Search Results (29)

Continuous and accurate biomass measurement is a critical enabler for control, decision making, and optimization in modern plant production systems. It supports the development of plant growth models for advanced control strategies like model predictive control, and enables responsive, data-driven, and plant state-dependent cultivation. Traditional biomass measurement methods, such as destructive sampling, are time-consuming and unsuitable for high-frequency monitoring. In contrast, image-based estimation using computer vision and deep learning requires frequent retraining and is sensitive to changes in lighting or plant morphology. This work introduces a low-cost, load-cell-based biomass monitoring system tailored for vertical farming applications. The system operates at the level of individual growing trays, offering a valuable middle ground between impractical plant-level sensing and overly coarse rack-level measurements. Tray-level data allow localized control actions, such as adjusting light spectrum and intensity per tray, thereby enhancing the utility of controllable LED systems. This granularity supports layer-specific optimization and anomaly detection, which are not feasible with rack-level feedback. The biomass sensor is easily scalable and can be retrofitted, addressing common challenges such as mechanical noise and thermal drift. It offers a practical and robust solution for biomass monitoring in dynamic, growing environments, enabling finer control and smarter decision making in both commercial and research-oriented vertical farming systems. The developed sensor was tested and validated against manual harvest data, demonstrating high agreement with actual plant biomass and confirming its suitability for integration into vertical farming systems. Full article

Load disaggregation has emerged as an effective tool for enabling smarter energy management in residential and commercial buildings. By providing appliance-level energy consumption estimation from aggregate data, it supports energy efficiency initiatives, demand-side management, and user awareness. However, several challenges remain in improving the accuracy of energy disaggregation methods. For instance, the amount of noise in energy consumption datasets can heavily impact the accuracy of disaggregation algorithms, especially for low-power consumption appliances. While disaggregation performance depends on hyperparameter tuning, the influence of data characteristics, such as noise, on hyperparameter selection remains underexplored. This work investigates the hypothesis that appliance-specific noise information can guide the selection of algorithm hyperparameters, like the input sequence length, to maximize disaggregation accuracy. The appliance-to-noise ratio metric is used to quantify the noise level relative to each appliance’s energy consumption. Then, the selection of the input sequence length hyperparameter is investigated for each case by inspecting disaggregation performance. The results indicate that the noise metric provides valuable guidance for selecting the input sequence length, particularly for user-dependent appliances with more unpredictable usage patterns, such as washing machines and electric kettles. Full article

Severe systemic toxicity and poor targeting efficiency remain major limitations of traditional chemotherapy, emphasising the need for smarter drug delivery systems. Magnetic 2D transition-metal-based nanomaterials offer a promising approach, as they can be designed to combine high drug loading, precise targeting, and controlled release. The key material classes—transition metal dichalcogenides, transition metal carbides/nitrides, transition metal oxides, and metal–organic frameworks—share important physicochemical properties. These include high surface-to-volume ratios, tuneable functionalities, and efficient intracellular uptake. Incorporating magnetic nanoparticles into these 2D structures broadens their potential beyond drug delivery, through enabling multimodal therapeutic strategies such as hyperthermia induction, real-time imaging, and photothermal or photodynamic therapy. This review outlines the potential of magnetic 2D transition-metal-based nanomaterials for biomedical applications by evaluating their therapeutic performance and biological response. In parallel, it offers a critical analysis of how differences in physicochemical properties influence their potential for specific cancer treatment applications, highlighting the most promising uses of each in bionanomedicine. Full article

This study focuses on enhancing the performance of Permanent Magnet Synchronous Motors (PMSMs) in pumping applications by improving motor torque through the integration of advanced control strategies. The dq-axis model of a PMSM is utilized to facilitate precise control and dynamic response. The proposed approach combines Fuzzy Logic Control (FLC) and Fuzzy Proportional-Integral-Derivative (fuzzy PID) controllers with Vector Control (VC) inverters, specifically designed for PMSMs with salient rotor structures. The salient rotor design inherently provides higher torque density, making it suitable for demanding applications like pumping. The FLC and fuzzy PID controllers are employed to optimize the motor’s dynamic response, ensuring precise torque control and improved efficiency under varying load conditions. The VC inverter further enhances the system’s performance by enabling rapid torque and flux control, reducing torque ripple, and improving overall motor stability. The simulation results demonstrate that the proposed control strategy significantly increases motor torque, enhances energy efficiency, and reduces operational losses in pumping applications. This makes the system more reliable and cost-effective for industrial and agricultural pumping systems, where high torque and energy savings are critical. The integration of FLC, fuzzy PID, and VC with a salient-rotor PMSM offers a robust solution for achieving superior motor performance in real-world pumping scenarios. This work contributes to the development of smarter, more efficient pumping systems, paving the way for enhanced industrial automation and energy management. Full article

The integration of cutting-edge technologies into reinforced concrete (RC) design is reshaping the construction industry, enabling smarter and more sustainable solutions. Among these, machine learning (ML), a subset of artificial intelligence (AI), has emerged as a transformative tool, offering unprecedented accuracy in prediction and optimization. This study investigated the flexural behavior of steel rebar RC beams, focusing on varying concrete compressive strengths via theoretical, experimental and ML analysis. Nine steel rebar RC beams with low (SC20), moderate (SC30) and high (SC40) concrete compressive strength, measuring 150 × 200 × 1100 mm, were produced and subjected to three-point bending tests. An average error of less than 5% was obtained between the theoretical calculations and the experiments of the ultimate load-carrying capacity of reinforced concrete beams. By combining three-point bending experiments with ML-powered prediction models, this research bridges the gap between experimental insights and advanced analytical techniques. A groundbreaking aspect of this work is the deployment of 18 ML regression models using Python’s PyCaret library to predict deflection values with an impressive average accuracy of 95%. Notably, the K Neighbors Regressor and Gradient Boosting Regressor models demonstrated exceptional performance, providing fast, consistent and highly accurate predictions, making them an invaluable tool for structural engineers. The results revealed distinct failure mechanisms: SC30 and SC40 RC beams exhibited ductile flexural cracking, while SC20 RC beams showed brittle shear cracking and failure with sudden collapse. Full article

As cities evolve into smarter and more connected environments, there is a growing need for innovative solutions to improve urban mobility. This study examines the potential of integrating blockchain technology into passenger transportation systems within smart cities, with a particular emphasis on a blockchain-enabled Mobility-as-a-Service (MaaS) solution. In contrast to traditional technologies, blockchain’s decentralized structure improves data security and guarantees transaction transparency, thus reducing the risk of fraud and errors. The proposed MaaS framework enables seamless collaboration between key transportation stakeholders, promoting more efficient utilization of services like buses, trains, bike-sharing, and ride-hailing. By improving integrated payment and ticketing systems, the solution aims to create a smoother user experience while advancing the urban goals of efficiency, environmental sustainability, and secure data handling. This research evaluates the feasibility of a Hyperledger Fabric-based solution, demonstrating its performance under various load conditions and proposing scalability adjustments based on pilot results. The conclusions indicate that blockchain-enabled MaaS systems have the potential to transform urban mobility. Further exploration into pilot projects and the expansion to freight transportation are needed for an integrated approach to city-wide transport solutions. Full article

The growing demand for consumer-end electrical load is driving the need for smarter management of power sector utilities. In today’s technologically advanced society, efficient energy usage is critical, leaving no room for waste. To prevent both electricity shortage and wastage, electrical load forecasting becomes the most convenient way out. However, the conventional and probabilistic methods are less adaptive to the acute, micro, and unusual changes in the demand trend. With the recent development of artificial intelligence (AI), machine learning (ML) has become the most popular choice due to its higher accuracy based on time-, demand-, and trend-based feature extractions. Thus, we propose an Extreme Gradient Boosting (XGBoost) regression-based model—PredXGBR-1, which employs short-term lag features to predict hourly load demand. The novelty of PredXGBR-1 lies in its focus on short-term lag autocorrelations to enhance adaptability to micro-trends and demand fluctuations. Validation across five datasets, representing electrical load in the eastern and western USA over a 20-year period, shows that PredXGBR-1 outperforms a long-term feature-based XGBoost model, PredXGBR-2, and state-of-the-art recurrent neural network (RNN) and long short-term memory (LSTM) models. Specifically, PredXGBR-1 achieves an mean absolute percentage error (MAPE) between 0.98 and 1.2% and an $R^2$ value of 0.99, significantly surpassing PredXGBR-2’s $R^2$ of 0.61 and delivering up to 86.8% improvement in MAPE compared to LSTM models. These results confirm the superior performance of PredXGBR-1 in accurately forecasting short-term load demand. Full article

To effectively manage the sustainable urban development of cities, it is crucial to quickly understand the geological and geotechnical attributes of the underground. Carrying out such studies entails significant investments and focused reconnaissance efforts, which might not align seamlessly with large-scale territorial planning initiatives within a city accommodating more than 3 million inhabitants, like Casablanca in Morocco. Additionally, various specific investigations have been conducted by municipal authorities in recent times. The primary aim of this study is to furnish city managers and planners with a tool for informed decision-making, enabling them to explore the geological and geotechnical properties of soil foundations using Geographic Information Systems (GISs) and geostatistics. This database, initially intended for utilization by developers and construction engineers, stands to economize a substantial amount of time and resources. During the urban planning of cities and prior to determining land usage (five- or seven-floor structures), comprehending the mechanical traits (bearing capacity, water levels, etc.) of the soil is crucial. To this end, geological and geotechnical maps, along with a collection of 100 surveys, were gathered and incorporated into a GIS system. These diverse data sources converged to reveal that the underlying composition of the surveyed area comprises silts, calcarenites, marls, graywackes, and siltstones. These formations are attributed to the Middle Cambrian and the Holocene epochs. The resultant geotechnical findings were integrated into the GIS and subjected to interpolation using ordinary kriging. This procedure yielded two distinct maps: one illustrating bearing capacity and the other depicting the substratum. The bearing capacity of the soil in the study zone is rated as moderate, fluctuating between two and four bars. The depth of the foundation remains relatively shallow, ranging from 0.8 m to 4.5 m. The outcomes are highly promising, affirming that the soil in Casablanca boasts commendable geotechnical attributes capable of enduring substantial loads and stresses. Consequently, redirecting future urban planning in the region toward vertical expansion seems judicious, safeguarding Casablanca’s remaining green spaces and the small agricultural belt. The results of this work help to better plan the urban development of the city of Casablanca in a smarter way, thus preserving space, agriculture, and the environment while promoting sustainability. In addition, the databases and maps created through this paper aim for a balanced financial management of city expenditures in urban planning. Full article

As automotive technology advances in the realm of digitization, vehicles are becoming smarter and, at the same time, more vulnerable to various threats. This paper focuses on techniques for detecting faults to mitigate the risk of freight transportation. Our observations show that vehicle uptime varies significantly even under similar operating conditions. This variation stems from differences in the wear and tear of moving and stationary parts, the characteristics of transported loads, driving styles, the quality of maintenance, etc. These factors are particularly crucial for abnormal vehicles designed to carry AILs (Abnormal Indivisible Loads). Such vehicles are especially prone to surprising threats, requiring efficient techniques for monitoring separate vehicle components and providing drivers with vital information about their operational status. The presented article proposes an original concept of an integrated three-level monitoring system based on the AOP (All-in-One Platform) principle, using the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm, which is a tool oriented to distinguish points from three categories: basic, boundary, and external. This is a solution not yet found in the literature. It is based on assessments of LOFs (Local Outlier Factors) and to detect anomalies in the measured values of operational parameters. The purpose of our study was to determine whether providing truck drivers with current information from an active threat warning system could help reduce unplanned downtimes. Full article

Electrical energy is often wasted through human negligence when people do not switch off electrical appliances such as lighting after leaving a place. Such a scenario often happens in a classroom when the last person leaves the class and forgets to switch off the electrical appliances. Such wastage may not be able to be afforded by schools that are limited financially. Therefore, this research proposed a simple and cost-effective system that can analyze whether there is or is not a human presence in the classroom by applying a counter to count the total number of people entering and leaving the classroom based on the sensing signals of a set of dual PIR sensors only and then correlating this to automatically turn on or off the electrical appliances mentioned. The total number of people identified in the classroom is also displayed on an LCD screen. A TRIZ approach is used to support the ideation of the system. The system can switch on several electrical output loads simultaneously when the presence of people is detected and switch them off when there are no people in the classroom. The proposed system can be expanded to be used in homes, offices, and buildings to prevent the high cost of electricity consumption caused by the negligence of people. This enables smarter control of electricity consumption. Full article

With the rise in traffic congestion in urban centers, predicting accidents has become paramount for city planning and public safety. This work comprehensively studied the efficacy of modern deep learning (DL) methods in forecasting traffic accidents and enhancing Level-4 and Level-5 (L-4 and L-5) driving assistants with actionable visual and language cues. Using a rich dataset detailing accident occurrences, we juxtaposed the Transformer model against traditional time series models like ARIMA and the more recent Prophet model. Additionally, through detailed analysis, we delved deep into feature importance using principal component analysis (PCA) loadings, uncovering key factors contributing to accidents. We introduce the idea of using real-time interventions with large language models (LLMs) in autonomous driving with the use of lightweight compact LLMs like LLaMA-2 and Zephyr-7b-$\alpha$. Our exploration extends to the realm of multimodality, through the use of Large Language-and-Vision Assistant (LLaVA)—a bridge between visual and linguistic cues by means of a Visual Language Model (VLM)—in conjunction with deep probabilistic reasoning, enhancing the real-time responsiveness of autonomous driving systems. In this study, we elucidate the advantages of employing large multimodal models within DL and deep probabilistic programming for enhancing the performance and usability of time series forecasting and feature weight importance, particularly in a self-driving scenario. This work paves the way for safer, smarter cities, underpinned by data-driven decision making. Full article

In a world increasingly aware of its carbon footprint, the quest for sustainable energy production and consumption has never been more urgent. A key player in this monumental endeavor is fuel conservation, which helps curb greenhouse gas emissions and preserve our planet’s finite resources. In the realm of the Industrial Internet of Things (IIoT) and artificial intelligence (AI) technologies, Caterpillar (CAT) generator set (genset) operations have been revolutionized, unlocking unprecedented fuel savings and reducing environmental harm. Envision a system that not only enhances fuel efficiency but also anticipates maintenance needs with state-of-the-art technology. This standalone IIoT platform crafted with Visual Basic.Net (VB.Net) and the KEPware Object linking and embedding for Process Control (OPC) server gathers, stores, and analyzes data from CAT gensets, painting a comprehensive picture of their inner workings. By leveraging the Modbus Remote Terminal Unit (RTU) protocol, the platform acquires vital parameters such as engine load, temperature, pressure, revolutions per minute (RPM), and fuel consumption measurements, from a radar transmitter. However, the magic does not stop there. Machine Learning.Net (ML.Net) empowers the platform with machine learning capabilities, scrutinizing the generator’s performance over time, identifying patterns and forecasting future behavior. Equipped with these insights, the platform fine tunes its operations, elevates fuel efficiency, and conducts predictive maintenance, minimizing downtime and amplifying overall efficiency. The evidence is compelling: IIoT and AI technologies have the power to yield substantial fuel savings and enhance performance through predictive maintenance. This research offers a tangible solution for industries eager to optimize operations and elevate efficiency by embracing IIoT and AI technologies in CAT genset operations. The future is greener and smarter, and it starts now. Full article

The growth of distributed power generation using renewable energy sources has led to the development of new-generation power electronic converters. This is because DC–DC converters and inverters form the fundamental building blocks in numerous applications, which include renewable integrations, energy harvesting, and transportation. Additionally, they play a vital role in microgrid applications. The deployment of distributed energy resources (DERs) with renewable sources such as solar has paved the way for microgrid support systems, thus forming an efficient electric grid. To enhance the voltage of such sources and to integrate them into the grid, high-gain DC–DC converters and inverter circuits are required. In this paper, a novel single-switch high-gain converter (HG-SIQBC) with quadratic voltage gain and wide controllable range of load is proposed, the output of which is fed to a modified multilevel inverter for conversion of voltage. The overall performance of the newly designed converter and inverter is analyzed and compared with the existing topologies. A prototype of the investigated multilevel inverter is designed and tested in the laboratory. Development and testing of such novel topologies have become the need of the hour as the grid becomes smarter with increased penetration of distributed resources. Full article

The electrification of the transport sector is of crucial importance for a successful transition to a fossil-free society. However, the electricity grid constitutes a bottleneck. This article provides a case study based on a real-world parking garage with a smart grid infrastructure, called Dansmästaren. The analysis shows how renewable energy sources, energy storage technologies, and smart charging of electric vehicles can smooth out the load curve of the parking garage and relieve the electric grid during peak hours. Dansmästaren is located in Uppsala, Sweden, and equipped with 60 charging points for electric vehicles, a PV system, and a battery storage system. The study utilizes an energy flow model to show the potential of a realistically dimensioned smart energy system, that can benefit the parking facility in itself and the local distribution grid in a city, Uppsala, with grid capacity challenges. The results suggest that the parking garage demand on the local grid can be significantly lowered by smarter control of its relatively small battery energy storage. Moreover, further smart control strategies can decrease demand up to 60% during high load hours while still guaranteeing fully charged vehicles at departure in near future scenarios. The study also shows that peak shaving strategies can lower the maximum peaks by up to 79%. A better understanding of the potential of public infrastructures for electric vehicle charging helps to increase knowledge on how they can contribute to more sustainable cities and a fossil-free society. Full article

Injury to lower genitourinary (GU) tissues, which may result in either infertility and/or organ dysfunctions, threatens the overall health of humans. Bioactive agent-based regenerative therapy is a promising therapeutic method. However, strategies for spatiotemporal delivery of bioactive agents with optimal stability, activity, and tunable delivery for effective sustained disease management are still in need and present challenges. In this review, we present the advancements of the pivotal components in delivery systems, including biomedical innovations, system fabrication methods, and loading strategies, which may improve the performance of delivery systems for better regenerative effects. We also review the most recent developments in the application of these technologies, and the potential for delivery-based regenerative therapies to treat lower GU injuries. Recent progress suggests that the use of advanced strategies have not only made it possible to develop better and more diverse functionalities, but also more precise, and smarter bioactive agent delivery systems for regenerative therapy. Their application in lower GU injury treatment has achieved certain effects in both patients with lower genitourinary injuries and/or in model animals. The continuous evolution of biomaterials and therapeutic agents, advances in three-dimensional printing, as well as emerging techniques all show a promising future for the treatment of lower GU-related disorders and dysfunctions. Full article