Implementation Of Convolutional Neural Network Research Articles

Emerging Technologies and Applications of AI Chips: Integrating Deep Learning Algorithms with Advanced Hardware Architectures

Due to the ongoing promotion of the latest technological revolution and industrial upgrading, as well as the widespread use of artificial intelligence and deep learning, the intelligent Internet of Things terminal has reached a more advanced stage of development. The combination of training data, model algorithms, and processing power is the basis for advancing artificial intelligence. The semiconductor business plays a crucial role in shaping the future of AI algorithms and the computing power industry. This study explores the progression of artificial intelligence, and essential technologies, and examines the categorization and structure of AI chips. The process of deep learning was then analyzed, demonstrating the application of AI in real life. Next, this study showcases distinct AI chip-related models, specifically designed for the automated implementation of Convolutional Neural Networks (CNNs) on Field-Programmable Gate Arrays (FPGAs). The study then proceeds to examine the unique procedure and the significance of the resulting data. The future of AI was examined in the domains of space exploration, healthcare, and autonomous driving, along with future forecasts.

Efficient Convolutional Neural Networks Utilizing Fine-Grained Fast Fourier Transforms

Convolutional Neural Networks (CNNs) are among the most prevalent deep learning techniques employed across various domains. The computational complexity of CNNs is largely attributed to the convolution operations. These operations are computationally demanding and significantly impact overall model performance. Traditional CNN implementations convert convolutions into matrix operations via the im2col (image to column) technique, facilitating parallelization through advanced BLAS libraries. This study identifies and investigates a significant yet intricate pattern of data redundancy within the matrix-based representation of convolutions, a pattern that, while complex, presents opportunities for optimization. Through meticulous analysis of the redundancy inherent in the im2col approach, this paper introduces a mathematically succinct matrix representation for convolution, leading to the development of an optimized FFT-based convolution with finer FFT granularity. Benchmarking demonstrates that our approach achieves an average speedup of 14 times and a maximum speedup of 17 times compared to the regular FFT convolution. Similarly, it outperforms the Im2col+GEMM approach from NVIDIA’s cuDNN library, achieving an average speedup of three times and a maximum speedup of five times. Our FineGrained FFT convolution approach, when integrated into Caffe, a widely used deep learning framework, leads to significant performance gains. Evaluations using synthetic CNNs designed for real-world applications show an average speedup of 1.67 times. Furthermore, a modified VGG network variant achieves a speedup of 1.25 times.

Forecasting carbon dioxide emissions in Chongming: a novel hybrid forecasting model coupling gray correlation analysis and deep learning method.

Predicting regional carbon dioxide (CO2) emissions is essential for advancing toward global carbon neutrality. This study introduces a novel CO2 emissions prediction model tailored to the unique environmental, economic, and energy consumption of Shanghai Chongming. Utilizing an innovative hybrid approach, the study first applies grey relational analysis to evaluate the influence of economic activity, natural conditions, and energy consumption on CO2 emissions. This is followed by the implementation of a dual-channel pooled convolutional neural network (DCNN) that captures both local and global features of the data, enhanced through feature stacking. Gated recurrent unit (GRU) network then assesses the temporal aspects of these features, culminating in precise CO2 emission predictions for the region. The results indicate: (1) The proposed hybrid model achieves accurate predictions based on accounting data, with high precision, low error, and good stability. (2) The study found an overall increase in Chongming's carbon emissions from 2000 to 2022, with the prediction results being generally consistent with existing research findings. (3) The proposed method, based on Chongming's CO2 emission predictions, addresses issues such as the scarcity of effective accounting data and inaccuracies in traditional calculation methods. The results can provide effective technical support for local government policies on carbon reduction and promote sustainable development.

Application of deep learning in summer climate prediction over northwestern China based on CWRF model

This study analyzes the performance of the Climate–Weather Research and Forecasting (CWRF) model in predicting the summer temperature and precipitation in northwestern China (NWC) for the 1991–2021 period. It also examines the improvements in prediction resulting from the implementation of convolutional neural network (CNN) and long short-term memory (LSTM) downscaling methods. The results indicate that the CWRF model demonstrates reasonable ability in capturing the characteristics of climatological temperature and precipitation in NWC. Both the climatological temperature and precipitation predictions consistently demonstrate a systematic underestimation, revealing evident biases in regions characterized by complex terrain. In terms of interannual variation, the temperature prediction outperforms the precipitation prediction, whereas there is no significant difference in the temperature predictions for lead Months 1–3. However, uncertainties increase as the lead time is extended in precipitation prediction. Therefore, the combination of dynamical and statistical downscaling is employed to the summer temperature and precipitation prediction over NWC. It is shown both the CNN and LSTM downscaling methods can improve the prediction ability of the CWRF model for summer climatological temperature and precipitation. The LSTM method significantly reduces the root mean square error (RMSE) of precipitation and temperature predictions, indicating an improvement in predicting the spatial structure. At the interannual scale, the CNN method is less dependent on the lead time of prediction than the LSTM method is, and the interannual correlation coefficient of precipitation and temperature is greater than 0.1 compared with that of the raw CWRF model. These results provide valuable insights into understanding the prediction capabilities of the CWRF model in NWC and highlight the necessity of applying downscaling methods to the CWRF model to increase its prediction ability.

Implementation of Scale-Invariant Feature Transform Convolutional Neural Network for Detecting Distracted Driver

Implementation of Scale-Invariant Feature Transform Convolutional Neural Network for Detecting Distracted Driver

Implementation of Convolutional Neural Networks (CNN) in An Emotion Detection System for Measuring Learning Concentration Levels

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

Leveraging convolutional neural networks for enhanced efficiency and safety in commercial applications

This essay describes the ways in which Convolutional Neural Networks (CNNs) can revolutionise the use of AI in many commercial applications, such as product quality inspection, automated monitoring and analysis of customer behaviours. These applications provide several important improvements in operational efficiency, especially for companies that used to perform human-based visual work. Moreover, through the ability of CNNs to process and provide real-time data, companies can analyse defects, predict equipment failures and understand customer preferences, which then can help them to make decisions and allocate resources effectively. Additionally, this essay discusses some difficulties in implementing CNNs, like data requirements and computing demands, as well as present some real-life case studies of the implementation of CNNs within different types of industries. Furthermore, the essay concludes that incorporating CNN with other new technologies such as Internet of Things (IoT) and edge computing can help businesses make progress in achieving their goals of having agile and responsive operations. The essay mentions several advantages in using CNNs, such as accuracy, cost minimisation and better customer experiences, but also some ethical concerns about privacy and data security.

Unveiling Anomalies in Surveillance Videos

Abstract: The implementation of Convolutional Neural Network (CNN) algorithm for the detection of anomalies like fire and potholes in images or videos. Leveraging deep learning technique, the model aims to accurately identify fire, potholes, etc. within various contexts. The CNN architecture is trained on a dataset comprising diverse images to enhance its ability to generalize. This proposed project not only addresses safety concerns by promoting helmet usage and proper maintenance of roads but also contributes to the broader field of computer vision and object detection. This implementation involves training the CNN on annotated datasets, fine-tuning the model for optimal performance, and integrating it into a practical application for efficient anomaly identification. With a focus on real-time detection, the system utilizes image processing techniques and a trained CNN model to analyze visual data from cameras or video feeds. The system's versatility allows integration into surveillance systems, industrial sites, or any environment where fire detection is crucial for safety. By automating the detection process, the project contributes to minimizing human error and ensuring consistent monitoring. The proposed solution holds the potential to significantly impact safety protocols, particularly in industries where protective headgear is paramount. Potholes pose a significant threat to both drivers and pedestrians, leading to accidents and infrastructure damage. The proposed solution leverages CNN's ability to effectively process visual data, making it well-suited for image recognition tasks. Our approach involves training the CNN on a diverse dataset of road images to enable it to accurately identify potholes. The model will learn distinctive features and patterns associated with potholes, allowing for robust detection under various environmental conditions. Real-time implementation on embedded systems or cameras along roadways will enable instantaneous identification and alerting.

Implementation of CNN of Mobile-based COVID-19 Chest X-Ray Images

The COVID-19 pandemic outbreak is the most significant event from 2019 until 2021. A medical examination of radiological images is carried out to check the condition of the patient's lungs. The limitations of this examination need alternative computer-assisted applications for patient CXR. This research aims to implement a back-end and front-end-based Convolutional Neural Network (CNN) model. Its advantage is that it can detect CXR images in real-time and non-real-time using multi-classification, namely normal, pneumonia, and COVID-19. The CNN model carries out the process of convolutional feature extraction and multi-layer perceptron classification at the back-end stage. In contrast, it uses an Android mobile-based application at the front-end stage. The research results show that the non-real-time condition has an accuracy of 98%, while the real-time is 95% lower. This research produces model and application performance that is flexible for user needs. The results can be recommended for developing applications for more comprehensive users.

Energy Complexity of Convolutional Neural Networks.

The energy efficiency of hardware implementations of convolutional neural networks (CNNs) is critical to their widespread deployment in low-power mobile devices. Recently, a number of methods have been proposed for providing energy-optimal mappings of CNNs onto diverse hardware accelerators. Their estimated energy consumption is related to specific implementation details and hardware parameters, which does not allow for machine-independent exploration of CNN energy measures. In this letter, we introduce a simplified theoretical energy complexity model for CNNs, based on only a two-level memory hierarchy that captures asymptotically all important sources of energy consumption for different CNN hardware implementations. In this model, we derive a simple energy lower bound and calculate the energy complexity of evaluating a CNN layer for two common data flows, providing corresponding upper bounds. According to statistical tests, the theoretical energy upper and lower bounds we present fit asymptotically very well with the real energy consumption of CNN implementations on the Simba and Eyeriss hardware platforms, estimated by the Timeloop/Accelergy program, which validates the proposed energy complexity model for CNNs.

Convolutional neural networks and Internet of Things for fault detection by aerial monitoring of photovoltaic solar plants

Aerial thermographic inspection is performed with thermal cameras embedded in unmanned aerial vehicles, being one of the most relevant monitoring techniques for photovoltaic panels. This technique allows the detection of thermal patterns associated with faults in the photovoltaic panels, although image analysis and fault detection require novel processing methodologies. The volume and variety of aerial thermal data together with the need for faster and more efficient analysis for early maintenance operations require efficient Internet of Things architectures to provide fast and effective diagnostics with easy access.This paper presents a new approach based on image analysis with two consecutive convolutional neural networks to detect hot spots in an Internet of Things platform and reduce the number of false positives. The architecture of the platform is designed to automatically process the received data through the implementation of different Convolutional Neural Networks. A real case study is proposed with thermograms from three photovoltaic solar plants with different sizes, shapes of panels and a wide temperature range. The results show an accuracy of 99 % for panel detection and 96 % for hot spot detection with a reduction of false positives compared to other studies, such as Support Vector Machine or different Artificial Neural Networks, demonstrating the robustness of the method.

Development of Face Recognition System Using Support Vector Machine Algorithm

This research paper describes a face recognition system constructed with the Support Vector Machine (SVM) method. The technique implements the Convolutional Neural Network (CNN) approach for extracting features, which improves the accuracy of recognising faces. The method confirms an efficient and accurate facial recognition procedure by utilising SVM's ability to detect complex patterns within retrieved characteristics. The article explores how the system is implemented and optimised performance, with a focus on obtaining performance in real time. The experimental findings demonstrate the practical application of the SVM-based facial recognition system, emphasising its numerous potential applications in security, the authentication process, as well as interaction between humans and computers. The implementation of CNN for extracting features provides refinement to the system, proving its flexibility to complex face characteristics and confirming its feasibility in actual applications. The results indicate that the suggested system is an effective facial recognition technique. Furthermore, the system is computationally efficient, taking just a few seconds to evaluate an individual face for extracting features and recognition. The system for identifying faces uses modern approaches to enhance both speed and precision, making it a potential option for a variety of applications. Its capacity to swiftly and correctly detect faces in real-time circumstances is a substantial development in facial identification technologies. The system's capability has been comprehensively evaluated, and it satisfies the essential criteria for practical implementation in real-world situations, making it an important addition to the continued development of secure and efficient face recognition systems.

Implementation of Convolutional Neural Network (CNN) Method for Fish Processed Cuisine Image Identification Application with Google Maps Features

The rapid advancement of science and technology encourages dynamic transformation in various sectors, especially in the field of information and communication technology (ICT), especially with the existence of Android-based smartphones. This advancement revolutionizes the way we access information, especially about various processed fish dishes in Indonesia. However, despite the plethora of culinary offerings, travelers often find it difficult to discover traditional dishes through social media platforms. To bridge this gap, a new app that utilizes artificial neural networks has been developed. The app allows users to photograph and upload images of processed fish dishes to recognize and provide detailed descriptions and recipes. In addition, integrating Google Maps makes it easy for users to find nearby places that serve these dishes. Testing the app with a dataset consisting of 1577 images of six types of processed fish dishes yielded promising results, with accuracy reaching 97.57% over 120 epochs. This innovation not only preserves cultural heritage but also enhances the culinary experience for locals and tourists.

Quantization-Based Optimization Algorithm for Hardware Implementation of Convolution Neural Networks

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.

Multilayer Neural Network Hardware Designs for Faster Convolutional Processing

The demand for efficient hardware implementations of convolutional neural networks (CNNs) has surged with the proliferation of deep learning applications in various domains such as computer vision, natural language processing, and autonomous systems. Convolutional layers, being the fundamental building blocks of CNNs, are computationally intensive, requiring optimized hardware architectures for real-time inference tasks. This paper presents novel hardware designs targeting faster convolutional processing within multilayer neural networks. We propose a multi-faceted approach that leverages parallelism, pipelining, and hardware acceleration techniques to enhance the efficiency of convolution operations. Our design optimally exploits the inherent data-level and model-level parallelism present in CNNs to achieve high throughput while minimizing latency.

Implementation of Convolutional Neural Network (CNN) Algorithm for Autonomous Robot

In Indonesia, the development of autonomous robots has emerged intensively since the last coronavirus pandemic, especially the autonomous UV disinfection (A-UV) robot. A-UV disinfection robot has the purpose of purifying germs and pathogens in critical areas, such as the hospital. As the minuscule creature can be difficult to control, the anticipation of letting no human have contact with it is one of the other purposes of the A-UV disinfection robot. However, the systematic development of the autonomous robot is the priority, where the robot can offer a collision-free obstacle, and target-lock when arriving at the designated location. In this study, two main contributions are proposed to develop the autonomous robot: 1) Convolutional Neural Network (CNN) algorithm to learn the potential surrounding the lock area from the dataset to ensure collision-free during the operation. 2) Original design to ensure the compactness of the autonomous robot with almost omnidirectional UV light. We design the surrounding area with “BOX” as the obstacle and “SIGN STOP” as the target in our CNN dataset. The performance is validated to have 97% and 99% for training and validation performance and 0.3% for loss. The robot prototype was also developed and tested inside a workspace with a size of 2.1 x 3 m. The robot prototype successfully performed the required tasks.

A SWOT ANALYSIS OF BREAST CANCER DIAGNOSIS IN DIGITAL MAMMOGRAPHY USING DEEP CONVOLUTIONAL NEURAL NETWORK

Breast cancer is a significant global health challenge that affects both men and women, leading to cause-specific deaths. Current early screening interventions, such as digital mammography (DM), are susceptible to high false-positives and false-negatives. This paper explores the potential of convolutional neural network (CNN), a form of artificial intelligence (AI), to support screening mammography with the aim to enhance accuracy in lesion detection, image classification and diagnostic prediction. Because the adoption of AI in cancer diagnosis is still in its infancy, the objective of this paper is to provide insight into the benefits and limitations of deep learning-based approaches to detect and diagnose cancer. An analysis of the implementation of CNN in AI-screening mammography models was conducted, using the SWOT strategic analysis tool. Internal strengths that improve the predictive accuracy of CNN include transfer learning and data augmentation, whereas the internal weaknesses include a lack of data standardisation and reproducibility. External opportunities consist of increased sensitivity in differentiating between microcalcifications and non-tumorous structures, improved predictive diagnosis and reduced workload. Nevertheless, integration within clinical settings must also consider the external threats of breaching patient privacy, automation biases and the role of clinical judgement.

FPGA acceleration of convolutional neural networks: Current applications and future prospects

In the contemporary era of big data, the utilization of deep learning technology has become widespread in the extraction of valuable analytical insights from the data under consideration. This technology finds extensive applications in various domains, including image information recognition, speech processing, and text language analysis. When it comes to accelerating convolutional neural networks (CNNs), the utilization of Field-Programmable Gate Arrays (FPGAs) offers distinct advantages over other hardware accelerators. Nevertheless, it is important to acknowledge that FPGA-based acceleration also comes with its own structural limitations. This article places its focus on two main aspects: firstly, it delves into the present-day application landscape and the latest developmental trajectories of convolutional neural networks. Secondly, it elucidates the inherent characteristics of FPGA implementations of CNNs. Furthermore, the article conducts a comprehensive examination of the pertinent constraints associated with FPGA-accelerated deep learning algorithms. The discussion extends beyond the present moment and ventures into the future, offering insights into the potential advancements in the field of deep learning. Importantly, it also brings into focus the prospective avenues for further research regarding the application of FPGAs in the domain of convolutional neural networks.

Implementation of FFT-Based Convolutional Neural Networks on Medical Imagery for Studying Performance Boost

This study focuses on the implementation of CNNs based on the Fast Fourier Transform (FFT) in medical images to study the performance boost compared to traditional neural networks. Using a Kaggle dataset of brain tumour imagery, we examine the effectiveness of FFT-based CNNs for the detection and classification of brain tumours. By leveraging the advantages of FFT, we aim to improve the efficiency and accuracy of CNNs in analyzing medical images. Our results demonstrate that FFT-based CNNs outperform traditional CNNs in terms of accuracy and computational efficiency. This performance boost is attributed to the inherent properties of FFT, which enable faster convolution operations and reduced complexity. In order to ensure a fair comparison between traditional CNNs and Fourier Transform-based convolutions, the forward pass for both methods was implemented from scratch using NumPy and SciPy libraries. By doing so, any optimization benefits gained by either technique through specific libraries or computation platforms are eliminated. This approach allows for a more accurate evaluation of the relative performance of each method in terms of inference time and accuracy, while also providing insights into potential areas for improvement and optimization.

Implementation of near-infrared spectroscopy and convolutional neural networks for predicting particle size distribution in fluidized bed granulation

Monitoring the particle size distribution (PSD) is crucial for controlling product quality during fluidized bed granulation. This paper proposed a rapid analytical method that quantifies the D10, D50, and D90 values using a Convolutional Block Attention Module-Convolutional Neural Network (CBAM-CNN) framework tailored for deep learning with near-infrared (NIR) spectroscopy. This innovative framework, which fuses CBAM with CNN, excels at extracting intricate features while prioritizing crucial ones, thereby facilitating the creation of a robust multi-output regression model. To expand the training dataset, we incorporated the C-Mixup algorithm, ensuring that the deep learning model was trained comprehensively. Additionally, the Bayesian optimization algorithm was introduced to optimize the hyperparameters, improving the prediction performance of the deep learning model. Compared with the commonly used Partial Least Squares (PLS), Support Vector Machine (SVM), and Artificial Neural Network (ANN) models, the CBAM-CNN model yielded higher prediction accuracy. Furthermore, the CBAM-CNN model avoided spectral preprocessing, preserved the spectral information to the maximum extent, and returned multiple predicted values at one time without degrading the prediction accuracy. Therefore, the CBAM-CNN model showed better prediction performance and modeling convenience for analyzing PSD values in fluidized bed granulation.