Increased industrial activity in South Cikarang has limited the availability of agricultural land, encouraging the adoption of controlled environment agriculture systems. This study describes the design and implementation of a smart hydroponic greenhouse that is fully supported by a 600 Wp solar photovoltaic (PV) system and controlled using an industrial-grade programmable logic controller (PLC). This system automatically regulates temperature and humidity through exhaust fans and sprayers based on real-time sensor feedback. Experimental results show that when the internal temperature exceeds 31 °C, the control system recovers to 29.7 °C within 15 minutes and maintains a temperature range of 24–30 °C. Relative humidity is maintained within the optimal range of 75–90%. The PV system produces an average daily energy output of approximately 2.0 kWh, resulting in an energy self-sufficiency ratio (ESR) of 138%, which indicates excess energy production compared to system demand. These results prove that the integration of industrial automation with renewable energy provides reliable environmental control, high energy efficiency, and operational stability for hydroponic greenhouse applications in urban industrial areas.

Pooling layers are essential in convolutional neural networks (CNNs) for reducing data size while preserving key features. Traditional methods such as Max and Average pooling have limitations. Max pooling is sensitive to noise, while Average pooling treats all activations equally. Although T-Max-Avg pooling addresses these limitations through adaptive top-k selection, its rigid decision rule requires multiple threshold comparisons and limits efficiency, motivating a simpler decision mechanism. This study introduces average-thresholding pooling (ATP), a simplified adaptive method that replaces multiple threshold comparisons with a single decision based on the average of the top-k activations. This design improves computational efficiency and reduces sensitivity to outliers. Experiments on the STL-10 dataset using a LeNet-5 architecture show that the proposed method achieves accuracy comparable to T-Max-Avg pooling (~55.5%) while consistently improving both training efficiency and inference speed. These results indicate that ATP provides a lightweight and practical alternative for CNN-based image classification, offering an improved balance between classification performance and computational efficiency.

Vehicle-to-vehicle (V2V) communication is a key component of intelligent transportation systems (ITS), enabling seamless data exchange between vehicles to limit collision risks. This study presents a hybrid communication framework that integrates light fidelity (LiFi) and wireless fidelity (WiFi) technologies to enhance safety and reliability in accident prevention. Lifi using visible light communication, provides line-of-sight for short-range communication, while WiFi ensures long-range coverage in dynamic traffic environments. The proposed system allows vehicles to share speed, braking, and positional data, enabling timely warnings to drivers in high-risk scenarios. The system fuses data communication protocol design, simulation, prototype development, testing, and evaluation. The prototype model was designed and simulated to evaluate the performance of the system in terms of functionality, timing and reliability. Results indicate that the hybrid LiFi-WiFi system improves data transmission efficiency and reduces delay compared to standalone wireless systems. This approach demonstrates significant potential in developing safer transportation networks by combining complementary wireless technologies for V2V communication.

This article presents our contribution to speaker recognition using Arabic numerals. This recognition is based on hybridization between the time encoded signal processing and recognition (TESPAR) technique and vector quantization (VQ), in order to consolidate the classification step thanks to this combination. To set up an effective and efficient recognition system, we used a corpus recorded under ideal conditions, minimizing the differences between the reference corpus and the test corpus. We also applied the linear discriminant analysis (LDA) technique in order to discriminate the acoustic vectors and minimize the representative space. This hybridization indicated a quantifiable increase in the speaker recognition rate with the ten Arabic numerals (0–9).

Hyperparameter optimization is a crucial process for enhancing the performance of deep learning models, particularly in the context of Indonesian sentiment classification. This study examines the impact of varying learning rates on a long short-term memory (LSTM) architecture trained with the adaptive moment estimation (Adam) optimizer. The dataset comprises 9,295 Indonesian comments automatically labeled by the Indonesian Bidirectional Encoder Representations from Transformers (IndoBERT) model. Stratified k-fold cross-validation was employed to maintain class balance during training. Learning curves were analyzed to evaluate convergence and identify potential overfitting, while early stopping was applied when performance improvements became insignificant. The one-way analysis of variance (ANOVA) test (p-adj = 0.000575 < 0.05) revealed significant differences among the learning rate variations. Post-hoc analysis indicated the learning rates of 0.0001, 0.001, and 0.002 differ significantly from 0.02. Descriptive statistics showed that a learning rate of 0.001 was the most optimal, achieving the highest validation accuracy while maintaining a relatively low variance. Evaluation across two data categories demonstrated that lower learning rates (0.0001 and 0.002) achieved the best accuracy, 78.71% on in-domain data, whereas higher learning rates (0.01 and 0.02) performed better on cross-domain data with 36% accuracy. These findings highlight the crucial role of learning rate selection in determining model stability and generalization capability.

Accurate modelling of milk cooling dynamics is essential to maintain product quality and improve energy efficiency in small-scale dairy operations. This study aims to develop a dynamic model for a batch milk-cooling system used at Koperasi Unit Desa Sinau Andandani Ekonomi (KUD SAE) Pujon. Synthetic temperature data were generated under controlled perturbations reflecting actual process conditions, and the data were analysed using the output error (OE) identification method implemented in the MATLAB System Identification Toolbox. Several OE model structures were compared using statistical indicators, including the coefficient of determination (R²) and root mean square error (RMSE). The OE (2,2,1) model achieved the best performance with R² = 0.9923 and RMSE = 0.0600, accurately representing the first-order dynamics of the cooling process. The identified model provides a reliable foundation for process optimisation, controller design, and operator training in dairy systems. Although the validation is limited to simulated data, the proposed approach offers substantial potential for real-time implementation and can be extended to other temperature-sensitive food processes.

Wireless sensor networks (WSNs) comprise large numbers of sensor nodes that are highly constrained by limited battery power, making energy-efficient routing essential for sustaining network lifetime and service quality. Among existing solutions, the general self-organized tree-based energy balancing (GSTEB) pro tocol with clustering has been widely adopted for energy-aware communication. However, GSTEB and its clustered variant often suffer from energy imbalance, high packet loss, and reduced quality of service (QoS) due to excessive load on cluster heads (CHs). To address these challenges, this paper introduces an enhanced routing framework that integrates firefly optimization with clustered GSTEB(CGSTEB)andintroduces subordinate energy alert gateways (SEAGs). The firefly algorithm is applied to optimize CH selection through a fitness func tion that balances residual energy and node proximity, ensuring efficient cluster formation and adaptive load distribution. Meanwhile, SEAGs establish a two hop communication model between CHs and the base station (BS), reducing CH energy consumption and preventing premature node failures. Simulation exper iments conducted in NS2 demonstrate that the proposed firefly-CGSTEB with SEAG significantly improves QoS metrics, including network lifetime, energy utilization, throughput, and packet loss rate, compared with conventional CG STEB. These results confirm the effectiveness of combining metaheuristic opti mization with gateway-assisted routing for resilient and energy-efficient WSNs.

Speech signal analysis aims to identify patterns within data to develop effec tive recognition algorithms. This process primarily utilizes feature extraction techniques such as linear predictive coding (LPC), linear predictive cepstral co efficients (LPCCs), and Mel-frequency cepstral coefficients (MFCCs). These features are crucial for constructing recognition algorithms that leverage both statistical and deep learning methods. While deep learning models require ex tensive datasets, they often prove unsuitable for low-resource languages. The Hidden Markov model (HMM)is the most widely adopted statistical framework in speech processing. However, HMMs are characterized by state-dependent models, where each state interacts only with its neighboring states. This limita tion restricts HMMs from capturing long-term signal properties, highlighting the need for addressing these constraints at the feature extraction stage. Most feature extraction methods rely on short-term signal processing, which further limits the comprehension of speech utterances. To overcome these limitations, alter native methods are necessary to capture more comprehensive patterns. This pa per presents a graph-based approach for analyzing speech trajectories and their temporal properties, which are subsequently validated using HMMs in speech recognition tasks. Graph-based representations on a low-resource Telugu dataset improve recognition accuracy by 13% while reducing processing time compared to traditional LPC.

Chronic autoimmune gastritis (CAG) is a condition in which the stomach membrane is significantly impacted by inflammation. Despite the availability of numerous modern medical techniques, the detection of this condition continues to be a difficult challenge. White light endoscopy (WLE) has been employed to diagnose gastritis, but it has been subject to certain constraints. This technique is most effective when executed by an endoscopist who possesses a high level of expertise. In the present day, WLE is frequently accompanied by artificial intelligence (AI) due to its superior ability to detect defects that lead to damage. Recently, there has been a substantial increase in the efficacy of AI in conjunction with the expertise of endoscopists in the detection of CAG. The 25,216 intriguing case studies were examined in the eight selected studies. The collection comprised 84,678 frames and 10,937 images. The AI was 94% sensitive (95% CI: 0.88-0.97, I2 = 96.2%) and 96% specific (95% CI: 0.88-0.98, I2 = 98.04%). The receiver operating characteristic curve had an area of 0.98 (95% confidence interval: 0.96–0.99). A camera is highly effective when combined with AI to assist in the identification of CAG and is advantageous for clinical review.

The study of lightning effects on distribution lines is of vital importance for the reliability and safety of electrical systems, as lightning is one of the main causes of failures. The purpose of this study is to perform a bibliometric analysis to evaluate academic productivity trends and research trajectories in this field. The methodology was based on a comprehensive search of the Scopus database, from which a total of 545 articles published between 1932 and 2024 were analyzed. For the analysis, the VOSviewer tool and the Bibliometrix library in R were used. The results reveal a constant increase in productivity since the 1970s, with Japan and China emerging as the most prolific countries. The research has evolved from early theoretical and experimental studies toward the use of advanced computational models and, more recently, the application of machine learning techniques for fault detection. In conclusion, the findings of this study provide a consolidated view of the field, which is fundamental for engineers to be able to design more robust protection systems and to guide future research toward model validation and the integration of renewable energy technologies.