Intelligent Fraud Detection in IoT-Driven Transactions Using Multi-Layer Neural Classification

여러 사물 인터넷 기기들을 조합, 활용하여 다양한 서비스를 제공할 수 있게 된 환경에서 추천시스템은 사용자가 원하는 서비스를 선택하는 데 있어 도움을 줄 수 있다. 기존의 추천 시스템에 대한 많은 연구는 주로 개인 사용자 대상의 추천에 집중되어 있으나 사물 인터넷 환경에서는 개인과 그룹 모두 사용자가 될 수 있으므로 그룹에 대한 추천 방법이 필요로 하다. 본 연구는 사물 인터넷 환경에서 그룹사용자들의 서비스 선호도를 분석하고, 이를 바탕으로 특정 장소에서 서비스를 이용한 적이 없는 새로운 그룹 사용자에게 서비스를 추천할 수 있는 방법을 개발하였다. 본 연구에서는 그룹의 구성 정보를 기반으로 그룹들 간의 유사도를 측정하여 사용자 기반 협업 필터링을 적용하였다. 실험에서는 실제 사물 인터넷 테스트 베드 환경에서 수집된 데이터를 사용하였으며 실험 결과를 통해 제안한 서비스 추천 방법이 효과적임을 확인할 수 있었다.

In the modern era, web data retrieval and data analytics play a crucial role for taking intelligent decisions in Internet of Things (IoT) environment. In IoT environment, various objects perform the tasks of sensing and computation for providing uninterrupted services (e.g., e-health, e- transportation, security access, etc.) to the end users. However, accessing the relevant and accurate information with reduced delay is still a challenging task in IoT environment. Although this aspect has been explored in the literature, the existing proposals have high complexity and require long time for accessing the relevant information from different IoT objects located across the globe. The information may be located across different web pages, which are linked together irrespective of their geographical locations. So, this paper addresses the issues such as accuracy, context- aware, reduced delay with low complexity in accessing the information from a remote device by the end users. In the proposed scheme, the strength of a web page which contains the relevant information to be fetched is judged by the quality of content and the inter- connections between different web pages. The proposed scheme simplifies the rank score calculation of these web pages and provides quality web pages at the top of the search result pages by demoting spam web pages. Bias connected web pages are verified by the linkage information of spam web pages. The Quality Assessment for Information Retrieval (QAIR) algorithm is proposed for the classification of web pages. The proposed algorithm computes the QAIR score by evaluating the web page quality. Microsoft Learning to Rank dataset has been used for the experiments, which consists of 239092 query-url pairs. By using this dataset, the computed QAIR score is compared with the PageRank score. This comparison determines the category of web page, i.e., either the page is strong or weak. The proposed scheme has been validated with decision tree followed by ten- fold cross validation, which results in an accuracy of 92.4%.

Recently, IETF (Internet Engineering Task Force) presented CoAP (Constrained Application Protocol) for the communication between sensor and actuator nodes in a constrained environment such as small amount of memory and low power. IETF CoAP protocol can convert easily, and can use to monitor or control infrastructure utilities through low-power sensor and actuator networks in IoT (Internet of Things) and M2M (Machine-to-Machine) environment. IETF CoAP protocol provides the special requirements of this constrained environment, especially considering energy, automation, and other IoT applications. In this paper, we design and implement a node registration and discovering based CoAP in IoT environment. The node is a CoAP node which is designed for working in constrained environment. For node registration in IoT, we used CoRE RD (Resource Directory) functionalities to register CoAP node’s information which works in IoT environment.

In the face of constantly changing cyber threats, a variety of actions, tools, and regulations must be considered to safeguard information assets and guarantee the confidentiality, reliability, and availability of digital resources. The purpose of this research is to create an artificial intelligence (AI)-driven system to enhance sustainability for cyber threat detection in Internet of Things (IoT) environments. This study proposes a modern technique named Artificial Fish Swarm-driven Weight-normalized Adaboost (AF-WAdaBoost) for optimizing accuracy and sustainability in identifying attacks, thus contributing to heightening security in IoT environments. CICIDS2017, NSL-KDD, and UNSW-NB15 were used in this study. Min-max normalization is employed to pre-process the obtained raw information. The proposed model AF-WAdaBoost dynamically adjusts classifiers, enhancing accuracy and resilience against evolving threats. Python is used for model implementation. The effectiveness of the suggested AF-WAdaBoost model in identifying different kinds of cyber-threats in IoT systems is examined through evaluation metrics like accuracy (98.69%), F-measure (94.86%), and precision (95.72%). The experimental results unequivocally demonstrate that the recommended model performed better than other traditional approaches, showing essential enhancements in accuracy and strength, particularly in a dynamic environment. Integrating AI-driven detection balances offers sustainability in cybersecurity, ensuring the confidentiality, reliability, and availability of information assets, and also helps in optimizing the accuracy of systems.

The growing number of Internet of Things devices has led to an increased risk of complex and diverse cyberattacks. However, a significant challenge in this domain is the imbalanced class distribution in most Internet of Things datasets, cautilizing classification algorithms to be biased towards the majority class, hindering effective threat detection. This study addresses this issue by leveraging the Random Forest algorithm optimised by the Synthetic Minority Oversampling Technique. This research aims to develop an effective model for detecting cyberattacks in Internet of Things environments by resolving class imbalance issues inside of the CIC-IoT2023 dataset. The methodology involves several stages, comprising data preprocessing and applying Synthetic Minority Oversampling Technique for data balancing. The balanced dataset was then used to train a Random Forest model, by its performance evaluated utilizing accuracy, precision, recall, F1-score, and Cohen's Kappa metrics. The results demonstrate the model's effectiveness, achieving an accuracy of 99.01%, an F1-score of 98.96%, and a Cohen's Kappa of 98.92%. This marks a notable improvement in performance, particularly in detecting minority classes, compared to the model trained devoid of Synthetic Minority Oversampling Technique, that struggled to identify several less common attack types. The outcomes suggest that combining Random Forest by Synthetic Minority Oversampling Technique can significantly enhance the development of intrusion detection systems by improving detection accuracy for all 33 attack types and reducing the risks associated by undetected threats. In conclusion, this study advances Internet of Things cybersecurity by presenting an effective and efficient method for addressing data imbalance in attack detection. Future research should focus on evaluating the model's robustness utilizing more complex datasets and enhancing its performance for real-time deployment on resource-constrained Internet of Things Devices.

Due to the advanced growth in the development of artificial intelligence (AI) and the Internet of Things (IoT) environment in smart societies, the identification of attacks and anomalies in the IoT environment has become more challenging. Owing to a raised utilization of IoT models in various fields, threats as well as attacks are increased significantly, which spoils the efficiency of the IoT model. In this chapter, an AI-based improved grasshopper optimization algorithm with tumbling effect (IGO-T) for attack and anomaly detection is presented for IoT sites. The presented IGO-T model will perform effective and rapid attack and anomaly identification in the IoT infrastructure. To improve the outcome of the grasshopper optimization algorithm, the tumbling effect is integrated into it. For evaluation purposes, a freely accessible dataset from Kaggle is employed. The dataset holds a total of 357,952 instances along with 13 attributes. The simulation outcome exhibited maximum performance with the accuracy of 99.6% in the training and testing datasets.

Hydroponics is the soil less agriculture farming, which consumes less water and other resources as compared to the traditional soil‐based agriculture systems. However, monitoring of hydroponics farming is a challenging task due to the simultaneous supervising of numerous parameters, nutrition suggestion, and plant diagnosis system. But the recent technological developments are quite useful to solve these problems by adopting the artificial intelligence‐based controlling algorithms in agriculture sector. Therefore, this article focuses on implementation of mobile application integrated artificial intelligence based smart hydroponics expert system, hereafter referred as AI‐SHES with Internet of Things (IoT) environment. The proposed AI‐SHES with IoT consists of three phases, where the first phase implements hardware environment equipped with real‐time sensors such as NPK soil, sunlight, turbidity, pH, temperature, water level, and camera module which are controlled by Raspberry Pi processor. The second phase implements deep learning convolutional neural network (DLCNN) model for best nutrient level prediction and plant disease detection and classification. In third phase, farmers can monitor the sensor data and plant leaf disease status using an Android‐based mobile application, which is connected over IoT environment. In this manner, the farmer can continuously track the status of his field using the mobile app. In addition, the proposed AI‐SHES also develops the automated mode, which makes the complete environment in automatic control manner and takes the necessary actions in hydroponics field to increase the productivity. The obtained simulation results on disease detection and classification using proposed AI‐SHES with IoT disclose superior performance in terms of accuracy, F‐measure with 99.29%, and 99.23%, respectively.

Load parameter identification is one of the keys and difficult points in power system analysis and research. With the rapid development of the grid scale, the load structure is becoming more and more complex, and the adaptability of the load model structure and typical parameters to the actual power grid has become increasingly prominent. In response to this problem, a parameter identification method for power grid load models in the internet of things (IoT) environment is proposed. Firstly, a load model is established under the power IoT “cloud-network-edge-terminal” architecture. Secondly, the genetic algorithm (GA) is used to identify the parameters of the dynamic load model in the edge layer. At the same time, without changing the structure of the load model, a load parameter security protection method based on edge computing is proposed to ensure the safety and effectiveness of the load parameter identification results. Finally, the effectiveness of the proposed load parameter identification method is tested by comparing response time, load parameter identification accuracy, and edge computing loss.

This study addresses the challenges of real-time channel state estimation and adaptive parameter adjustment in dynamic LoRa networks, where the existing methods often fail to adapt efficiently to highly variable channel conditions. This study presents an innovative approach for real-time channel state estimation and adaptive parameter adjustment in long-range (LoRa) networks in dynamic Internet of Things (IoT) environments. When these types of networks are used in dynamic IoT environments, they are known to face challenges in the two above-mentioned areas. In our approach, a hybrid feature extraction method that integrates statistical analysis with domain-specific knowledge is utilized for real-time data labeling, focusing on the signal-to-noise (SNR) and received signal strength indicator (RSSI) metrics. This approach employs an adaptive sliding window technique for efficient processing of recent data. Subsequently, a multi-task long short-term memory (LSTM) neural network is introduced for the simultaneous prediction of multiple channel states. This multi-task model employs an online incremental learning approach to enhance the real-time performance and responsiveness of the model within dynamic environments. It also incorporates a confidence measure for estimated states to increase the prediction reliability. Finally, based on the confidence measure predictions and channel state estimation, the system dynamically adjusts the LoRa parameters, including the spreading factor, coding rate, transmission power, and bandwidth. Our results demonstrate that the confidence-based adaptive strategy coupled with adaptive sliding window processing and incremental learning effectively balances performance optimization with stability in challenging IoT scenarios. This study contributes a robust, data-driven approach for real-time channel state estimation and adaptive parameter control, addressing the unique challenges of IoT networks in dynamic environments. Our approach achieved a packet delivery ratio of 100%, reduced energy consumption to 0.07987 Joules per packet, and demonstrated a prediction accuracy between 97.70% and 97.9% for estimating the different channel states. This innovative framework provides significant improvements in channel state estimation, communication reliability, adaptive parameter control, and computational efficiency, thereby ensuring robust performance in IoT environments at the same time.

Consumer electronics is a device designed to meet the everyday needs of individuals, including home appliances, smartphones, and laptops. The Internet of Things (IoT) environment is witnessing tremendous growth, driven by the simultaneous increase and continuous cyber-attack innovation. The imperative to fortify IoT devices against emerging threats became more prevalent as these threats became increasingly complex. In this context, threats include malware attacks, unauthorized access, and data breaches. Securing these devices requires robust encryption, regular software updates, and vigilant monitoring to protect sensitive information and ensure user safety. Threat detection using deep learning (DL) includes leveraging cutting-edge neural network models to detect and alleviate security threats within digital environments. DL, a branch of machine learning (ML), excels in processing abundant data to detect anomalies and patterns that might indicate possible threats. This technique improves classical threat detection techniques by reducing false positives and enhancing accuracy. By continuously analyzing data from various sources, such as network traffic and user behavior, DL techniques can quickly recognize and respond to emerging vulnerabilities, providing a proactive and adaptive security solution essential for protecting consumer electronics and IoT devices. This study develops a new Hybrid DL-based Threat Detection with Blockchain Technology (HDLTD-BCT) technique for secure IoT-based consumer electronics. The presented HDLTD-BCT technique can improve security among consumer electronics in the IoT environment. For this purpose, the HDLTD-BCT technique initially applies BC technology to monitor data flow in the IoT platform. The HDLTD-BCT technique scales the input data for threat detection using a min–max scalar. Besides, the detection process is performed by HDL, comprising a stacked LSTM-based denoising autoencoder (LSDAE) model. To enhance the HDL method’s performance, the Maritime Cyber Warfare Officers (MCWO) performs the hyperparameter selection process. The experimental results of the HDLTD-BCT technique can be validated utilizing the NSLKDD dataset. The simulation outcomes of the HDLTD-BCT technique exhibited a superior accuracy value of 99.68% compared to other DL models.

ABSTRACTIndustrial automation and smart ecological monitoring are key fields of Internet of Things environments, where devices function under complex practical conditions and with restricted infrastructure. In such conditions, devices often face critical concerns in guaranteeing trustworthiness and better outcomes. In this article, we preliminarily suggest a thoughtful design that anticipates the programming complexities of Internet of Things (IoT) environments and accounts for their unpredictable conduct under practical conditions. Central to our strategy is the use of a method grounded in mathematical logic to allow their core properties to be rigorously checked through mathematical proofs. This process builds trustworthy IoT infrastructures and ensures dependability of their conduct before practical programming. Beyond theoretical design, we perform programming and field experiments, demonstrating that mathematically grounded designs lead directly to more productive environment outcomes, particularly in restricted conditions where infrastructure must be exploited judiciously. The results underscore the value of integrating our mathematically checked design not only at the design level but also in shaping concrete solutions for critical blockchain‐enabled IoT environments. Finally, the results show that applying our design translates into demonstrable outcomes and easier environment adaptation during practical programming.

Traditional indoor human activity recognition (HAR) has been defined as a time-series data classification problem and requires feature extraction. The current indoor HAR systems still lack transparent, interpretable, and explainable approaches that can generate human-understandable information. This paper proposes a new approach, called Human Activity Recognition on Signal Images (HARSI), which defines the HAR problem as an image classification problem to improve both explainability and recognition accuracy. The proposed HARSI method collects sensor data from the Internet of Things (IoT) environment and transforms the raw signal data into some visual understandable images to take advantage of the strengths of convolutional neural networks (CNNs) in handling image data. This study focuses on the recognition of symmetric human activities, including walking, jogging, moving downstairs, moving upstairs, standing, and sitting. The experimental results carried out on a real-world dataset showed that a significant improvement (13.72%) was achieved by the proposed HARSI model compared to the traditional machine learning models. The results also showed that our method (98%) outperformed the state-of-the-art methods (90.94%) in terms of classification accuracy.

The paper considers the proposed method for the camera-less remote surveillance on hydraulically actuated heavy equipment. The method uses the data about the pressure and position of hydraulic actuators as an input. These data are transmitted over the internet in the Internet of Things (IoT) environment to the IoT cloud computing platform. A simulation model consisting of hydraulic and multibody dynamics submodels composes the digital twin of the machine under surveillance. This digital twin is maintained and calculated in the cloud. It reproduces the movements of the machine and calculates the forces acting in it. Together with the GPS coordinates, these data provide the full information on the machine operation. As a result, the productivity of the machine can be estimated, the misuse can be detected, and the load history can be gathered in order to estimate the remaining life of the machine or to plan the maintenance activities. The influence of the sensor accuracy on the simulation results is evaluated. The experimental results are presented that verify the feasibility of the proposed method on the example case of hydraulic mobile crane.

Efficient resource management within Internet of Things (IoT) environments remains a pressing challenge due to the increasing number of devices and their diverse functionalities. This study introduces a neural network-based m... | Find, read and cite all the research you need on Tech Science Press

The proposed system comprises of dynamic and heterogeneous sensors in internet of things (IoT) environment and aims at achieving an efficient communication among sensor devices by choosing the most...