Claim Missing Document
Check
Articles

Found 2 Documents
Search

AVX2 SIMD Optimization for DSP Load and QoS in a srsRAN-Based Private LTE Network Muhammad Arcy Alfaathir; Sopian Soim; Mohammad Fadhli; Achmad Aflah Jamazy
Aviation Electronics, Information Technology, Telecommunications, Electricals, and Controls (AVITEC) Vol 8, No 2 (2026): August
Publisher : Institut Teknologi Dirgantara Adisutjipto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28989/avitec.v8i2.4147

Abstract

Private 4G LTE networks built on open-source platforms provide cost-effective localized connectivity. However, executing baseband Digital Signal Processing (DSP) imposes a massive computational burden on general-purpose CPUs. This study evaluates the correlation between DSP load and end-to-end Quality of Service (QoS) in a USRP B210-based Private 4G LTE prototype using srsRAN and Open5GS. To prevent CPU saturation, Advanced Vector Extensions 2 (AVX2) SIMD instructions and CPU core affinity were applied. The experimental design evaluated the system using two concurrent User Equipment (UEs) under Line-of-Sight (LOS) outdoor conditions. Compared to a non-optimized baseline, the AVX2 optimization successfully stabilized the host processor at a 60.8% peak load and achieved a downlink throughput of 35.3 Mbps without radio underflows. However, multiplexing complex baseband signals under heavy concurrent traffic severely congested the OS-level queues. This caused severe bufferbloat, escalating the average end-to-end latency to 2021 ms compared to its idle state. These findings demonstrate that while AVX2 optimization resolves the CPU bottleneck, software-induced bufferbloat remains the primary limitation in SDR deployments.
Data Integrated K-Means Clustering And Random Forest Classification For Crop Recommendation Based On Environmental Parameters Aryanti Aryanti; M. Dimas Putra Ramadhan; Muhammad Arcy Alfaathir; Ghefira Fariah; Putri Arum Sari
Journal of Technology and Informatics (JoTI) Vol. 8 No. 2 (2026): Vol. 8 N. 2 (2026)
Publisher : Universitas Dinamika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37802/

Abstract

The agricultural sector plays a strategic role in Indonesia’s economy, yet inappropriate crop selection under specific environmental conditions can reduce yields and cause economic losses. Existing studies commonly apply individual classifiers to environmental data, while clustering is often used only for descriptive analysis. This study proposes an integrated two-stage pipeline combining K-Means clustering and Random Forest classification for crop recommendation. First, K-Means groups 22 crop types based on four environmental parameters: temperature, humidity, soil pH, and rainfall. The resulting cluster membership is then encoded as an additional categorical feature and combined with normalized environmental features for Random Forest classification. Experiments using 2,200 samples from Kaggle identified four clusters, achieving a Davies–Bouldin Index of 0.84 and a Silhouette Score of 0.61. The integrated model achieved 97.7% test accuracy, with precision, recall, and F1-score of 0.99, outperforming the Random Forest baseline accuracy of 96.9%. These findings demonstrate the potential benefits of incorporating unsupervised cluster information into supervised classification. This approach offers a reusable feature-augmentation framework for agricultural intelligent decision support systems.