Search Results (910)

UML (Unified Modeling Language) diagrams are graphical representations used in software engineering which play a vital role in the design and development of software systems and various engineering processes. Large, good-quality datasets containing UML diagrams are essential for different areas in the industry, research, and teaching purposes; however, few exist in the literature and it is common to find duplicate elements in the existing datasets. This might affect the evaluation of the models obtained when using these datasets. This paper addresses the challenge of creating a ground truth dataset of UML diagrams, including semi-automated inspection to remove duplicates and ensuring the correct labeling of all UML diagrams contained in the dataset. In particular, a dataset of six UML diagram classes was assembled, comprising a total of 2626 images (426 activity diagrams, 636 class diagrams, 352 component diagrams, 357 deployment diagrams, 435 sequence diagrams, and 420 use case diagrams). Importantly, unlike other existing datasets, ours contains no duplicate elements and all diagrams are correctly labeled. Our curated dataset is a valuable and unique resource for the research community, serving as a foundation for training and evaluating diverse artificial intelligence models. In this paper, we demonstrate this by training and testing several deep learning models using our dataset, achieving highly satisfactory results compared to those presented in other works in the literature. Additionally, our experimental results highlight the potential of visual transformers for UML diagram classification, setting our approach apart from others that predominantly used convolutional neural networks for similar tasks. Full article

Ecological importance evaluation can clearly identify the ecological service functions and ecological values of a region. This paper takes the Yanshan-Taihang Mountain area in Hebei Province as the research area, utilizing 2020 land use data. With the help of various analytical models and GIS spatial analysis methods, this paper selects water conservation, soil and water conservation, biodiversity, carbon sequestration and oxygen release to evaluate the importance of ecosystem services, and selects soil and water loss sensitivity and land desertification sensitivity to evaluate the ecological sensitivity, so as to identify the important areas of ecological protection in the study area, analyze their spatial change characteristics and divide the leading ecological functions according to the results. The results show that the moderately important and highly important areas in the Yanshan-Taihang region of Hebei Province account for more than 70% of the total study area. Based on the importance evaluation results, three types of dominant ecological function zones were obtained using self-organized feature mapping neural network analysis in the R language, and control measures were proposed. The research results can provide strategic support for local ecological protection and regional ecological restoration, as well as serving as a reference for the optimization of land spatial development patterns. Full article

Commonsense question answering (CSQA) is a challenging task in the field of knowledge graph question answering. It combines the context of the question with the relevant knowledge in the knowledge graph to reason and give an answer to the question. Existing CSQA models combine pretrained language models and graph neural networks to process question context and knowledge graph information, respectively, and obtain each other’s information during the reasoning process to improve the accuracy of reasoning. However, the existing models do not fully utilize the textual representation and graph representation after reasoning to reason about the answer, and they do not give enough semantic representation to the edges during the reasoning process of the knowledge graph. Therefore, we propose a novel parallel fusion framework for text and knowledge graphs, using the fused global graph information to enhance the semantic information of reasoning answers. In addition, we enhance the relationship embedding by enriching the initial semantics and adjusting the initial weight distribution, thereby improving the reasoning ability of the graph neural network. We conducted experiments on two public datasets, CommonsenseQA and OpenBookQA, and found that our model is competitive when compared with other baseline models. Additionally, we validated the generalizability of our model on the MedQA-USMLE dataset. Full article

The widespread reuse of code in the open-source community has led to the proliferation of homologous vulnerabilities, which are security flaws propagated across diverse software systems through the reuse of vulnerable code. Such vulnerabilities pose serious cybersecurity risks, as attackers can exploit the same weaknesses across multiple platforms. Deep learning has emerged as a promising approach for detecting homologous vulnerabilities in binary code due to their automated feature extraction and high efficiency. However, existing deep learning methods often struggle to capture deep semantic features in binary code, limiting their effectiveness. To address this limitation, this paper presents GMN+, which is a novel graph matching neural network with enhanced attention for detecting homologous vulnerabilities. This method comprehensively considers the information contained in instructions and incorporates types of input instruction. Masked Language Modeling and Instruction Type Prediction are developed as pre-training tasks to enhance the ability of GMN+ in extracting semantic information from basic blocks. GMN+ utilizes an attention mechanism to focus concurrently on the critical semantic information within functions and differences between them, generating robust function embeddings. Experimental results indicate that GMN+ outperforms state-of-the-art methods in various tasks and achieves notable performance in real-world vulnerability detection scenarios. Full article

Recurrent neural networks (RNNs) have produced significant results in many fields, such as natural language processing and speech recognition. Owing to their computational complexity and sequence dependencies, RNNs need to be deployed on customized hardware accelerators to satisfy performance and energy-efficiency constraints. However, designing hardware accelerators for RNNs is challenged by the vast design space and the reliance on ineffective optimization. An efficient automated design space exploration (DSE) strategy that can balance conflicting objectives is wanted. To address the low efficiency and insufficient universality of the resource allocation process employed for hardware accelerators, we propose an automated two-stage design space exploration (DSE) strategy for customized RNN accelerators. The strategy combines a genetic algorithm (GA) and a reinforcement learning (RL) algorithm, and it utilizes symmetrical exploration and exploitation to find the optimal solutions. In the first stage, the area of the hardware accelerator is taken as the optimization objective, and the GA is used for partial exploration purposes to narrow the design space while maintaining diversity. Then, the latency and power of the hardware accelerator are taken as the optimization objectives, and the RL algorithm is used in the second stage to find the corresponding Pareto solutions. To verify the effectiveness of the developed strategy, it is compared with other algorithms. We use three different network models as benchmarks: a vanilla RNN, LSTM, and a GRU. The results demonstrate that the strategy proposed in this paper can provide better solutions and can achieve latency, power, and area reductions of 9.35%, 5.34%, and 11.95%, respectively. The HV of GRMD is reduced by averages of 6.33%, 6.32%, and 0.67%, and the runtime is reduced by averages of 18.11%, 14.94%, and 10.28%, respectively. Additionally, given different weights, it can make reasonable trade-offs between multiple objectives. Full article

In a recent study, I demonstrated that large numbers of L2 (second language) speakers do not appear to influence the morphological or information-theoretic complexity of natural languages. This paper has three primary aims: First, I address recent criticisms of my analyses, showing that the points raised by my critics were already explicitly considered and analysed in my original work. Furthermore, I show that the proposed alternative analyses fail to withstand detailed examination. Second, I introduce new data on the information-theoretic complexity of natural languages, with the estimates derived from various language models—ranging from simple statistical models to advanced neural networks—based on a database of 40 multilingual text collections that represent a wide range of text types. Third, I re-analyse the information-theoretic and morphological complexity data using novel methods that better account for model uncertainty in parameter estimation, as well as the genealogical relatedness and geographic proximity of languages. In line with my earlier findings, the results show no evidence that large numbers of L2 speakers have an effect on natural language complexity. Full article

The complexities inherent in drug development are multi-faceted and often hamper accuracy, speed and efficiency, thereby limiting success. This review explores how recent developments in machine learning (ML) are significantly impacting target-based drug discovery, particularly in small-molecule approaches. The Simplified Molecular Input Line Entry System (SMILES), which translates a chemical compound’s three-dimensional structure into a string of symbols, is now widely used in drug design, mining, and repurposing. Utilizing ML and natural language processing techniques, SMILES has revolutionized lead identification, high-throughput screening and virtual screening. ML models enhance the accuracy of predicting binding affinity and selectivity, reducing the need for extensive experimental screening. Additionally, deep learning, with its strengths in analyzing spatial and sequential data through convolutional neural networks (CNNs) and recurrent neural networks (RNNs), shows promise for virtual screening, target identification, and de novo drug design. Fragment-based approaches also benefit from ML algorithms and techniques like generative adversarial networks (GANs), which predict fragment properties and binding affinities, aiding in hit selection and design optimization. Structure-based drug design, which relies on high-resolution protein structures, leverages ML models for accurate predictions of binding interactions. While challenges such as interpretability and data quality remain, ML’s transformative impact accelerates target-based drug discovery, increasing efficiency and innovation. Its potential to deliver new and improved treatments for various diseases is significant. Full article

Deep learning has made significant strides, driving advances in areas like computer vision, natural language processing, and autonomous systems. In this paper, we further investigate the implications of the role of additive shortcut connections, focusing on models such as ResNet, Vision Transformers (ViTs), and MLP-Mixers, given that they are essential in enabling efficient information flow and mitigating optimization challenges such as vanishing gradients. In particular, capitalizing on our recent information bottleneck approach, we analyze how additive shortcuts influence the fitting and compression phases of training, crucial for generalization. We leverage Z-X and Z-Y measures as practical alternatives to mutual information for observing these dynamics in high-dimensional spaces. Our empirical results demonstrate that models with identity shortcuts (ISs) often skip the initial fitting phase and move directly into the compression phase, while non-identity shortcut (NIS) models follow the conventional two-phase process. Furthermore, we explore how IS models are still able to compress effectively, maintaining their generalization capacity despite bypassing the early fitting stages. These findings offer new insights into the dynamics of shortcut connections in neural networks, contributing to the optimization of modern deep learning architectures. Full article

The proliferation of deep learning has transformed artificial intelligence, demonstrating prowess in domains such as image recognition, natural language processing, and robotics. Nonetheless, deep learning models are susceptible to adversarial examples, well-crafted inputs that can induce erroneous predictions, particularly in safety-critical contexts. Researchers actively pursue countermeasures such as adversarial training and robust optimization to fortify model resilience. This vulnerability is notably accentuated by the ubiquitous utilization of ReLU functions in deep learning models. A previous study proposed an innovative solution to mitigate this vulnerability, presenting a capped ReLU function tailored to bolster neural network robustness against adversarial examples. However, the approach had a scalability problem. To address this limitation, a series of comprehensive experiments are undertaken across diverse datasets, and we introduce the dynamic-max-value ReLU function to address the scalability problem. Full article

Recent studies have shown that, due to redundancy, some heads of the Transformer model can be pruned without diminishing the efficiency of the model. In this paper, we propose a constrained optimization algorithm based on Hebbian learning, which trains specific layers in the Transformer architecture in order to enforce diversification between the different heads in the multi-head attention module. The diversification of the heads is achieved through a single-layer feed-forward neural network that is added to the Transformer architecture and is trained with the proposed algorithm. We utilize the algorithm in three different architectural variations of the baseline Transformer model. In addition to the diversification of the heads, the proposed methodology can be used to prune the heads that capture redundant information. Experiments on diverse NLP tasks, including machine translation, text summarization, question answering and large language modeling, show that our proposed approach consistently improves the performance of baseline Transformer models. Full article

This paper presents a comparative study on license plate detection and recognition algorithms in unconstrained environments, which include varying illuminations, nonstandard plate templates, and different English language fonts. A prime objective of this study is to assess how well these models handle such challenges. These problems are common in developing countries like Pakistan where diverse license plates, styles, and abrupt changes in illuminations make license plates detection and recognition a challenging task. To analyze the license plate detection problem Faster-RCNN and end-to-end (E2E) methods are implemented. For the license plate recognition task, deep neural network and the CA-CenterNet-based methods are compared. Detailed simulations were performed on authors’ own collected dataset of Pakistani license plates, which contains substantially different multi-styled license plates. Our study concludes that, for the task of license plate detection, Faster-RCNN yields a detection accuracy of 98.35%, while the E2E method delivers 98.48% accuracy. Both detection algorithms yielded a mean detection accuracy of 98.41%. For license plate recognition task, the DNN-based method yielded a recognition accuracy of 98.90%, while the CA-CenterNet-based method delivered a high accuracy of 98.96%. In addition, a detailed computational complexity comparison on various image resolutions revealed that E2E and the CA-CenterNet are more efficient than their counterparts during detection and recognition tasks, respectively. Full article

The text-to-SQL task aims to convert natural language questions into corresponding SQL queries based on a given database schema. Previous models that rely on graph neural networks often struggle to accurately capture the complex grammatical relationships present in these questions, leading to poor performance when generating queries for longer requests. To address these challenges, we propose RGISQL, which integrates refined grammatical information extracted from the question and employs segmentation processing to effectively manage long queries. Additionally, RGISQL minimizes the complexity of edge embeddings by reducing the coupling within graph neural networks. By utilizing grammatical dependency trees, RGISQL is better equipped to capture the inherent structure and grammatical rules of questions. This refined grammatical information offers additional contextual and semantic cues for the model, thereby enhancing both its generalizability and interpretability. Furthermore, we dynamically assess the importance of different edges based on the graph structure, which helps reduce the coupling of edge embeddings and further improves the model’s performance. Multiple sets of experiments conducted on the Spider and Spider-Syn datasets demonstrate that RGISQL outperforms other baselines, achieving the best results in both datasets. Full article

The integration of artificial intelligence, particularly Large Language Models (LLMs), has the potential to significantly enhance therapeutic decision-making in clinical oncology. Initial studies across various disciplines have demonstrated that LLM-based treatment recommendations can rival those of multidisciplinary tumor boards (MTBs); however, such data are currently lacking for urological cancers. This preparatory study establishes a robust methodological foundation for the forthcoming CONCORDIA trial, including the validation of the System Causability Scale (SCS) and its modified version (mSCS), as well as the selection of LLMs for urological cancer treatment recommendations based on recommendations from ChatGPT-4 and an MTB for 40 urological cancer scenarios. Both scales demonstrated strong validity, reliability (all aggregated Cohen’s K > 0.74), and internal consistency (all Cronbach’s Alpha > 0.9), with the mSCS showing superior reliability, internal consistency, and clinical applicability (p < 0.01). Two Delphi processes were used to define the LLMs to be tested in the CONCORDIA study (ChatGPT-4 and Claude 3.5 Sonnet) and to establish the acceptable non-inferiority margin for LLM recommendations compared to MTB recommendations. The forthcoming ethics-approved and registered CONCORDIA non-inferiority trial will require 110 urological cancer scenarios, with an mSCS difference threshold of 0.15, a Bonferroni corrected alpha of 0.025, and a beta of 0.1. Blinded mSCS assessments of MTB recommendations will then be compared to those of the LLMs. In summary, this work establishes the necessary prerequisites prior to initiating the CONCORDIA study and validates a modified score with high applicability and reliability for this and future trials. Full article

Human Activity Recognition (HAR) is an essential area of research in Artificial Intelligence and Machine Learning, with numerous applications in healthcare, sports science, and smart environments. While several advancements in the field, such as attention-based models and Graph Neural Networks, have made great strides, this work focuses on data augmentation methods that tackle issues like data scarcity and task variability in HAR. In this work, we investigate and expand the use of mixup and cutout data augmentation methods to sensor-based and skeleton-based HAR datasets. These methods were first widely used in Computer Vision and Natural Language Processing. We use both augmentation techniques, customized for time-series and skeletal data, to improve the robustness and performance of HAR models by diversifying the data and overcoming the drawbacks of having limited training data. Specifically, we customize mixup data augmentation for sensor-based datasets and cutout data augmentation for skeleton-based datasets with the goal of improving model accuracy without adding more data. Our results show that using mixup and cutout techniques improves the accuracy and generalization of activity recognition models on both sensor-based and skeleton-based human activity datasets. This work showcases the potential of data augmentation techniques on transformers and Graph Neural Networks by offering a novel method for enhancing time series and skeletal HAR tasks. Full article

In the prokaryotic kingdom, protein phosphorylation serves as one of the most important posttranslational modifications (PTMs) and is involved in orchestrating a broad spectrum of biological processes. Here, we report an updated online server named the group-based prediction system for prokaryotic phosphorylation language model (GPS-pPLM), used for predicting phosphorylation sites (p-sites) in prokaryotes. For model training, two deep learning methods, a transformer and a deep neural network, were employed, and a total of 10 sequence features and contextual features were integrated. Using 44,839 nonredundant p-sites in 16,041 proteins from 95 prokaryotes, two general models for the prediction of O-phosphorylation and N-phosphorylation were first pretrained and then fine-tuned to construct 6 predictors specific for each phosphorylatable residue type as well as 134 species-specific predictors. Compared with other existing tools, the GPS-pPLM exhibits higher accuracy in predicting prokaryotic O-phosphorylation p-sites. Protein sequences in FASTA format or UniProt accession numbers can be submitted by users, and the predicted results are displayed in tabular form. In addition, we annotate the predicted p-sites with knowledge from 22 public resources, including experimental evidence, 3D structures, and disorder tendencies. The online service of the GPS-pPLM is freely accessible for academic research. Full article