Real-Time Face Mask Detection Using Machine Learning Algorithm

The hardware implementation of convolutional neural network has the problem of resource limitation, which can be solved by the design of convolutional neural network accelerator based on FPGA dynamic reconstruction. The whole parallel strategy and architecture of CNN accelerator are designed, and the functional modules of CNN are designed based on pipeline. The dynamic reconstruction technology is used to redesign the convolutional neural network accelerator, and the dynamic reconstruction region and division are established; BPI flash is selected to store the configuration file, and the configuration file is read internally to dynamically configure the dynamic reconstruction area. Finally, for lenet. 5 handwriting recognition, compared with the corresponding static design, the use of slice LUTS, slice registers and DSP resources of the accelerator based on dynamic reconstruction design is reduced by 46%, 25% and 68% respectively. Compared with the implementation based on software platform. The system execution time is greatly reduced. However, due to the bandwidth limitation of the internal configuration port, the reconfiguration configuration time prolongs the execution time of the whole convolutional network.

Based on a survey released by the TomTom Traffic Index in 2018, Indonesia was ranked seventh in the category of the most congested country in the world. One of the factors affecting traffic congestion in Indonesia is an inflexible and conventional traffic management system. In this regard, it is necessary to have a better traffic management system such as a Smart Traffic Light. One way to implement a smart traffic light system is to make a vehicle detection and counting system on the traffic CCTV video automatically. The methods used in this research are Haar Cascade Classifiers and Convolutional Neural Network. Haar Cascade Classifiers have fast computation processes and CNN is applied to validate the detection results of the Haar Cascade method for better accuracy. The average level of accuracy achieved by the system on quiet test data is 82%, normal test data is 69%, and busy test data is 60%. Meanwhile, the average computation time needed by the system for the quiet test data is 0.63 seconds, the normal test data is 0.52 seconds, and the busy test data is 1.05 seconds.

Convolutional neural networks (CNNs) have demonstrated remarkable performance in many areas but require significant computation and storage resources. Quantization is an effective method to reduce CNN complexity and implementation. The main research objective is to develop a scalable quantization algorithm for CNN hardware design and model the performance metrics for the purpose of CNN implementation in resource-constrained devices (RCDs) and optimizing layers in deep neural networks (DNNs). The algorithm novelty is based on blending two quantization techniques to perform full model quantization with optimum accuracy, and without additional neurons. The algorithm is applied to a selected CNN model and implemented on an FPGA. Implementing CNN using broad data is not possible due to capacity issues. With the proposed quantization algorithm, we succeeded in implementing the model on the FPGA using 16-, 12-, and 8-bit quantization. Compared to the 16-bit design, the 8-bit design offers a 44% decrease in resource utilization, and achieves power and energy reductions of 41% and 42%, respectively. Models show that trading off one quantization bit yields savings of approximately 5.4K LUTs, 4% logic utilization, 46.9 mW power, and 147 μJ energy. The models were also used to estimate performance metrics for a sample DNN design.

Over the last years, Convolutional Neural Networks (CNNs) have been widely used in remote sensing applications, such as marine surveillance, traffic management or road networks detection. However, since CNNs have extremely high computation, bandwith and memory requirements, the hardware implementation of a CNN on space-grade devices like FPGAs for the on-board processing of the acquired images has brought many challenges. In fact, FPGAs show great advantages in terms of reconfigurability and performance-power ratio, whichmakes them a suitable election to deploy CNNs, although the computational capabilities of this type of hardware devices available on-board is limited, so implementations have to be carefully planned. In this paper, the authors present their work towards the implementation of an efficient CNN onto a spacegrade FPGA in order to achieve the on-board processing of very-high resolution remotely sensed images as soon as the data are provided by the sensor. All this work has been conducted within the EU-funded VIDEO project. As it will be presented in this paper, the work includes the introduction of a methodology based on the project constraints, the evaluation of different state-of-the-art CNN architectures by means of a new efficiency measurement also proposed in this work, the introduction of a new efficient CNN architecture, and finally, its optimized hardware implementation by means of high-level synthesis tools.

The growing development of IoT (Internet of Things) devices creates a large attack surface for cybercriminals to conduct potentially more destructive cyberattacks; as a result, the security industry has seen an exponential increase in cyber-attacks. Many of these attacks have effectively accomplished their malicious goals because intruders conduct cyber-attacks using novel and innovative techniques. An anomaly-based IDS (Intrusion Detection System) uses machine learning techniques to detect and classify attacks in IoT networks. In the presence of unpredictable network technologies and various intrusion methods, traditional machine learning techniques appear inefficient. In many research areas, deep learning methods have shown their ability to identify anomalies accurately. Convolutional neural networks are an excellent alternative for anomaly detection and classification due to their ability to automatically categorize main characteristics in input data and their effectiveness in performing faster computations. In this paper, we design and develop a novel anomaly-based intrusion detection model for IoT networks. First, a convolutional neural network model is used to create a multiclass classification model. The proposed model is then implemented using convolutional neural networks in 1D, 2D, and 3D. The proposed convolutional neural network model is validated using the BoT-IoT, IoT Network Intrusion, MQTT-IoT-IDS2020, and IoT-23 intrusion detection datasets. Transfer learning is used to implement binary and multiclass classification using a convolutional neural network multiclass pre-trained model. Our proposed binary and multiclass classification models have achieved high accuracy, precision, recall, and F1 score compared to existing deep learning implementations.

Technological advancements have had a significant impact on the education sector, including the application of Convolutional Neural Networks (CNN) for facial image analysis. This research aims to implement CNN to measure students' learning concentration levels. The FER2013 dataset, which includes seven emotion classifications and comprises 28,709 images for training data, is used as the database. The data is processed through rescaling and augmentation to prepare the CNN model. The model consists of several convolutional layers, pooling layers, and fully connected layers designed to extract crucial features from facial images. Evaluation results demonstrate a very high accuracy of 94.95% on training data, indicating that the model effectively recognizes complex patterns within the data. Although there is a higher loss value of 157% and a decreased accuracy of 62.75% on validation data, this suggests that the model possesses a strong foundational capability and can still be improved through further adjustments. With high accuracy in training and promising validation results, the model shows substantial potential for real-world application, where it can assist teachers in understanding students' emotional responses in real-time. The implementation of CNN aids educators in comprehending students' emotional responses and adapting their teaching methods more effectively, thereby creating a more conducive learning environment and enhancing students' academic and social development. These findings also open opportunities for further research to improve the performance and generalization of the model on unseen data, making this technology an increasingly reliable tool in education

Randomly switching neurons ON/OFF while training and inference process is an interesting characteristic of biological neural networks, that potentially results in inherent adaptability and creativity expressed by human mind. Dropouts inspire from this random switching behaviour and in the artificial neural network they are used as a regularization techniques to reduce the impact of over-fitting during the training. The energy-efficient digital implementations of convolutional neural networks (CNN) have been on the rise for edge computing IoT applications. Pruning larger networks and optimization for performance accuracy has been the main direction of work in this field. As opposed to this approach, we propose to build a near-sensor analogue CNN with high-density memristor crossbar arrays. Since several active elements such as amplifiers are used in analogue designs, energy efficiency becomes a main challenge. To address this, we extend the idea of using dropouts in training to also the inference stage. The CNN implementations require a subsampling layer, which is implemented as a mean pooling layer in the design to ensure lower energy consumption. Along with the dropouts, we also investigate the effect of non-idealities of memristor and that of the network.

Background: Memristor-based implementations of Convolutional Neural Networks (CNNs) offer the potential to reduce power consumption and improve computational efficiency significantly. However, the non-ideal characteristics of memristive devices, such as variability and limited switching behavior, can introduce nonlinearity and degrade network performance. It is therefore essential to simulate memristor-based deep learning systems and evaluate the impact of these imperfections before proceeding with hardware-level deployment. Objective: This study aims to design a lightweight memristor-based MobileNetV2 model for smoking behavior detection and analyze the influence of memristor non-idealities on the network’s detection accuracy. Methods: A lightweight MobileNetV2 network was constructed and trained on a self-developed dataset for smoking behavior detection, achieving a peak accuracy of 92.25%. Based on the trained model, a memristor-based MobileNetV2 architecture was implemented using the Mem- Torch simulation framework. Two memristor models, VTEAM and Data-Driven Verilog-A RRAM, were employed to replace the convolutional and fully connected layers with memristor crossbar arrays. The impact of non-ideal memristor properties, including conductance variability and resistance state faults, was systematically evaluated. Results: Simulation results demonstrated that the memristor-based MobileNetV2 network achieved detection accuracies of 92.11% with the VTEAM model and 91.82% with the Verilog-A RRAM model. As device non-idealities increased, the detection accuracy declined significantly, indicating a strong correlation between memristor imperfections and the performance of CNN- based target detection tasks. Conclusion: Memristor non-idealities substantially affect the performance of neuromorphic CNNs. This study provides targeted analyses and proposes mitigation strategies, such as differential encoding and improved fabrication techniques, to support the practical deployment of memristor- based neural networks in energy-efficient AI applications.

Effective disease control in crops is essential for ensuring food security, as numerous diseases can significantly reduce agricultural productivity. Leaf disease is a crucial determinant of crop yield and quality. Potatoes are widely regarded as a vital staple in diets around the world. Potato blight, often known as late blight, is a severe disease impacting Solanaceae plants, particularly the potato. The oomycete Phytophthora infestans serves as the causal agent, posing a significant threat to potato crops by reducing yields and leading to financial losses. Identifying potato diseases is essential for ensuring food security and minimizing economic losses in agriculture. Numerous studies have explored the applications of machine learning and deep learning technologies for detecting blight diseases in affected crops. The proposed methodology outlined in our study offers a promising and effective means to enhance the accuracy of potato late blight classification. Advancements in technology can significantly improve the identification and treatment of diseases. Deep learning algorithms have been effectively employed in a range of practical applications. In our investigation, convolutional neural network models are used to analyze images of leaves. The primary aim of this initiative is to gain insights into and enhance the capacity to recognize diseases in their early phases. After the input images undergo preprocessing, the target region is distinctly isolated. CNN examines images to identify unique features, including edges, colours, and textures. This study evaluates the effectiveness of the proposed model through a diverse dataset of potato leaf images, making essential contributions to the domain of automated disease detection systems. The results of this study could enhance techniques for agricultural management and strengthen the sustainability of agriculture. This study introduces an improved CNN model designed to identify the blight disease state in potato leaf images, providing a valuable tool for farmers. The findings may aid in the evaluation and implementation of Convolutional Neural Network (CNN) models for classifying proximal sensing images of potato plant leaves. Additional investigations could leverage this modelling framework and have the opportunity to examine various other factors to identify leaf infections at an earlier stage for crop protection.

Deep convolutional neural network (DCNN) is an advanced technology in image recognition. Because of extreme computing resource requirements, DCNN implementation with software alone cannot achieve real-time requirement. Therefore, the need to implement DCNN accelerator hardware is increasing. In this paper, we present a field programmable gate array (FPGA)-based hardware accelerator design of DCNN targeting handwritten Hangul character recognition application. Also, we present design optimization techniques in SDAccel environments for searching the optimal FPGA design space. The techniques we used include memory access optimization and computing unit parallelism, and data conversion. We achieved about 11.19 ms recognition time per character with Xilinx FPGA accelerator. Our design optimization was performed with Xilinx HLS and SDAccel environment targeting Kintex XCKU115 FPGA from Xilinx. Our design outperforms CPU in terms of energy efficiency (the number of samples per unit energy) by 5.88 times, and GPGPU in terms of energy efficiency by 5 times. We expect the research results will be an alternative to GPGPU solution for real-time applications, especially in data centers or server farms where energy consumption is a critical problem.

The concept of smart vehicles is becoming an essential feature that ensures driver comfort and security. Smart vehicles are equipped with intelligent systems based on advanced technologies that perform a set of tasks for the mentioned purposes. Recognizing Traffic sign is one the most important systems that guarantee a high-security level. However, it is difficult to develop the best traffic sign recognition system due to numerous obstacles. such as weather conditions, geometric deformation, and most important is the material limitation. In this work, we proposed the implementation of a lightweight convolutional neural network (CNN) model on a mobile device to overcome the mentioned challenges. The proposed CNN combines high performances and low computation complexity. Evaluating the proposed model on publicly available datasets proved its efficiency. Besides, the implementation of the CNN model on the pynq platform demonstrates the possibility of using a wide range of mobile devices for the inference of the proposed model.

The paper proposes a self-driving car model also called autonomous, robotic or driver-less car is one that operates and navigates using its intelligence. The basic idea behind the paper is to develop a 1/10 scale RC car to portray an automated car. The model consists of the following software and hardware components such as CNN (Convolutional neural network), Monocular vision algorithm, Haar cascade classifier, Raspberry Pi Board model B+, Pi camera, Arduino, and an Ultrasonic sensor. The Pi camera and ultrasonic sensor are attached to the raspberry pi board to collect input images along with sensor data to stream these data to the server which in our case is the laptop. The (CNN) convolutional neural network running on the server will be used to enable lane detection to provide steering predictions that are left, right, forward based on the input image. The haar cascade classifier will be used to detect signals and stop sign and monocular vision algorithms to calculate distance from them. The ultrasonic sensor will be used for front collision avoidance by stopping the car at a certain distance before the obstacle ahead. The navigation commands such as right, left, forward, stop will be sent to the car through Arduino which is connected to the RC car's remote, this will make the car drive autonomously based on neural network predictions and some hard coded rules. Thus this model will enable autonomous driving by self-navigation via lane detection, stopping at detection of stop signs, red lights and moving on green signal and front collision avoidance in a cost-effective manner. Hardcoded rules, obstacle avoidance mechanisms, machine learning models, and smart object discrimination will help the system follow traffic rules and navigate the car using artificial intelligence.

Horticultural plants are widely cultivated in Indonesia, but failure because of the wrong cultivation technique is common. In this research, we focus on the broccoli plant because it is famous and watering is very important for this plant. To help the farmer, we try to develop the technology to control the water content and give the water to broccoli. In this case, we use object recognition to detect broccoli by using a webcam. The object detection method in the broccoli image is carried out using the Convolutional Neural Network (CNN) method with the You Only Look Once (YOLO) object recognition algorithm and the shape detection method as a detector for measuring floret area. This method is used to classify and measure floret area on broccoli plants via video or real-time webcam. From the results of the shape detection experiment, we succeed in classifying small florets which have a floret area with a range of (3479 -7787) pixels, while the area of medium florets has a range (of 14321 - 16822) pixels and large florets have a range (23316 - 36790) pixels. The average accuracy that we get from the implementation of the YOLO algorithm in this research reaches 99% accuracy.

Implementation of convolutional neural network and 8-bit reservoir computing in CMOS compatible VRRAM

Convolutional neural networks are promising tool for pattern recognition. Implementations of convolutional neural networks require a significant number of computations during training and processing. In this paper we propose to use Winograd method to reduce computational complexity in convolutional layers of convolutional neural networks. Theoretical analysis of the convolutional layer’s computational complexity of convolutional neural networks showed that the use of the Winograd method can reduce the computational complexity compared with direct method by 26,75%, 17,01%, with filter sizes of 3×3, 5×5, respectively. A promising area of further research is the hardware implementation of convolutional layers with Winograd calculations on modern computing devices, such as FPGA and ASIC.