum acceptable noise and the sensor frame rate needed to obtain an accurate position estimation. The analysis is performed using an autonomous car in complex field scenarios equipped with a 3D LiDAR Velodyne HDL-32E. Several experiments were conducted reducing the number of frames, the number of scans per 3D point-cloud and artificially adding up to 15% of error in the ray length. Among other results, we found that using only 4 vertical lines per scan and with an artificial error added up to 15% of the ray length, the car was capable to localize itself within 2.11 meters error average. All experimental results and the followed methodology are explained in detail herein.

Autonomous terrestrial vehicles must be capable of perceiving traffic lights and recognizing their current states to share the streets with human drivers. Most of the time, human drivers can easily identify the relevant traffic lights. To deal with this issue, a common solution for autonomous cars is to integrate recognition with prior maps. However, additional solution is required for the detection and recognition of the traffic light. Deep learning techniques have showed great performance and power of generalization including traffic related problems. Motivated by the advances in deep learning, some recent works leveraged some state-of-the-art deep detectors to locate (and further recognize) traffic lights from 2D camera images. However, none of them combine the power of the deep learning-based detectors with prior maps to recognize the state of the relevant traffic lights. Based on that, this work proposes to integrate the power of deep learning-based detection with the prior maps used by our car platform IARA (acronym for Intelligent Autonomous Robotic Automobile) to recognize the relevant traffic lights of predefined routes. The process is divided in two phases: an offline phase for map construction and traffic lights annotation; and an online phase for traffic light recognition and identification of the relevant ones. The proposed system was evaluated on five test cases (routes) in the city of Vitória, each case being composed of a video sequence and a prior map with the relevant traffic lights for the route. Results showed that the proposed technique is able to correctly identify the relevant traffic light along the trajectory.