In recent times the concept of smart cities have gained grate popularity. Thanks to the evolution of Internet of things the idea of smart city now seems to be achievable. Consistent efforts are being made in the field of IoT in order to maximize the productivity and reliability of urban infrastructure. Problems such as, traffic congestion, limited car parking facilities and road safety are being addressed by IoT. In this paper, we present an IoT based cloud integrated smart parking system. The proposed Smart Parking system consists of an on-site deployment of an IoT module that is used to monitor and signalize the state of availability of each single parking space. A mobile application is also provided that allows an end user to check the availability of parking space and book a parking slot accordingly. The paper also describes a high-level view of the system architecture. Towards the end, the paper discusses the working of the system in form of a use case that proves the correctness of the proposed model.
Abstract The radical evolution of internet into a network of interconnected objects that create a smart environment is characterized by the term Internet of Things (IoT). The adoption of IoT in manufacturing enables the transition of tradition manufacturing systems into modern digitalized ones, generating significant economic opportunities through industries re-shaping. Industrial IoT empowers the modern companies to adopt new data-driven strategies and handle the global competitive pressure more easily. However, the adoption of IoT, increases the total volume of the generated data transforming the industrial data into industrial Big Data. The work demonstrated in this paper presents how the adoption of IoT in manufacturing, considering sensory systems and mobile devices, will generate industrial Big Data. Moreover, a developed IoT application is presented showing how real industrial data can be generated leading to Industrial Big Data. The proposed methodology is validated in a real life case study from a mould-making industry.
María Teresa García-Ordás, Jose Aveleira-Mata, Isaías García-Rodríguez
et al.
The Internet of Things (IoT) presents a unique cybersecurity challenge due to its vast network of interconnected, resource-constrained devices. These vulnerabilities not only threaten data integrity but also the overall functionality of IoT systems. This study addresses these challenges by exploring efficient data reduction techniques within a model-based intrusion detection system (IDS) for IoT environments. Specifically, the study explores the efficacy of an autoencoder's latent space combined with three different classification techniques. Utilizing a validated IoT dataset, particularly focusing on the Constrained Application Protocol (CoAP), the study seeks to develop a robust model capable of identifying security breaches targeting this protocol. The research culminates in a comprehensive evaluation, presenting encouraging results that demonstrate the effectiveness of the proposed methodologies in strengthening IoT cybersecurity with more than a 99% of precision using only 2 learned features.
E. B. Farquhar, E. B. Goldstein, P. J. Bresnahan
et al.
Abstract Chronic flooding is an issue for low‐lying coastal communities globally, and it is expected to worsen with rising sea levels. Predicting when and where these floods occur can be difficult as they can be hyper‐local and ephemeral, depending on the flood drivers (e.g., tides, rain). These factors make it difficult to measure the full spatial and temporal extent of chronic floods with in situ sensors. Here, we introduce a low‐cost (<$400 USD), privacy‐preserving camera system that identifies flooding over block‐by‐block spatial extents at high frequencies (20 s–6 min). Our device—a Tiny Camera with machine learning (ML) (TinyCamML)—is a small, solar‐powered, microcontroller‐based camera that uses on‐device ML to classify images of roadways as containing a “flood” or “no flood.” TinyCamMLs transmit only the classifications (a 1 or 0) to a website in real time, providing situation awareness during flood events over the entire image area while keeping data‐transmission costs low and preserving privacy. We demonstrate the TinyCamML's utility during both tidal and compound flood events in North Carolina, USA, which showed differences in flood spatial extents. During this deployment, the TinyCamML detected floods with an 81% accuracy, a 72% precision, and a 90% recall. The utility of the device extends beyond roadway flooding, as the onboard ML model can be easily retrained to capture other rare or ephemeral phenomena.
The Internet of Things (IoT) is expanding rapidly, but the security of IoT devices remains a noteworthy concern due to resource limitations and existing security conventions. This research investigates and proposes the use of a Light certificate with the Constrained Application Protocol (CoAP) instead of the X509 certificate based on traditional PKI/CA. We start by analyzing the impediments of current CoAP security over DTLS with the certificate mode based on CA root in the constrained IoT device and suggest the implementation of LightCert4IoT for CoAP over DTLS. The paper also describes a new modified handshake protocol in DTLS applied for IoT devices and Application server certificate authentication verification by relying on a blockchain without the complication of the signed certificate and certificate chain. This approach streamlines the DTLS handshake process and reduces cryptographic overhead, making it particularly suitable for resource-constrained environments. Our proposed solution leverages blockchain to reinforce IoT gadget security through immutable device characters, secure device registration, and data integrity. The LightCert4IoT is smaller in size and requires less power consumption. Continuous research and advancement are pivotal to balancing security and effectiveness. This paper examines security challenges and demonstrates the effectiveness of giving potential solutions, guaranteeing the security of IoT networks by applying LightCert4IoT and using the CoAP over DTLS with a new security mode based on blockchain.
The article highlights the theoretical aspects of e-commerce as the foundation of the modern economy. The study examines the main trends in the industry’s development and emphasizes its rapid growth worldwide. It analyzes the theoretical foundations of marketplaces and their role in the platform economy. An important component of the study is the analysis of the dynamics of the total value of goods sold on marketplaces and the examination of the largest marketplaces by gross profit.
In particular, special attention is paid to digital innovations and technologies that form the basis of their operations, including artificial intelligence (AI), blockchain, robotics, data analytics, Internet of Things (IoT) technologies, and cloud computing. The authors provide a detailed analysis of the role of these technologies in optimizing business processes and forecast their growth rates in the coming years. It is predicted that the demand for the implementation of digital innovations and the amount of investment in their adoption will continue to grow in the years ahead.
Special attention is given to the comparative analysis of investment volumes in digital innovations by leading marketplaces such as Rozetka, Amazon, Walmart, and Alibaba. Within the framework of the analysis, the amount of investment and the impact of technologies on business performance are determined. The article emphasizes the importance of implementing digital technologies and their positive impact on company development. The study devotes considerable attention to the advantages and disadvantages of integrating digital innovations into company operations, focusing on enhancing companies’ adaptability to changing market conditions and their ability to respond quickly to customer needs, as well as challenges related to investment costs and cybersecurity.
The authors conclude that the results of this study provide a better understanding of the economic impact of digitalization on e-commerce and help identify optimal approaches for implementing cutting-edge technologies in the operations of marketplaces.
Nicolò Grasso, Benedetta Fasciolo, Giulia Bruno
et al.
Climate change and population increase are becoming a threat to human feeding. New technologies and practices are under development, and a significant effort is being put into developing indoor farming, which allows for all-year-round production of high-quality food, regardless of the climate. Moreover, indoor farming promises extreme water and chemical usage reduction, specifically when the system is autonomously regulated with an IoT architecture. Despite these attractive characteristics, indoor systems require considerable energy to provide adequate temperature and lighting for cultivated crops. This demand is often high enough to make the production system economically unsustainable. This work aims to develop a cultivation protocol for baby lettuce plants (up to three weeks old plants) that can increase overall productivity while mitigating the issue of high energy demand. To this aim, we performed a Design of Experiment to assess crop responses to different levels of nutrients, temperature, and light intensity with the productivity of the system and the quality of the harvested product. The collected data were used to design a dynamic cultivation protocol, which defines different growing conditions according to the plant development stage. Results demonstrate that the dynamic protocol can enhance system productivity by up to 25 % in biomass accumulation, compared with the productivity obtained with fixed growing conditions, while maintaining the same high quality. Furthermore, the improvement is achieved without increasing the resource use, confirming the potential of this approach to enhance the economic sustainability of indoor soilless farming.
Rapid growth in usage of Internet of Things (IoT) devices has created a situation where security is highly vulnerable, and people require more sophisticated and evolving solutions. Conventional security solutions cannot overcome the issue of heterogeneity, resource scarcity, and dynamism of IoT environments. This paper suggests the use of a machine learning-based Intrusion Detection System (IDS) to identify and attempt to reduce the presence of real-time threats within IoT networks. The results of different machine learning models which include the Logistic Regression, the Decision Tree, the Random Forest, the XGBoost, the AdaBoost, the Gradient Boosting, Bagging, K-Nearest Neighbors (KNN), and the Naive Bayes are compared based on some of the key performance indicators that are accuracy, precision, recall, F1-score, ROC-AUC, and log loss. Our findings indicate that ensemble algorithms, especially Random Forest, Decision Tree, and Bagging, can be more effective than other models in identifying a large number of detections with low false positives, and Random Forest offers an accuracy of 99.99%, precision of 99.96%, a recall rate of 99.96% and ROC-AUC of 99.99%. By contrast, the results of Naive Bayes were much worse, showing an accuracy rate of 74.28 %, a precision rate of 23.32% and an F1-score of 37.71. These findings underline that ensemble algorithms, in particular Random Forest, are also very successful in real-time intrusion detection on IoT systems. The given approach proves that ensemble learning, which possesses the capability to merge several classifiers, is an effective solution to enhancing the IoT safety of systems.
Padmavathi Vurubindi, Jaroslav Frnda, Canavoy Narahari Sujatha
et al.
Abstract The Internet of Things (IoT) is an emerging, promising technology developed with the objective of establishing global connectivity among devices. IoT is highly susceptible to malicious attacks, owing to its resource-constrained architecture, insecure wireless communication, diverse device ecosystems, and the vast volume of sensor data transmitted over networks. An effective Intrusion Detection System (IDS) is essential to address these security concerns. However, challenges such as irrelevant features and poor class separability complicate its development. This research proposes a novel IDS by introducing an Improved Random Reversal Learning (IRRL) and Dimensional Adaptive Gaussian Variation (DAGV)-based Dung Beetle Optimizer (RGDBO) for optimal feature selection, enhancing exploration, and avoiding premature convergence. For classification, a Convolutional Neural Network (CNN) integrated with CosFace and ArcFace loss functions, termed CACNN, is employed to enhance intrusion classification through more efficient discrimination among classes. The combined RGDBO-CACNN framework is evaluated on three benchmark datasets: UNSW-NB15, NSL-KDD, and CICIDS-2017, using accuracy, recall, precision, and F1-score as performance metrics. A comparative analysis of existing methods, including GA-FR-CNN, GTO-BSA, and BMRF-RF, demonstrates the superiority of the proposed model, with RGDBO-CACNN achieving an accuracy of 99.999% on the UNSW-NB15 dataset.
Federated Learning (FL) enables decentralized Machine Learning (ML), focusing on preserving data privacy, but faces a unique set of optimization challenges, such as dealing with non-IID data, communication overhead, and client drift. Adaptive optimizers like AdaGrad, Adam, and Adam variations have been applied in FL, showing good results in convergence speed and accuracy. However, it can be quite challenging to combine good convergence, model generalization, and stability in an FL setup. Data-bound adaptive methods like AdaDB have demonstrated promising results in centralized settings by incorporating dynamic, data-dependent bounds on Learning Rates (LRs). In this paper, FedAdaDB is introduced, which is an FL version of AdaDB aiming to address the aforementioned challenges. FedAdaDB uses the AdaDB optimizer at the server-side to dynamically adjust LR bounds based on the aggregated client updates. Extensive experiments have been conducted comparing FedAdaDB with FedAvg and FedAdam on three different datasets (EMNIST, CIFAR100, and Shakespeare). The results show that FedAdaDB consistently offers better and more robust outcomes, in terms of the measured final validation accuracy across all datasets, for a trade-off of a small delay in the convergence speed at an early stage.
Yosia Adi Susetyo, Hanna Arini Parhusip, Suryasatriya Trihandaru
et al.
Masalah dalam industri terkait kehilangan data suhu dan kelembaban sering terjadi akibat gangguan perangkat atau hilangnya koneksi. Data ini penting untuk menentukan kelayakan produk yang akan didistribusikan. Untuk mengatasi permasalahan tersebut, dikembangkan inovasi LSTM-IOT, yaitu perangkat IoT yang terintegrasi dengan model Long Short-Term Memory (LSTM) dalam arsitektur Environment Intelligence. Arsitektur ini telah dioptimalkan melalui eksperimen menggunakan berbagai jenis optimizer, seperti Adam, RMSprop, AdaGrad, SGD, Nadam, dan Adadelta. Dari hasil optimasi, kombinasi Nadam Optimizer dengan arsitektur terpilih menunjukkan kinerja unggul dengan nilai Mean Square Error (MSE) sebesar 5,844 x10⁻⁵, Mean Absolute Error (MAE) sebesar 0,005971, dan Root Mean Square Error (RMSE) sebesar 0, 007645. Arsitektur Environment Intelligence versi (a) dengan Nadam Optimizer terbukti paling efektif dalam memproses data sensor, sehingga dipilih untuk integrasi dengan perangkat LSTM-IOT. Implementasi LSTM-IOT dalam skenario dunia nyata dilakukan pada wadah web lokal yang memungkinkan akses real-time ke data suhu dan kelembaban di berbagai lokasi. Halaman web berbasis Streamlit ini menampilkan visualisasi data, performa LSTM, dan hasil prediksi. Uji fungsional menunjukkan bahwa LSTM-IOT memenuhi kebutuhan perusahaan, termasuk penyimpanan data dalam database internal serta prediksi kondisi lingkungan hingga 150 menit ke depan. Dengan fitur prediksi dan pemantauan yang canggih, perangkat ini memberikan solusi efisien dan bernilai tinggi bagi perusahaan dalam memantau kondisi lingkungan secara akurat dan proaktif. Abstract Problems in the industry related to temperature and humidity data loss are often caused by device interference or loss of connection. This data is important to determine the feasibility of the product to be distributed. To overcome these problems, an LSTM-IOT innovation was developed, namely an IoT device that is integrated with the Long Short-Term Memory (LSTM) model in the Environment Intelligence architecture. This architecture has been optimized through experiments using different types of optimizers, such as Adam, RMSprop, AdaGrad, SGD, Nadam, and Adadelta. From the optimization results, the combination of Nadam Optimizer with the selected architecture shows superior performance with a mean square error (MSE) value of 5.844 x 10⁻⁵, a mean absolute error (MAE) of 0.005971, and a root mean square error (RMSE) of 0.007645. The Environment Intelligence architecture version (a) with Nadam Optimizer proved to be the most effective in processing sensor data, so it was chosen for integration with LSTM-IOT devices. The implementation of LSTM-IOT in real-world scenarios is carried out on a local web container that allows real-time access to temperature and humidity data in various locations. This Streamlit-based webpage displays data visualizations, LSTM performance, and prediction results. Functional tests show that LSTM-IOT meets the needs of the company, including data storage in an internal database and prediction of environmental conditions for up to the next 150 minutes. With advanced prediction and monitoring features, these devices provide efficient and high-value solutions for companies to monitor environmental conditions accurately and proactively.
Mira Maisura, Cut Putroe Yuliana, Ridwan Ridwan
et al.
Revolusi Industri 4.0 menuntut integrasi literasi teknologi seperti Internet of Things (IoT) ke dalam kurikulum pendidikan. Namun, kendala utama di tingkat SMA/Madrasah adalah minimnya media pelatihan IoT yang terjangkau, praktis, dan sesuai dengan konteks, infrastruktur sekolah yang terbatas, dan sumber daya yang kompeten. Penelitian ini bertujuan untuk mengembangkan dummy boom IoT yang dapat digunakan sebagai media pelatihan IoT yang layak digunakan dalam pembelajaran. Metode pengembangan yang diterapkan adalah model 4D dengan tahapan define, design, develop dan dissemination. Penggunaan model 4D memastikan quality control dari media,. Hasil uji kelayakan media didapatkan nilai rata-rata 4,414 (dalam skala likert), yang menunjukkan bahwa 92,45 % dari total responden setuju bahwa media sangat sesuai dan layak digunakan.
The widespread use of the Internet of Things has led to the development of large amounts of perception data, making it necessary to develop effective and scalable data analysis tools. Federated Learning emerges as a promising paradigm to address the inherent challenges of power consumption and data privacy in IoT environments. This paper explores the transformative potential of FL in enhancing the longevity of IoT devices by mitigating power consumption and enhancing privacy and security measures. We delve into the intricacies of FL, elucidating its components and applications within IoT ecosystems. Additionally, we discuss the critical characteristics and challenges of IoT, highlighting the need for such machine learning solutions in processing perception data. While FL introduces many benefits for IoT sustainability, it also has limitations. Through a comprehensive discussion and analysis, this paper elucidates the opportunities and constraints of FL in shaping the future of sustainable and secure IoT systems. Our findings highlight the importance of developing new approaches and conducting additional research to maximise the benefits of FL in creating a secure and privacy-focused IoT environment.
Luis Eduardo Pessoa, Cristovao Freitas Iglesias, Claudio Miceli
Designing resilient Internet of Things (IoT) systems requires i) identification of IoT Critical Objects (ICOs) such as services, devices, and resources, ii) threat analysis, and iii) mitigation strategy selection. However, the traditional process for designing resilient IoT systems is still manual, leading to inefficiencies and increased risks. In addition, while tools such as ChatGPT could support this manual and highly error-prone process, their use raises concerns over data privacy, inconsistent outputs, and internet dependence. Therefore, we propose RITA, an automated, open-source framework that uses a fine-tuned RoBERTa-based Named Entity Recognition (NER) model to identify ICOs from IoT requirement documents, correlate threats, and recommend countermeasures. RITA operates entirely offline and can be deployed on-site, safeguarding sensitive information and delivering consistent outputs that enhance standardization. In our empirical evaluation, RITA outperformed ChatGPT in four of seven ICO categories, particularly in actuator, sensor, network resource, and service identification, using both human-annotated and ChatGPT-generated test data. These findings indicate that RITA can improve resilient IoT design by effectively supporting key security operations, offering a practical solution for developing robust IoT architectures.
IoT devices fundamentally lack built-in security mechanisms to protect themselves from security attacks. Existing works on improving IoT security mostly focus on detecting anomalous behaviors of IoT devices. However, these existing anomaly detection schemes may trigger an overwhelmingly large number of false alerts, rendering them unusable in detecting compromised IoT devices. In this paper we develop an effective and efficient framework, named CUMAD, to detect compromised IoT devices. Instead of directly relying on individual anomalous events, CUMAD aims to accumulate sufficient evidence in detecting compromised IoT devices, by integrating an autoencoder-based anomaly detection subsystem with a sequential probability ratio test (SPRT)-based sequential hypothesis testing subsystem. CUMAD can effectively reduce the number of false alerts in detecting compromised IoT devices, and moreover, it can detect compromised IoT devices quickly. Our evaluation studies based on the public-domain N-BaIoT dataset show that CUMAD can on average reduce the false positive rate from about 3.57% using only the autoencoder-based anomaly detection scheme to about 0.5%; in addition, CUMAD can detect compromised IoT devices quickly, with less than 5 observations on average.