Retrieval-augmented generation (RAG) is a framework enabling large language models (LLMs) to enhance their accuracy and reduce hallucinations by integrating external knowledge bases. In this paper, we introduce a hybrid RAG system enhanced through a comprehensive suite of optimizations that significantly improve retrieval quality, augment reasoning capabilities, and refine numerical computation ability. We refined the text chunks and tables in web pages, added attribute predictors to reduce hallucinations, conducted LLM Knowledge Extractor and Knowledge Graph Extractor, and finally built a reasoning strategy with all the references. We evaluated our system on the CRAG dataset through the Meta CRAG KDD Cup 2024 Competition. Both the local and online evaluations demonstrate that our system significantly enhances complex reasoning capabilities. In local evaluations, we have significantly improved accuracy and reduced error rates compared to the baseline model, achieving a notable increase in scores. In the meanwhile, we have attained outstanding results in online assessments, demonstrating the performance and generalization capabilities of the proposed system. The source code for our system is released in \url{https://gitlab.aicrowd.com/shizueyy/crag-new}.

The growth of digitalization services via web browsers has simplified our daily routine of doing business. But at the same time, it has made the web browser very attractive for several cyber-attacks. Web phishing is a well-known cyberattack that is used by attackers camouflaging as trustworthy web servers to obtain sensitive user information such as credit card numbers, bank information, personal ID, social security number, and username and passwords. In recent years many techniques have been developed to identify the authentic web pages that users visit and warn them when the webpage is phishing. In this paper, we have developed an extension for Chrome the most favorite web browser, that will serve as a middleware between the user and phishing websites. The Chrome extension named "NoPhish" shall identify a phishing webpage based on several Machine Learning techniques. We have used the training dataset from "PhishTank" and extracted the 22 most popular features as rated by the Alexa database. The training algorithms used are Random Forest, Support Vector Machine, and k-Nearest Neighbor. The performance results show that Random Forest delivers the best precision.

Accurate classification of weather conditions in images is essential for enhancing the performance of object detection and classification models under varying weather conditions. This paper presents a comprehensive study on classifying weather conditions in images into four categories: rainy, low light, haze, and clear. The motivation for this work stems from the need to improve the reliability and efficiency of automated systems, such as autonomous vehicles and surveillance, which must operate under diverse weather conditions. Misclassification of weather conditions can lead to significant performance degradation in these systems, making robust weather classification crucial. Utilizing the Support Vector Machine (SVM) algorithm, our approach leverages a robust set of features, including brightness, saturation, noise level, blur metric, edge strength, motion blur, Local Binary Patterns (LBP) mean and variance for radii 1, 2, and 3, edges mean and variance, and color histogram mean and variance for blue, green, and red channels. Our SVM-based method achieved a notable accuracy of 92.8%, surpassing typical benchmarks in the literature, which range from 80% to 90% for classical machine learning methods. While deep learning methods can achieve up to 94% accuracy, our approach offers a competitive advantage in terms of computational efficiency and real-time classification capabilities. Detailed analysis of each feature's contribution highlights the effectiveness of texture, color, and edge-related features in capturing the unique characteristics of different weather conditions. This research advances the state-of-the-art in weather image classification and provides insights into the critical features necessary for accurate weather condition differentiation, underscoring the potential of SVMs in practical applications where accuracy is paramount.

Twin support vector machine (TSVM), a variant of support vector machine (SVM), has garnered significant attention due to its $3/4$ times lower computational complexity compared to SVM. However, due to the utilization of the hinge loss function, TSVM is sensitive to outliers or noise. To remedy it, we introduce the guardian loss (G-loss), a novel loss function distinguished by its asymmetric, bounded, and smooth characteristics. We then fuse the proposed G-loss function into the TSVM and yield a robust and smooth classifier termed GL-TSVM. Further, to adhere to the structural risk minimization (SRM) principle and reduce overfitting, we incorporate a regularization term into the objective function of GL-TSVM. To address the optimization challenges of GL-TSVM, we devise an efficient iterative algorithm. The experimental analysis on UCI and KEEL datasets substantiates the effectiveness of the proposed GL-TSVM in comparison to the baseline models. Moreover, to showcase the efficacy of the proposed GL-TSVM in the biomedical domain, we evaluated it on the breast cancer (BreaKHis) and schizophrenia datasets. The outcomes strongly demonstrate the competitiveness of the proposed GL-TSVM against the baseline models.

This study examines the impact of historical text normalization on the classification of medieval charters, specifically focusing on document dating and locating. Using a data set of Middle High German charters from a digital archive, we evaluate various classifiers, including traditional and transformer-based models, with and without normalization. Our results indicate that the given normalization minimally improves locating tasks but reduces accuracy for dating, implying that original texts contain crucial features that normalization may obscure. We find that support vector machines and gradient boosting outperform other models, questioning the efficiency of transformers for this use case. Results suggest a selective approach to historical text normalization, emphasizing the significance of preserving some textual characteristics that are critical for classification tasks in document analysis.

Customer churn, the discontinuation of services by existing customers, poses a significant challenge to the telecommunications industry. This paper proposes a novel adaptive ensemble learning framework for highly accurate customer churn prediction. The framework integrates multiple base models, including XGBoost, LightGBM, LSTM, a Multi-Layer Perceptron (MLP) neural network, and Support Vector Machine (SVM). These models are strategically combined using a stacking ensemble method, further enhanced by meta-feature generation from base model predictions. A rigorous data preprocessing pipeline, coupled with a multi-faceted feature engineering approach, optimizes model performance. The framework is evaluated on three publicly available telecom churn datasets, demonstrating substantial accuracy improvements over state-of-the-art techniques. The research achieves a remarkable 99.28% accuracy, signifying a major advancement in churn prediction.The implications of this research for developing proactive customer retention strategies withinthe telecommunications industry are discussed.

Human pose estimation involves detecting and tracking the positions of various body parts using input data from sources such as images, videos, or motion and inertial sensors. This paper presents a novel approach to human pose estimation using machine learning algorithms to predict human posture and translate them into robot motion commands using ultra-wideband (UWB) nodes, as an alternative to motion sensors. The study utilizes five UWB sensors implemented on the human body to enable the classification of still poses and more robust posture recognition. This approach ensures effective posture recognition across a variety of subjects. These range measurements serve as input features for posture prediction models, which are implemented and compared for accuracy. For this purpose, machine learning algorithms including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and deep Multi-Layer Perceptron (MLP) neural network are employed and compared in predicting corresponding postures. We demonstrate the proposed approach for real-time control of different mobile/aerial robots with inference implemented in a ROS 2 node. Experimental results demonstrate the efficacy of the approach, showcasing successful prediction of human posture and corresponding robot movements with high accuracy.

Anomaly detection is a long-standing challenge in manufacturing systems. Traditionally, anomaly detection has relied on human inspectors. However, 3D point clouds have gained attention due to their robustness to environmental factors and their ability to represent geometric data. Existing 3D anomaly detection methods generally fall into two categories. One compares scanned 3D point clouds with design files, assuming these files are always available. However, such assumptions are often violated in many real-world applications where model-free products exist, such as fresh produce (i.e., ``Cookie", ``Potato", etc.), dentures, bone, etc. The other category compares patches of scanned 3D point clouds with a library of normal patches named memory bank. However, those methods usually fail to detect incomplete shapes, which is a fairly common defect type (i.e., missing pieces of different products). The main challenge is that missing areas in 3D point clouds represent the absence of scanned points. This makes it infeasible to compare the missing region with existing point cloud patches in the memory bank. To address these two challenges, we proposed a unified, unsupervised 3D anomaly detection framework capable of identifying all types of defects on model-free products. Our method integrates two detection modules: a feature-based detection module and a reconstruction-based detection module. Feature-based detection covers geometric defects, such as dents, holes, and cracks, while the reconstruction-based method detects missing regions. Additionally, we employ a One-class Support Vector Machine (OCSVM) to fuse the detection results from both modules. The results demonstrate that (1) our proposed method outperforms the state-of-the-art methods in identifying incomplete shapes and (2) it still maintains comparable performance with the SOTA methods in detecting all other types of anomalies.

This paper explores machine learning (ML) models for classifying lung cancer levels to improve diagnostic accuracy and prognosis. Through parameter tuning and rigorous evaluation, we assess various ML algorithms. Techniques like minimum child weight and learning rate monitoring were used to reduce overfitting and optimize performance. Our findings highlight the robust performance of Deep Neural Network (DNN) models across all phases. Ensemble methods, including voting and bagging, also showed promise in enhancing predictive accuracy and robustness. However, Support Vector Machine (SVM) models with the Sigmoid kernel faced challenges, indicating a need for further refinement. Overall, our study provides insights into ML-based lung cancer classification, emphasizing the importance of parameter tuning to optimize model performance and improve diagnostic accuracy in oncological care.

With the emergence of new technologies and a growing number of wireless networks, we face the problem of radio spectrum shortages. As a result, identifying the wireless channel spectrum to exploit the channel's idle state while also boosting network security is a pivotal issue. Detecting and classifying protocols in the MAC sublayer enables Cognitive Radio users to improve spectrum utilization and minimize potential interference. In this paper, we classify the Wi-Fi and Bluetooth protocols, which are the most widely used MAC sublayer protocols in the ISM radio band. With the advent of various wireless technologies, especially in the 2.4 GHz frequency band, the ISM frequency spectrum has become crowded and high-traffic, which faces a lack of spectrum resources and user interference. Therefore, identifying and classifying protocols is an effective and useful method. Leveraging machine learning and deep learning techniques, known for their advanced classification capabilities, we apply Support Vector Machine and K-Nearest Neighbors algorithms, which are machine learning algorithms, to classify protocols into three classes: Wi-Fi, Wi-Fi Beacon, and Bluetooth. To capture the signals, we use the USRP N210 Software Defined Radio device and sample the real data in the indoor environment in different conditions of the presence and absence of transmitters and receivers for these two protocols. By assembling this dataset and studying the time and frequency features of the protocols, we extract the frame width and the silence gap between the two frames as time features and the PAPR of each frame as a power feature. By comparing the output of the protocols classification in different conditions and also adding Gaussian noise, it was found that the samples in the nonlinear SVM method with RBF and KNN functions have the best performance, with 97.83% and 98.12% classification accuracy, respectively.