Search Results (41)

YOLOv5 is currently one of the mainstream algorithms for object detection. In this paper, we propose the FRL-YOLO model specifically for river floating object detection. The algorithm integrates the Fasternet block into the C3 module, conducting convolutions only on a subset of input channels to reduce computational load. Simultaneously, it effectively captures spatial features, incorporates reparameterization techniques into the feature extraction network, and introduces the RepConv design to enhance model training efficiency. To further optimize network performance, the ACON-C activation function is employed. Finally, by employing a structured non-destructive pruning approach, redundant channels in the model are trimmed, significantly reducing the model’s volume. Experimental results indicate that the algorithm achieves an average precision value (mAP) of 79.3%, a 0.4% improvement compared to yolov5s. The detection speed on the NVIDIA GeForce RTX 4070 graphics card reaches 623.5 fps/s, a 22.8% increase over yolov5s. The improved model is compressed to a volume of 2 MB, representing only 14.7% of yolov5s. Full article

Smart cities are now embracing the new frontier of urban living, with advanced technology being used to enhance the quality of life for residents. Many of these cities have developed transportation systems that improve efficiency and sustainability, as well as quality. Integrating cutting-edge transportation technology and data-driven solutions improves safety, reduces environmental impact, optimizes traffic flow during peak hours, and reduces congestion. Intelligent transportation systems consist of many systems, one of which is traffic sign detection. This type of system utilizes many advanced techniques and technologies, such as machine learning and computer vision techniques. A variety of traffic signs, such as yield signs, stop signs, speed limits, and pedestrian crossings, are among those that the traffic sign detection system is trained to recognize and interpret. Ensuring accurate and robust traffic sign recognition is paramount for the safe deployment of self-driving cars in diverse and challenging environments like the Arab world. However, existing methods often face many challenges, such as variability in the appearance of signs, real-time processing, occlusions that can block signs, low-quality images, and others. This paper introduces an advanced Lightweight and Efficient Convolutional Neural Network (LE-CNN) architecture specifically designed for accurate and real-time Arabic traffic sign classification. The proposed LE-CNN architecture leverages the efficacy of depth-wise separable convolutions and channel pruning to achieve significant performance improvements in both speed and accuracy compared to existing models. An extensive evaluation of the LE-CNN on the Arabic traffic sign dataset that was carried out demonstrates an impressive accuracy of 96.5% while maintaining superior performance with a remarkably low inference time of 1.65 s, crucial for real-time applications in self-driving cars. It achieves high accuracy with low false positive and false negative rates, demonstrating its potential for real-world applications like autonomous driving and advanced driver-assistance systems. Full article

The rapid advancement of intelligent assisted driving technology has significantly enhanced transportation convenience in society and contributed to the mitigation of traffic safety hazards. Addressing the potential for drivers to experience abnormal physical conditions during the driving process, an enhanced lightweight network model based on YOLOv5 for detecting abnormal facial expressions of drivers is proposed in this paper. Initially, the lightweighting of the YOLOv5 backbone network is achieved by integrating the FasterNet Block, a lightweight module from the FasterNet network, with the C3 module in the main network. This combination forms the C3-faster module. Subsequently, the original convolutional modules in the YOLOv5 model are replaced with the improved GSConvns module to reduce computational load. Building upon the GSConvns module, the VoV-GSCSP module is constructed to ensure the lightweighting of the neck network while maintaining detection accuracy. Finally, channel pruning and fine-tuning operations are applied to the entire model. Channel pruning involves removing channels with minimal impact on output results, further reducing the model’s computational load, parameters, and size. The fine-tuning operation compensates for any potential loss in detection accuracy. Experimental results demonstrate that the proposed model achieves a substantial reduction in both parameter count and computational load while maintaining a high detection accuracy of 84.5%. The improved model has a compact size of only 4.6 MB, making it more conducive to the efficient operation of onboard computers. Full article

The realm of medical imaging is a critical frontier in precision diagnostics, where the clarity of the image is paramount. Despite advancements in imaging technology, noise remains a pervasive challenge that can obscure crucial details and impede accurate diagnoses. Addressing this, we introduce a novel teacher–student network model that leverages the potency of our bespoke NoiseContextNet Block to discern and mitigate noise with unprecedented precision. This innovation is coupled with an iterative pruning technique aimed at refining the model for heightened computational efficiency without compromising the fidelity of denoising. We substantiate the superiority and effectiveness of our approach through a comprehensive suite of experiments, showcasing significant qualitative enhancements across a multitude of medical imaging modalities. The visual results from a vast array of tests firmly establish our method’s dominance in producing clearer, more reliable images for diagnostic purposes, thereby setting a new benchmark in medical image denoising. Full article

In the production process of metal industrial products, the deficiencies and limitations of existing technologies and working conditions can have adverse effects on the quality of the final products, making surface defect detection particularly crucial. However, collecting a sufficient number of samples of defective products can be challenging. Therefore, treating surface defect detection as a semi-supervised problem is appropriate. In this paper, we propose a method based on a Transformer with pruned and merged multi-scale masked feature fusion. This method learns the semantic context from normal samples. We incorporate the Vision Transformer (ViT) into a generative adversarial network to jointly learn the generation in the high-dimensional image space and the inference in the latent space. We use an encoder–decoder neural network with long skip connections to capture information between shallow and deep layers. During training and testing, we design block masks of different scales to obtain rich semantic context information. Additionally, we introduce token merging (ToMe) into the ViT to improve the training speed of the model without affecting the training results. In this paper, we focus on the problems of rust, scratches, and other defects on the metal surface. We conduct various experiments on five metal industrial product datasets and the MVTec AD dataset to demonstrate the superiority of our method. Full article

Trunk borers are among the most destructive forest pests. The larvae of some species living and feeding in the trunk, relying solely on the tree’s appearance to judge infestation is challenging. Currently, one of the most effective methods to detect the larvae of some trunk-boring beetles is by analyzing the vibration signals generated by the larvae while they feed inside the tree trunk. However, this method faces a problem: the field environment is filled with various noises that get collected alongside the vibration signals, thus affecting the accuracy of pest detection. To address this issue, vibration signal enhancement is necessary. Moreover, deploying sophisticated technology in the wild is restricted due to limited hardware resources. In this study, a lightweight vibration signal enhancement was developed using EAB (Emerald Ash Borer) and SCM (Small Carpenter Moth) as insect example. Our model combines CRN (Convolutional Recurrent Network) and Transformer. We use a multi-head mechanism instead of RNN (Recurrent Neural Network) for intra-block processing and retain inter-block RNN. Furthermore, we utilize a dynamic pruning algorithm based on sparsity to further compress the model. As a result, our model achieves excellent enhancement with just 0.34M parameters. We significantly improve the accuracy rate by utilizing the vibration signals enhanced by our model for pest detection. Our results demonstrate that our method achieves superior enhancement performance using fewer computing and storage resources, facilitating more effective use of vibration signals for pest detection. Full article

Data stored in the Internet of Vehicles (IoV) face problems with ease of tampering, easy disclosure and single access control. Based on this problem, we propose an access control scheme for the IoV based on blockchain, trust values and weighted attribute-based encryption, called the Blockchain Trust and Weighted Attribute-Based Access Control Strategy (BTWACS). First, we utilize both local and global blockchains to jointly maintain the generation, verification and storage of blocks, achieving distributed data storage and ensuring that data cannot arbitrarily be tampered with. Local blockchain mainly uses Road Side Unit (RSU) technology to calculate trust values, while global blockchain is mainly responsible for data storage and access policy selection. Secondly, we design a blockchain-based trust evaluation scheme called Blockchain-Based Trust Evaluation (BBTE). In this evaluation scheme, the trust value of the vehicle node is based on four factors: initial trust, historical experience trust, recommendation trust and RSU observation trust. CRITIC is used to determine the optimal weights of four factors to obtain the trust value. Then, we use the Network Simulator version 3 (NS3) to verify the security and accuracy of BBTE, improving the recognition accuracy and detection rate of malicious vehicle nodes. Finally, by mining the association relationships between attribute permissions among various roles, we construct a hierarchical access control strategy based on weight and trust, and further optimize the access strategy through pruning techniques. The experiment results indicate that this scheme can effectively respond to gray hole attacks, defamation attacks and collusion attacks from other vehicle nodes. This method can effectively reduce the computing and transmission costs of vehicles and meet the access requirements of multiple entities and roles in the IoV. Full article

Convolutional neural networks (CNNs) play a crucial role in many EdgeAI and TinyML applications, but their implementation usually requires external memory, which degrades the feasibility of such resource-hungry environments. To solve this problem, this paper proposes memory-reduction methods at the algorithm and architecture level, implementing a reasonable-performance CNN with the on-chip memory of a practical device. At the algorithm level, accelerator-aware pruning is adopted to reduce the weight memory amount. For activation memory reduction, a stream-based line-buffer architecture is proposed. In the proposed architecture, each layer is implemented by a dedicated block, and the layer blocks operate in a pipelined way. Each block has a line buffer to store a few rows of input data instead of a frame buffer to store the whole feature map, reducing intermediate data-storage size. The experimental results show that the object-detection CNNs of MobileNetV1/V2 and an SSDLite variant, widely used in TinyML applications, can be implemented even on a low-end FPGA without external memory. Full article

In the domain of video recognition, video transformers have demonstrated remarkable performance, albeit at significant computational cost. This paper introduces TSNet, an innovative approach for dynamically selecting informative tokens from given video samples. The proposed method involves a lightweight prediction module that assigns importance scores to each token in the video. Tokens with top scores are then utilized for self-attention computation. We apply the Gumbel-softmax technique to sample from the output of the prediction module, enabling end-to-end optimization of the prediction module. We aim to extend our method on hierarchical vision transformers rather than single-scale vision transformers. We use a simple linear module to project the pruned tokens, and the projected result is then concatenated with the output of the self-attention network to maintain the same number of tokens while capturing interactions with the selected tokens. Since feedforward networks (FFNs) contribute significant computation, we also propose linear projection for the pruned tokens to accelerate the model, and the existing FFN layer progresses the selected tokens. Finally, in order to ensure that the structure of the output remains unchanged, the two groups of tokens are reassembled based on their spatial positions in the original feature map. The experiments conducted primarily focus on the Kinetics-400 dataset using UniFormer, a hierarchical video transformer backbone that incorporates convolution in its self-attention block. Our model demonstrates comparable results to the original model while reducing computation by over 13%. Notably, by hierarchically pruning 70% of input tokens, our approach significantly decreases 55.5% of the FLOPs, while the decline in accuracy is confined to 2%. Additional testing of wide applicability and adaptability with other transformers such as the Video Swin Transformer was also performed and indicated its progressive potentials in video recognition benchmarks. By implementing our token sparsification framework, video vision transformers can achieve a remarkable balance between enhanced computational speed and a slight reduction in accuracy. Full article

The influence of some seemingly anomalous samples on modeling is often ignored in the quantitative prediction of soil composition modeling with hyperspectral data. Soil spectral transformation based on wavelet packet technology only performs pruning and threshold filtering based on experience. The feature bands selected by the Pearson correlation coefficient method often have high redundancy. To solve these problems, this paper carried out a study of the prediction of soil total iron composition based on a new method. First, regarding the problem of abnormal samples, the Monte Carlo method based on particle swarm optimization (PSO) is used to screen abnormal samples. Second, feature representation based on Shannon entropy is adopted for wavelet packet processing. The amount of information held by the wavelet packet node is used to decide whether to cut the node. Third, the feature bands selected based on the correlation coefficient and the competitive adaptive reweighted sampling (CARS) algorithm using the least squares support vector regression (LSSVR) are applied to the soil spectra before and after wavelet packet processing. Finally, the Fe content was calculated based on a 1D convolutional neural network (1D-CNN). The results show that: (1) The Monte Carlo method based on particle swarm optimization and modeling multiple times was able to handle the abnormal samples. (2) Based on the Shannon entropy wavelet packet transformation, simple operations could simultaneously preserve the spectral information while removing high-frequency noise from the spectrum, effectively improving the correlation between soil spectra and content. (3) The 1D-CNN with added residual blocks could also achieve better results in soil hyperspectral modeling with few samples. Full article

A startling shift in waste composition has been brought on by a dramatic change in lifestyle, the quick expansion of consumerism brought on by fierce competition among producers of consumer goods, and revolutionary advances in the packaging sector. The overflow or overspill of garbage from the bins causes poison to the soil, and the total obliteration of waste generated in the area or city is unknown. It is challenging to pinpoint with accuracy the specific sort of garbage waste; predictive image classification is lagging, and the existing approach takes longer to identify the specific garbage. To overcome this problem, image classification is carried out using a modified ResNeXt model. By adding a new block known as the “horizontal and vertical block,” the proposed ResNeXt architecture expands on the ResNet architecture. Each parallel branch of the block has its own unique collection of convolutional layers. Before moving on to the next layer, these branches are concatenated together. The block’s main goal is to expand the network’s capacity without considerably raising the number of parameters. ResNeXt is able to capture a wider variety of features in the input image by using parallel branches with various filter sizes, which improves performance on image classification. Some extra dense and dropout layers have been added to the standard ResNeXt model to improve performance. In order to increase the effectiveness of the network connections and decrease the total size of the model, the model is pruned to make it smaller. The overall architecture is trained and tested using garbage images. The convolution neural Network is connected with a modified ResNeXt that is trained using images of metal, trash, and biodegradable, and ResNet 50 is trained using images of non-biodegradable, glass, and hazardous images in a parallel way. An input image is fed to the architecture, and the image classification is achieved simultaneously to identify the exact garbage within a short time with an accuracy of 98%. The achieved results of the suggested method are demonstrated to be superior to those of the deep learning models already in use when compared to a variety of existing deep learning models. The proposed model is implemented into the hardware by designing a three-component smart bin system. It has three separate bins; it collects biodegradable, non-biodegradable, and hazardous waste separately. The smart bin has an ultrasonic sensor to detect the level of the bin, a poisonous gas sensor, a stepper motor to open the lid of the bin, a solar panel for battery storage, a Raspberry Pi camera, and a Raspberry Pi board. The levels of the bin are maintained in a centralized system for future analysis processes. The architecture used in the proposed smart bin properly disposes of the mixed garbage waste in an eco-friendly manner and recovers as much wealth as possible. It also reduces manpower, saves time, ensures proper collection of garbage from the bins, and helps attain a clean environment. The model boosts performance to predict waste generation and classify it with an increased 98.9% accuracy, which is more than the existing system. Full article

Transformer models are being increasingly used in end-to-end speech recognition systems for their performance. However, their substantial size poses challenges for deploying them in real-world applications. These models heavily rely on attention and feedforward layers, with the latter containing a vast number of parameters that significantly contribute to the model’s memory footprint. Consequently, it becomes pertinent to consider pruning these layers to reduce the model’s size. In this article, our primary focus is on the feedforward layers. We conduct a comprehensive analysis of their parameter count and distribution. Specifically, we examine the weight distribution within each layer and observe how the weight values progress across the transformer model’s blocks. Our findings demonstrate a correlation between the depth of the feedforward layers and the magnitude of their weights. Consequently, layers with higher weight values require less pruning. Building upon this insight, we propose a novel pruning algorithm based on variable rates. This approach sets the pruning rate according to the significance and location of each feedforward layer within the network. To evaluate our new pruning method, we conduct experiments on various datasets. The results reveal its superiority over conventional pruning techniques, such as local pruning and global pruning. Full article

Maintaining the plant architecture of Psidium guajava L. (guava tree) is essential for enhancing capture and distribution in the plant, directly affecting the fruit quality. The lifespan of the harvest period can be extended by proper pruning. Both timeliness and proper pruning play crucial roles in achieving high-quality fruit production and in maintaining a consistent fruit size while stimulating ascorbic acid levels, sugar content, total soluble solids (TSS), and titratable acidity. From this perspective, this study aimed to characterize the influence of different intensities of fruit pruning and thinning on guava trees grown under a seasonal tropical climate in two growing seasons in Currais, Piauí, Brazil. The experiment was set up in a randomized block design with a 3 × 3 × 2 factorial arrangement corresponding to short, medium, and long pruning intensities and 0%, 10%, and 20% thinning intensities during the two growth seasons, respectively. An analysis was performed to discriminate the treatment groups according to the physicochemical variables of the guava tree cv. Paluma and canonical discriminant analysis. There was significant variation in the SS, titratable acidity, ascorbic acid, and pH contents. Cluster analysis of all treatments allowed division into five different groups for the two pruning times. Canonical discriminant analysis showed that the first two canonical variables explained 91% of the total variance. The fruits of the second harvest exhibited a lower level of acidity, higher levels of soluble solids, and higher levels of ascorbic acid contents. In addition, these fruits also obtained better nutrient contents. Short pruning with up to 20% thinning, medium pruning with up to 10%, and long pruning without thinning favored better levels of macronutrients and micronutrients and, consequently, better fruit quality. Medium or long pruning with up to 20% thinning resulted in higher average fruit weights and nutrient contents (especially of Fe and Cu), lower acidity, and higher ascorbic acid contents. Thus, in general, the importance of production pruning in guava plants is evidenced and thinning of 20% is recommended to improve the fruit quality. Full article

In guava plants, production pruning can be performed twice a year, and the return of growth is dependent on the physiological responses that are altered by the different cultivation environments and adopted management. From this perspective, this study aimed to characterize the photosynthetic dynamics of guava plants influenced by different pruning and fruit thinning intensities during two growing seasons in the region of Currais, Piauí, Brazil. The plants were distributed in a randomized block design with a factorial arrangement (3 × 3 × 2) consisting of three pruning intensities (short, medium, and long) and three fruit thinning intensities (0, 10, and 20%) during two growing seasons. The data were subjected to a cluster analysis and canonical discriminant analysis to discriminate treatment groups based on the variables. Through a cluster analysis for the evaluated treatments, it was possible to split the two pruning seasons into five different groups clustered for the first pruning season and the second pruning season. The highest assimilation values were observed in the first pruning season and especially in plants that received short pruning with 0% fruit thinning, medium pruning with 10% and 20% fruit thinning, and long pruning with 10% fruit thinning. Through the graphic representation of the canonical discriminant analysis, the first two variables explained 93.40% of the total variance contained in the nine original variables. The highest means of ambient PAR, transpiration, leaf temperature, internal carbon, and ambient temperature were observed in the second pruning season and in plants that received short pruning with 10% and 20% fruit thinning, medium pruning with 0% and 20% fruit thinning, and long pruning with 0%, 10%, and 20% fruit thinning favors a higher photosynthetic accumulation in guava plants. We observed a multiplicity of responses; however, short pruning with 10% thinning should be considered for both seasons. Full article

This paper presents a method for simplifying and quantizing a deep neural network (DNN)-based object detector to embed it into a real-time edge device. For network simplification, this paper compares five methods for applying channel pruning to a residual block because special care must be taken regarding the number of channels when summing two feature maps. Based on the comparison in terms of detection performance, parameter number, computational complexity, and processing time, this paper discovers the most satisfying method on the edge device. For network quantization, this paper compares post-training quantization (PTQ) and quantization-aware training (QAT) using two datasets with different detection difficulties. This comparison shows that both approaches are recommended in the case of the easy-to-detect dataset, but QAT is preferable in the case of the difficult-to-detect dataset. Through experiments, this paper shows that the proposed method can effectively embed the DNN-based object detector into an edge device equipped with Qualcomm’s QCS605 System-on-Chip (SoC), while achieving a real-time operation with more than 10 frames per second. Full article