The rapid growth of Internet of Things (IoT) is expected to add billions of IoT devices connected to the Internet. These devices represent a vast attack surface for cyberattacks. For example, these IoT devices can be infected with botnets to enable Distributed Denial of Service (DDoS) attacks. Signature-based intrusion detection systems are traditional countermeasures for such attacks. However, these methods rely on human experts and are time-consuming in terms of updates and may not exhaust all attack types especially zero-day attacks. Deep learning has shown some promise in intrusion detection. This paper shows that it is possible to use generative deep learning methods like Adversarial Autoencoders (AAE) and Bidirectional Generative Adversarial Networks (BiGAN) to detect intruders based on an analysis of the network data. The recently posted full IoT-23 dataset based on Somfy door lock, Philips Hue and Amazon Echo devices was used to train generative deep learning models to detect a variety of attacks like DDoS, and various botnets like Mirai, Okiruk and Torii. Over 1.8 million network flows were used to train the various models. The resulting generative models outperform traditional machine learning techniques like Random Forests. Both AAE and BiGAN-based models were able to achieve an F1-Score of 0.99. A BiGAN to detect unknown attacks was also trained to detect novel zero-day attacks with an F1-Score from 0.85 to 1.

Unmanned aerial vehicles (UAVs) are increasingly being integrated into the domain of precision agriculture, revolutionizing the agricultural landscape. Specifically, UAVs are being used in conjunction with machine learning techniques to solve a variety of complex agricultural problems. This paper provides a careful survey of more than 70 studies that have applied machine learning techniques utilizing UAV imagery to solve agricultural problems. The survey examines the models employed, their applications, and their performance, spanning a wide range of agricultural tasks, including crop classification, crop and weed detection, cropland mapping, and field segmentation. Comparisons are made among supervised, semi-supervised, and unsupervised machine learning approaches, including traditional machine learning classifiers, convolutional neural networks (CNNs), single-stage detectors, two-stage detectors, and transformers. Lastly, future advancements and prospects for UAV utilization in precision agriculture are highlighted and discussed. The general findings of the paper demonstrate that, for simple classification problems, traditional machine learning techniques, CNNs, and transformers can be used, with CNNs being the optimal choice. For segmentation tasks, UNETs are by far the preferred approach. For detection tasks, two-stage detectors delivered the best performance. On the other hand, for dataset augmentation and enhancement, generative adversarial networks (GANs) were the most popular choice.

Manufacturers of smart home consumer devices like home theatres, music players, voice-based assistants, smart lighting, and security cameras have widely adopted the Internet of Things (IoT). These devices pose a significant security risk to consumers because the devices are exposed to mobile applications and cloud-based services with known security vulnerabilities. Most current home consumer devices provide little or no information about the level of security they afford. Since most consumers are not tech-savvy, it is currently difficult for a consumer to make an informed decision about which consumer device model (e.g., smart television model) has the best security. Hence, consumers need an objective security ranking of each type (e.g., security cameras) of home consumer devices. This paper proposes a novel methodology to systematically build such security rankings for home consumer devices. The proposed methodology can be applied by utilizing data from any security assessment study. The paper discusses previous efforts in applying Analytic Hierarchy Process (AHP) to rank security risks in general. The paper also presents a systematic survey of security vulnerabilities of smart home consumer devices when viewed from an IoT lens. Using the proposed methodology, a case study, employing an AHP model for ranking commonly used home consumer devices including home theatres, security cameras, smart lighting, smart speakers, video surveillance, smart switches, home automation systems, home security systems, smart routers, wireless doorbell cameras, and home audio systems, was developed. Relative security rankings for each type of consumer device were derived from the AHP model. According to the AHP model, network security was the primary driver of smart home device security with a priority of 0.6893 while application security had the least priority of 0.0591. Critical Vulnerabilities were the most important for device security (priority=0.4397), Man-in-The-Middle attacks for network security (priority=0.2019), exploitable services for cloud security (priority=0.26), and sensitive data for application security (0.7626). The AHP model was internally consistent (Consistency Ratio < 0.1). Sensitivity analysis showed that the AHP model was robust against pairing assumptions.

Camera traps deployed in remote locations provide an effective method for ecologists to monitor and study wildlife in a non-invasive way. However, current camera traps suffer from two problems. First, the images are manually classified and counted, which is expensive. Second, due to manual coding, the results are often stale by the time they get to the ecologists. Using the Internet of Things (IoT) combined with deep learning represents a good solution for both these problems, as the images can be classified automatically, and the results immediately made available to ecologists. This paper proposes an IoT architecture that uses deep learning on edge devices to convey animal classification results to a mobile app using the LoRaWAN low-power, wide-area network. The primary goal of the proposed approach is to reduce the cost of the wildlife monitoring process for ecologists, and to provide real-time animal sightings data from the camera traps in the field. Camera trap image data consisting of 66,400 images were used to train the InceptionV3, MobileNetV2, ResNet18, EfficientNetB1, DenseNet121, and Xception neural network models. While performance of the trained models was statistically different (Kruskal–Wallis: Accuracy H(5) = 22.34, p < 0.05; F1-score H(5) = 13.82, p = 0.0168), there was only a 3% difference in the F1-score between the worst (MobileNet V2) and the best model (Xception). Moreover, the models made similar errors (Adjusted Rand Index (ARI) > 0.88 and Adjusted Mutual Information (AMU) > 0.82). Subsequently, the best model, Xception (Accuracy = 96.1%; F1-score = 0.87; F1-Score = 0.97 with oversampling), was optimized and deployed on the Raspberry Pi, Google Coral, and Nvidia Jetson edge devices using both TenorFlow Lite and TensorRT frameworks. Optimizing the models to run on edge devices reduced the average macro F1-Score to 0.7, and adversely affected the minority classes, reducing their F1-score to as low as 0.18. Upon stress testing, by processing 1000 images consecutively, Jetson Nano, running a TensorRT model, outperformed others with a latency of 0.276 s/image (s.d. = 0.002) while consuming an average current of 1665.21 mA. Raspberry Pi consumed the least average current (838.99 mA) with a ten times worse latency of 2.83 s/image (s.d. = 0.036). Nano was the only reasonable option as an edge device because it could capture most animals whose maximum speeds were below 80 km/h, including goats, lions, ostriches, etc. While the proposed architecture is viable, unbalanced data remain a challenge and the results can potentially be improved by using object detection to reduce imbalances and by exploring semi-supervised learning.

In recent times, transformer-based deep learning models have risen in prominence in the field of machine learning for a variety of tasks such as computer vision and text generation. Given this increased interest, a historical outlook at the development and rapid progression of transformer-based models becomes imperative in order to gain an understanding of the rise of this key architecture. This paper presents a survey of key works related to the early development and implementation of transformer models in various domains such as generative deep learning and as backbones of large language models. Previous works are classified based on their historical approaches, followed by key works in the domain of text-based applications, image-based applications, and miscellaneous applications. A quantitative and qualitative analysis of the various approaches is presented. Additionally, recent directions of transformer-related research such as those in the biomedical and timeseries domains are discussed. Finally, future research opportunities, especially regarding the multi-modality and optimization of the transformer training process, are identified.

The challenge of aligning Information Technology (IT) to business has often been cited as a key issue by IT executives. This paper presents a simple, flexible, and easy-to-use instrument that measures the alignment maturity between business and IT and identifies major gaps. The proposed instrument is based on Luftman's “Strategy Alignment Maturity Model” (SAMM); it directly encodes all attributes of SAMM alignment areas using a unidimensional framework. The instrument supports multiple levels of analysis with minimum assumptions about data using non-parametric statistical tools. In addition, the instrument provides an aggregation procedure to summarize the alignment maturity level for high-level executives. The instrument can also be customized to incorporate the contextual parameters of a company. In addition to the development of the instrument, this paper also shows how this instrument was applied to assess the alignment maturity level between IT and business in a rapidly growing company that had recently been publicly listed. The instrument was successful in identifying six major gaps for the company across the various alignment areas. These gaps were benchmarking, business metrics, strategic business planning, inter / intra organizational learning, architectural integration, and the impact of IT on business processes.