this study was conducted withthe aim of detecting hate speech in song lyrics. the background of this study stems from the numerous negative impacts caused by hate speech. We focus on detecting hate speech in song lyr...
this study was conducted withthe aim of detecting hate speech in song lyrics. the background of this study stems from the numerous negative impacts caused by hate speech. We focus on detecting hate speech in song lyrics because music is a popular form of art that can have significant impacts on people’s lives. there have been many previous studies that attempted hate speech detection using various methods. However, one issue still persists, especially when dealing with slang or uncommon sentence structures. According to the previous works, deep learning algorithms, such as using pre-trained BERT model for sentiment analysis and R-CNN as a classifier, have shown promise in addressing these issues. Hence, we decided to utilize the BERT pre-trained model for sentiment analysis and R-CNN as the classifier in their study. the dataset used in this research was collected from the Twitter dataset on Kaggle and also utilized the Spotify API. the study resulted in an precision score of 100% a recall score of 37% and an F1-score of 54% for the hate speech detection. Our result suggests that more relevant data, such as datasets consisting of poetry or sentences with implicit meanings, will be beneficial to enhance hate speech detection in song lyrics.
Withthe rapid development of science and technology today, computer technology and Internet technology have led to a new technological revolution. Under the background of Internet technology, people9;s lifestyles ...
详细信息
ISBN:
(纸本)9781450390255
Withthe rapid development of science and technology today, computer technology and Internet technology have led to a new technological revolution. Under the background of Internet technology, people's lifestyles and information acquisition methods are undergoing tremendous changes, and the entire education industry has also been significantly affected. the Internet technology has given birth to a software for making basketball teaching and training tactics design drawings, which has greatly enriched teaching resources and teaching methods. the purpose of this article is to study the software application of basketball teaching and training tactics design drawing under the background of Internet technology. this article first uses computer technology to develop the human-computer interaction software for basketball training tactics teaching, so that basketball players can initially establish the perceptual understanding of basketball skills and tactics, and improve the teaching effect of teachers explaining basketball training techniques and tactics. then, it compares and analyzes the difference between traditional basketball teaching and the software application teaching, and draws out the advantages of this basketball teaching training tactical design drawing software. Finally, using teaching experiment method, expert interview method, mathematical statistics method, logical analysis method and other methods, the students of the basketball team of school A are used as the experimental objects, and the traditional design drawing method and the design drawing software production method of this research are used for experimental research. the experimental data shows that before the basketball teaching training of the training tactics design drawing, 6 of the experimental group scored more than 5 fixed-point shots, and after the basketball teaching training, 9 of the experimental group scored more than 5 fixed-point shots. the software has obvious advantages in basketb
A switch-mode power amplifier (PA), like the proposed class-E renders itself capable of achieving a theoretical power conversion efficiency (PE) of 100% by ensuring specific bias and switching conditions of the active...
A switch-mode power amplifier (PA), like the proposed class-E renders itself capable of achieving a theoretical power conversion efficiency (PE) of 100% by ensuring specific bias and switching conditions of the active device and presenting an idealized impedance at the drain of the active device [1] [2] [3]. the design presented satisfies the zero-voltage switching (ZVS) and zero derivative voltage switching (ZVDS) conditions which are fundamental to correct class-E PA operation. the output network performs a dual function of impedance transformation to a standard 50 ohm impedance and harmonic suppression for any power being transmitted at harmonic frequencies.
the paper presents the design of a dynamic damping device to reduce the vibration amplitude of a Cartesian robot prototype used for high-precision computer Numerical Control (CNC) machining under high accelerations. F...
详细信息
In this paper, a reference tracking controller for an 8-compartment epidemic model is proposed. the dynamical model describing the disease spread and progression is given in nonlinear input-affine form. the manipulabl...
In this paper, a reference tracking controller for an 8-compartment epidemic model is proposed. the dynamical model describing the disease spread and progression is given in nonlinear input-affine form. the manipulable input is the transmission rate, while the output to be tracked is the number of infected people. the model parameters correspond to the COVID-19 pandemic. the control design uses a simple SEIR model and it is based on feedback linearization combined with extended Kalman filter for state estimation. Simulation results show good tracking performance even with model mismatch and significant parameter uncertainty.
Unlike the fifth generation (5G), which is well recognized for network cloudification with micro-service-oriented design, the sixth generation (6G) of networks is directly tied to intelligent network orchestration and...
Unlike the fifth generation (5G), which is well recognized for network cloudification with micro-service-oriented design, the sixth generation (6G) of networks is directly tied to intelligent network orchestration and management. the Attacks Detection in 6G (AD6Gs) wireless networks created by this research uses a Machine Learning (ML) algorithm. the pre-processing stage of the ML-AD6Gs process is the initial step. the second stage involves the feature selection approach. Correlation Feature Selection algorithm (CFS) is used to implement the suggested hybrid strategy. It selects the best subset feature and reduces dimensionality for each independent analyses of the dataset CICDDOS2019. the voting average method is used as an aggregation step, and two classifiers—Random Forest (RF) and Support Vector Machine (SVM)—are modified to be used as ML Algorithms. the proposed method shown an outperformed the existing classification method. the accuracy was 99.9%% for CICDDOS2019 dataset with a false alarm rate of 0.00102
the Internet of things (IoT) has greatly increased the possibility for developing intelligent connections and applications in many facets of daily life. Traditional security solutions frequently fail to solve security...
the Internet of things (IoT) has greatly increased the possibility for developing intelligent connections and applications in many facets of daily life. Traditional security solutions frequently fail to solve security issues in cloud-based IoT systems, proving ineffective and insufficient. Software Defined Networking (SDN), which effectively detects and monitors network security vulnerabilities thanks to its programmable characteristics, presents a viable solution to these problems. In order to strengthen computer systems and fend off threats to network security, machine learning (ML) techniques have recently been included into SDN-Network Intrusion Detection Systems (NIDS). Deep learning (DL), one of these cutting-edge ML techniques, has become more popular in the SDN environment. For SDN-based cloud IoT networks, this paper design an efficient path selection system in this study utilizing DL approaches. the strategy comprises employing a Recurrent Neural Network (RNN) to identify threats and a selection mechanism to pick the best route for data delivery. this study performed tests on two datasets, KDD and UNSWNB15, and the results show that the suggested RNN outperformed existing DL methods by achieving an amazing accuracy ranging from 91% to 95% on both datasets.
this study focuses on the design and implementation of a robust H ∞ controller for an AC microgrid islanding system with uncertain parameters, incorporating tracking objectives. the microgrid system contains some un...
this study focuses on the design and implementation of a robust H ∞ controller for an AC microgrid islanding system with uncertain parameters, incorporating tracking objectives. the microgrid system contains some uncertain parameters, and the goal is to guarantee its stability while achieving precise tracking. A state feedback controller is initially designed to stabilize the system. Subsequently, an H ∞ controller is developed to achieve the following objectives: ensuring system stability in the presence of uncertainties, precise tracking, and disturbance rejection. the study emphasizes the importance of considering these objectives to enhance the performance and stability of the microgrid. the proposed approach contributes to the advancement of microgrid control strategies and lays the foundation for more efficient and reliable microgrid operation in islanded scenarios.
the advancement of containerization and various integration tools has greatly reduced the development cost of microservice architecture. Under this premise, many companies have begun to migrate their legacy systems (m...
the advancement of containerization and various integration tools has greatly reduced the development cost of microservice architecture. Under this premise, many companies have begun to migrate their legacy systems (monolithic applications) to microservice architectures in order to adapt to market demands. Instead of migrating legacy systems to microservice architecture from scratch, we provide another approach of splitting an existing monolithic system into microservices. In this paper, we use Go language’s AST as a basis to split the original project into multiple independent components and design a method for analyzing dependencies, classifying them, and producing independently runnable microservices.
Diabetic retinopathy, a commonly observed disorder associated with diabetes mellitus, is distinguished by the emergence of irregularities in the retina that adversely affect visual capabilities. In the absence of time...
详细信息
ISBN:
(数字)9798350394474
ISBN:
(纸本)9798350394481
Diabetic retinopathy, a commonly observed disorder associated with diabetes mellitus, is distinguished by the emergence of irregularities in the retina that adversely affect visual capabilities. In the absence of timely identification, the condition above has the potential to advance and result in compromised visual function. While proven to be effective, the process of manual diagnosis conducted by ophthalmologists is characterized by time-consuming procedures, labor-intensive efforts, significant costs, and a susceptibility to misdiagnosis. On the other hand, computer-aided diagnosis procedures provide a highly efficient and precise alternative. the utilization of deep learning techniques, namely in medical picture interpretation, has demonstrated improved effectiveness. this study introduces an innovative deep-learning methodology for detecting and classifying diabetic retinopathy automatically. this study proposes the utilization of a Convolutional Neural Network model based on ResNet50 architecture to identify and classify retinal pictures into five distinct categories, which correspond to different phases of diabetic retinopathy. the model demonstrates a validation accuracy of 95.01% and a training accuracy of 98.70%, accompanied by a Cohen Kappa score of 0.96 with negligible loss. the efficiency of the proposed model is assessed by utilizing the Diabetic Retinopathy Detection dataset, demonstrating its capability to automatically identifying diabetic retinopathy. this research has the potential to be applied within the healthcare domain, specifically to diagnose retinal complications in individuals with diabetes.
暂无评论