The aim of the study was to compare microleakage and fracture loads of all ceramic crowns luted with conventional polymer resins and polymeric bioactive cements and to assess the color stability of polymeric bioactive cements. Seventy-five extracted premolar teeth were tested for fracture loads and microleakage in all-ceramic crowns cemented with two types of polymeric bioactive cements and resin cements. In addition, the degree of color change for each cement with coffee was assessed. Thirty maxillary premolar teeth for fracture loads and thirty mandibular premolar teeth for microleakage were prepared; standardized teeth preparations were performed by a single experienced operator. All prepared specimens were randomly distributed to three groups (n = 20) based on the type of cement, Group 1: resin cement (Multilink N); Group 2: polymeric bioactive cement (ACTIVA); Group 3: polymeric bioactive cement (Ceramir). The cementation procedures for all cements (Multilink, ACTIVA, and Ceramir) were performed according to the manufacturers’ instructions. All specimens were aged using thermocycling for 30,000 cycles (5–55 °C, dwell time 30 s). These specimens were tested using the universal testing machine for fracture strength and with a micro-CT for microleakage. For the color stability evaluation, the cement specimens were immersed in coffee and evaluated with a spectrometer. Results: The highest and lowest means for fracture loads were observed in resin cements (49.5 ± 8.85) and Ceramir (39.8 ± 9.16), respectively. Ceramir (2.563 ± 0.71) showed the highest microleakage compared to resin (0.70 ± 0.75) and ACTIVA (0.61 ± 0.56). ACTIVA cements showed comparable fracture loads, microleakage, and stain resistance compared to resin cements.

As cyber-attacks evolve in complexity and frequency; the development of effective network intrusion detection systems (NIDS) has become increasingly important. This paper investigates the efficacy of the XGBoost algorithm for feature selection combined with deep learning (DL) techniques, such as ANN, 1DCNN, and BiLSTM, to create accurate intrusion detection systems (IDSs) and evaluating it against NSL-KDD, CIC-IDS2017, and UNSW-NB15 datasets. The high accuracy and low error rate of the classification models demonstrate the potential of the proposed approach in IDS design. The study applied the XGBoost feature extraction technique to obtain a reduced feature vector and addressed data imbalance using the synthetic minority oversampling technique (SMOTE), significantly improving the models' performance in terms of precision and recall for individual attack classes. The ANN + BiLSTM model combined with SMOTE consistently out performed other models within this paper, emphasizing the importance of data balancing techniques and the effectiveness of integrating XGBoost and DL approaches for accurate IDSs. Future research can focus on implementing novel sampling techniques explicitly designed for IDSs to enhance minority class representation in public datasets during training.