FIGURE 2 - uploaded by Swapnil Bagwari
Content may be subject to copyright.
Source publication
In the context of an early warning system for landslides, monitoring of prone areas is a long-lasting process, little human intervention, and a resource less environment. Data changes in the monitoring area may be noticed in many days, months, or years depending on the weather characteristics. Therefore, a frequent and large amount of data of monit...
Contexts in source publication
Context 1
... the device detects a downlink preamble at this period, the radio receiver remains open until the downlinks are demodulated. The LoRaWAN Class A operation is shown in Figure 2. Downlinks from a base station to the previously set periods are scheduled by Class B devices to determine if applications can deliver control messages to end devices [34]. ...
Context 2
... dBm, if the value exceeds that number shows a decrease in the sensitivity. Figure 12 shows the sensitivity in different bandwidths with respect to the spreading factor. As we can observe, sensitivity at 500KHz for SF 7 is highest, i.e. −118, and sensitivity at 7.8KHz for SF12 is lowest, i.e. −149. ...
Similar publications
The equal time interval sampling in the existing landslide monitoring system cannot detect the abnormal change of landslides in real time. This study proposes a novel landslide monitoring method based on the long range (LoRa) network and intelligent sensing Internet of Things (IoT) to address these drawbacks. The overall structure, hardware circuit...
Citations
... Traditional monitoring methods often rely on cellular networks, which still need to be more present and reliable in remote areas [4]. One way to address this challenge is using Long-range Wide Area Networks (LoRaWAN) that do not require Internet connectivity while operating independently. ...
... LoRa is suitable for near real-time critical alerts, poten-tially leading to quicker emergency response times [4]. However, it is ineffective for high-bandwidth demanding applications because it operates on low-data networks [13]. ...
... LoRaWAN, an open system based on robust LoRa modulation, is highly suitable for rural coverage using lowpower IoT devices. For instance, it has been used widely in agriculture, where it connects environmental IoT sensors for temperature and soil moisture with cloud servers [5], controls IoT actuators like irrigation valves [22], and supports tractor communications [4], livestock monitoring [23], and location tracing [24]. LoRaWAN can monitor livestock in real-time to ensure animal welfare, optimize resource allocation, and maximize productivity. ...
With the advent of the Internet of Things (IoT), Long-range Wide Area Networks (LoRaWAN), and high-speed internet, the potential to use such technologies for monitoring remote areas with limited cellular coverage is becoming increasingly important. However, existing remote monitoring solutions rely on cellular networks, which often do not exist or are unreliable in remote communities such as oil & gas and mining sites, livestock farms, and some specialized care clinics for monitoring individuals with Alzheimer’s disease. Furthermore, existing LoRa-based systems that are geolocation aware used star network topology, which has been proven to be not scalable to cover remote communities due to maintaining a massive volume of routing tables. This paper introduces a LoRaWAN-based geofencing system designed to address the unique challenges faced by these communities, especially areas with limited cellular coverage. The proposed system uses an optimized version of the Echo protocol to enhance the system’s reliability, which runs over a mesh network topology that provides a scalable solution for monitoring remote areas. In particular, we developed a geolocation and geofencing alert system tailored to overcome the limitations of cellular coverage in remote areas. Our system utilized LoRaWAN hardware supported by an optimized Echo protocol in a zero-control mesh network to efficiently detect boundary breaches of the monitored subjects such as cattle, patients with Alzheimer’s disease, robots mounted with IoT devices and sensors, etc. Experimental results showed that our system outperformed cellular-based systems regarding energy efficiency and scalability.
... Low-cost sensors have been integrated into so-called Early Warning Systems, composing Wireless Sensors Networks. Sensors are usually used to measure rainfall indices, soil moisture content, seismic vibration, and angular variations (Ruzza et al., 2020;Bagwari et al., 2022;Thirugnanam et al., 2022;Lau et al., 2023;Marino et al., 2023). ...
This paper presents a scoping review on the use of digital technologies for predicting, mapping, or continuously monitoring landslides on natural slopes. Articles and reviews published between 2001 and 2023 indexed by Scopus (Elsevier) were selected. The results showed that the number of publications involving this theme has been growing every year, with two periods of prominence: 2008-2010 and 2015-2021. China, Italy, India, USA and Taiwan are the five countries that published the most on the subject during the studied period. It was also found that remote sensing tools were the most used and showed strong stability, accompanied by artificial intelligence tools. Digital sensors have been widely used in Early Warning Systems, composing Wireless Sensors Network, monitoring terrain or climate variables. There is no doubt that digital technologies are extremely advantageous in relation to traditional technologies and that they already present themselves as a solution and confirm their trend of future consolidation.
... Some of these notable benefits are: 1) Extended Range: LoRa's capacity to transmit data over expansive distances, even up to several kilometers, without an internet connection makes it particularly suitable for vast agricultural terrains where traditional wireless modalities might be inadequate [18]. 2) Minimal Power Usage: Owing to its design tailored for low power consumption, LoRa-based WSNs operate over extended periods, diminishing the necessity for frequent battery replacements [19], [20]. 3) Cost-Efficiency: Relative to other wireless communication modalities, LoRa emerges as a more cost-effective option, aligning with the budgetary constraints of many farmers [18]. ...
In modern agriculture, the capability to promptly detect and respond to specific events is crucial. This study centres on the transformative potential of TinyML for enhancing event detection in Smart Agriculture, particularly when integrated with LoRa-based Wireless Sensor Networks (WSNs). In this work, we underscore the unique advantages of utilizing TinyML at the edge-bypassing the latency and overhead associated with cloud-centric models and ensuring immediate, on-site analytical insights. Employing LoRa WSNs as the backbone provides a seamless, low-power, and expansive data communication framework. Detailed experiments demonstrate TinyML's efficacy in accurately predicting agricultural events while reducing computational and energy consumption. In conclusion, the synergy between TinyML and LoRa WSNs offers a promising approach for fine-tuned, real-time event detection, aiming for sustainable and high-yield agricultural practices.
... Aside from the mathematical model underlying EWSs, some devices have been deployed for the effective monitoring of climate events and the collection of sufficient data for prediction models. The use of devices determines the choice of computational models, and among such devices include the use of IoT and sensor-enabled devices [80,81]. This suggests the possible hybridization of prediction and monitoring approaches to facilitate data processing on EWSs [82], where the hybrid approach uses neural network and heuristic approaches. ...
... The IoT cloud computing platform offers an opportunity to monitor and analyse flood images through cloud computer vision with image processing models. Also, LoRa technology in cloud computing frameworks helps customise sensors and gateway devices because of their low energy consumption capabilities [80]. The web environment offers the needed tools for data collection and remote control, which enables technical maintenance and calibration of sensors [20]. ...
This paper assessed existing EWS challenges and opportunities in cloud computing through the PSALSAR framework for systematic literature review and meta-analysis. The research used extant literature from Scopus and Web of Science, where a total of 2516 pieces of literature were extracted between 2004 and 2022, and through inclusion and exclusion criteria, the total was reduced to 98 for this systematic review. This review highlights the challenges and opportunities in transferring in-house early warning systems (that is, non-cloud) to the cloud computing infrastructure. The different techniques or approaches used in different kinds of EWSs to facilitate climate-related data processing and analytics were also highlighted. The findings indicate that very few EWSs (for example, flood, drought, etc.) utilize the cloud computing infrastructure. Many EWSs are not leveraging the capability of cloud computing but instead using online application systems that are not cloud-based. Secondly, a few EWSs have harnessed the computational techniques and tools available on a single platform for data processing. Thirdly, EWSs combine more than one fundamental tenet of the EWS framework to provide a holistic warning system. The findings suggest that reaching a global usage of climate-related EWS may be challenged if EWSs are not redesigned to fit the cloud computing service infrastructure.
In the current era of computing, communication, and technology, hydrological, metrological, and geographical parameters supported by sensor-based systems are available to detect, monitor, and analyze natural disasters like landslides. The landslide-related information from the study area is collected in offline mode through site visits. This process of collecting data in offline mode may cause delays in prediction and proactive decision-making in real-time mode. Although landslides cannot be prevented, their impact on human life and the environment can be reduced through real-time monitoring and prediction using IoT, Cloud, and Machine Learning Technologies. This manuscript aims to present a robust, real-time monitoring system that can minimize losses and save lives. The proposed model utilizes Internet of Things (IoT) technology integrated with cloud services to monitor and analyze landslides in a specific study area. The real-time monitoring system relies on three types of parameters: hydrological, meteorological, and geographical. These parameters are used to collect and store real-time information in an IoT cloud platform. The IoT cloud information is fetched on the LANDSLIDE MONITOR application for proactive decisions. To predict landslide events in areas prone to disasters, supervised learning classifiers were employed. The prediction analysis takes into account meteorological, hydrological, and geographical factors. The effectiveness of the proposed real-time landslide monitoring system was tested and evaluated in the Varunavat hills of the Uttarkashi District in Uttarakhand, India. The performance of the system was assessed by analyzing the accuracy of the model at different levels. The major focus of the developed system includes real-time data storage of landslide-prone areas in the IoT cloud, predictive modeling, and lastly the real-time landslide responses on LANDSLIDE MONITOR. The present landslide monitoring system uses long short-term memory networks (LSTM) and gated recurrent units (GRU) for predictive modeling of the landslide events in the study area. Hence the unique contribution of the work includes the technologies integration and real-time data collection from the study area and stored in the IoT cloud. The novel contribution of the work also includes the predictive modeling of landslide events using LSTM and GRU, and study area people awareness using LANDSLIDE MONITOR for level of risk from landslide events. The accuracy rates for the alert classes, ‘no threat’, ‘mild threat’, and ‘high threat’ events are 96.83%, 97.07%, and 98.56%, respectively. With a mean F1 score of 0.96 across the three classes of landslide occurrences, the proposed system demonstrates a high level of accuracy.
In order to get around the inherent constraints of distinct imaging modalities, multimodal fusion in neuroimaging integrates data from various imaging modalities. Higher temporal and spatial precision, improved contrast, the correction of imaging distortions, and the bridging of physiological and cognitive data can all be achieved through neuroimaging fusion. This analysis aims to examine the fusion and optimization of the multimodal neuroimaging technique and to examine a multimodal neuroimaging-based technique for measuring brain fatigue. Four-dimensional consistency of local neural activities (FOCA) and local multimodal serial analysis (LMSA) are primarily presented to naturally merge electroencephalogram (EEG) and functional magnetic resonance imaging (fMRI). With the time precision relying on EEG and the space precision focused on fMRI, the time–space matching in the data fusion system has acceptable outcomes, with the time precision above 88% and the space precision above 89%.
Medical imaging methods using multiple modalities are used more frequently in both clinical settings and academic studies. The use of ensemble learning and associated multimodal image processing has grown quickly and has a special benefit for medical uses. This study suggested a deep learning (DL) convolutional neural network (CNN) method for fusing multimodal medical images that is effective. The multimodality medical images that were used as input for the experimental study included computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET). The proposed approach utilizes a Siamese convolutional network to generate a weight map that incorporates the movement of pixels from multiple medical images. To meet a level of accuracy similar to human visual recognition, the medical image fusion operation is performed through a multiscale approach with the use of medical image pyramids. The decomposed coefficients are automatically adjusted using a comparison-based approach which is local in nature. The best fused multimodal medical images with the highest quality, quickest processing times, and best visualization in terms of both visual quality and objective evaluation criteria are produced experimentally using the suggested fusion methods.
Data processing applied science techniques like artificial intelligence and the Internet of Things are grand inventions in tech history that are revolutionary themselves. This highly advanced and intelligent mechanism calls the attention of business concerns and enterprises to implement these applications to facilitate the productivity of the establishments gain better results from Corporate Social Responsibility (CSR) activities and achieve sustainable development goals. In this study, the author examines how innovative technologies like AI, IoT, and blockchain are executed by organisations to assist CSR operations and be effective instruments for economic resilience and security. The study focuses on how AI and IoT can transform CSR initiatives by automating tasks, improving efficiency, and enabling new and innovative ways to engage with stakeholders and address social and environmental challenges. For this purpose, the researcher comes to grips with various monitoring reports and examination papers to collect statistics regarding technologies and CSR and implement the same from a different perspective and also explore the challenges faced due incorporation of this automation are measured in this overview. Finally, the author concludes this study with suggestions that may be utilized in the forthcoming research and academic work.
