Offline Arabic handwritten character recognition: from conventional machine learning system to deep learning approaches

Faouci, Soumia; Gaceb, Djamel; Haddad, Mohammed

doi:10.1504/ijcse.2022.124562

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(3) Abnormal behavior management module based on rule template The abnormal behavior management module in this paper mainly uses the camera to detect the monitoring area and the association rules to judge the abnormal situation. If the abnormal situation is identified, the alarm will be timely sent and the alarm information will be transmitted to the supervisor for processing [17][18]. The flow chart of intelligent alarm logic is shown in Figure 2.…”

Section: Figure 1 Function Module Diagram Of Unattended Platform For ...mentioning

confidence: 99%

Unmanned Ship Target Recognition System Based on Association Rules

2022

View full text Add to dashboard Cite

With the advent of the era of intelligence, the development of unmanned ship technology, greatly improve the efficiency of ocean monitoring, in civilian, unmanned ship can detect the sea surface weather conditions and underwater current, but also can monitor the sea surface ship accidents, illegal fishing and other phenomena; Militarily, unmanned vessels can conduct border patrols to monitor maritime violations and carry military weapons to safeguard China's maritime rights and interests. The purpose of this paper is to study the unmanned ship target recognition system based on association rule algorithm. From the point of view of system development, the hardware structure of unmanned ship target recognition system is put forward, and the system function module is described. The design of video acquisition, intelligent recognition, intelligent alarm, data transmission and other functional modules in the unmanned ship target recognition system is carried out with the idea of modularity. The association rule mining algorithm is used to mine the navigation beacon accident data, and the potential information mining is carried out in a variety of ways. The causes and internal rules of navigation beacon accidents are analyzed. The experimental results show that the southeast wind is easy to cause navigation beacon accidents due to natural causes under heavy rain.

show abstract

Section: Figure 1 Function Module Diagram Of Unattended Platform For ...mentioning

confidence: 99%

Unmanned Ship Target Recognition System Based on Association Rules

2022

View full text Add to dashboard Cite

show abstract

“…ML algorithms can learn from high-dimensional, large amounts of non-linear data and explore the laws from these 'experiences' to generate models, overcoming the potential corruption of traditional linear regression methods when dealing with high-dimensional data by downscaling, and are flexible enough to solve the problems of traditional statistical methods in dealing with unstructured information. At the same time, the ML algorithm is not limited by the number of independent variables, and will not affect the model results because of the excessive number of variables [17][18].…”

Section: MLmentioning

confidence: 99%

Machine Learning-Based Study on the Identification of Misstatements in Annual Reports of Listed Companies - A Financial Restatement Prediction Perspective

2021

View full text Add to dashboard Cite

The significance and importance of financial reporting as the basis and foundation for relevant decision makers to make judgments cannot be overstated, and both capital market participants and regulators attach great importance to the disclosure of financial reports. Although relevant regulatory authorities such as China's Securities Regulatory Commission and Accounting Standards Board have issued corresponding standards and regulations to strictly regulate the disclosure behaviour of companies' financial reports, due to insufficient supervision or relatively low costs of non-compliance, listed companies have committed FF in violation of relevant laws and regulations in order to preserve their own interests, causing unmeasurable losses to stakeholders. The main objective of this paper is to launch a study on the identification of misstatements in listed companies' annual reports based on ML under the perspective of financial restatement prediction. Based on the research on FF patterns and FFI in the first part, we firstly select the set of primary features based on the theory of FF motive, then perform Mann-Whitney test on the set of primary features to obtain the set of original features, and then use Bortua algorithm to select the final set of FI features from the set of original features. The data of the fraud samples and non-fraud samples were loaded into the four types of financial fraud identification models (FFIM) in the order of the original FI features and the FI features constructed by the BA. The model identification results showed that the combination of the FFI features constructed by the BA and the RFM had a good identification effect, and the overall evaluation indexes of G-mean and F-value were 75.9% and 78.3% respectively.

show abstract

Offline Arabic handwritten character recognition: from conventional machine learning system to deep learning approaches

Cited by 2 publications

References 0 publications

Unmanned Ship Target Recognition System Based on Association Rules

Unmanned Ship Target Recognition System Based on Association Rules

Machine Learning-Based Study on the Identification of Misstatements in Annual Reports of Listed Companies - A Financial Restatement Prediction Perspective

Contact Info

Product

Resources

About