This paper presents a low-cost, fully on-premise Edge Artificial Intelligence (AI) system designed to support real-time pest and disease detection in open-field chili pepper cultivation. The proposed architecture integrates AI-Thinker ESP32-CAM module (ESP32-CAM) image acquisition nodes (“Sticks”) with a Raspberry Pi 5–based edge server (“Module”), forming a plug-and-play Internet of Things (IoT) pipeline that enables autonomous operation upon simple power-up, making it suitable for aging farmers and resource-limited environments. A Leaf-First 2-Stage vision model was developed by combining YOLOv8n-based leaf detection with a lightweight ResNet-18 classifier to improve the diagnostic accuracy for small lesions commonly occurring in dense pepper foliage. To address network instability, which is a major challenge in open-field agriculture, the system adopted a dual-protocol communication design using Hyper Text Transfer Protocol (HTTP) for Joint Photographic Experts Group (JPEG) transmission and Message Queuing Telemetry Transport (MQTT) for event-driven feedback, enhanced by Redis-based asynchronous buffering and state recovery. Deployment-oriented experiments under controlled conditions demonstrated an average end-to-end latency of 0.86 s from image capture to Light Emitting Diode (LED) alert, validating the system’s suitability for real-time decision support in crop management. Compared to heavier models (e.g., YOLOv11 and ResNet-50), the lightweight architecture reduced the computational cost by more than 60%, with minimal loss in detection accuracy. This study highlights the practical feasibility of resource-constrained Edge AI systems for open-field smart farming by emphasizing system-level integration, robustness, and real-time operability, and provides a deployment-oriented framework for future extension to other crops.
Dian Megah Sari, Musyrifah Musyrifah, Andi Seppewali
et al.
Kelompok Usaha Maloppo merupakan usaha mikro yang bergerak dalam produksi minyak kelapa murni di Kabupaten Majene, Sulawesi Barat. Meskipun produk yang dihasilkan telah memiliki sertifikat halal dan berpotensi besar di pasaran, proses produksi masih menggunakan metode tradisional sehingga menyebabkan suhu pemanasan tidak stabil, kualitas produk tidak konsisten, dan masa simpan singkat. Selain itu, pemasaran masih terbatas pada pasar tradisional tanpa memanfaatkan media digital. Program pengabdian kepada masyarakat ini bertujuan untuk meningkatkan proses produksi serta memperkuat kapasitas pemasaran melalui penerapan teknologi tepat guna dan strategi digital. Kegiatan dilaksanakan melalui beberapa tahap, yaitu sosialisasi, pelatihan, penerapan teknologi, pendampingan, dan keberlanjutan program. Hasil kegiatan menunjukkan bahwa penggunaan evaporator berbasis IoT mampu meningkatkan konsistensi produk, membuat minyak lebih jernih dan beraroma segar, serta memperpanjang masa simpan hingga dua bulan. Kapasitas produksi juga meningkat sekitar 40%. Dari sisi pemasaran, penerapan digital marketing memungkinkan mitra memanfaatkan media sosial seperti Facebook, WhatsApp Business, dan TikTok untuk promosi dengan konten yang lebih menarik. Perubahan ini memperluas jangkauan pasar dan meningkatkan interaksi dengan konsumen. Dengan demikian, integrasi teknologi tepat guna dan strategi digital marketing berkontribusi signifikan terhadap pemberdayaan UMKM lokal dan peningkatan kesejahteraan masyarakat.
Social history and conditions. Social problems. Social reform, Communities. Classes. Races
In the rapid development of the Internet of Things (IoT) and large-scale distributed networks, Intrusion Detection Systems (IDS) face significant challenges in handling complex spatiotemporal features and addressing data imbalance issues. This article systematically reviews recent advancements in applying deep learning techniques in IDS, focusing on the core challenges of spatiotemporal feature extraction and data imbalance. First, this article analyzes the spatiotemporal dependencies of Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) in network traffic feature extraction and examines the main methods these models use to solve this problem. Next, the impact of data imbalance on IDS performance is explored, and the effectiveness of various data augmentation and handling techniques, including Generative Adversarial Networks (GANs) and resampling methods, in improving the detection of minority class attacks is assessed. Finally, the paper highlights the current research gaps and proposes future research directions to optimize deep learning models further to enhance the detection capabilities and robustness of IDS in complex network environments. This review provides researchers with a comprehensive perspective, helping them identify the challenges in the current field and laying a foundation for future research efforts.
This research investigates the energy consumption of buildings managed by traditional Building Management Systems (BMSs) and proposes the integration of Internet of Things (IoT) technology to enhance energy efficiency. Conventional BMSs often suffer from significant energy wastage and safety hazards due to sensor failures or malfunctions. These issues arise when building systems continue to operate under unknown conditions while the BMS is offline, leading to increased energy consumption and operational risks. The study demonstrates that integrating IoT systems with existing BMSs can substantially improve energy efficiency in smart buildings. The research involved designing a system architecture prototype, performing MATLAB simulations, and a real-life case study which revealed that IoT devices are effective in reducing energy waste, particularly in Heating, Ventilation, and Air Conditioning (HVAC) systems and lighting. Additionally, an auxiliary bypass system was incorporated in parallel with the IoT system to enhance reliability in the event of IoT system failures. Preliminary findings indicate that the integration of IoT systems with traditional BMSs significantly boosts energy efficiency and safety in smart buildings. Simulation results reveal an hourly average power savings of 36.8 kw with the integrated failsafe model for all scenarios. This integration offers a promising solution for advancing energy management practices and policies, thereby improving both operational performance and sustainability in building management.
Industry 4.0 is positioned at the junction of different disciplines, aiming to re-engineer processes and improve effectiveness and efficiency. It is taking over many industries whose traditional practices are being disrupted by advances in technology and inter-connectivity. In this context, enhanced agriculture systems incorporate new components that are capable of generating better decision making (humidity/temperature/soil sensors, drones for plague detection, smart irrigation, etc.) and also include novel processes for crop control (reproducible environmental conditions, proven strategies for water stress, etc.). At the same time, advances in model-driven development (MDD) simplify software development by introducing domain-specific abstractions of the code that makes application development feasible for domain experts who cannot code. XMDD (eXtreme MDD) makes this way to assemble software even more user-friendly and enables application domain experts who are not programmers to create complex solutions in a more straightforward way. Key to this approach is the introduction of high-level representations of domain-specific functionalities (called SIBs, service-independent building blocks) that encapsulate the programming code and their organisation in reusable libraries, and they are made available in the application development environment. This way, new domain-specific abstractions of the code become easily comprehensible and composable by domain experts. In this paper, we apply these concepts to a smart agriculture solution, producing a proof of concept for the new methodology in this application domain to be used as a portable demonstrator for MDD in IoT and agriculture in the Confirm Research Centre for Smart Manufacturing. Together with model-driven development tools, we leverage here the capabilities of the Nordic Thingy:53 as a multi-protocol IoT prototyping platform. It is an advanced sensing device that handles the data collection and distribution for decision making in the context of the agricultural system and supports edge computing. We demonstrate the importance of high-level abstraction when adopting a complex software development cycle within a multilayered heterogeneous IT ecosystem.
In this project, a smart knee sleeve was developed for the purpose of measuring a subject’s knee angle continually. The device is wireless and washable, making it suitable for rehabilitation at home. Two separate methods were incorporated onto a standard knee sleeve: a flexible silicone-based bend sensor and two IMUs. Each approach was evaluated, and testing was conducted on three subjects wearing the knee sleeve, using a reference video motion-tracking method. Squats were used as the exercise protocol for testing. The results showed that the flex sensor performed better for two of the three participants, with an average RMSE of 8.3 degrees, which is comparable to results from related research.
Data centres have grown drastically in size and in number as the digital economy has proliferated. For the advancement of society and the economy, data centres are becoming increasingly important. But even a little period of data centre downtime can be extremely harmful. Secure management of the physical infrastructure of data centres is essential to resolving this problem. A decentralized approach to healthcare systems is also made possible by blockchain technology, which gets rid of some of the drawbacks of centralized systems like single points of failure. Currently, a number of enhanced resilience security solutions using blockchain and ANP (Analytical Neural Processes) techniques have been presented to improve the security of transformation-based technologies. ANP finds false data and recognizes harmful data measured by medical sensors. For the Internet of Things (IoT) and Cyber Physical Systems (CPS), the development of defences against diverse cyber threats is advancing. Leveraging cloud environments to discover harmful code may not be a practical strategy in the future as malicious code grows in prevalence and there are no established techniques for identifying malicious code. Therefore, before the fog layer processes the data, transformation-based systems can identify and stop cyber-attacks. Additionally, it makes use of a blockchain network at the fog layer to guarantee data integrity and privacy by preventing data modification. Experimental findings demonstrate that the ANP and block chain models deliver what is promised. Additionally, the Transformer Neural Network (TNN) model's accuracy is 99.99% according to the F1 score accuracy indicator.
A fog-based IoT platform model involving three layers, i.e., IoT devices, fog nodes, and the cloud, was proposed using an open Jackson network with feedback. The system performance was analyzed for individual subsystems, and the overall system was based on different input parameters. Interesting performance metrics were derived from analytical results. A resource optimization problem was developed and solved to determine the optimal service rates at individual fog nodes under some constraint conditions. Numerical evaluations for the performance and the optimization problem are provided for further understanding of the analysis. The modeling and analysis, as well as the optimization design method, are expected to provide a useful reference for the design and evaluation of fog computing systems.
The access control (AC) system in an IoT (Internet of Things) context ensures that only authorized entities have access to specific devices and that the authorization procedure is based on pre-established rules. Recently, blockchain-based AC systems have gained attention within research as a potential solution to the single point of failure issue that centralized architectures may bring. Moreover, zero-knowledge proof (ZKP) technology is included in blockchain-based AC systems to address the issue of sensitive data leaking. However, current solutions have two problems: (1) systems built by these works are not adaptive to high-traffic IoT environments because of low transactions per second (TPS) and high latency; (2) these works cannot fully guarantee that all user behaviors are honest. In this work, we propose a blockchain-based AC system with zero-knowledge rollups to address the aforementioned issues. Our proposed system implements zero-knowledge rollups (ZK-rollups) of access control, where different AC authorization requests can be grouped into the same batch to generate a uniform ZKP, which is designed specifically to guarantee that participants can be trusted. In low-traffic environments, sufficient experiments show that the proposed system has the least AC authorization time cost compared to existing works. In high-traffic environments, we further prove that based on the ZK-rollups optimization, the proposed system can reduce the authorization time overhead by 86%. Furthermore, the security analysis is presented to show the system’s ability to prevent malicious behaviors.
We know that in today’s advanced world, artificial intelligence (AI) and machine learning (ML)-grounded methodologies are playing a very optimistic role in performing difficult and time-consuming activities very conveniently and quickly. However, for the training and testing of these procedures, the main factor is the availability of a huge amount of data, called big data. With the emerging techniques of the Internet of Everything (IoE) and the Internet of Things (IoT), it is very feasible to collect a large volume of data with the help of smart and intelligent sensors. Based on these smart sensing devices, very innovative and intelligent hardware components can be made for prediction and recognition purposes. A detailed discussion was carried out on the development and employment of various detectors for providing people with effective services, especially in the case of smart cities. With these devices, a very healthy and intelligent environment can be created for people to live in safely and happily. With the use of modern technologies in integration with smart sensors, it is possible to use energy resources very productively. Smart vehicles can be developed to sense any emergency, to avoid injuries and fatal accidents. These sensors can be very helpful in management and monitoring activities for the enhancement of productivity. Several significant aspects are obtained from the available literature, and significant articles are selected from the literature to properly examine the uses of sensor technology for the development of smart infrastructure. The analytical hierarchy process (AHP) is used to give these attributes weights. Finally, the weights are used with the multi-objective optimization on the basis of ratio analysis (MOORA) technique to provide the different options in their order of importance.
Kanak Kumar, Shiv Nath Chaudhri, Navin Singh Rajput
et al.
Detection and monitoring of airborne hazards using e-noses has been lifesaving and prevented accidents in real-world scenarios. E-noses generate unique signature patterns for various volatile organic compounds (VOCs) and, by leveraging artificial intelligence, detect the presence of various VOCs, gases, and smokes onsite. Widespread monitoring of airborne hazards across many remote locations is possible by creating a network of gas sensors using Internet connectivity, which consumes significant power. Long-range (LoRa)-based wireless networks do not require Internet connectivity while operating independently. Therefore, we propose a networked intelligent gas sensor system (N-IGSS) which uses a LoRa low-power wide-area networking protocol for real-time airborne pollution hazard detection and monitoring. We developed a gas sensor node by using an array of seven cross-selective tin-oxide-based metal-oxide semiconductor (MOX) gas sensor elements interfaced with a low-power microcontroller and a LoRa module. Experimentally, we exposed the sensor node to six classes i.e., five VOCs plus ambient air and as released by burning samples of tobacco, paints, carpets, alcohol, and incense sticks. Using the proposed two-stage analysis space transformation approach, the captured dataset was first preprocessed using the standardized linear discriminant analysis (SLDA) method. Four different classifiers, namely AdaBoost, XGBoost, Random Forest (RF), and Multi-Layer Perceptron (MLP), were then trained and tested in the SLDA transformation space. The proposed N-IGSS achieved “all correct” identification of 30 unknown test samples with a low mean squared error (MSE) of 1.42 × 10<sup>−4</sup> over a distance of 590 m.
Kittens in their first four weeks are in their most critical period because they do not yet have the ability to thermoregulate their bodies, and it is still difficult for them to adapt to environmental temperatures. Due to this condition, veterinary clinics and cat-lover communities need facilities that can maintain a kitten’s body temperature within the normal range. One way to help in the care of these kittens is to use a special incubator for animals. Incubators are useful in situations where animals cannot control their body temperature conditions. The expected method to monitor the work system of the incubator is internet-based monitoring, as part of IoT (internet of things). Monitoring is very important for animal health workers and cat lovers in monitoring the temperature and humidity in the incubator using the internet, which allows monitoring to be carried out anytime and anywhere from a smartphone through the Blynk application. The purpose of this research is to create an IoT-based kitten incubator monitoring system through the blynk application so that the owner or nurse of the kitten can monitor in real time via a smartphone so that time efficiency can be improved, by using NodeMCU ESP8266 microcontroller with fuzzy logic method. The incubator can work automatically to regulate the temperature through lighting and air settings in it, with the applied temperature ranging from 26 degrees to 30 degrees Celsius.
Internet of Things (IoT) systems are becoming ubiquitous in various cyber–physical infrastructures, including buildings, vehicular traffic, goods transport and delivery, manufacturing, health care, urban farming, etc. Often multiple such IoT subsystems are deployed in the same physical area and designed, deployed, maintained, and perhaps even operated by different vendors or organizations (or “parties”). The collective operational behavior of multiple IoT subsystems can be characterized via (1) a set of operational rules and required safety properties and (2) a collection of IoT-based services or applications that interact with one another and share concurrent access to the devices. In both cases, this collective behavior often leads to situations where their operation may conflict, and the conflict resolution becomes complex due to lack of visibility into or understanding of the cross-subsystem interactions and inability to do cross-subsystem actuations. This article addresses the fundamental problem of detecting and resolving safety property violations. We detail the inherent complexities of the problem, survey the work already performed, and layout the future challenges. We also highlight the significance of detecting/resolving conflicts proactively, i.e., dynamically but with a look-ahead into the future based on the context.
With the proliferation of multimedia services, Quality of Experience (QoE) has gained a lot of attention. QoE ties together the users’ needs and expectations to multimedia application and network performance. However, in various Internet of Things (IoT) applications such as healthcare, surveillance systems, traffic monitoring, etc., human feedback can be limited or infeasible. Moreover, for immersive augmented and virtual reality, as well as other mulsemedia applications, the evaluation in terms of quality cannot only focus on the sight and hearing senses. Therefore, the traditional QoE definition and approaches for evaluating multimedia services might not be suitable for the IoT paradigm, and more quality metrics are required in order to evaluate the quality in IoT. In this paper, we review existing quality definitions, quality influence factors (IFs) and assessment approaches for IoT. This paper also introduces challenges in the area of quality assessment for the IoT paradigm.
Digital forensics deals with digital evidence. Digital forensics is the study of data detection, acquisition, processing, analysis, and reporting. Encouraging the use of digital forensics in law enforcement investigations. With digital forensics, you can find out what data was taken and how it was copied or spread. Some hackers purposefully destroy data to harm their targets. In other cases, malicious software or hacker involvement can accidentally corrupt vital data. Digital forensics faces challenges of security and integrity. IoT devices can collect digital forensic evidence in an IoT setting, putting cybercrime agencies at danger owing to security and integrity. Many studies have been done recently to improve IoT based digital forensics integrity and security, but researchers face the risk of confidentiality. Recent research shows that digital forensics still faces manipulation and security issues. So a clever and effective approach is needed that not only protects security and integrity but also anticipates threats. So we propose an intelligent and effective solution based on Blockchain and Hashing algorithms. We will store the data collected from IoT devices into Blockchain. Anomalies in the evidence and transactions will be predicted using Machine Learning boosted models. So the proposed model works well because it can predict attacks early on.
Because of toxic gases and fast propagation speed, smoke causes the major injuries and deaths than burns in the fire. Deploying IoT enabled smoke sensors not only help to sense, collect, and transmit the smoke data to the control station, but also enable a dynamic and real-time evacuation approach to increase the evacuation success probability. In this paper, two smoke-aware evacuation approaches are proposed. The individual evacuation mathematical model and the associated SIEP algorithm are first devised to identify a fastest smoke toxic safe evacuation path for an evacuee. Next, the group evacuation mathematical model and the associated SGEP algorithm are devised to evacuate as many evacuees as possible in considering the smoke toxicity and flow congestion along the evacuation routes. SGEP circumvents the congestion problem by scheduling the evacuation sequence according to evacuee’s accumulated smoke toxicity value, where higher accumulated smoke toxicity value has higher evacuation priority to prevent incapacitation at evacuation. The FDS simulations based on the real layout of Taipei 101 mall are performed to compare the evacuation success probability between SIEP and SGEP at methane fire and PVC fire. The simulation results show that smoke from PVC fire is more toxic than that of methane fire. In addition, enabling sprinklers can reduce the percentage of toxic nodes up to 41% at methane fire and up to 10% at PCV fire, as compared to not enabling them. These results indicate that it is more challenging to evacuate at PVC fire than at methane fire. The simulation results in SGEP and SIEP justify the above conclusions where the success evacuation probability differences between methane fire and PVC fire are up to 39% (i.e., 100% and 61%) and 52.5% (i.e., 82.5% and 30%) for SGEP and SIEP, respectively. The simulation results also show that SGEP outperforms SIEP in terms of evacuation success probability at all simulation settings, especially when large number of evacuees are to be evacuated. At methane fire, the largest evacuation success probability difference between SGEP and SIEP is 68.1% at 1000 evacuees, 0.3 FED threshold and without sprinklers. At PVC fire, the largest difference is 50% at 1000 evacuees, 0.5 FED threshold and with sprinklers. These significant differences in evacuation success probability come from the evacuation congestion in SIEP. The evacuation scheduling approach based on accumulated smoke toxicity policy enables SGEP to circumvent the evacuation congestion, and to get better evacuation success probability. Besides identifying safe evacuation route and evacuation scheduling policy during congestion to evacuate more evacuees, another contribution of this paper is to identify the critical percentage of toxic nodes for safe fire evacuation and rescue operations.