Search Results (61)

In complex dynamic environments, the performance of SLAM systems on bionic robots is susceptible to interference from dynamic objects or structural changes in the environment. To address this problem, we propose a semantic visual SLAM (vSLAM) algorithm based on loop closure detection with combinatorial graph entropy. First, in terms of the dynamic feature detection results of YOLOv8-seg, the feature points at the edges of the dynamic object are finely judged by calculating the mean absolute deviation (MAD) of the depth of the pixel points. Then, a high-quality keyframe selection strategy is constructed by combining the semantic information, the average coordinates of the semantic objects, and the degree of variation in the dense region of feature points. Subsequently, the unweighted and weighted graphs of keyframes are constructed according to the distribution of feature points, characterization points, and semantic information, and then a high-performance loop closure detection method based on combinatorial graph entropy is developed. The experimental results show that our loop closure detection approach exhibits higher precision and recall in real scenes compared to the bag-of-words (BoW) model. Compared with ORB-SLAM2, the absolute trajectory accuracy in high-dynamic sequences improved by an average of 97.01%, while the number of extracted keyframes decreased by an average of 61.20%. Full article

The autonomous positioning of drone-based remote sensing plays an important role in navigation in urban environments. Due to GNSS (Global Navigation Satellite System) signal occlusion, obtaining precise drone locations is still a challenging issue. Inspired by vision-based positioning methods, we proposed an autonomous positioning method based on multi-view reference images rendered from the scene’s 3D geometric mesh and apply a bag-of-words (BoW) image retrieval pipeline to achieve efficient and scalable positioning, without utilizing deep learning-based retrieval or 3D point cloud registration. To minimize the number of reference images, scene coverage quantification and optimization are employed to generate the optimal viewpoints. The proposed method jointly exploits a visual-bag-of-words tree to accelerate reference image retrieval and improve retrieval accuracy, and the Perspective-n-Point (PnP) algorithm is utilized to obtain the drone’s pose. Experiments are conducted in urban real-word scenarios and the results show that positioning errors are decreased, with accuracy ranging from sub-meter to 5 m and an average latency of 0.7–1.3 s; this indicates that our method significantly improves accuracy and latency, offering robust, real-time performance over extensive areas without relying on GNSS or dense point clouds. Full article

Compilers play a crucial role in software development, as most software must be compiled into binaries before release. Analyzing the compiler version from binary files is of great importance in software reverse engineering, maintenance, traceability, and information security. In this work, we propose a novel framework for compiler version identification. Firstly, we generated 1000 C language source codes using CSmith and subsequently compiled them into 16,000 binary files using 16 distinct versions of compilers. The symmetric distribution of the dataset among different compiler versions may ensure unbiased model training. Then, IDA Pro was used to decompile the binary files into assembly instruction sequences. From these sequences, we extracted frequency-based features via the Bag-of-Words (BOW) model and sequence-based features derived from the grey-level co-occurrence matrix (GLCM). Finally, we introduced a divide-and-conquer framework (DIANA-SVM) to effectively classify compiler versions. The experimental results demonstrate that traditional Support Vector Machine (SVM) models struggle to accurately identify compiler versions using compiled executable files. In contrast, DIANA-SVM’s symmetric data separation approach enhances performance, achieving an accuracy of 94% (±0.375%). This framework enables precise identification of high-risk compiler versions, offering a reliable tool for software supply chain security. Theoretically, our GLCM-based sequence modeling and divide-and-conquer framework advance feature extraction methodologies for binary files, offering a scalable solution for similar classification tasks beyond compiler identification. Full article

Sentiment analysis is a crucial component of text mining and natural language processing (NLP), involving the evaluation and classification of text data based on its emotional tone, typically categorized as positive, negative, or neutral. While significant research has focused on structured languages like English, unstructured languages, such as the Moroccan Dialect (MD), face substantial resource limitations and linguistic challenges, making effective sentiment analysis difficult. This study addresses this gap by exploring the integration of data-balancing techniques with machine learning (ML) methods, specifically investigating the impact of resampling techniques and feature extraction methods, including Term Frequency–Inverse Document Frequency (TF-IDF), Bag of Words (BOW), and N-grams. Through rigorous experimentation, we evaluate the effectiveness of these approaches in enhancing sentiment analysis accuracy for the Moroccan dialect. Our findings demonstrate that strategic resampling, combined with the TF-IDF method, significantly improves classification accuracy and robustness. We also explore the interaction between resampling strategies and feature extraction methods, revealing varying levels of effectiveness across different combinations. Notably, the Support Vector Machine (SVM) classifier, when paired with TF-IDF representation, achieves superior performance, with an accuracy of 90.24% and a precision of 90.34%. These results highlight the importance of tailored resampling techniques, appropriate feature extraction methods, and machine learning optimization in advancing sentiment analysis for under-resourced and dialect-heavy languages like the Moroccan dialect, providing a practical framework for future research and development in NLP for unstructured languages. Full article

The loop closure detection (LCD) methods in Unmanned Aerial Vehicle (UAV) Visual Inertial Navigation System (VINS) are often affected by issues such as insufficient image texture information and limited observational perspectives, resulting in constrained UAV positioning accuracy and reduced capability to perform complex tasks. This study proposes a Bag-of-Words (BoW) LCD method based on Neural Radiance Field (NeRF), which estimates camera poses from existing images and achieves rapid scene reconstruction through NeRF. A method is designed to select virtual viewpoints and render images along the flight trajectory using a specific sampling approach to expand the limited observational angles, mitigating the impact of image blur and insufficient texture information at specific viewpoints while enlarging the loop closure candidate frames to improve the accuracy and success rate of LCD. Additionally, a BoW vector construction method that incorporates the importance of similar visual words and an adapted virtual image filtering and comprehensive scoring calculation method are designed to determine loop closures. Applied to VINS-Mono and ORB-SLAM3, and compared with the advanced BoW model LCDs of the two systems, results indicate that the NeRF-based BoW LCD method can detect more than 48% additional accurate loop closures, while the system’s navigation positioning error mean is reduced by over 46%, validating the effectiveness and superiority of the proposed method and demonstrating its significant importance for improving the navigation accuracy of VINS. Full article

Stemming vulnerabilities out of a smart contract prior to its deployment is essential to ensure the security of decentralized applications. As such, numerous tools and machine-learning-based methods have been proposed to help detect vulnerabilities in smart contracts. Furthermore, various ways of encoding the smart contracts for analysis have also been proposed. However, the impact of these input methods has not been systematically studied, which is the primary goal of this paper. In this preliminary study, we experimented with four common types of input, including Word2Vec, FastText, Bag-of-Words (BoW), and Term Frequency–Inverse Document Frequency (TF-IDF). To focus on the comparison of these input types, we used the same deep-learning model, i.e., convolutional neural networks, in all experiments. Using a public dataset, we compared the vulnerability detection performance of the four input types both in the binary classification scenarios and the multiclass classification scenario. Our findings show that TF-IDF is the best overall input type among the four. TF-IDF has excellent detection performance in all scenarios: (1) it has the best F1 score and accuracy in binary classifications for all vulnerability types except for the delegate vulnerability where TF-IDF comes in a close second, and (2) it comes in a very close second behind BoW (within 0.8%) in the multiclass classification. Full article

Sentiment analysis holds great importance within the domain of natural language processing as it examines both the expressed and underlying emotions conveyed through review content. Furthermore, researchers have discovered that relying solely on the overall sentiment derived from the textual content is inadequate. Consequently, sentiment analysis was developed to extract nuanced expressions from textual information. One of the challenges in this field is effectively extracting emotional elements using multi-label data that covers various aspects. This article presents a novel approach called the Ensemble of DenseNet based on Aquila Optimizer (EDAO). EDAO is specifically designed to enhance the precision and diversity of multi-label learners. Unlike traditional multi-label methods, EDAO strongly emphasizes improving model diversity and accuracy in multi-label scenarios. To evaluate the effectiveness of our approach, we conducted experiments on seven distinct datasets, including emotions, hotels, movies, proteins, automobiles, medical, news, and birds. Our initial strategy involves establishing a preprocessing mechanism to obtain precise and refined data. Subsequently, we used the Vader tool with Bag of Words (BoW) for feature extraction. In the third stage, we created word associations using the word2vec method. The improved data were also used to train and test the DenseNet model, which was fine-tuned using the Aquila Optimizer (AO). On the news, emotion, auto, bird, movie, hotel, protein, and medical datasets, utilizing the aspect-based multi-labeling technique, we achieved accuracy rates of 95%, 97%, and 96%, respectively, with DenseNet-AO. Our proposed model demonstrates that EDAO outperforms other standard methods across various multi-label datasets with different dimensions. The implemented strategy has been rigorously validated through experimental results, showcasing its effectiveness compared to existing benchmark approaches. Full article

Multilabel classification of Arabic text is an important task for understanding and analyzing social media content. It can enable the categorization and monitoring of social media posts, the detection of important events, the identification of trending topics, and the gaining of insights into public opinion and sentiment. However, multilabel classification of Arabic contents can present a certain challenge due to the high dimensionality of the representation and the unique characteristics of the Arabic language. In this paper, an effective approach is proposed for Arabic multilabel classification using a metaheuristic Genetic Algorithm (GA) and ensemble learning. The approach explores the effect of Arabic text representation on classification performance using both Bag of Words (BOW) and Term Frequency-Inverse Document Frequency (TF-IDF) methods. Moreover, it compares the performance of ensemble learning methods such as the Extra Trees Classifier (ETC) and Random Forest Classifier (RFC) against a Logistic Regression Classifier (LRC) as a single and ensemble classifier. We evaluate the approach on a new public dataset, namely, the MAWQIF dataset. The MAWQIF is the first multilabel Arabic dataset for target-specific stance detection. The experimental results demonstrate that the proposed approach outperforms the related work on the same dataset, achieving 80.88% for sentiment classification and 68.76% for multilabel tasks in terms of the F1-score metric. In addition, the data augmentation with feature selection improves the F1-score result of the ETC from 65.62% to 68.80%. The study shows the ability of the GA-based feature selection with ensemble learning to improve the classification of multilabel Arabic text. Full article

In the last fifteen years, an immense expansion has been witnessed in mobile app usage and production. The intense competition in the tech sector and also the rapidly and constantly evolving user requirements have led to increased burden on mobile app creators. Nowadays, fulfilling users’ expectations cannot be readily achieved and new and unconventional approaches are needed to permit an interested crowd of users to contribute in the introduction of creative mobile apps. Indeed, users and developers of mobile apps are the most influential candidates to engage in any of the requirements engineering activities. The place where both can best be found is on Twitter, one of the most widely used social media platforms. More interestingly, Twitter is considered as a fertile ground for textual content generated by the crowd that can assist in building robust predictive classification models using machine learning (ML) and natural language processing (NLP) techniques. Therefore, in this study, we have built two classification models that can identify mobile apps users and developers using tweets. A thorough empirical comparison of different feature extraction techniques and machine learning classification algorithms were experimented with to find the best-performing mobile app user and developer classifiers. The results revealed that for mobile app user classification, the highest accuracy achieved was ≈0.86, produced via logistic regression (LR) using Term Frequency Inverse Document Frequency (TF-IDF) with N-gram (unigram, bigram and trigram), and the highest precision was ≈0.86, produced via LR using Bag-of-Words (BOW) with N-gram (unigram and bigram). On the other hand, for mobile app developer classification, the highest accuracy achieved was ≈0.87, produced by random forest (RF) using BOW with N-gram (unigram and bigram), and the highest precision was ≈0.88, produced by multi-layer perception neural network (MLP NN) using BERTweet for feature extraction. According to the results, we believe that the developed classification models are efficient and can assist in identifying mobile app users and developers from tweets. Moreover, we envision that our models can be harnessed as a crowd selection approach for crowdsourcing requirements engineering activities to enhance and design inventive and satisfying mobile apps. Full article

This paper proposes a novel approach for appearance-based loop closure detection using incremental Bag of Words (BoW) with gradient orientation histograms. The presented approach involves dividing and clustering image blocks into local region features and representing them using gradient orientation histograms. To improve the efficiency of the loop closure detection process, the vocabulary Clustering Feature (CF) tree is generated and updated in real time using the Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH) algorithm, which is combined with an inverted index for the efficient selection of candidates and calculation of similarity. Moreover, temporally close and highly similar images are grouped to generate islands, which enhances the accuracy and efficiency of the loop closure detection process. The proposed approach is evaluated on publicly available datasets, and the results demonstrate high recall and precision. Full article

Feature selection and feature extraction have always been of utmost importance owing to their capability to remove redundant and irrelevant features, reduce the vector space size, control the computational time, and improve performance for more accurate classification tasks, especially in text categorization. These feature engineering techniques can further be optimized using optimization algorithms. This paper proposes a similar framework by implementing one such optimization algorithm, Ant Colony Optimization (ACO), incorporating different feature selection and feature extraction techniques on textual and numerical datasets using four machine learning (ML) models: Logistic Regression (LR), K-Nearest Neighbor (KNN), Stochastic Gradient Descent (SGD), and Random Forest (RF). The aim is to show the difference in the results achieved on both datasets with the help of comparative analysis. The proposed feature selection and feature extraction techniques assist in enhancing the performance of the machine learning model. This research article considers numerical and text-based datasets for stroke prediction and detecting hate speech, respectively. The text dataset is prepared by extracting tweets consisting of positive, negative, and neutral sentiments from Twitter API. A maximum improvement in accuracy of 10.07% is observed for Random Forest with the TF-IDF feature extraction technique on the application of ACO. Besides, this study also highlights the limitations of text data that inhibit the performance of machine learning models, justifying the difference of almost 18.43% in accuracy compared to that of numerical data. Full article

Image tracking and retrieval strategies are of vital importance in visual Simultaneous Localization and Mapping (SLAM) systems. For most state-of-the-art systems, hand-crafted features and bag-of-words (BoW) algorithms are the common solutions. Recent research reports the vulnerability of these traditional algorithms in complex environments. To replace these methods, this work proposes HFNet-SLAM, an accurate and real-time monocular SLAM system built on the ORB-SLAM3 framework incorporated with deep convolutional neural networks (CNNs). This work provides a pipeline of feature extraction, keypoint matching, and loop detection fully based on features from CNNs. The performance of this system has been validated on public datasets against other state-of-the-art algorithms. The results reveal that the HFNet-SLAM achieves the lowest errors among systems available in the literature. Notably, the HFNet-SLAM obtains an average accuracy of 2.8 cm in EuRoC dataset in pure visual configuration. Besides, it doubles the accuracy in medium and large environments in TUM-VI dataset compared with ORB-SLAM3. Furthermore, with the optimisation of TensorRT technology, the entire system can run in real-time at 50 FPS. Full article

Sentiment analysis (SA), and emotion detection and recognition from text (EDRT) are recent areas of study that are closely related to each other. Sentiment analysis strives to identify and detect neutral, positive, or negative feelings from text. On the other hand, emotion analysis seeks to identify and distinguish types of feelings such as happiness, surprise, grief, disgust, fear, and anger through the expression of texts. We suggest a four-level strategy in this paper for recommending the best book to users. The levels include semantic network grouping of comparable sentences, sentiment analysis, reviewer clustering, and recommendation system. The semantic network groups comparable sentences at the first level utilizing pre-processed data from reviewer and book datasets using the parts of speech (POS) tagger. In order to extract keywords from the pre-processed data, feature extraction uses the bag of words (BOW) and term frequency-inverse document frequency (TF-IDF) approaches. SA is performed at the second level in two phases: training and testing, employing deep learning methodologies such as convolutional neural networks (CNN)-long short-term memory (LSTM). The results of this level are sent into the third level (clustering), which uses the clustering method to group the reviewers by age, location, and gender. In the last level, the model assessment is carried out with accuracy, precision, recall, sensitivity, specificity, G-mean, and F1-measure. The book suggestion system is designed to provide the highest level of accuracy within a minimum number of epochs when compared to the state-of-the methods, SVM, CNN, ANN, LSTM, and Bi-directional (BI)-LSTM. Full article

Structure from Motion (SfM) for large-scale UAV (Unmanned Aerial Vehicle) images has been widely used in the fields of photogrammetry and computer vision. Its efficiency, however, decreases dramatically as well as with the memory occupation rising steeply due to the explosion of data volume and the iterative BA (bundle adjustment) optimization. In this paper, an efficient SfM solution is proposed to solve the low-efficiency and high memory consumption problems. First, an algorithm is designed to find UAV image match pairs based on a graph-indexed bag-of-words (BoW) model (GIBoW), which treats visual words as vertices and link relations as edges to build a small-world graph structure. The small-world graph structure can be used to search the nearest-neighbor visual word for query features with extremely high efficiency. Reliable UAV image match pairs can effectively improve feature matching efficiency. Second, a central bundle adjustment with object point-wise parallel construction of the Schur complement (PSCBA) is proposed, which is designed as the combination of the LM (Levenberg–Marquardt) algorithm with the preconditioned conjugate gradients (PCG). The PSCBA method can dramatically reduce the memory consumption in both error and normal equations, as well as improve efficiency. Finally, by using four UAV datasets, the effectiveness of the proposed SfM solution is verified through comprehensive analysis and comparison. The experimental results show that compared with Colmap-Bow and Dbow2, the proposed graph index BoW retrieval algorithm improves the efficiency of image match pair selection with an acceleration ratio ranging from 3 to 7. Meanwhile, the parallel-constructed BA optimization algorithm can achieve accurate bundle adjustment results with an acceleration ratio by 2 to 7 times and reduce memory occupation by 2 to 3 times compared with the BA optimization using Ceres solver. For large-scale UAV images, the proposed method is an effective and reliable solution. Full article

Digital media has a massive presence in the modern world, and it significantly impacts kids’ intellectual, cognitive, ethical, and social development. It is nearly impossible to isolate kids from digital media. Therefore, adult content on mobile applications should be avoided by children. Although mobile operating systems provide parental controls, handling such rules is impossible for illiterate people. Consequently, kids may download and use adults’ mobile applications. Mobile applications for adults often publish age group information to distinguish user segments that can be used to automate the downloading process. Sustainable Development Goal (SDG) #4 emphasizes inclusivity and equitability in terms of quality of education and the facilitation of conditions for the promotion of lifelong learning for everyone. The current study can be counted as being in line with SDG#4, as it proposes a machine-learning-based approach to the prediction of the suitability of mobile applications for kids. The approach first leverages natural language processing (NLP) techniques to preprocess user reviews of mobile applications. Second, it performs feature engineering based on the given bag of words (BOW), e.g., abusive words, and constructs a feature vector for each mobile app. Finally, it trains and tests a machine learning algorithm on the given feature vectors. To evaluate the proposed approach, we leverage the 10-fold cross-validation technique. The results of the 10-fold cross-validation indicate that the proposed solution is significant. The average results of the exploited metrics (precision, recall, and F1-score) are 92.76%, 99.33%, and 95.93%, respectively. Full article