Implementation Of Network Research Articles

Sustainable value networks: A focus on operational, environmental, and social performance

Smallholder paprika farmers in Zimbabwe contribute to local economies and food security but face supply chain challenges like limited market access and poor infrastructure which lead to post harvest losses and unpredictable prices. To survive, these farmers must adopt sustainable value networks to reduce operational costs and improve performance. This study sought to establish the effect of sustainable value networks on the operational performance of smallholder paprika farming in Zimbabwe. This study, using a positivist research philosophy and a quantitative approach, surveyed 288 smallholder paprika farmers in Zimbabwe. Exploratory factor analysis and partial least squares structural equation modelling were used to validate the constructs and test the hypothesised relationships. Results demonstrate a moderate level of implementation of value networks in smallholder paprika farming characterised by successes and challenges. The findings illustrated resource sharing among smallholder farmers, facilitated by initiatives, such as recycled seed exchanges and financial support through village savings and loan associations. However, results show that challenges persist, particularly with market access and financial support. Results indicate that there is a significant awareness and implementation of green supply chain management practices among smallholder paprika farmers even though they do not have access to resources and live in rural areas. The findings demonstrate that value networks significantly influence the adoption of green supply chain management practices, which in turn positively impact operational performance, environmental performance, and social performance. Green supply chain management practices were found to mediate the relationship between value networks and environmental performance, social performance, and operational performance, underlining the critical role of sustainable practices in enhancing performance outcomes. While environmental performance showed a positive effect on operational performance, the direct influence of social performance on operational performance was found to be statistically insignificant, suggesting the need for further exploration of the factors linking social benefits to operational efficiency. The research contributes to both theory and practice by presenting a sustainable value network model for smallholder paprika farmers, integrating value network, green supply chain management practices and environmental performance to enhance operational performance. Practical implications include policy recommendations to strengthen collaboration between smallholder farmers and other stakeholdersand address power imbalances with intermediaries. Future research should extend the study to other agricultural sectors and incorporate more diverse stakeholder perspectives to validate and generalise the proposed sustainable value network model.

Bidirectional synapse based on anti-resonance modulation of a photonic microring

A synaptic device is fundamental for memory and learning functions of neural networks. In this work, we demonstrated a GST (Ge2Sb2Te5)-based microring synapse with nonvolatile reconfigurable characteristics. The device shows bidirectional weight modulation during unidirectional crystallization or amorphization of GST, simulating long-term depression (LTD) and long-term potentiation (LTP). In addition, we adopted an anti-resonance pump scheme to reduce the fluctuations in pump energy coupled into the device to less than 12%. This scheme significantly enhances the programming precision of the microring synapse, achieving 24 resolvable states over 15 cycles. This work holds promise for laying the foundation for novel, to the best of our knowledge, photonic computing architectures and provides possibilities for the implementation of vision and adaptive optical neural networks that rely on bidirectional plasticity.

Deep photonic reservoir computing based on a distributed feedback laser array

Photonic reservoir computing (RC) is emerging as a competitive candidate for ultra-fast and energy-efficient neuromorphic computing, noted for its physical compatibility and straightforward training process. However, this widely appreciated form of machine learning typically employs only a single hidden layer with a feedback loop (FL), which essentially constrains the capability for complex task processing and poses challenges to integration. Here, we present an integrated deep photonic RC setup based on a distributed feedback laser array. This setup eliminates the dependence of the FL through the pre-processing termed quasi-convolution coding (QC), where the QC-based RC (QRC) significantly reduces the complexity of the network under the ensured performance. In particular, we extend this QRC into an on-chip deep structure, where this deep QRC (DQRC) exhibits remarkable superiority to its shallow counterparts. We demonstrate the augmented capabilities of DQRC through both simulations and experimental comparisons with QRC, extreme learning machine, and time-delay RC in time-dependent tasks. Moreover, the proposed deep configuration also excels in static image processing. We confirm the potential for simplifying the hardware implementations of deep neural networks, revealing a promising solution to satisfy the urgent demand for high-integration brain-inspired systems.

Using VANET as mechanism for monitoring compliance of speed and mobility restrictions: a Quito-Ecuador case study

Quito city in Ecuador is well know for its traffic issues. This is mostly generated because the geography of the capital city. It is a narrow but long territory that makes transportation to be difficult and generates traffic jams, specially in rush hours. For a long time this problem has been the center of attention of the municipality of Quito, some programs have been adopted in the urban area of the city. One of the most important was "Pico y placa", now called "Hoy no circula" because its implementation changed to have more impact in the mobility of Quito. Other program adopted by the municipality is speed control, done by fixed radars in the main highways, or by the transit agents found in strategic locations. The main purpose of this work is the analysis of the implementation of Vehicular Ad Hoc Networks(VANET) to solve some problems arising from the application of this programs in the city of Quito. VANET allows all the network to be aware of every car connected to it by the use of communication units, making it easier to control traffic flow and even controlling what cars are inside the network and what cars should not be in the network at a specific time. The simulation was done in Omnett++ and with help of SUMO and Veins to obtain the desired simulation process where data was obtained for prior analysis. At the end the paper the main results found during the research are presented, and some recommendations for the adaptation of this project to the city of Quito and what advantages will it bring. This information could be used by the municipality to adopt this project or a similar idea to solve the mobility problems found in Quito.

Wastewater-Based Epidemiological Surveillance in France: The SUM’EAU Network

Wastewater surveillance is a powerful public health tool which gained global prominence during the COVID-19 pandemic. This article describes the development and implementation of the national wastewater surveillance network in France: SUM’EAU. Preliminary work included defining a sampling strategy, evaluating/optimising analytical methods, launching a call for tenders to select network laboratories and producing wastewater monitoring indicators. SUM’EAU was then deployed in three stages: (i) a pilot study, (ii) the transfer of analytical activities from the National Reference Laboratory to four selected network laboratories, and (iii) the extension of the system to additional sampling sites. Currently, SUM’EAU monitors SARS-CoV-2 across 54 wastewater treatment plants in mainland France. Once a week on business days, 24 h flow-proportional composite samples are collected at plant inlets and transported at 5 °C (±3 °C) to partner laboratories for analysis. The analytical process involves sample concentration, RNA extraction, and digital RT-PCR/q-RT-PCR to detect and quantify the presence of the SARS-CoV-2 genome in wastewater. Subsequently, data are transferred to Santé publique France, the French National Public Health Agency, for analysis and interpretation. While SUM’EAU has been instrumental in monitoring the COVID-19 pandemic and holds significant potential for broader application, securing sustainable funding for its operation remains a major challenge.

Public Policy Network Implementation: A Case Study in the Development Urban Farming for Sustainable Food Independence in Makassar City

Urban farming uses land intensification to meet the daily need for fresh fruit and vegetables for residential areas in urban areas. Urban agriculture provides positive value in meeting food needs and practical values ​​that are meaningful for environmental and regional economic sustainability. Urban farming solves the problems above by creating green open space through open land management amid dense buildings and urban settlements. This research aims to analyze the implementation of development network policies for urban farming for sustainable food independence in Makassar City. This research uses a descriptive qualitative approach with data collection methods, namely observation, in-depth interviews, and documentation. The informants in this research are the authorities and are directly involved in the development of urban farming for sustainable food independence in Makassar City. The research results show that the implementation of the development policy network urban farming for sustainable food independence in Makassar City, it still needs to be improved through joint actions carried out between stakeholder. This is because there is still a lack of instructors assisting the Women Farmers Group (KWT) which is the target of the program urban farming in Makassar City. So, this influences the sustainability of the activities of utilizing yard land into productive land which can help in food independence for the people of Makassar City.

Automatic Diagnosis of Thyromegaly by Using Ultrasound Measurements Based on Artificial Neural Network

Background: The thyroid size increases in some diseases of this gland, which is known as goiter or thyromegaly. Thyromegaly is more prevalent in women than men. Thyroid ultrasound is a non-invasive, inexpensive, and safe method for assessing thyroid disorders. Length, width (W), and height measuring of the thyroid lobes and volume is a time-consuming process. Objectives: The object of the present study was to offer a rapid artificial neural network (ANN) system for automatic detection of thyromegaly and to investigate the relationship between thyroid dimensions and its volume. Methods: The thyroid dimensions including longitudinal (L) diameter, anterior-posterior or depth (AP) diameter, W diameter, and AP diameter of isthmus were measured among 131 individuals, assigned to thyromegaly and normal groups during the years 2018 and 2019. Proposed ANN system containing of one hidden layer, 3 neurons, and one output for representing the presence of thyromegaly was created by MATALB software. Results: The implementation of the neural network showed that the use of the measured parameters of the right lobe is able to detect thyromegaly with an accuracy of 94.74, and the isthmus information does not increase the accuracy of the network very much. Also, "width of the right lobe" is the most appropriate parameter and the isthmus thickness was the least important parameter for automatic detection of thyromegaly. Conclusions: Artificial neural network as a decision-support system can be useful in reducing measurement error while performing ultrasound in detection of thyromegaly and also reducing time of diagnostic processes

Electrosynthesis of Ru (II)-Polypyridyl Oligomeric Films on ITO Electrode for Two Terminal Non-Volatile Memory Devices and Neuromorphic Computing.

Molecular electronics exhibiting resistive-switching memory features hold great promise for the next generation of digital technology. In this work, electrosynthesis of ruthenium polypyridyl nanoscale oligomeric films is demonstrated on an indium tin oxide (ITO) electrode followed by an ITO top contact deposition yielding large-scale (junction area = 0.7 × 0.7 cm2) two terminal molecular junctions. The molecular junctions exhibit non-volatile resistive switching at a relatively lower operational voltage, ±1V, high ON/OFF electrical current ratio (≈103), low-energy consumption (SET/RESET = 27.94/14400 nJ), good cyclic stability (>300 cycles), and switching speed (SET/RESET = 25ms/20ms). A computational study suggests that accessible frontier molecular orbitals of metal-complex to the Fermi level of ITO electrodes facilitate charge transport at a relatively lower bias followed by a filamentformation. An extensive analysis is performed of the performance of binary neural networks exploiting the current-voltage features of the devices as binary synaptic weights and exploring their potential for neuromorphic logic-in-memory implementation of IMPLICATION (IMPLY) operation which can realize universal gates. The comprehensive analysis indicates that the proposed redox-active complex-based memory device may be a promising candidate for high-density data storage, energy-efficient implementation of neuromorphic networks with software-level accuracy, and logic-in-memory implementations.

Implementation of data transmission mechanism in a Bi-directional optical fiber network

Abstract Passive optical network (PON) has become the leader in delivering broadband high-speed connectivity. The paper introduces a detailed description of PON, its working principle, key features, and their potential applications. In addition, we discuss the types of PON architectures including GPON, EPON, and XG-PON with merits and demerits. Finally, we discuss the technical considerations of PONs in data transmission mechanisms, network design, and component selection. This paper further demonstrates the use of PON technology via a case study on the design and implementation of a bidirectional optical fiber network. Within this project, we went ahead to demonstrate the use of PON components including optical splitters, transmitters, receivers, and power controllers towards the development of an efficient and functional network structure. It mainly covered the results of the project since the PONs appeared to be a promising solution for obtaining high-performing and reliable broadband services.

Multi-stakeholder networks in the higher education context: a configurative literature review of university-community interactions

ABSTRACT Driven by the demand to address complex societal issues, stakeholders from higher education and society increasingly form multi-stakeholder networks. Despite their potential, realising such networks proves complex, often yielding elusive outcomes. To explore how multi-stakeholder networks navigate these complexities, this configurative literature review analyses 17 cases, revealing patterns in university-community interactions across network formation, implementation, and outcomes. Two primary modes emerged: the Centralised (or University-Centred) mode, characterised by university dominance, and the Polycentric (or Collaborative) mode, emphasising cooperative relationships. Existing on a continuum rather than as distinct categories, these modes provide a framework to interpret collaborative- and decision-making processes that occur within multi-stakeholder networks, shaping what is recognised as knowledge, and identifying who benefits most. This modal awareness enhances the potential of multi-stakeholder networks in higher education. Future research could explore the multiplicity of community perspectives. Our study serves as a stepping stone for advancing multi-stakeholder network theory and practice.

Performance analysis of artificial neural networks for predicting propagation losses in suburban environments for 4G LTE and 5G networks

<p>This study analyzes two distinct approaches for predicting path loss at frequencies of 800 MHz, 1800 MHz, and 2600 MHz in suburban areas. These frequencies are commonly utilized in broadcasting, 4G LTE, and 5G networks. Two models of Artificial Neural Networks (ANN) were implemented: an Error-Based Neural Network (EBNN), which incorporates error correction by combining empirical propagation models with an ANN, and a Terrain Parameters Based Neural Network (TBNN), which uses input parameters commonly applied in related studies, such as the distance from the transmitter to the receiver, receiver altitude, average terrain level, and azimuth angle between the transmitter and receiver. The performance of these models was evaluated using root mean square error (RMSE) and the Wilcoxon rank-sum test, comparing them with empirical propagation models such as SUI, ECC-33, Ericsson, and TR 25.942. The results were then compared with data obtained from a measurement campaign conducted along three routes in the city of Natal, Brazil. The findings from both simulations and actual measurements showed good metric alignment, particularly highlighting the performance of the error-based model. The primary contribution of this study is demonstrating that these techniques enable more accurate prediction of signal information, thereby reducing errors in the planning and implementation of wireless networks.</p>

In-Plane Polarization-Triggered WS2-Ferroelectric Heterostructured Synaptic Devices.

To date, various kinds of memristors have been proposed as artificial neurons and synapses for neuromorphic computing to overcome the so-called von Neumann bottleneck in conventional computing architectures. However, related working principles are mostly ascribed to randomly distributed conductive filaments or traps, which usually lead to high stochasticity and poor uniformity. In this work, a heterostructure with a two-dimensional WS2 monolayer and a ferroelectric PZT film were demonstrated for memristors and artificial synapses, triggered by in-plane ferroelectric polarization. It is noted that the properties of the WS2/PZT heterostructures, including photoluminescence (PL) and conductivity, can be effectively tuned by in-plane polarization. In contrast to conventional memristors, the resistance switch of our memristors relies on the dynamic regulation of Schottky barriers at the WS2/metal contacts by ferroelectric polarization. PL characterizations verified the existence of lateral fields inside the WS2 originating from the polarization of the PZT. In particular, such memristors can emulate neuromorphic functions, including threshold-driven spiking, excitatory postsynaptic current, paired-pulse promotion (PPF), and so on. The results indicate that the WS2/PZT heterostructures with in-plane polarization are promising for the hardware implementation of artificial neural networks.

A Cascaded Duplex Organic Vertical Memory with Learning Rate Scheduling for Efficient Artificial Neural Network Training

AbstractLearning rate scheduling (LRS) is a critical factor influencing the performance of neural networks by accelerating the convergence of learning algorithms and enhancing the generalization capabilities. The escalating computational demands in artificial intelligence (AI) necessitate advanced hardware solutions capable of supporting neural network training with LRS. This not only requires linear and symmetric analog programming capabilities but also the precise adjustment of channel conductance to achieve tunable slope in weight update behaviors. Here, a cascaded duplex organic vertical memory is proposed with the coupling of ferroelectric polarization effect and Schottky gate control on the same semiconducting channel, exhibiting adjustable‐slope conductance update with high linearity and symmetry. Therefore, in the chest X‐ray image detection, a fast‐to‐slow LRS is used for a bi‐layer ANN training, achieving a rapid, stable convergence behavior within only 15 epochs and a high recognition accuracy. Moreover, the proposed LRS training is also suitable for the Mackey Glass prediction task using long short‐term memory networks. This work integrates LRS into synaptic devices, enabling efficient hardware implementation of neural networks and thus enhancing AI performance in practical applications.

Neural network framework for predicting groundnut price volatility in india

Groundnut, predominantly cultivated as a rainfed crop, is highly susceptible to significant price volatility. This study aimed to investigate and enhance the performance of traditional models for forecasting the realized volatility of groundnut price returns across five Indian states (Tamil Nadu, Telangana, Karnataka, Maharashtra, and Gujarat) by evaluating traditional models and neural network-based frameworks. Using groundnut price returns data spanning fourteen years and six months (01 January 2010 to 30 June 2024), weekly realized volatility was computed. The predictive behaviour of Heterogeneous Autoregression (HAR)-based neural network frameworks was evaluated. Neural networks were assessed using time series crossvalidation, and model metrics were employed to generate Model Confidence Sets (MCS). These sets were ranked based on model inclusion. The Extended Cochran–Armitage test was applied to identify and compare the best-performing models. Subsequently, model forecasts were tested and compared using the two-sided Diebold-Mariano test, and Model Confidence Sets were generated to evaluate predictive performance. For this unconventional weekly realized volatility forecast, the HAR (1,6,12) framework emerged as the most effective. Notably, the implementation of Convolutional Neural Network (CNNs) combined with RNNs, such as Conv1D -GRU and Conv1D-LSTM, demonstrated superior and consistent predictive performance across all states. Among standalone neural networks, GRU performed on par with CNN-based RNNs. These findings highlight the potential of CNN and GRU models as effective and accurate methods for forecasting agricultural price volatility.

Implementation of Recurrent Neural Network Gated Recurrent Unit (GRU) Model for Predicting Top-Tier Bitcoin

Cryptocurrency investments are becoming increasingly popular due to their potential as digital assets, though high price volatility poses significant challenges for investment decision-making. This study employs the Gated Recurrent Unit (GRU) model to forecast the closing prices of five prominent cryptocurrencies: Bitcoin (BTC), Ethereum (ETH), Ripple (XRP), Binance Coin (BNB), and Dogecoin (DOGE), using historical data from Yahoo Finance spanning 2019 to 2024. The model's performance was assessed using evaluation metrics, including Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). The results demonstrate that BNB achieved the best performance, with a MAPE of 2.38% and RMSE of 17.03, followed by ETH and XRP, which recorded MAPEs of 2.51% and 2.64%, respectively. BTC exhibited the highest RMSE at 2280.73, highlighting its significant price volatility, while DOGE had the lowest RMSE at 0.01, despite recording the highest MAPE at 4.11%. Forecasts for the next six periods indicate that BTC and ETH are likely to experience gradual price increases, XRP and BNB are expected to stabilize, and DOGE will remain relatively stable with low volatility. The study concludes that the GRU model is effective for cryptocurrency price forecasting, but integrating it with fundamental and technical analysis could further enhance accuracy and support more informed investment decisions.

Free-space optical spiking neural network.

Neuromorphic engineering has emerged as a promising avenue for developing brain-inspired computational systems. However, conventional electronic AI-based processors often encounter challenges related to processing speed and thermal dissipation. As an alternative, optical implementations of such processors have been proposed, capitalizing on the intrinsic information-processing capabilities of light. Among the various Optical Neural Networks (ONNs) explored within the realm of optical neuromorphic engineering, Spiking Neural Networks (SNNs) have exhibited notable success in emulating the computational principles of the human brain. The event-based spiking nature of optical SNNs offers capabilities in low-power operation, speed, temporal processing, analog computing, and hardware efficiency that are difficult or impossible to match with other ONN types. In this work, we introduce the pioneering Free-space Optical Deep Spiking Convolutional Neural Network (OSCNN), a novel approach inspired by the computational model of the human eye. Our OSCNN leverages free-space optics to enhance power efficiency and processing speed while maintaining high accuracy in pattern detection. Specifically, our model employs Gabor filters in the initial layer for effective feature extraction, and utilizes optical components such as Intensity-to-Delay conversion and a synchronizer, designed using readily available optical components. The OSCNN was rigorously tested on benchmark datasets, including MNIST, ETH80, and Caltech, demonstrating competitive classification accuracy. Our comparative analysis reveals that the OSCNN consumes only 1.6 W of power with a processing speed of 2.44 ms, significantly outperforming conventional electronic CNNs on GPUs, which typically consume 150-300 W with processing speeds of 1-5 ms, and competing favorably with other free-space ONNs. Our contributions include addressing several key challenges in optical neural network implementation. To ensure nanometer-scale precision in component alignment, we propose advanced micro-positioning systems and active feedback control mechanisms. To enhance signal integrity, we employ high-quality optical components, error correction algorithms, adaptive optics, and noise-resistant coding schemes. The integration of optical and electronic components is optimized through the design of high-speed opto-electronic converters, custom integrated circuits, and advanced packaging techniques. Moreover, we utilize highly efficient, compact semiconductor laser diodes and develop novel cooling strategies to minimize power consumption and footprint.

Implementation of Artificial Neural Network for Forecasting California Bearing Ratio of Treated Cement-Laterite Soil Improved with Bamboo Leaf Ash

Implementation of Artificial Neural Network for Forecasting California Bearing Ratio of Treated Cement-Laterite Soil Improved with Bamboo Leaf Ash

IOT NETWORKS AND TECHNOLOGICAL INNOVATION IN INDUSTRY

Technology has been seen as a competitive advantage in our industrial environments. From basic activities such as planting and farming to the transformation and development of finished products, it can be used domestically to add value, safety and profitability to industries. This scientific article addresses the relevance of industrial networks in the Industry 4.0 era, focusing on the implementation and organization of networks that integrate IoT devices - Internet of Things - to optimize processes and generate competitive advantages. The different types of industrial networks, communication protocols, connectivity technologies for IoT devices and equipment used will be explored. In addition, the challenges and opportunities in the implementation of IIoT networks will be analyzed, such as security, scalability and interoperability. Finally, case studies will be presented that demonstrate how the adoption of IIoT networks can generate tangible benefits for industries, such as increased efficiency, cost reduction and improved quality of products and services.

STRATEGIC NETWORK PLANNING FOR OPTIMIZING DIGITAL TRANSFORMATION IN THE COAL MINING INDUSTRY

The coal mining industry is one of the most important sectors in Indonesia's economy, and it has become a vital part of the national economy. As a result, the mining industry has become more and more digital. The application of the overlay method in this study aims to improve operational efficiency and work safety in the coal mine of PT Putra Perkasa Abadi (PPA) in Indonesia. The overlay method combines WiFi and LTE networks in the mining area, which improves network performance in terms of throughput, latency, packet loss, and signal coverage. The implementation of Strategic Network Planning to Optimize Digital Transformation in the Coal Mining Industry has proven to be effective in improving the quality of networks that support digital transformation in mining areas. The solution has the potential to be applied to other industrial sectors with similar operational challenges, optimizing the use of network technologies to support sustainability and productivity. Overall, this study makes a significant contribution to designing and implementing network systems that can support operational efficiency, improve occupational safety, and offer sustainable and adaptive solutions in the industry, ultimately supporting the digitalization and transformation of the industry.

Analysis of the Level of Public Transportation Accessibility at the Type A Bimoku Inter-Border Terminal (Albn), Kupang City

The Bimoku Type A Cross Border Terminal located in Kupang City, East Nusa Tenggara, is a cross-border transport hub that has been operating since 2023. However, its performance has not been optimal and accessibility to this terminal is still low. This study aims to analyse the level of accessibility of public transport to the Type A Bimoku Cross-Border Terminal in Kupang City and provide recommendations for improving performance. The method used is Generalised Cost (GC) analysis with a do nothing and do something approach. The results show that the largest GC values in the existing conditions are in the Fatukoa, Naioni, and Bello zones. The implementation of the new route network in the do something scenario succeeded in significantly reducing the GC value, thereby increasing the accessibility and efficiency of transportation to the Bimoku Type A Cross Border Terminal in Kupang City. Recommendations are to develop new public transport routes and improve intermodal connectivity to support overall terminal performance.