Search

PCB defect detection aims to identify the presence of gaps, open circuits, short circuits, and other defects in the PCB boards produced in the industry. Designing effective deep learning algorithms is crucial to finding a solution. Previously proposed PCB defect detection algorithms are limited in detecting tiny objects in high-density. Directly applying previous models to tackle PCB defect detection tasks will cause serious issues, such as missed detection and false detection. In this paper, we present a detection algorithm for tiny PCB defect targets in high-density regions to solve the above-mentioned problems. We firstly propose a detection head to detect tiny objects. Then, we design a four-channel feature fusion mechanism to fuse four different scale features and add an attention mechanism to find the attention region in scenarios with dense objects. Finally, we achieved accurate detection of tiny targets in high-density areas. Experiments were performed on the publicly available PCB defect dataset from Peking University. Our mAP@.5:.95 achieves 48.6%, while mAP@0.5 exceeds 90%. Compared with YOLOX and YOLOv5, our improved model can better localize tiny objects in high-density scenes. The experimental results certify that our model can obtain higher performance in comparison with the baseline and the state of the art. [ABSTRACT FROM AUTHOR]

The use of command and control (C2) servers in cyberattacks has risen considerably, attackers frequently employ the domain generated algorithm (DGA) technique to conceal their C2 servers. Various machine learning models have been suggested for binary identification of domain names as either benign or DGA domain. The Existing techniques are inefficient and have real-time detection issues and are also very data hypersensitive, therefore, they can be circumvented by the attackers. The main problem this article addresses is how to automatically detect DGA in a way that does not rely solely on reverse engineering, not strongly affected by data size, and allows detection of this DGA in real time. This paper presents DTFS-DGA model that combine neural networks models with traditional machine learning models and maintains its performance even if the data size changes to detect DGA in real time. The model uses 15 linguistics and networks features with the features extracted by long short-term memory and convolutional neural network to classify domain names using random forest and support vector machines. The comprehensive experimental findings confirm the suggested model's accuracy. To be precise, the model achieve an average accuracy of 99.8 % for the classification. [ABSTRACT FROM AUTHOR]

Artificial intelligence speech recognition mostly judges the accuracy of grammar or sentence in the detection of pronunciation error, but has little research on pronunciation judgment, so it cannot effectively correct the pronunciation. This study analyzes the application of image target recognition in English learning task. Task-based approach emphasizes the process of English learning, not the result, the purposeful communication and meaning expression, encourages learners to open their mouths, and emphasizes that English language learning activities and their tasks are realistic in life. In addition, this paper introduces the DNN adaptive technique based on KL divergence regularization to adapt the acoustic model. Finally, this paper uses the experimental contrast method to compare and analyze the algorithm of this research with the traditional algorithm. The research shows that the recognition ability of the algorithm for confusing phonemes is improved than that of traditional algorithms, and this conclusion provides a powerful result for the introduction of error correction algorithms into education networks. By using the platform of autonomous learning center, students can improve their English level by completing the tasks chosen by teachers or by themselves and through training. [ABSTRACT FROM AUTHOR]

Detecting vehicle at night is critical to both assistant driving systems and autonomous driving systems. In this paper, we propose a deep network scheme assisted by light information with good generalization to detect vehicle at night. Our approach is divided into two branches, the object stream and the pixel stream. The object stream generates a batch of bounding boxes, and the pixel stream utilizes the vehicle light information to calibrate the bounding boxes of the object stream. In the object stream, we propose a new structure, Direction Attention Pooling (DAP), to improve the accuracy of the prior boxes. DAP leads into attention mechanism. The feature maps obtained from backbone network is divided into two branches. One branch obtains direction perception information through IRNN layer, and the other branch learns attention weights. The weights are multiplied with the direction perception features in an element-wise manner. In the pixel stream, we propose a corner localization algorithm based on Bayes to get more accurate corners with the vehicle light pixels. The locations of the corners are considered as a discrete random variable. When the mask of the object is known, solving the probability distribution of the corner of the object is the next step. The corners with the highest probability is the correct corner. On the nighttime vehicle detection datasets CHUK and SYSU, our method achieves the accuracy of 97.2% and 96.86%, which outperforms other state-of-the-art methods by at least 0.31% and 0.34%. [ABSTRACT FROM AUTHOR]

Protecting information from manipulation is important challenge in current days. Digital images are one of the most popular information representation. Images could be used in several fields such as military, social media, security purposes, intelligence fields, evidences in courts, and newspapers. Digital image forgeries mean adding unusual patterns to the original images that cause a heterogeneity manner in form of image properties. Copy move forgery is one of the hardest types of image forgeries to be detected. It is happened by duplicating part or section of the image then adding again in the image itself but in another location. Forgery detection algorithms are used in image security when the original content is not available. This paper illustrates a new approach for Copy Move Forgery Detection (CMFD) built basically on deep learning. The proposed model is depending on applying (Convolution Neural Network) CNN in addition to Convolutional Long Short-Term Memory (CovLSTM) networks. This method extracts image features by a sequence number of Convolutions (CNVs) layers, ConvLSTM layers, and pooling layers then matching features and detecting copy move forgery. This model had been applied to four aboveboard available databases: MICC-F220, MICC-F2000, MICC-F600, and SATs-130. Moreover, datasets have been combined to build new datasets for all purposes of generalization testing and coping with an over-fitting problem. In addition, the results of applying ConvLSTM model only have been added to show the differences in performance between using hybrid ConvLSTM and CNN compared with using CNN only. The proposed algorithm, when using number of epoch's equal 100, gives high accuracy reached to 100% for some datasets with lowest Testing Time (TT) time nearly 1 second for some datasets when compared with the different previous algorithms. [ABSTRACT FROM AUTHOR]

The recent successful methods of person re-identification (person Re-ID) involving deep learning have mostly adopted supervised learning algorithms, which require large amounts of manually labelled data to achieve good performance. However, there are two important unresolved problems, dataset annotation is an expensive and time-consuming process, and the performance of recognition model is seriously affected by visual change. In this paper, we primarily study an unsupervised method for learning visual invariant features using networks with temporal coherence for person Re-ID; this method exploits unlabelled data to learn expressions from video. In addition, we propose an unsupervised learning integration framework for pedestrian detection and person Re-ID for practical applications in natural scenarios. In order to prove the performance of the unsupervised person re-identification algorithm based on visual invariance features, the experimental results were verified on the iLIDS-VID, PRID2011 and MARS datasets, and a better performance of 57.5% (R-1) and 73.9% (R-5) was achieved on the iLIDS-VID and MARS datasets, respectively. The efficiency of the algorithm was validated by using BING + R-CNN as the pedestrian detector, and the person Re-ID system achieved a computation speed of 0.09s per frame on the PRW dataset. [ABSTRACT FROM AUTHOR]

Computing derivatives of tensor expressions, also known as tensor calculus, is a fundamental task in machine learning. A key concern is the efficiency of evaluating the expressions and their derivatives that hinges on the representation of these expressions. Recently, an algorithm for computing higher order derivatives of tensor expressions like Jacobians or Hessians has been introduced that is a few orders of magnitude faster than previous state-of-the-art approaches. Unfortunately, the approach is based on Ricci notation and hence cannot be incorporated into automatic differentiation frameworks from deep learning like TensorFlow, PyTorch, autograd, or JAX that use the simpler Einstein notation. This leaves two options, to either change the underlying tensor representation in these frameworks or to develop a new, provably correct algorithm based on Einstein notation. Obviously, the first option is impractical. Hence, we pursue the second option. Here, we show that using Ricci notation is not necessary for an efficient tensor calculus and develop an equally efficient method for the simpler Einstein notation. It turns out that turning to Einstein notation enables further improvements that lead to even better efficiency. The methods that are described in this paper for computing derivatives of matrix and tensor expressions have been implemented in the online tool . [ABSTRACT FROM AUTHOR]

Topic modeling for short texts is a challenging and interesting problem in the machine learning and knowledge discovery domains. Nowadays, millions of documents published on the internet from various sources. Internet websites are full of various topics and information, but there is a lot of similarity between topics, contents, and total quality of sources, which causes data repetition and gives the user the same information. Another issue is data sparsity and ambiguity because the length of the short text is limited, which causes unsatisfactory results and give irrelevant results to end-users. All these mentioned issues in short texts made an interesting topic for researchers to use machine learning and knowledge discovery techniques to discover underlying topics from a massive amount of data. In this paper, we propose a combination of deep reinforcement learning (RL) and semantics-assisted non-negative matrix factorization model to extract meaningful and underlying topics from short document contents. The main objective of this work is to reduce the problem of repetitive information and data sparsity in short texts to help the users to get meaningful and relevant contents. Furthermore, our propose model reviews an issue of the Seq2Seq approach based on the reinforcement learning perspective and provides a combination of reinforcement learning and SeaNMF formulation using the block coordinate descent algorithm. Moreover, we compare different real-world datasets by using numerical calculation and present a couple of state-of-art models to get better performance on short text document topic modeling. Based on experimental results and comparative analysis, our propose model outperforms the state of art techniques in terms of short document topic modeling. [ABSTRACT FROM AUTHOR]