Cybercriminals use domain generation algorithms (DGAs) to prevent their servers from being potentially blacklisted or shut down. Existing reverse engineering techniques for DGA detection is labor intensive, extremely time-consuming, prone to human errors, and have significant limitations. Hence, an automated real-time technique with a high detection rate is warranted in such applications. In this article, we present a novel technique to detect randomly generated domain names and domain name system (DNS) homograph attacks without the need for any reverse engineering or using nonexistent domain (NXDomain) inspection using deep learning. We provide an extensive evaluation of our model over four large, real-world, publicly available datasets. We further investigate the robustness of our model against three different adversarial attacks: DeepDGA, CharBot, and MaskDGA. Our evaluation demonstrates that our method is effectively able to identify DNS homograph attacks and DGAs and also is resilient to common evading cyberattacks. Promising results show that our approach provides a more effective detection rate with an accuracy of 0.99. Additionally, the performance of our model is compared against the most popular deep learning architectures. Our findings highlight the essential need for more robust detection models to counter adversarial learning.

Quick, early, and precise detection is important for diagnosis to control the spread of COVID-19 infection. Artificial Intelligence (AI) technology could certainly be used as a modulating tool to ease the detection, and help with the preventive steps further. Convolutional neural networks (CNNs) have achieved state-of-the-art performance in many visual recognition tasks. Nevertheless, most of these state-of-the-art networks highly rely on the availability of a high amount of labeled data, being an essential step in supervised machine learning tasks. Conventionally, this manual, mundane, and time-consuming process of annotating images is done by humans. Learning to localize or detect COVID-19 infection masks in our specific case study typically requires the collection of CT scan data that has been labeled with bounding boxes or similar annotations, which generally is limited. A technique that could perform such learning with much less annotations, and transfer the learned proposals that are algorithm-driven to generate more synthetic annotated samples would be helpful & quite valuable. We present such a technique inspired by weakly trained mask region based convolutional neural networks (R-CNN) architecture for localization, in which the number of images with their pixel-level masks can be a small proportion of the total dataset, and then further improvise CNNs by inversely generating dense annotations on-the-go using an algorithmic-based computational approach. We focus on alleviating the bottleneck associated with deep learning models needing annotated data for training in an intuitive reverse engineering fashion through this work. Our proposed solution can certainly provide the prospect of automated labeling on-the-fly, thereby reducing much of the manual work. As a result, one can quickly train a precise COVID-19 infection detector with the leverage of autonomous frame-by-frame machine generated annotations. The model achieved mean precision accuracy (%) of 0.99, 0.931, and 0.8 for train, validation, and test set, respectively. The results demonstrate that the proposed method can be adopted in a clinical setting for assisting radiologists, and also our fully autonomous approach can be generalized to any detection/recognition tasks at ease.

Continuous monitoring of crops is critical for the sustainability of agriculture. The effects of changes in temperature, light intensity, humidity, pH, soil moisture, gas intensities, etc. have an overall impact on the plant growth. Growth chambers are environmental controlled facilities which needs to be monitored round‐the‐clock. To improve both the reproducibility, and maintenance of such facilities, remote monitoring plays a very pivotal role. An automated re‐configurable & persistent mirrored storage‐based remote monitoring system is developed with low‐cost open source hardwares and softwares. The system automates sensors deployment, storage (database, logs), and provides an elegant dashboard to visualize the real‐time continuous data stream. We propose a new smart AGRO IoT system with robust data acquisition mechanism, and also propose two software component nodes, (i.e., Mirroring and Reconfiguration) running as an instance of the whole IoT facility. The former one is aimed to minimize/avoid the downtime, while the latter one is aimed to leverage the available cores, and better utilization of the computational resources. Our system can be easily deployed in growth chambers, greenhouses, CNC farming test‐bed setup, cultivation plots, and further can be also extended to support large‐farms with either using multiple individual standalone setup as heterogeneous instances of this facility, or by extending it as master‐slave cluster configuration for communication as a single homogeneous instance. Our RaspberryPi‐Arduino (RPA) powered solution is scalable, and provides stability for monitoring any environment continuously at ease.

The implementation of image-based phenotyping systems has become an important aspect of crop and plant science research which has shown tremendous growth over the years. Accurate determination of features using images requires stable imaging and very precise processing. By installing a camera on a mechanical arm driven by motor, the maintenance of accuracy and stability becomes non-trivial. As per the state-of-the-art, the issue of external camera shake incurred due to vibration is a great concern in capturing accurate images, which may be induced by the driving motor of the manipulator. So, there is a requirement for a stable active controller for sufficient vibration attenuation of the manipulator. However, there are very few reports in agricultural practices which use control algorithms. Although, many control strategies have been utilized to control the vibration in manipulators associated to various applications, no control strategy with validated stability has been provided to control the vibration in such envisioned agricultural manipulator with simple low-cost hardware devices with the compensation of non-linearities. So, in this work, the combination of proportional-integral-differential (PID) control with type-2 fuzzy logic (T2-F-PID) is implemented for vibration control. The validation of the controller stability using Lyapunov analysis is established. A torsional actuator (TA) is applied for mitigating torsional vibration, which is a new contribution in the area of agricultural manipulators. Also, to prove the effectiveness of the controller, the vibration attenuation results with T2-F-PID is compared with conventional PD/PID controllers, and a type-1 fuzzy PID (T1-F-PID) controller.

Digital plant inventory provides critical growth insights, given the associated data quality is good. Stable & high-quality image acquisition is critical for further examination. In this work, we showcase an affordable, portable, and modular spectral camera prototype, designed with open hardware’s and open-source software’s. The image sensors used were color, and infrared Pi micro-camera. The designed prototype presents the advantage as being low-cost and modular with respect to other general commercial market available spectral devices. The micro-size connected sensors make it a compact instrument that can be used for any general spectral acquisition purposes, along with the provision of custom selection of the bands, making the presented prototype design a Plug-nd-Play (PnP) setup that can be used in different wide application areas. The images acquired from our custom-built prototype were back-tested by performing image analysis and qualitative assessments. The image acquisition software, and processing algorithm has been programmed, which is bundled with our developed system. Further, an end-to-end automation script is integrated for the users to readily leverage the services on-demand. The design files, schematics, and all the related materials of the spectral block design is open-sourced with open-hardware license & is made available at https://github.com/ajayarunachalam/Multi-Spectral-Imaging-RaspberryPi-Design. The automated data acquisition scripts & the spectral image analysis done is made available at https://github.com/ajayarunachalam/SI-RPi.