Rushendra Rushendra

Real-world IoT network security generates traffic at big-data scale with extreme class imbalance, temporal non-stationarity, and continuously evolving attack strategies that overwhelm static supervised classifiers. This paper presents a cognitive computing framework for network intrusion detection: a CNN–LSTM–DQN architecture with Prioritized Experience Replay (PER) evaluated on a 5,000,000-flow naturalistic sample of the TON_IoT Processed_Network dataset (4,000,000 training/1,000,000 temporally held-out test flows; 94.5% attack ratio) under a strict temporal split. The cognitive agent optimizes detection decisions using an Alerts per Million Flows (ARMF)-aware reward function that encodes both alert-fatigue cost and missed-attack penalty. We conduct a cross-attack-family generalization study: the methodology—architecture template, reward design, and hyperparameter calibration—is inherited from a framework previously validated on CSE-CIC-IDS2018, re-instantiated and retrained on the structurally different TON_IoT environment, and compared against the previously published benchmark. Initialization sensitivity is characterized across five independent random seeds using paired Wilcoxon signed-rank and t-tests. Across the five seeds, the proposed X2 model attains recall 0.833 ± 0.306 and F1 0.874 ± 0.241 (mean ± sample SD), versus the supervised X1 baseline at 0.858 ± 0.178 and 0.912 ± 0.116; the best-performing seed (42) achieves 97.52% accuracy, 98.02% attack recall, 99.46% precision, and 98.73% F1-score on 1,000,000 held-out XSS flows—an attack family entirely absent from training—with temporal stability variances of 4.63 × 10⁻⁷ (recall) and 1.38 × 10⁻⁷ (F1). The X2 advantage observed among the four stable seeds is not statistically demonstrated at n = 5 (statistical power ≈ 5.1%); the initialization-sensitivity finding itself, including one degenerate alert-suppression seed, is reported as a primary contribution. A formal, exactly additive ARMF decomposition distinguishes the detected-attack (structural) component (99.46%) from the model-induced false-positive component (0.54%), and we report a multi-seed, ARMF-aware cognitive IDS evaluation on naturalistic TON_IoT traffic under an unseen-attack-family test condition that, to the best of our knowledge, has not been reported in the surveyed RL-based NIDS literature.

Purpose – This study aims to examine intrusion detection as a policy learning problem and determine how replay strategy alone controls the operational trade-off between attack recall and alert volume under extreme class imbalance. Design/methods/approach – A controlled ablation study was conducted using a fixed CNN–LSTM feature extractor, fixed feature set, and fixed reward structure combined with a Deep Q-Network (DQN) agent. Three configurations were compared: naïve DQN without replay, uniform experience replay with a target network, and Prioritized Experience Replay (PER). Experiments used the CSE-CIC-IDS2018 dataset, consisting of 10,788,508 training flows and 2,697,128 testing flows, with attack events occurring at fewer than 70 per million flows. Performance was assessed through recall and alerts per million flows (ARMF). Findings - Supervised CNN–LSTM baselines achieved recall above 95% but generated 31,000–45,000 ARMF. Naïve DQN reduced ARMF to 383 but sharply decreased recall to 42.47%. Uniform replay improved recall to 84.95% but increased ARMF to 12,728. PER achieved the most balanced operating point, reaching 91.40% recall at 1,031 ARMF, approximately 30 times fewer alerts than the supervised CNN–LSTM reference, with a 5.91-percentage-point recall cost. Research implications/limitations – The findings indicate that replay distribution is a critical operational design variable for controlling alert volume in highly imbalanced intrusion detection settings. However, the study is limited to a fixed backbone, feature set, reward shape, and dataset. Originality/value – This study demonstrates that replay strategy can substantially reshape IDS operating points independently of model architecture or feature representation.

This study addresses the challenge of accurately clustering earthquake events based on depth to better understand seismic activity patterns in Sulawesi from 2019 to 2023. Traditional clustering algorithms often fail to capture the complex spatial and depth-based structures of earthquake data. To overcome this, we employed the DBSCAN algorithm, which is well-suited for identifying irregularly shaped clusters and handling noise in spatial datasets. A key focus of this research is the systematic optimization of DBSCAN’s parameters—epsilon (ε) and minimum samples (min_samples)—using a grid search approach. Epsilon values varied from 0.1 to 0.5, and min_samples ranged from 6 to 60. The optimal parameters, determined using the Calinski-Harabasz (CH) index, were ε = 0.4 and min_samples = 54. Compared with previous heuristic settings, the optimized configuration produced better separated and more interpretable clusters. Using the optimized parameters, nine distinct clusters were identified, capturing meaningful patterns in both depth and magnitude. The results revealed that shallow earthquakes (0–20 km) tend to exhibit greater magnitude variation, with some clusters averaging magnitudes up to 3.7. This suggests a higher seismic hazard potential associated with brittle crustal activity. The findings contribute to seismic hazard analysis by providing a more robust understanding of three-dimensional earthquake distribution, aiding regional risk assessment and disaster preparedness efforts. These insights can support agencies such as BMKG and BPBD in hazard mapping, sensor deployment, and contingency planning for high-risk zones.

Sulawesi is a region in Indonesia known for its significant seismic activity, and its history of impactful earthquakes makes it an area of crucial importance for in-depth analysis. This study analyses earthquake occurrence data in the Sulawesi region from 2019 to 2023 using clustering methods with the DBSCAN algorithm. The utilization of the DBSCAN algorithm was chosen for its ability to cluster data based on spatial density, well-suited for analyzing the spatial patterns of earthquakes. DBSCAN is known for its effectiveness in identifying spatial clusters, especially in handling data with undefined density patterns. The primary aim of this research is to identify spatial earthquake occurrence patterns, classify regions with similar earthquake occurrence rates, describe the characteristics of the resulting spatial clusters, and identify seismic gap areas. The results of analysis and clustering using the DBSCAN algorithm have identified clusters with earthquake depth characteristics, which are expected to make a significant contribution to mapping and understanding earthquake vulnerability and distribution in this region. These findings can aid in more effective disaster mitigation planning, support sustainable development efforts, and enhance earthquake preparedness and response in Sulawesi. This study contributes to a better understanding of earthquake patterns and potential seismic gaps in Sulawesi, which is crucial for developing improved risk mitigation strategies and supporting sustainable development policies.

Currently, utilizing virtualization technology in data centers often imposes an increasing burden on the host machine (HM), leading to a decline in VM performance. To address this issue, live virtual migration (LVM) is employed to alleviate the load on the VM. This study introduces a hybrid machine learning model designed to estimate the direct migration of pre-copied migration virtual machines within the data center. The proposed model integrates Markov Decision Process (MDP), genetic algorithm (GA), and random forest (RF) algorithms to forecast the prioritized movement of virtual machines and identify the optimal host machine target. The hybrid models achieve a 99% accuracy rate with quicker training times compared to the previous studies that utilized K-nearest neighbor, decision tree classification, support vector machines, logistic regression, and neural networks. The authors recommend further exploration of a deep learning approach (DL) to address other data center performance issues. This paper outlines promising strategies for enhancing virtual machine migration in data centers. The hybrid models demonstrate high accuracy and faster training times than previous research, indicating the potential for optimizing virtual machine placement and minimizing downtime. The authors emphasize the significance of considering data center performance and propose further investigation. Moreover, it would be beneficial to delve into the practical implementation and dissemination of the proposed model in real-world data centers.

The aim of this research is to implement an intrusion detection system using rule-based methods on websites. The approach in this research is the development of an intrusion detection system (IDS). research results after implementation, testing, and acceptance of test results, conclusions can be drawn. The detection system can be implemented well in website-based applications using a rule-based method.

Pulau Jawa merupakan salah satu daerah rawan gempa bumi dan memiliki populasi penduduk yang padat. Dalam hal ini pemerintah diharuskan untuk memberikan perhatian lebih pada penanggulangan bencana khusunya di pulau jawa. Maka dari itu penelitian ini hadir untuk mengetahui dampak gempa bumi berdasarkan tingkat keparahannya dengan cara melakukan klasterisasi data pesebaran dampak bencana gempa bumi (2012 - 2021) dari Badan Nasional Penanggunlangan Bencana (BNPB) menggunakan algoritma K-Means Clustering. Dari penelitian ini ditemukan bahwa dampak bencana dapat dibagi menjadi 4 klaster. Klaster 1 memiliki dampak bencana paling banyak meliputi meninggal, luka, menderita, mengungsi, kerusakan rumah, fasilitas pendidikan, fasilitas kesehatan, fasilitas ibadah, kantor, jembatan, dan kios. Klaster ini memiliki Mean Absolute Error (MAE) senilai 0,017, Mean Square Error (MSE) senilai 0,002, standar deviasi senilai 0,255 dan variance senilai 0,065. Klaster 2 meliputi meninggal, luka, menderita, mengungsi, rumah, fasilitas pendidikan, fasilitas kesehatan, fasilitas ibadah, pada korban menderita, mengungsi, kerusakan rumah dan fasilitas ibadah. Klaster ini memperoleh MAE senilai 0,053, MSE senilai 0,011, standar deviasi senilai 0,249 dan variance senilai 0,062. Klaster 3 meliputi korban luka, menderita, mengungsi, kerusakan rumah, fasilitas pendidikan, fasilitas kesehatan, fasilitas ibadah dan kantor. klaster ini memperoleh MAE senilai 0,102, MSE senilai 0,039, standar deviasi senilai 0,212 dan variance senilai 0,045. Klaster 0 memiliki dampak bencana paling sedikit meliputi kerusakan rumah, fasilitas pendidikan, fasilitas kesehatan, fasilitas ibadah, kantor, dan kios. klaster ini memperoleh MAE sebesar 0,021, MSE senilai 0,005, standar deviasi senilai 0,251 dan variance senilai 0,063.

Dalam sebuah perusahaan penyedia layanan jaringan internet, di tuntut untuk memiliki kulitas jaringan high availability dan high reliability. Dalam mendukung kualifikasi jaringan internet terbaik maka salah satunya perlu menjaga kestabilan bandwidth internet pelanggan. Salah satunya menjaga kepadatan traffic data pada jaringan internet. Congestion merupakan pengumpulan paket data yang melebihi kapasitas bandwidth yang tersedia padasebuah link, hal ini memberikan dampak penurunan kinerja jaringan internet. Permasalahan di atas dapat di selesaikan salah satunya dengan menerapkan penggunaan metode link aggregation dan teknologi load balance. Pada penelitian ini penulis menerapkan metode link aggregation yang digunakan dalam merancang redundancy link dan load balance dalam membuat skema membagi traffic untuk penyeimbang beban berdasarkan src address dan src port, serta dst address dan dst port. Dari hasil pengujian penggunaan link aggregation dan load balance pada penenlitian ini dapat membantu menjaga kestabilan throughput dengan nilai pengukuran sebesar 10GB dengan standart MTU (Maximum Transmission Unit) yang menandakan hasil test pengukuran paket data terbesar yang dapat di transmisikan melalui sebuah jaringan. Keyword : link aggregation, load balance, congestion, MTU

M-ary frequency shift keying (FSK) is a low-power, low-data-rate modulation scheme currently used by manufacturers of data transmission equipment. Inter symbol interference (ISI) occurs in all communication systems. To analyze the effect of the raised cosine filter and adaptive equalizer on reducing the ISI, the binary FSK (BFSK) modulation technique has been studied extensively in this research. In this study, we have selected the square root raised cosine filter and the sign least mean square (LMS) equalizer. The bit error rate (BER) performance of the 2-FSK system with the additive white Gaussian noise (AWGN) channel is evaluated and analyzed with the help of Simulink. The best BER value of 1.7e-03 was obtained in this study.