This thesis is part of a CIFRE agreement between the company Othello and the LIASD laboratory. The objective is to develop an artificial intelligence system that can detect real-time dangers in a video stream. To achieve this, a novel approach combining temporal and spatial analysis has been proposed. Several avenues have been explored to improve anomaly detection by integrating object detection, human pose detection, and motion analysis. For result interpretability, techniques commonly used for image analysis, such as activation and saliency maps, have been extended to videos, and an original method has been proposed. The proposed architecture performs binary or multiclass classification depending on whether an alert or the cause needs to be identified. Numerous neural networkmodels have been tested, and three of them have been selected. You Only Looks Once (YOLO) has been used for spatial analysis, a Convolutional Recurrent Neuronal Network (CRNN) composed of VGG19 and a Gated Recurrent Unit (GRU) for temporal analysis, and a multi-layer perceptron for classification. These models handle different types of data and can be combined in parallel or in series. Although the parallel mode is faster, the serial mode is generally more reliable. For training these models, supervised learning was chosen, and two proprietary datasets were created. The first dataset focuses on objects that may play a potential role in anomalies, while the second consists of videos containing anomalies or non-anomalies. This approach allows for the processing of both continuous video streams and finite videos, providing greater flexibility in detection.

With the recent advancements in generative modeling, the realism of deepfake content has been increasing at a steady pace, even reaching the point where people often fail to detect manipulated media content online, thus being deceived into various kinds of scams. In this paper, we survey deepfake generation and detection techniques, including the most recent developments in the field, such as diffusion models and Neural Radiance Fields. Our literature review covers all deepfake media types, comprising image, video, audio and multimodal (audio-visual) content. We identify various kinds of deepfakes, according to the procedure used to alter or generate the fake content. We further construct a taxonomy of deepfake generation and detection methods, illustrating the important groups of methods and the domains where these methods are applied. Next, we gather datasets used for deepfake detection and provide updated rankings of the best performing deepfake detectors on the most popular datasets. In addition, we develop a novel multimodal benchmark to evaluate deepfake detectors on out-of-distribution content. The results indicate that state-of-the-art detectors fail to generalize to deepfake content generated by unseen deepfake generators. Finally, we propose future directions to obtain robust and powerful deepfake detectors. Our project page and new benchmark are available at https://github.com/CroitoruAlin/biodeep.

With the rise of online education platforms, there is a growing abundance of educational content across various domain. It can be difficult to navigate the numerous available resources to find the most suitable training, especially in domains that include many interconnected areas, such as ICT. In this study, we propose a domain-specific chatbot application that requires limited resources, utilizing versions of the Phi language model to help learners with educational content. In the proposed method, Phi-2 and Phi-3 models were fine-tuned using QLoRA. The data required for fine-tuning was obtained from the Huawei Talent Platform, where courses are available at different levels of expertise in the field of computer science. RAG system was used to support the model, which was fine-tuned by 500 Q&A pairs. Additionally, a total of 420 Q&A pairs of content were extracted from different formats such as JSON, PPT, and DOC to create a vector database to be used in the RAG system. By using the fine-tuned model and RAG approach together, chatbots with different competencies were obtained. The questions and answers asked to the generated chatbots were saved separately and evaluated using ROUGE, BERTScore, METEOR, and BLEU metrics. The precision value of the Phi-2 model supported by RAG was 0.84 and the F1 score was 0.82. In addition to a total of 13 different evaluation metrics in 4 different categories, the answers of each model were compared with the created content and the most appropriate method was selected for real-life applications.

The abundance of complex and interconnected healthcare data offers numerous opportunities to improve prediction, diagnosis, and treatment. Graph-structured data, which includes entities and their relationships, is well-suited for capturing complex connections. Effectively utilizing this data often requires strong and efficient learning algorithms, especially when dealing with limited labeled data. It is increasingly important for downstream tasks in various domains to utilize self-supervised learning (SSL) as a paradigm for learning and optimizing effective representations from unlabeled data. In this paper, we thoroughly review SSL approaches specifically designed for graph-structured data in healthcare applications. We explore the challenges and opportunities associated with healthcare data and assess the effectiveness of SSL techniques in real-world healthcare applications. Our discussion encompasses various healthcare settings, such as disease prediction, medical image analysis, and drug discovery. We critically evaluate the performance of different SSL methods across these tasks, highlighting their strengths, limitations, and potential future research directions. Ultimately, this review aims to be a valuable resource for both researchers and practitioners looking to utilize SSL for graph-structured data in healthcare, paving the way for improved outcomes and insights in this critical field. To the best of our knowledge, this work represents the first comprehensive review of the literature on SSL applied to graph data in healthcare.

In recent years, labor shortages due to the declining birthrate and aging population have become significant challenges at construction sites in developed countries, including Japan. To address these challenges, we are developing an open platform called ROS2-TMS for Construction, a Cyber-Physical System (CPS) for construction sites, to achieve both efficiency and safety in earthwork operations. In ROS2-TMS for Construction, the system comprehensively collects and stores environmental information from sensors placed throughout the construction site. Based on these data, a real-time virtual construction site is created in cyberspace. Then, based on the state of construction machinery and environmental conditions in cyberspace, the optimal next actions for actual construction machinery are determined, and the construction machinery is operated accordingly. In this project, we decided to use the Open Platform for Earthwork with Robotics and Autonomy (OPERA), developed by the Public Works Research Institute (PWRI) in Japan, to control construction machinery from ROS2-TMS for Construction with an originally extended behavior tree. In this study, we present an overview of OPERA, focusing on the newly developed navigation package for operating the crawler dump, as well as the overall structure of ROS2-TMS for Construction as a Cyber-Physical System (CPS). Additionally, we conducted experiments using a crawler dump and a backhoe to verify the aforementioned functionalities.

Knowledge-augmented learning enables the combination of knowledge-based and data-driven approaches. For anomaly detection and diagnosis, understandability is typically an important factor, especially in high-risk areas. Therefore, explainability and interpretability are also major criteria in such contexts. This chapter focuses on knowledge-augmented explainable and interpretable learning to enhance understandability, transparency and ultimately computational sensemaking. We exemplify different approaches and methods in the domains of anomaly detection and diagnosis - from comparatively simple interpretable methods towards more advanced neuro-symbolic approaches.

This short paper gives an overview of the XCSP3 solver implemented in Picat. Picat provides several constraint modules, and the Picat XCSP3 solver uses the sat module. The XCSP3 solver mainly consists of a parser implemented in Picat, which converts constraints from XCSP3 format to Picat. The solver demonstrates the strengths of Picat, a logic-based language, in parsing, modeling, and encoding constraints into SAT. The high performance of the solver in recent XCSP competitions demonstrates the viability of using a SAT solver to solve general constraint satisfaction and optimization problems.

In-Context Learning (ICL) enables Large Language Models (LLMs) to perform new tasks by conditioning on prompts with relevant information. Retrieval-Augmented Generation (RAG) enhances ICL by incorporating retrieved documents into the LLM's context at query time. However, traditional retrieval methods focus on semantic relevance, treating retrieval as a search problem. In this paper, we propose reframing retrieval for ICL as a recommendation problem, aiming to select documents that maximize utility in ICL tasks. We introduce the In-Context Learning Embedding and Reranker Benchmark (ICLERB), a novel evaluation framework that compares retrievers based on their ability to enhance LLM accuracy in ICL settings. Additionally, we propose a novel Reinforcement Learning-to-Rank from AI Feedback (RLRAIF) algorithm, designed to fine-tune retrieval models using minimal feedback from the LLM. Our experimental results reveal notable differences between ICLERB and existing benchmarks, and demonstrate that small models fine-tuned with our RLRAIF algorithm outperform large state-of-the-art retrieval models. These findings highlight the limitations of existing evaluation methods and the need for specialized benchmarks and training strategies adapted to ICL.

The expanding influence of social media platforms over the past decade has impacted the way people communicate. The level of obscurity provided by social media and easy accessibility of the internet has facilitated the spread of hate speech. The terms and expressions related to hate speech gets updated with changing times which poses an obstacle to policy-makers and researchers in case of hate speech identification. With growing number of individuals using their native languages to communicate with each other, hate speech in these low-resource languages are also growing. Although, there is awareness about the English-related approaches, much attention have not been provided to these low-resource languages due to lack of datasets and online available data. This article provides a detailed survey of hate speech detection in low-resource languages around the world with details of available datasets, features utilized and techniques used. This survey further discusses the prevailing surveys, overlapping concepts related to hate speech, research challenges and opportunities.

The introduction of Transformers in 2017 reshaped the landscape of deep learning. Originally proposed for sequence modelling, Transformers have since achieved widespread success across various domains. However, the scalability limitations of Transformers - particularly with respect to sequence length - have sparked renewed interest in novel recurrent models that are parallelizable during training, offer comparable performance, and scale more effectively. In this work, we revisit sequence modelling from a historical perspective, focusing on Recurrent Neural Networks (RNNs), which dominated the field for two decades before the rise of Transformers. Specifically, we examine LSTMs (1997) and GRUs (2014). We demonstrate that by simplifying these models, we can derive minimal versions (minLSTMs and minGRUs) that (1) use fewer parameters than their traditional counterparts, (2) are fully parallelizable during training, and (3) achieve surprisingly competitive performance on a range of tasks, rivalling recent models including Transformers.