Financial fraud undermines the sustainable development of financial markets. Financial statements can be regarded as the key source of information to obtain the operating conditions of listed companies. Current research focuses more on mining financial digital data instead of looking into text data. However, text data can reveal emotional information, which is an important basis for detecting financial fraud. The audit opinion of the financial statement is especially the fair opinion of a certified public accountant on the quality of enterprise financial reports. Therefore, this research was carried out by using the data features of 4,153 listed companies' financial annual reports and audits of text opinions in the past six years, and the paper puts forward a financial fraud detection model integrating audit opinions. First, the financial data index database and audit opinion text database were built. Second, digitized audit opinions with deep learning Bert model was employed. Finally, both the extracted audit numerical characteristics and the financial numerical indicators were used as the training data of the LightGBM model. What is worth paying attention to is that the imbalanced distribution of sample labels is also one of the focuses of financial fraud research. To solve this problem, data enhancement and Focal Loss feature learning functions were used in data processing and model training respectively. The experimental results show that compared with the conventional financial fraud detection model, the performance of the proposed model is improved greatly, with Area Under the Curve (AUC) and Accuracy reaching 81.42% and 78.15%, respectively.

Ensuring reliability of a machinery system involve the prediction of remaining useful life (RUL). In most RUL prediction approaches, noise is always considered for removal. Nevertheless, noise could be properly utilized to enhance the prediction capabilities. In this paper, we proposed a novel RUL prediction approach based on noise injection and a Kalman filter ensemble of modified bagging predictors. Firstly, we proposed a new method to insert Gaussian noises into both observation and feature spaces of an original training dataset, named GN-DAFC. Secondly, we developed a modified bagging method based on Kalman filter averaging, named KBAG. Then, we developed a new ensemble method which is a Kalman filter ensemble of KBAGs, named DKBAG. Finally, we proposed a novel RUL prediction approach GN-DAFC-DKBAG in which the optimal noise-injected training dataset was determined by a GN-DAFC-based searching strategy and then inputted to a DKBAG model. Our approach is validated on the NASA C-MAPSS dataset of aero-engines. Experimental results show that our approach achieves significantly better performance than a traditional Kalman filter ensemble of single learning models (KESLM) and the original DKBAG approaches. We also found that the optimal noise-injected data could improve the prediction performance of both KESLM and DKBAG. We further compare our approach with two advanced ensemble approaches, and the results indicate that the former also has better performance than the latters. Thus, our approach of combining optimal noise injection and DKBAG provides an effective solution for RUL estimation of machinery systems.

With the popularity of online learning, intelligent tutoring systems are starting to become mainstream for assisting online question practice. Surrounded by abundant learning resources, some students struggle to select the proper questions. Personalized question recommendation is crucial for supporting students in choosing the proper questions to improve their learning performance. However, traditional question recommendation methods (i.e., collaborative filtering (CF) and cognitive diagnosis model (CDM)) cannot meet students' needs well. The CDM-based question recommendation ignores students' requirements and similarities, resulting in inaccuracies in the recommendation. Even CF examines student similarities, it disregards their knowledge proficiency and struggles when generating questions of appropriate difficulty. To solve these issues, we first design an enhanced cognitive diagnosis process that integrates students' affection into traditional CDM by employing the non-compensatory bidimensional item response model (NCB-IRM) to enhance the representation of individual personality. Subsequently, we propose an affection-enhanced personalized question recommendation (AE-PQR) method for online learning. It introduces NCB-IRM to CF, considering both individual and common characteristics of students' responses to maintain rationality and accuracy for personalized question recommendation. Experimental results show that our proposed method improves the accuracy of diagnosed student cognition and the appropriateness of recommended questions.

This study empirically investigates the impact of informatization on China's inbound tourism development. The analysis utilizes data on the number of inbound tourist arrivals in 30 Chinese provinces from 13 tourist origin countries between 2004 and 2016. The regional informatization level is measured by the internet penetration rate. It is found that informatization in tourist destination provinces has a significant positive impact on inbound tourism. Moreover, the local public service supply plays a moderating role. The positive effect of informatization is stronger in regions with better public services. The study results imply that China can boost its inbound tourism by further improving the level of informatization as well as local public services.

This work designs an eighteen-channel bidirectional Intensity Modulation with Direct Detection (IM/DD) Wavelength Division Multiplexing-Passive Optical Network (WDM-PON) system. The proposed system meets the requirement of the ITU-T 5G fronthaul link suggested design in G-series Recommendations-Supplement 66. The newly designed system, with a 25Gb/s/λ data rate (450Gbps as a system capacity), has been tested and simulated using OptiSystem V.19 software. The system has been evaluated by the BER with respect to variable the optical span and CW laser power. Based on the ITU-T recommendations, the simulation results demonstrate that this system might be used as an F1 and as an Fx 5G fronthaul link for functional split choices starting from options 1 to 7a. These options are required under 25Gbps/λ for each upstream and downstream link direction. Furthermore, the proposed system utilized a bidirectional single-mode optical fiber within short optical spans of up to 10 km. The proposed system is characterized by a low-cost, simple, DSP-free and amplifier-free system with a reasonable system capacity.

This paper proposes an antenna performance prediction model in the autonomous driving radar manufacturing process. Our research work is based upon a challenge dataset, Driving Radar Manufacturing Process Dataset, and a typical AutoML machine learning workflow engine, Pycaret open-source Python library. Note that the dataset contains the total 70 data-items, out of which 54 used as input features and 16 used as output features, and the dataset is properly built into resolving the multi-output regression problem. During the data regression analysis and preprocessing phase, we identified several input features having similar correlations and so detached some of those input features, which may become a serious cause of the multicollinearity problem that affect the overall model performance. In the training phase, we train each of output-feature regression models by using the AutoML approach. Next, we selected the top 5 models showing the higher performances in the AutoML result reports and applied the ensemble method so as for the selected models' performances to be improved. In performing the experimental performance evaluation of the regression prediction model, we particularly used two metrics, MAE and RMSE, and the results of which were 0.6928 and 1.2065, respectively. Additionally, we carried out a series of experiments to verify the proposed model's performance by comparing with other existing models' performances. In conclusion, we enhance accuracy for safer autonomous vehicles, reduces manufacturing costs through AutoML-Pycaret and machine learning ensembled model, and prevents the production of faulty radar systems, conserving resources. Ultimately, the proposed model holds significant promise not only for antenna performance but also for improving manufacturing quality and advancing radar systems in autonomous vehicles.

Developers often use cross-platform frameworks to create mobile apps that can run on multiple platforms with minimal code changes. However, these frameworks may not suit all the needs of a specific app, so developers may also use native APIs to add platform-specific features. This method eventually dilutes the advantages of cross-platform development methodology that aims to reduce development costs and time, and often leads to a decision to return back to the original native mobile development methodology. In this study, we explore a different approach: combining different cross-platform tools to develop a storybook mobile app that meets various requirements. We have demonstrated that integrating two cross-platform solutions can be used reliably to develop complex mobile applications. However, we also report that this approach can introduce unforeseen issues such as sandbox redundancy, unexpected functional burdens, and redundant permission requests. Despite these challenges, we believe that combining two cross-platform solutions can be applied to a variety of functional and performance requirements, enabling the development of more sophisticated mobile applications at lower costs and with shorter development timelines than traditional mobile app development methodologies.

Remote sensing image segmentation plays an important role in realizing intelligent city construction. The current mainstream segmentation networks effectively improve the segmentation effect of remote sensing images by deeply mining the rich texture and semantic features of images. But there are still some problems such as rough results of small target region segmentation and poor edge contour segmentation. To overcome these three challenges, we propose an improved semantic segmentation model, referred to as MRU-Net, which adopts the U-Net architecture as its backbone. Firstly, the convolutional layer is replaced by BasicBlock structure in U-Net network to extract features, then the activation function is replaced to reduce the computational load of model in the network. Secondly, a hybrid multi-scale recognition module is added in the encoder to improve the accuracy of image segmentation of small targets and edge parts. Finally, test on Massachusetts Buildings Dataset and WHU Dataset the experimental results show that compared with the original network the ACC, mIoU and F1 value are improved, and the imposed network shows good robustness and portability in different datasets.

Scene graphs serve as semantic abstractions of images and play a crucial role in enhancing visual comprehension and reasoning. However, the performance of Scene Graph Generation is often compromised when working with biased data in real-world situations. While many existing systems focus on a single stage of learning for both feature extraction and classification, some employ Class-Balancing strategies, such as Re-weighting, Data Resampling, and Transfer Learning from head to tail. In this paper, we propose a novel approach that decouples the feature extraction and classification phases of the scene graph generation process. For feature extraction, we leverage a transformer-based architecture and design an adaptive calibration function specifically for predicate classification. This function enables us to dynamically adjust the classification scores for each predicate category. Additionally, we introduce a Distribution Alignment technique that effectively balances the class distribution after the feature extraction phase reaches a stable state, thereby facilitating the retraining of the classification head. Importantly, our Distribution Alignment strategy is model-independent and does not require additional supervision, making it applicable to a wide range of SGG models. Using the scene graph diagnostic toolkit on Visual Genome and several popular models, we achieved significant improvements over the previous state-of-the-art methods with our model. Compared to the TDE model, our model improved mR@100 by 70.5% for PredCls, by 84.0% for SGCls, and by 97.6% for SGDet tasks.

Internet-of-Things (IoT) is an emerging technology that interconnects millions of small devices to enable communication between the devices. It is heavily deployed across small scale to large scale industries because of its wide range of applications. These devices are very capable of transferring data over the internet including critical data in few applications. Such data is exposed to various security threats and thereby raises privacy-related concerns. Even devices can be compromised by the attacker. Modern cryptographic algorithms running on traditional machines provide authentication, confidentiality, integrity, and non-repudiation in an easy manner. IoT devices have numerous constraints related to memory, storage, processors, operating systems and power. Researchers have proposed several hardware and software implementations for addressing security attacks in lightweight encryption mechanism. Several works have made on lightweight block ciphers for improving the confidentiality by means of providing security level against cryptanalysis techniques. With the advances in the cipher breaking techniques, it is important to increase the security level to much higher. This paper, focuses on securing the critical data that is being transmitted over the internet by PRESENT using key-based dynamic S-Box. Security analysis of the proposed algorithm against other lightweight block cipher shows a significant improvement against linear and differential attacks, biclique attack and avalanche effect. A novel key-based dynamic S-Box approach for PRESENT strongly withstands cryptanalytic attacks in the IoT Network.

Task offloading in vehicular networks is hot topic in the development of autonomous driving. In these scenarios, due to the role of vehicles and pedestrians, task characteristics are changing constantly. The classical deep learning algorithm always uses a pre-trained neural network to optimize task offloading, which leads to system performance degradation. Therefore, this paper proposes a neural network fine-tuning task offloading algorithm, combining with location prediction for pedestrians and vehicles by the Payne model of fluid dynamics and the car-following model, respectively. After the locations are predicted, characteristics of tasks can be obtained and the neural network will be fine-tuned. Finally, the proposed algorithm continuously predicts task characteristics and fine-tunes a neural network to maintain high system performance and meet low delay requirements. From the simulation results, compared with other algorithms, the proposed algorithm still guarantees a lower task offloading delay, especially when congestion occurs.