Explore the vast range of titles available.

By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices.

Many Internet of Things (IoT) services utilize an IoT access network to connect small devices with remote servers. They can share an access network with standard communication technology, such as IEEE 802.11ah. However, an authentication and key management (AKM) mechanism for resource constrained IoT devices using IEEE 802.11ah has not been proposed as yet. We therefore propose a new AKM mechanism for an IoT access network, which is based on IEEE 802.11 key management with the IEEE 802.1X authentication mechanism. The proposed AKM mechanism does not require any pre-configured security information between the access network domain and the IoT service domain. It considers the resource constraints of IoT devices, allowing IoT devices to delegate the burden of AKM processes to a powerful agent. The agent has sufficient power to support various authentication methods for the access point, and it performs cryptographic functions for the IoT devices. Performance analysis shows that the proposed mechanism greatly reduces computation costs, network costs, and memory usage of the resource-constrained IoT device as compared to the existing IEEE 802.11 Key Management with the IEEE 802.1X authentication mechanism.

In recent years, machine learning (ML) and deep learning (DL) have shown remarkable improvement in computer vision, natural language processing, stock prediction, forecasting, and audio processing to name a few. The size of the trained DL model is large for these complex tasks, which makes it difficult to deploy on resource-constrained devices. For instance, size of the pre-trained VGG16 model trained on the ImageNet dataset is more than 500 MB. Resource-constrained devices such as mobile phones and internet of things devices have limited memory and less computation power. For real-time applications, the trained models should be deployed on resource-constrained devices. Popular convolutional neural network models have millions of parameters that leads to increase in the size of the trained model. Hence, it becomes essential to compress and accelerate these models before deploying on resource-constrained devices while making the least compromise with the model accuracy. It is a challenging task to retain the same accuracy after compressing the model. To address this challenge, in the last couple of years many researchers have suggested different techniques for model compression and acceleration. In this paper, we have presented a survey of various techniques suggested for compressing and accelerating the ML and DL models. We have also discussed the challenges of the existing techniques and have provided future research directions in the field.

The IoT has become an integral part of the technological ecosystem that we all depend on. The increase in the number of IoT devices has also brought with it security concerns. Lightweight cryptography (LWC) has evolved to be a promising solution to improve the privacy and confidentiality aspect of IoT devices. The challenge is to choose the right algorithm from a plethora of choices. This work aims to compare three different LWC algorithms: AES-128, SPECK, and ASCON. The comparison is made by measuring various criteria such as execution time, memory utilization, latency, throughput, and security robustness of the algorithms in IoT boards with constrained computational capabilities and power. These metrics are crucial to determine the suitability and help in making informed decisions on choosing the right cryptographic algorithms to strike a balance between security and performance. Through the evaluation it is observed that SPECK exhibits better performance in resource-constrained IoT devices.

The growth in artificial intelligence and its applications has led to increased data processing and inference requirements. Traditional cloud-based inference solutions are often used but may prove inadequate for applications requiring near-instantaneous response times. This review examines Tiny Machine Learning, also known as TinyML, as an alternative to cloud-based inference. The review focuses on applications where transmission delays make traditional Internet of Things (IoT) approaches impractical, thus necessitating a solution that uses TinyML and on-device inference. This study, which follows the PRISMA guidelines, covers TinyML’s use cases for real-world applications by analyzing experimental studies and synthesizing current research on the characteristics of TinyML experiments, such as machine learning techniques and the hardware used for experiments. This review identifies existing gaps in research as well as the means to address these gaps. The review findings suggest that TinyML has a strong record of real-world usability and offers advantages over cloud-based inference, particularly in environments with bandwidth constraints and use cases that require rapid response times. This review discusses the implications of TinyML’s experimental performance for future research on TinyML applications.

Blockchain is one of the promising technologies nowadays due to its unique characteristics like security, privacy, data integrity, decentralization, immutability, and traceability. Originally used to implement cryptocurrencies, recently numerous applications have employed blockchain in their architectures including applications targeted for the internet of things (IoT) environments. It is expected that by 2025 more than 21 billion IoT devices will be used especially with use of cloud, fog and edge computing architectures. Integrating blockchain in the IoT architecture provides many advantages such as enhancing security and privacy, better speed and costs, traceability and reliability, and elimination of single point of failure. On the other hand, many issues and challenges have arisen and should be addressed. Typically, IoT system consists of lightweight devices with limited hardware resources and constraints. Hence, the energy efficiency is a fundamental challenge in such devices. The main motivation of this paper is to survey designing a secure and energy efficient blockchain-based IoT implementation using a suitable hardware design. The paper classifies, presents and analyzes existing solutions to better implement IoT environment combined with blockchain technology. Our investigation demonstrations that most of lightweight solutions handle either the energy or security issue separately. Moreover, many works are theoretical-based analysis and solutions without considering the real blockchain-based IoT validation design. Energy evaluation for IoT hardware devices is not given the adequate research bandwidth. Additionally, limited works evaluated their techniques from hardware constrained device perspective. It is recommended that the performance of any proposed solution should be validated using real designs. The hardware perspective evaluation should be in mind for efficient blockchain-based IoT hardware implementation. The proposed lightweight solutions should focus more on efficient energy implementation while considering the lightweight security mechanisms.

The existence of quantum computers and Shor’s algorithm poses an imminent threat to classical public-key cryptosystems. These cryptosystems are currently used for the exchange of keys between servers and clients over the Internet. The Internet of Things (IoT) is the next step in the evolution of the Internet, and it involves the connection of millions of low-powered and resource-constrained devices to the network. Because quantum computers are becoming more capable, the creation of a new cryptographic standard that cannot be compromised by them is indispensable. There are several current proposals of quantum-resistant or post-quantum algorithms that are being considered for future standards. Given that the IoT is increasing in popularity, and given its resource-constrained nature, it is worth adapting those new standards to IoT devices. In this work, we study some post-quantum cryptosystems that could be suitable for IoT devices, adapting them to work with current cryptography and communication software, and conduct a performance measurement on them, obtaining guidelines for selecting the best for different applications in resource-constrained hardware. Our results show that many of these algorithms can be efficiently executed in current IoT hardware, providing adequate protection from the attacks that quantum computers will eventually be capable of.

Blockchain is among the most promising new technologies due to its unique features, encompassing security, privacy, data integrity, and immutability. Blockchain applications include cryptocurrencies such as Bitcoin. Recently, many other applications have begun to deploy blockchain in their systems. These applications include internet of things (IoT) environments. Although deploying blockchain in IoT architecture has yielded numerous advantages, issues and challenges have arisen that require further research. Most IoT devices and platforms have limited storage capacity, low battery power, and limited hardware resources for computation and network communication. Thus, energy efficiency is a critical factor in these devices. On the other hand, blockchain requires extensive resources and high computational capabilities for mining and communication processes. Balancing computation complexity and IoT resources is a fundamental design challenge in implementing blockchain functions, including the hash function, which is crucial to blockchain design for the mining process. In this study, we present a literature review on the common hash functions used in blockchain-based applications, in addition to the lightweight hash functions available in literature. We evaluate and test the common lightweight hash functions (SPONGENT, PHOTON, and QUARK) on FPGA platforms to determine which is most suitable for blockchain-IoT devices. Moreover, we assess lightweight hash functions in terms of area, power, energy, security, and throughput. The results show tradeoffs between these hash functions. SPONGENT performs best on security and throughput. QUARK consumes the least power and energy but has the lowest security parameters. PHOTON utilizes less area and offers a balance between multiple performance metrics (area, energy, and security), rendering it the most suitable lightweight hash function.

Blockchain is a technology that can ensure data integrity in a distributed network, and it is actively applied in various fields. Recently, blockchain is gaining attention due to combining with the Internet of Things (IoT) technology in the industrial field. Moreover, many researchers have proposed the Industrial IoT (IIoT) architecture with blockchain for data integrity and efficient management. The IIoT network consists of many heterogeneous devices (e.g., sensors, actuators, and programmable logic controllers (PLC)) with resources-constrained, and the availability of the network must be preferentially considered. Therefore, applying the existed blockchain technology is still challenging. There are some results about the technique of constructing blockchain lightly to solve this challenge. However, in these results, the analysis in perspective of cryptographic performance (area, throughput, and power consumption) has not been considered sufficiently, or only focused on the architecture of the blockchain network. The blockchain technology is based on cryptographic techniques, and the main part is a cryptographic hash function. Therefore, if we construct the blockchain-based IIoT architecture, we have to consider the performance of the hash function. Many lightweight hash functions have been proposed recently for the resource-constrained environment, and it can also be used to the blockchain. Therefore, in this paper, we analyze the considerations of lightweight blockchain for IIoT. Also, we conduct an analysis of lightweight hash for blockchain, and propose a new lightweight hash-based blockchain architecture that can change the hash algorithm used for mining adjust to network traffic.

Mechanical weed management is a drudging task that requires manpower and has risks when conducted within rows of orchards. However, intrarow weeding must still be conducted by manual labor due to the restricted movements of riding mowers within the rows of orchards due to their confined structures with nets and poles. However, autonomous robotic weeders still face challenges identifying uncut weeds due to the obstruction of Global Navigation Satellite System (GNSS) signals caused by poles and tree canopies. A properly designed intelligent vision system would have the potential to achieve the desired outcome by utilizing an autonomous weeder to perform operations in uncut sections. Therefore, the objective of this study is to develop a vision module using a custom-trained dataset on YOLO instance segmentation algorithms to support autonomous robotic weeders in recognizing uncut weeds and obstacles (i.e., fruit tree trunks, fixed poles) within rows. The training dataset was acquired from a pear orchard located at the Tsukuba Plant Innovation Research Center (T-PIRC) at the University of Tsukuba, Japan. In total, 5000 images were preprocessed and labeled for training and testing using YOLO models. Four versions of edge-device-dedicated YOLO instance segmentation were utilized in this research—YOLOv5n-seg, YOLOv5s-seg, YOLOv8n-seg, and YOLOv8s-seg—for real-time application with an autonomous weeder. A comparison study was conducted to evaluate all YOLO models in terms of detection accuracy, model complexity, and inference speed. The smaller YOLOv5-based and YOLOv8-based models were found to be more efficient than the larger models, and YOLOv8n-seg was selected as the vision module for the autonomous weeder. In the evaluation process, YOLOv8n-seg had better segmentation accuracy than YOLOv5n-seg, while the latter had the fastest inference time. The performance of YOLOv8n-seg was also acceptable when it was deployed on a resource-constrained device that is appropriate for robotic weeders. The results indicated that the proposed deep learning-based detection accuracy and inference speed can be used for object recognition via edge devices for robotic operation during intrarow weeding operations in orchards.