Human Detection and tracking have become a focal area of research as it plays a major role in computer vision applications. Methods and equipment for the detection and tracking of humans are constantly being changed a...
详细信息
This paper sets forth a bivariate, real-time NFT (nonfungible token) model based on a Markovian queueing process. This model is proposed with the goal of simulating and observing the performance of an NFT system as it...
This paper sets forth a bivariate, real-time NFT (nonfungible token) model based on a Markovian queueing process. This model is proposed with the goal of simulating and observing the performance of an NFT system as it behaves under real-time constraints, as well as to see how various on-/off-chain transaction rates, service rates, blocksizes, and deadline-miss rates affect the overall performance of the system. The system is assumed to operate at a steady state, thus allowing for each probabilistic state (which at a given time consists of ion-chain transactions and j off-chain transactions that have arrived) to be calculated using balance equations (all incoming transactions to a state equal all outgoing from the state when the relevant probabilities are considered). The Markovian assumption necessitates that the full state space must sum to 1.0, and because all states derive from $\mathrm{p}_{0,0}$ , P0,0 may be factored out and solved using this constraint. This in turn facilitates the computation of the remaining probabilities. The on-/off-chain transaction rates $\lambda_{on}$ and $\lambda_{off}$ , service rate $\mu$ , and deadline-miss rate $\lambda_{F}$ are the primary parameters within the model, and $\lambda_{F}$ is the key parameter for modeling the real-time behavior of the system $(\lambda_{F}$ represents a failure for a transaction to meet the deadline, and it causes the current state to self-loop). An analysis of the system via metrics including average wait time, average number of transactions, and throughput is presented, and the implications of the simulation on the overall performance of the system are discussed.
Nowadays, smart mobile devices (SMDs) support various computation-intensive and delay-sensitive applications, e.g., online games, and figure compression. However, SMDs have limited computing resources and battery ener...
详细信息
Nowadays, rapid development of Internet has brought a sharp increase in traffic data. Abnormal traffic haS serious impact on network security. Traffic anomaly detection can be achieved by extracting characteristics of...
详细信息
The persistent and evolving threat of phishing attacks demands effective and adaptive detection techniques. This research paper presents a comprehensive evaluation and comparison of various machine learning approaches...
The persistent and evolving threat of phishing attacks demands effective and adaptive detection techniques. This research paper presents a comprehensive evaluation and comparison of various machine learning approaches to detect phishing attacks. We investigated five prominent algorithms: Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), Naive Bayes, and Extreme Gradient Boosting (XGBoost), to determine their efficacy in identifying phishing activities. Our methodology involved a systematic analysis using a large dataset of phishing and legitimate URLs, where each model was trained, tested, and validated to ensure robustness and reliability. The performance of each algorithm was assessed based on accuracy, precision, recall, and F1 score. Among the evaluated models, XGBoost demonstrated superior performance, achieving an exceptional accuracy of 99.75%. This result underscores the potential of XGBoost in phishing attack detection, offering a promising tool for cybersecurity applications.
Foreign exchange trading basically bridges a gap between buyer and seller to transact at a set of prices of the currencies to make profit out of it by the traders and investors. In this paper, foreign exchange predict...
Foreign exchange trading basically bridges a gap between buyer and seller to transact at a set of prices of the currencies to make profit out of it by the traders and investors. In this paper, foreign exchange predictive models are explored based on basic Extreme Learning Machine (ELM) along with optimized version of ELM. Initially, this work tried to obtain the best optimized ELM network based upon the four nature-inspired optimization methodologies such as; particle swarm, ant colony, moth flame and grey wolf optimization (GWO). From this phase, it has been observed that the ELM network optimized with GWO outperforms rest of other experimented optimized ELM networks with respect to error graphs and performance metrics. In order to evaluate the performance, the ELM-GWO currency exchange predictor, the recognition performance metrics such as; EVS, MAE, MSE and R 2 Score are computed, the error graphs are obtained and the average computational time taken are compared.
Internet of Vehicle (IoV) is a combined form of Internet of Things (IoT) and Vehicular Ad-hoc Network (VANET). Its fundamental goal is to increase the service quality of Intelligent Transportation System (ITS). The dy...
Internet of Vehicle (IoV) is a combined form of Internet of Things (IoT) and Vehicular Ad-hoc Network (VANET). Its fundamental goal is to increase the service quality of Intelligent Transportation System (ITS). The dynamic nature of IoV such as high dynamic topology, high mobility of vehicles, etc. are some of the factors that causes more congestion thus reducing the efficiency of routing. Many algorithms were designed to obtain the shortest path from the source to the destination. Choosing of Ant Colony Optimization (ACO) algorithm is one of the best ways to obtain the shortest path. In this paper, an Enhanced Ant Colony Optimization with Dynamic Evaporation rate (EACODE) algorithm is proposed to obtain the congestion-free optimized path which reduces the travel time, travel cost and traffic problems. Instead of fixed evaporation rate, it dynamic predicts the pheromone evaporation rate with the help of run time metrics to avoid the congested paths thus improving the efficiency of the travel. The simulation results show that the proposed EACO-DE algorithm improves the efficiency of the routing compared with primitive Ant Colony Optimization (ACO) algorithm and Enhanced Hybrid Ant Colony Optimization Routing Protocol (EHACORP) under various performance metrics.
In this work, we study simulation-based optimization, where the agent aims to select the best configuration from the design space with as few as possible iterations. Inspired by the success of deep reinforcement learn...
详细信息
In this work, we study simulation-based optimization, where the agent aims to select the best configuration from the design space with as few as possible iterations. Inspired by the success of deep reinforcement learning (DRL), we formulate the sampling process as policy searching and give a solving method from the perspective of policy iteration. Concretely, a surrogate model for predicting the performance of each configuration and a parameterized sampling policy are applied, which correspond to the critic and actor in actor-critic (AC) method, respectively. We further derive the updating rule and propose two algorithms for configuration selection in continuous and discrete design spaces, respectively. Finally, the algorithms are validated experimentally on 1) two toy examples to intuitively explain the principle and 2) two high-dimensional tasks to reveal the effectiveness in large-scale problems. The results show that the proposed algorithms can efficiently deal with large-scale problems and effectively eliminate sub-optimal configurations.
Non-card retail payments, such as direct-from-the-bank programs and E-wallets, have become increasingly common at both brick-and-mortar and online establishments. In recent years, the use of mobile wallets has increas...
详细信息
Sentiment analysis, a key area in Natural Language Processing (NLP), involves categorizing text data based on its emotional tone-positive, negative, or neutral. With the growing reliance on online interactions, unders...
详细信息
ISBN:
(数字)9798331522612
ISBN:
(纸本)9798331522629
Sentiment analysis, a key area in Natural Language Processing (NLP), involves categorizing text data based on its emotional tone-positive, negative, or neutral. With the growing reliance on online interactions, understanding sentiments expressed in text is vital for assessing user opinions, behaviours, and engagement. In peer-to-peer (P2P) networks, where content sharing and decentralized user interaction dominate, sentiment analysis can uncover critical insights into digital relationships and collaborative tendencies. This paper explores sentiment analysis within P2P platforms using the BERT (Bidirectional Encoder Representations from Transformers) algorithm, a state-of-the-art NLP model. Unlike traditional methods, BERT effectively captures contextual and nuanced sentiments, enabling more accurate classification. The methodology includes preprocessing data, extracting embeddings using BERT, and employing fine-tuned models for sentiment categorization. Dimensionality reduction and visualization techniques further reveal patterns, sentiment clusters, and alignment between emotional tones in user interactions. Results demonstrate that BERT-powered sentiment analysis identifies content trends, emotional polarities, and behavioural dynamics in decentralized environments. The research also addresses challenges such as handling diverse content and biases in sentiment interpretation. This study highlights the growing need for advanced sentiment analysis techniques to enhance content profiling, trend forecasting, and user understanding on decentralized platforms, offering valuable implications for businesses and researchers.
暂无评论