T R A C K       P A P E R
Close

Login Panel

Close tab

Password Meter

Volume 11 Issue 05 (May 2024)

S.No. Title & Authors Page No View
1

Title : A New Many-Objective Evolutionary Algorithm for Adjusting Reference Vectors Based On Vector Angles and Convergence Metrics

Authors : WenJie Wang

Click Here For Abstract

Download Certificate
Abstract :

In decomposition-based MOEAs, the inconsistency of the distribution of reference vectors with the shape of the PF is a long-standing problem. To address this challenge, strategies to adjust the reference vectors during the evolutionary process have been proposed. However, most of the methods either adjust the reference vectors fixedly in each generation or at a fixed frequency, ignoring the dynamic information during population evolution. To solve the above problem, this work proposes a strategy to judge the timing of reference vector adjustment based on the change of population convergence. By calculating the improvement rate of subproblem convergence, it can reflect the current convergence state of the population. The algorithm performs reference vector adjustment only when the subproblems are considered to be converged in general. To make the reference vectors better adapt to different shapes of the Pareto fronts, this work draws on the concept of vector angle and proposes a method to adjust the reference vector based on the maximum vector angle. Specifically, by maintaining an archive with well-distributed nondominated solutions, the individual among them that possesses the largest vector angle with the current population is selected for the adjustment of the reference vector. Experiments on WFG test problems show that the proposed algorithm is competitive compared to the state-of-the-art algorithms for solving problems with different Pareto fronts.

1-8
2

Title : A Dual Metric Mechanism for Federated Learning Based On Data and Arithmetic Resources

Authors : WenXia Ge, ShaoHeng Wang

Click Here For Abstract

Download Certificate
Abstract :

With the increasingly stringent data privacy protection regulations and the decentralisation of computing resources, federated learning has gradually become a current research hotspot. Currently federated learning can effectively solve the problem of data silos, but there are still several notable challenges in the current federated learning in specific application practices, including the lack of efficient and secure incentive mechanisms, the increasingly obvious drawbacks of the traditional centralised management model, and the training security problems caused by malicious users. This paper is dedicated to solving these problems by proposing a secure federated learning mechanism based on a dual incentive strategy of data and arithmetic resources, aiming to improve the performance and security of the system through innovative algorithms and framework design.

This paper proposes a dual metric mechanism based on data resources and arithmetic resources. Contribution measurement is the antecedent problem of designing the federated learning incentive mechanism, this paper improves the data resources and arithmetic resources of the federated training client to be evaluated from multiple dimensions, and selects multiple indicators for specific measurements, in which the innovative introduction of task relevance indicators can more accurately match the client with the learning task, which further improves the resource utilisation rate and the efficiency of federated training.

9-12
3

Title : Research on Neural Network Optimization Method Based on Genetic Algorithm

Authors : Yaxin Lu, Han Wu

Click Here For Abstract

Download Certificate
Abstract :

The design of neural network models relies on the expertise and experience of experts, which makes it difficult to obtain excellent neural network models, and manual adjustment of model parameters is time-consuming and complex. LSTM neural network shows good performance in time series prediction. The parameters and structure of the LSTM neural network will affect the fitting ability of the model, and have a great influence on the prediction performance of the model. As a global optimization algorithm, genetic algorithm has the advantages of strong searching ability and good robustness, which is suitable for the optimization of neural networks. Therefore, this paper will study the optimization method of LSTM neural network based on genetic algorithm. This paper first introduces the basic principle of genetic algorithm and LSTM neural network, then expounds the flow and method of genetic algorithm optimization of LSTM neural network model, and verifies the optimization effect through experiments.

13-16
4

Title : Research on Key Technologies for Big Data Classification Transactions and Privacy Protection

Authors : Shaoheng Wang, Wenxia Ge

Click Here For Abstract

Download Certificate
Abstract :

As the data trading market continues to expand, the issues of privacy information leakage, data leakage, and data quality in data trading are becoming increasingly prominent, and to a certain extent, constraining the development of the data trading market. Blockchain, as a distributed ledger technology, with its characteristics of decentralization, traceability, and tamper resistance, can effectively avoid problems such as single point of failure and data tampering in data trading. This paper addresses the issues of privacy information leakage, data quality, and transaction fairness in data trading. Firstly, this paper introduces a decision tree classification model to classify the source data, and removes data that does not meet the transaction requirements before data trading. During the secure comparison phase, a lightweight ciphertext comparison algorithm is designed so that data owners can obtain classification results without revealing plaintext data to the decision tree classification model.

During the data trading phase, this paper conducts transactions on a per-data fragment basis, granting data buyers trial rights. Subsequently, upon data buyers obtaining transaction data, consistency verification is conducted on the transaction data to prevent data owners from adding garbage data to the transaction data before data trading, thereby avoiding dishonest trading behavior by data owners. Finally, this paper designs a decentralized data trading model, DCTM (Data Classification Transaction Model), based on smart contract technology. This model addresses issues such as data quality, single point of failure, privacy leakage, and data resale in data trading, ensuring transaction fairness and security

17-20
5

Title : Cellular Automaton Model Based On the G0 Cell Cycle

Authors : Yakun Li

Click Here For Abstract

Download Certificate
Abstract :

The epithelial-mesenchymal transition (EMT) of tumor cells is a crucial prerequisite for tumor metastasis, and quantitative research on the process of epithelial-mesenchymal transition is of great significance. This article mainly discusses the growth kinetics of tumor cells by designing a cellular automaton model based on the cell cycle mechanism to replicate the process of epithelial-mesenchymal transition

21-23
6

Title : Evolutionary Multi-task Optimization Algorithm Based On Prior Knowledge

Authors : Gaomin Yin

Click Here For Abstract

Download Certificate
Abstract :

Traditional evolutionary algorithms are often used to solve single-task optimization problems. With the study of evolutionary algorithms, it is found that most optimization tasks often have potential correlation, which indicates that the knowledge obtained in the evolution process of one optimization task can be used to optimize another task to further optimize the performance of the target task. With the rapid development of machine learning technology, the idea of making use of commonalities or differences among multiple tasks for efficient learning has been widely studied in the field of multi-task learning.In order to strengthen the positive transfer of knowledge, we can consider using strong correlation prior knowledge to construct help tasks and optimize the original tasks together. In this paper, a method of constructing help tasks is proposed, which is based on the original problem and constructed by multi-objective decomposition of sub-problem groups. These sub-problem sets are closely related to the original problem and belong to the strongly correlated tasks. Therefore, the help tasks constructed by this method can promote the forward knowledge transfer of multi-task optimization theoretically. The experimental results show that the efficiency of the proposed algorithm is improved significantly in task optimization.

24-29
7

Title : Exploration on the Elements of Curriculum Politics Construction in Chinese University

Authors : Jing Guo

Click Here For Abstract

Download Certificate
Abstract :

In recent years, the phenomenon of forcefully integrating ideological and political education into the curriculum is quite common in China. The effectiveness of curriculum politics education is still not satisfactory. During the construction process, issues such as a lack of overall design sense, excessive reliance on teachers, and unclear direction in development exist. It is necessary to focus on three key elements: grassroots teaching organization, engineering certification, and school situation and history. By creating distinctive theoretical courses and personalized practical courses, in conjunction with artistic and physical education and the school's own situation, the specialization and effectiveness of ideological and political education in the curriculum can be enhanced.

30-31
8

Title : Violence Detection in Surveillance Videos Using Artificial Intelligence

Authors : Atharva Wankhade, prof Snehil Jaiswal, Snehal Tingane

Click Here For Abstract

Download Certificate
Abstract :

In recent years, the role of monitoring systems in upholding public order and ensuring public safety has expanded. Video monitoring in locations such as train stations, schools, and hospitals necessitates the automatic identification of hostile and suspicious behaviours to avert any potential harm to society, the economy, and the environment. The optimal utilization of computerized violence detection by law enforcement is crucial. An all-encompassing methodology is necessary to identify instances of violence and the use of weapons in closed circuit television (CCTV) recordings. This work presents the Smart-City CCTV Violence Detection (SCVD) dataset, which is used for detecting occurrences of violence in surveillance films, including both cases including weapons and those without weapons. The proposed system utilizes a model based on deep learning approach to detect violence in videos. The model uses a comprehensive set of characteristics to describe violence occurrences in the dataset. The model was created using MATLAB software, utilizing image processing and machine and deep learning toolkit. It achieved an overall accuracy rate of 96.4%. The proposed endeavour has practical applications in the industry and is advantageous to society in terms of security

32-39