Smart agriculture has taken more attention during the last decade due to the bio-hazards of climate change impacts, extreme weather events, population explosion, food security demands and natural resources shortage. The Egyptian government has taken initiative in dealing with plants diseases especially tomato which is one of the most important vegetable crops worldwide that are affected by many diseases causing high yield loss. Deep learning techniques have become the main focus in the direction of identifying tomato leaf diseases. This study evaluated different deep learning models pre-trained on ImageNet dataset such as ResNet50, InceptionV3, AlexNet, MobileNetV1, MobileNetV2 and MobileNetV3.To the best of our knowledge MobileNetV3 has not been tested on tomato leaf diseases. Each of the former deep learning models has been evaluated and optimized with different techniques. The evaluation shows that MobileNetV3 Small has achieved an accuracy of 98.99% while MobileNetV3 Large has achieved an accuracy of 99.81%. All models have been deployed on a workstation to evaluate their performance by calculating the prediction time on tomato leaf images. The models were also deployed on a Raspberry Pi 4 in order to build an Internet of Things (IoT) device capable of tomato leaf disease detection. MobileNetV3 Small had a latency of 66 ms and 251 ms on the workstation and the Raspberry Pi 4, respectively. On the other hand, MobileNetV3 Large had a latency of 50 ms on the workstation and 348 ms on the Raspberry Pi 4.

In recent decades, there has been considerable interest in developing underwater remotely operated vehicles (ROVs) due to their vital role in exploring ocean depths to perform missions in various applications, including offshore oil and gas, military and defense, scientific research, and aquaculture. To this end, researchers must consider multiple aspects to develop ROVs, such as general design, power and thrust system, navigation and control, and obstacle avoidance. Accordingly, this paper proposes an integrated framework for designing and implementing an ROV prototype, considering the mechanical, electrical, and software systems. Eventually, image processing was implemented using Python to examine the ROV’s capabilities in performing underwater missions. The proposed design employs six thrusters to provide controllability of the ROV in six-degrees-of-freedom (DOF). We coated the track width of the printed circuit board (PCB) with a composite mixture of tin, silver, and gold to resist corrosion and harsh environments, enhance the circuit performance and solderability, and increase its life span. The PCB was designed to sustain 30 A with 10 cm × 10 cm dimensions. The image processing results revealed that the proposed ROV could successfully identify the benthic species, follow the desired routes, detect cracks, and analyze obstacles.

Interest in developing techniques for acquiring and decoding biological signals is on the rise in the research community. This interest spans various applications, with a particular focus on prosthetic control and rehabilitation, where achieving precise hand gesture recognition using surface electromyography signals is crucial due to the complexity and variability of surface electromyography data. Advanced signal processing and data analysis techniques are required to effectively extract meaningful information from these signals. In our study, we utilized three datasets: NinaPro Database 1, CapgMyo Database A, and CapgMyo Database B. These datasets were chosen for their open-source availability and established role in evaluating surface electromyography classifiers. Hand gesture recognition using surface electromyography signals draws inspiration from image classification algorithms, leading to the introduction and development of the Novel Signal Transformer. We systematically investigated two feature extraction techniques for surface electromyography signals: the Fast Fourier Transform and wavelet-based feature extraction. Our study demonstrated significant advancements in surface electromyography signal classification, particularly in the Ninapro database 1 and CapgMyo dataset A, surpassing existing results in the literature. The newly introduced Signal Transformer outperformed traditional Convolutional Neural Networks by excelling in capturing structural details and incorporating global information from image-like signals through robust basis functions. Additionally, the inclusion of an attention mechanism within the Signal Transformer highlighted the significance of electrode readings, improving classification accuracy. These findings underscore the potential of the Signal Transformer as a powerful tool for precise and effective surface electromyography signal classification, promising applications in prosthetic control and rehabilitation.

Free Space Optical (FSO) communication systems have extensively invaded the speed of smart city evolution due to the current surge in demand for wireless communication spots that can match recent challenges due to high technical leaps in smart city evolution. As the number of users is vastly increasing throughout all networks in the form of machines, devices, and variously distinct objects, FSO is a hugely recommended robust communication system that mitigates a lot of RF disadvantages on the field with no need for licensing, fast rollout time, and low cost. This paper shows an exploit of a Low Power Field Programmable Gate Array (FPGA) based FSO communication system designed for Line of Sight (LOS) Building to Building Communication over a distance of 12 m using a 650 nm Visible Light (VL) red laser source via On-Off Keying (OOK) and higher-level Intensity Modulation (IM)/Pulse Width Modulation (PWM) schemes. The implemented system reached a doubled data rate than OOK of 230 kbps using the IM technique. Traffic monitoring and building security status can be frequently updated between adherent buildings, each scanning its zone real-time conditions and sharing them with the neighboring links.

Precisely forecasting electrical load, especially through univariate time series analysis, is pivotal for effectively operating and planning power systems. This research introduces a hybrid model leveraging univariate time series and deep learning techniques. The model combines the Bidirectional Gated Recurrent Units (Bi-GRU) based encoder-decoder structure with the Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) architecture to enhance single-step short-term electrical demand forecasting. Integrating Bi-GRUs ensures adept capture of temporal dependencies, while CNNs meticulously extract spatial features. Concurrently, LSTMs provide a robust mechanism to memorize long-range dependencies. The model's competence was rigorously assessed through evaluations using the publicly available American Electric Power (AEP) dataset, which represents real-world electrical load patterns. Findings highlight that the proposed model outstrips competing models in algorithmic stability and prediction accuracy. With a Mean Absolute Percentage Error (MAPE) of 80.032, this research posits a promising avenue for utilizing deep learning in univariate time series power load prediction.