Estimating the difficulty of chess puzzles provides a rich testbed for studying human-computer interaction and adaptive learning.Building on recent advances and the FedCSIS 2025 Challenge, we address the task of predicting chess puzzle difficulty ratings using a multi-source representation approach.Our approach integrates pre-trained neural embeddings of board states, solution move sequences, and engine-derived success probabilities.These heterogeneous features are fused via dedicated embedding and projection layers, followed by a multilayer perceptron regressor.Post-processing calibration and model ensemble further enhance robustness and generalization.Experiments on the FedCSIS 2025 dataset demonstrate that our method effectively leverages both structural and empirical information, achieving strong predictive performance.Our approach achieved fifth place on the final official leaderboard, highlighting the effectiveness of combining neural representations with domainspecific probabilistic features for robust chess puzzle difficulty prediction.

With the digital transformation of enterprises, the increasing complexity of their internal information systems poses a growing challenge in terms of insider threats. Most existing research focuses on user-level and session-level insider threat detection, neglecting activity-level detection, leading to a lack of fine-grained insider threat detection. To tackle the aforementioned issue, we propose MADE, a novel method for detecting malicious activities within enterprise environments. MADE first encodes user multi-source activity logs into activity sequences and learns the semantic representations of activities within the sequences through embedding. Following this, we design an activity detection network based on Bidirectional Long Short-Term Memory (BiLSTM), Convolutional Neural Network (CNN), and Conditional Random Field (CRF). Combining adversarial training, our activity detection network learns the embedded activity sequences and identifies malicious activities. Extensive experimental results on the CERT R4.2 and R5.2 datasets demonstrate the effectiveness of our proposed MADE method.

In complex battlefield environments, Flying Ad-hoc NETwork (FANET) faces challenges of manually extracting communication interference signals features, low recognition rate in strong noise environment, and inability to recognize unknown interference types. To solve these problems, one Simple Non-local Correction Shrinkage (SNCS) module is constructed, which modifies the soft threshold function in the traditional denoising method and embeds it into the neural network, so that the threshold can be adjusted adaptively. Local Importance-based Pooling (LIP) is introduced to enhance the useful features of interference signals to reduce noise in the downsampling process, and the joint loss function is constructed by combining cross-entropy loss and center loss to jointly train the model. To distinguish unknown class interference signals, the acceptance factor is proposed, and the One Class Support Vector Machine Simplified Non-local Residual Shrinkage Network (OCSVM-SNRSN) model with the ability of both known class recognition and new class rejection is constructed by combining OCSVM and SNRSN. Experimental results show that the recognition accuracy of the OCSVM-SNRSN model is the highest in the scenario of low Jamming Noise Ratio (JNR). The accuracy is increased by about 4%-9% compared with other methods on the known class interference signal dataset, and the recognition accuracy reaches 99% when the JNR is -6dB. At the same time, compared with other methods, the False Positive Rate (FPR) for recognizing unknown class interference signals drops to 9%.

Predicting the cost of forwarding contract is a severe challenge to road transport management system.The transportation cost of a forwarding contract often depends on many factors.It is hard for humans to evaluate the various factors in transportation and calculate the cost of forwarding contract.In this paper, we propose an approach to address such a problem by following the sequence of machine learning steps which consist of data analysis, feature engineering and model construction.First, we conduct a detailed analysis of the given data.Then, we generate effective features to characterize the cost of forwarding contract and eliminate redundant features.Finally, in the model construction phase, we propose a gradient boosting decision tree based method to train and predict the cost of forwarding contract.The proposed approach achieves RMSE scores of 0.1391 on the test set, which is the 2 nd final score in the competition.

Predicting victories in video games from rich history of gameplay logs is a severe challenge to game developers. It is hard for humans to evaluate the real-time game situation and predict who will win the video game. In this paper, we propose an approach to this problem by following the sequence of machine learning steps which consist of feature engineering, feature selection, and model construction. We conduct a detailed analysis of the game logs and generate effective features from different granularity gameplay logs in the feature engineering phase. Then, we design a group based recursive feature elimination method for feature selection. In model construction, we present an ensemble approach that combines stacking and averaging for prediction to improve the generalization performance of models. The proposed approach achieves AUC scores of 0.8997 on the test set, which is the highest final score in the competition.

Intelligent reflecting surface (IRS) has been proposed as a very promising technique for beyond 5G and 6G communications. In this paper, we apply IRS to enhance the secure transmission of secondary user in a multi-input multioutput (MIMO) cognitive radio (CR) wiretap channel. Since the study of secure IRS-assisted CR communication is still an open problem, all the existing numerical solutions for enhancing secure communications in non-CR setting as well as non-secure communications in CR setting in the literature fail to this work due to the complicated structure of objective functions as well as the constraints. Therefore, to maximize the secrecy rate of secondary user, an efficient alternating optimization (AO) algorithm is proposed to jointly optimize the transmit covariance at base station and phase shift coefficients at IRS. Simulation results show that our proposed algorithm have fast monotonic convergence as well as better performance on enhancing the secrecy rate than the benchmark schemes.

In this paper, an intelligent reflecting surface (IRS) assisted spectrum sharing underlay cognitive radio (CR) wiretap channel (WTC) is studied, and we aim at enhancing the secrecy rate of secondary user in this channel subject to total power constraint at secondary transmitter (ST), interference power constraint (IPC) at primary receiver (PR) as well as unit modulus constraint at IRS. Due to extra IPC and eavesdropper (Eve) are considered, all the existing solutions for enhancing secrecy rate of IRS-assisted non-CR WTC as well as enhancing transmission rate in IRS-assisted CR channel without eavesdropper fail in this work. Therefore, we propose new numerical solutions to optimize the secrecy rate of this channel under full primary, secondary users’ channel state information (CSI) and three different cases of Eve’s CSI: full CSI, imperfect CSI with bounded estimation error, and no CSI. To solve the difficult non-convex optimization problem, an efficient alternating optimization (AO) algorithm is proposed to jointly optimize the beamformer at ST and phase shift coefficients at IRS. In particular, when optimizing the phase shift coefficients during each iteration of AO, a Dinkelbach based solution in combination with successive approximation and penalty based solution is proposed under full CSI and a penalty convex-concave procedure solution is proposed under imperfect Eve’s CSI. For no Eve’s CSI case, artificial noise (AN) aided approach is adopted to help enhancing the secrecy rate. Simulation results show that our proposed solutions for the IRS-assisted design greatly enhance the secrecy performance compared with the existing numerical solutions with and without IRS under full and imperfect Eve’s CSI. And positive secrecy rate can be achieved by our proposed AN aided approach given most channel realizations under no Eve’s CSI case so that secure communication also can be guaranteed. All of the proposed AO algorithms are guaranteed to monotonic convergence.

Due to the oceanic climate and frequent earthquakes in Japan, bridge health diagnosis is a problem of greater complexity. In bridge diagnosis system, we develop a wireless sensor network to sample and gather the vibration data of bridge. Time synchronization is a crucial component for the wireless sensor network (WSN), because large populations of sensor nodes will collaborate in order to complete the measuring data at the same time, data gathering, data fusion and localization. In the wireless sensor network with large scale of energy limited nodes, multi-hop time synchronization is necessarily applied. To solve above mentioned problem, some protocols are proposed. However most of the algorithms mainly focus on the precision of synchronization. In fact energy efficiency is also a challenge in a resource-limited WSN. In this paper a novel time synchronization scheme is proposed with the purpose of reducing energy consumption and lengthening whole WSN' life. Performance analyses, simulations and realization in node hardware of WSN are also presented.