Multi-label classification faces significant challenges from high-dimensional features and complex label dependencies. Traditional feature selection methods often fail to capture these dependencies effectively or suffer from high computational costs. This paper proposes a novel Robust Low-Rank Subspace Learning (RLRSL) framework for multi-label feature selection. Our method integrates global label correlations and local feature structures within a unified objective function, utilizing Schatten-p norm for low-rank subspace learning, l_(2,1),-norm for joint feature sparsity, and manifold regularization for local geometry preservation. We develop an efficient optimization algorithm to solve the resulting non-convex problem. Comprehensive experiments on seven benchmark datasets demonstrate that RLRSL consistently outperforms state-of-the-art methods across multiple evaluation metrics, including ranking loss, multi-label accuracy, and F1-score, using both ML-*k* NN and SVM classifiers. The results confirm the robustness, efficiency, and superior generalization capability of our proposed approach

Deep-sea debris poses a significant threat to marine life and human health. Traditional methods for underwater debris detection and classification are labour-intensive and inefficient. The major challenge for using vision robots or autonomous underwater vehicles(AUVs) to remove deep sea debris is to exactly identify the marine debris. Marine debris gets deformed, eroded, and blocked due to seawater. Marine debris changes its shape, size, and texture in sea environment. Sea environment is challenging for the task of debris detection because of weak light. Uncertainty about the task of debris detection is due to marine life, rocks, marine flora, fauna, algae, etc. This study aims to develop a robust deep learning model for underwater debris detection and classification using YOLOV8. We evaluate the performance of YOLOV8 against YOLOV3 and YOLOV5 on the JAMSTEC TrashCan dataset. By employing an anchor-free detection head, YOLOV8 demonstrates improved accuracy in detecting underwater debris of varying shapes, sizes, and textures. Here, we show that YOLOV8 achieves a mean Average Precision (mAP) of 0.5095, outperforming YOLOV3 (mAP: 0.31879) and YOLOV5 (mAP: 0.43608). Our findings underscore the potential of anchor-free YOLOV8 in addressing the challenges of underwater debris detection, which is crucial for marine conservation efforts.

In the modern global economy, sustainability has emerged as a crucial foundation for achieving long-term stability and growth. Escalating environmental challenges, depletion of natural resources, and growing social expectations have made the selection of suitable technologies and innovations essential for sustainable economic progress. Yet, such decisions are often made amid uncertainty driven by technological risks, volatile markets, evolving regulations, and geopolitical instability. These factors complicate decision-making for policymakers, industry leaders, and investors, underscoring the need for resilient analytical frameworks that support informed innovative choices while mitigating risks. Achieving harmony between innovation and sustainability requires balancing economic feasibility, environmental responsibility, and social well-being. This study introduces a holistic framework for evaluating advanced technologies that contribute to economic development under uncertain and complex conditions. Utilizing the fuzzy Analytic Hierarchy Process (AHP) with Z numbers, the approach combines fuzzy logic and Z-numbers to effectively represent uncertainty and the reliability of expert evaluations. The model supports a structured multi-criteria assessment that integrates economic, environmental, and social dimensions, guiding stakeholders in selecting technologies that foster sustainable and adaptable growth. Through conceptual analysis and practical case applications, the research validates the efficiency of the fuzzy Z-AHP approach as a robust, transparent, and flexible decision-making tool for technology evaluation in dynamic economic environments. The outcomes enhance methodological advancement in sustainable development and strategic innovation management. 

This study investigates the application of deep learning techniques for the detection of Denial of Service (DoS) attacks in network traffic using the NSL-KDD dataset. A Deep Neural Network (DNN) model is proposed and optimized for intrusion detection. The model consists of a 41-feature input layer, two fully connected hidden layers containing 128 and 64 neurons respectively and a SoftMax activated output layer for multiclass classification. The hidden layer used ReLU activation function and the model was optimized using Adam optimizer. The dataset was preprocessed using feature encoding, normalization and label transformation. The dataset was used with its standard predefined split: KDDTrain+ for training/validation and KDDTest+ for testing. The training data was further divided into 80% for training and 20% for validation. The effectiveness of the DNN was compared against traditional machine learning models, including Logistic Regression, LightGBM (LGBM), and CatBoost. Key evaluation metrics such as accuracy, precision, recall, and F1-score are used to assess the effectiveness of each model in detecting network intrusions. The results demonstrate that the DNN model achieves an accuracy of 86% on the test dataset, consistently outperforming the traditional models across all key metrics. These findings highlight the advantages of deep learning for anomaly-based intrusion detection, particularly in handling complex network traffic patterns. This study contributes to advancing network security by leveraging the capabilities of DNNs for real-time DoS detection, scalability, and practical implementation in modern cybersecurity frameworks.

Volume estimation of three-dimensional (3D) objects is fundamental in various scientific and engineering fields. While analytical expressions exist for the simple geometric shapes, they become impractical for complex or irregular structures. Monte Carlo simulation is a statistical method which is based on the random sampling, which offers an efficient numerical alternative. This research explores the application of Monte Carlo integration method for the estimation of the volumes of three different 3D objects viz. sphere, cylinder, and cone. The paper elaborates on the mathematical background of the simulation by presenting detailed Python implementations, and analyzes the accuracy, convergence rates, and computational efficiency of the method. The study concludes that the simulation, despite their probabilistic nature, provide an effective and scalable technique for volume estimation, particularly for the shapes without closed-form volume expressions.