FPGA-based implementation of classification techniques: A survey

Recently, a number of classification techniques have been introduced. However, processing large dataset in a reasonable time has become a major challenge. This made classification task more complex and expensive in calculation. Thus, the need for solutions to overcome these constraints such as field programmable gate arrays (FPGAs). In this paper, we give an overview of the various classification techniques. Then, we present the existing FPGA based implementation of these classification methods. After that, we investigate the confronted challenges and the optimizations strategies. Finally, we highlight the hardware accelerator architectures and tools for hardware design suggested to improve the FPGA implementation of classification methods.     

Residual attention-based tracking-by-detection network with attention-driven data augmentation

Tracking-by-detection (TBD) is a significant framework for visual object tracking. However, current trackers are usually updated online based on random sampling with a probability distribution. The performance of the learning-based TBD trackers is limited by the lack of discriminative features, especially when the background is full of semantic distractors. We propose an attention-driven data augmentation method, in which a residual attention mechanism is integrated into the TBD tracking network as supplementary references to identify discriminative image features. A mask generating network is used to simulate changes in target appearances to obtain positive samples, where attention information and image features are combined to identify discriminative features. In addition, we propose a method for mining hard negative samples, which searches for semantic distractors with the response of the attention module. The experiments on the OTB2015, UAV123, and LaSOT benchmarks show that this method achieves competitive performance in terms of accuracy and robustness.     

Vulnerable objects detection for autonomous driving: A review

Object detection performed by Autonomous Vehicles (AV)s is a crucial operation that comes ahead of various autonomous driving tasks, such as object tracking, trajectories estimation, and collision avoidance. Dynamic road elements (pedestrians, cyclists, vehicles) impose a greater challenge due to their continuously changing location and behaviour. This paper presents a comprehensive review of the state-of-the-art object detection technologies focusing on both the sensory systems and algorithms used. It begins with a brief introduction on the autonomous driving operations and challenges. Then, different sensory systems employed on existing AVs are elaborated while illustrating their advantages, limitations and applications. Also, sensory systems employed by different research are reviewed. Moreover, due to the significant role Deep Neural Networks (DNN)s are playing in object detection tasks, different DNN-based networks are also highlighted. Afterwards, previous research on dynamic objects detection performed by AVs are reviewed in tabular forms. Finally, a conclusion summarizes the outcomes of the review and suggests future work towards the development of vehicles with higher automation levels.     

Transmission line detection in aerial images: An instance segmentation approach based on multitask neural networks

Camera-based transmission line detection (TLD) is a fundamental and crucial task for automatically patrolling powerlines by aircraft. Motivated by instance segmentation, a TLD algorithm is proposed in this paper with a novel deep neural network, i.e., CableNet. The network structure is designed based on fully convolutional networks (FCNs) with two major improvements, considering the specific appearance characteristics of transmission lines. First, overlaying dilated convolutional layers and spatial convolutional layers are configured to better represent continuous long and thin cable shapes. Second, two branches of outputs are arranged to generate multidimensional feature maps for instance segmentation. Thus, cable pixels can be detected and assigned cable IDs simultaneously. Multiple experiments are conducted on aerial images, and the results show that the proposed algorithm obtains reliable detection performance and is superior to traditional TLD methods. Meanwhile, segmented pixels can be accurately identified as cable instances, contributing to line fitting for further applications.     

煤炭资源型城市转型模式研究：以徐州贾汪区为例

煤炭资源型城市为我国经济发展提供了重要的资源和能源支持,研究资源型城市转型的经验模式对调整区域经济结构、确保社会稳定和改善生态环境具有重要的实践意义。本文采用文献综述法和实证分析法,研究我国东部煤炭资源枯竭型城市转型所面临的共性难题,并以徐州贾汪区转型探索经历为例,总结城市转型的"徐州贾汪区模式",主要包括放大正向外部效应、长期坚持矿地融合、大力建设矿区社会生态系统恢复力三条路径。研究结果表明,煤炭城市转型发展的共性问题相互联系、相互影响,是一个系统性难题,必须引入系统性思维。我国东部矿区普遍人口密集,农业发达、沉陷积水是最主要的共性特征,煤炭开采产生的社会问题、经济问题、生态问题、环境问题基本相同,转型发展模式值得互鉴。     

The influence of mining factors on seismic activity during longwall mining of a coal seam

In this article an attempt to determine the influence of mining factors on the seismic activity during the longwall mining of the upper layer of coal seam no. 405/2 in one of the Polish hard coal mines in the Upper Silesian Coal Basin was conducted. Two longwall panels were mined in analogous geological conditions and based on the same mining system and technology. However, there was significant difference with regards to the mining factors, which was reflected in the observed seismic activity. Some tools used in mining seismology were applied to illustrate the aforementioned influence of mining factors, e.g. the frequency-energy distribution, the frequency-magnitude distribution, the 2 D distribution of released seismic energy, the relationship between released seismic energy and the volume of mined coal, the Benioff strain release, and the Gutenberg-Richter(GR) b coefficient distribution(b is the proportion between high and low energy tremors). Concerning the Benioff strain release, a new solution, based on the slope of a fitted line in a moving time window, is proposed.     

InSAR技术在矿区地表变形监测中的应用

以禹州市梁北矿为研究区，利用2018年11月—2020年6月间35景5 m×20 m分辨率Sentinel-1A数据，采用InSAR技术，利用SBAS（短基线集InSAR）雷达干涉测量方法对梁北矿进行地面沉降信息提取解译，并通过实地调查成果认为，采用InSAR技术适合在矿区开展地表变形监测。     

Metal chlorides-promoted ammonia absorption of deep eutectic solvent

Ammonia is considered as a promising hydrogen or energy carrier. Ammonia absorption or adsorption is an important aspect for both ammonia removal, storage and separation applications. To these ends, a wide range of solid and liquid sorbents have been investigated. Among these, the deep eutectic solvent (DES) is emerging as a promising class of ammonia absorbers. Herein, we report a novel type of DES, i.e., metal-containing DESs for ammonia absorption. Specifically, the NH₃ absorption capacity is enhanced by ca. 18.1–36.9% when a small amount of metal chlorides, such as MgCl₂, MnCl₂ etc., are added into a DES composed of resorcinol (Res) and ethylene glycol (EG). To our knowledge, the MgCl₂/Res/EG (0.1:1:2) DES outperforms most of the reported DESs. The excellent NH₃ absorption performances of metal–containing DESs have been attributed to the synergy of Lewis acid–base and hydrogen bonding interactions. Additionally, good reversibility and high NH₃/CO₂ selectivity are achieved over the MgCl₂/Res/EG (0.1:1:2) DES, which enables it to be a potential NH₃ absorber for further investigations.     

Convolutional Neural Network Auto Encoder Channel Estimation Algorithm in MIMO-OFDM System

Higher transmission rate is one of the technological features of prominently used wireless communication namely Multiple Input Multiple Output-Orthogonal Frequency Division Multiplexing (MIMO–OFDM). One among an effective solution for channel estimation in wireless communication system, specifically in different environments is Deep Learning (DL) method. This research greatly utilizes channel estimator on the basis of Convolutional Neural Network Auto Encoder (CNNAE) classifier for MIMO-OFDM systems. A CNNAE classifier is one among Deep Learning (DL) algorithm, in which video signal is fed as input by allotting significant learnable weights and biases in various aspects/objects for video signal and capable of differentiating from one another. Improved performances are achieved by using CNNAE based channel estimation, in which extension is done for channel selection as well as achieve enhanced performances numerically, when compared with conventional estimators in quite a lot of scenarios. Considering reduction in number of parameters involved and re-usability of weights, CNNAE based channel estimation is quite suitable and properly fits to the video signal. CNNAE classifier weights updation are done with minimized Signal to Noise Ratio (SNR), Bit Error Rate (BER) and Mean Square Error (MSE).     

Retinal microaneurysms detection using adversarial pre-training with unlabeled multimodal images

The detection of retinal microaneurysms is crucial for the early detection of important diseases such as diabetic retinopathy. However, the detection of these lesions in retinography, the most widely available retinal imaging modality, remains a very challenging task. This is mainly due to the tiny size and low contrast of the microaneurysms in the images. Consequently, the automated detection of microaneurysms usually relies on extensive ad-hoc processing. In this regard, although microaneurysms can be more easily detected using fluorescein angiography, this alternative imaging modality is invasive and not adequate for regular preventive screening.In this work, we propose a novel deep learning methodology that takes advantage of unlabeled multimodal image pairs for improving the detection of microaneurysms in retinography. In particular, we propose a novel adversarial multimodal pre-training consisting in the prediction of fluorescein angiography from retinography using generative adversarial networks. This pre-training allows learning about the retina and the microaneurysms without any manually annotated data. Additionally, we also propose to approach the microaneurysms detection as a heatmap regression, which allows an efficient detection and precise localization of multiple microaneurysms. To validate and analyze the proposed methodology, we perform an exhaustive experimentation on different public datasets. Additionally, we provide relevant comparisons against different state-of-the-art approaches. The results show a satisfactory performance of the proposal, achieving an Average Precision of 64.90%, 31.36%, and 33.55% in the E-Ophtha, ROC, and DDR public datasets. Overall, the proposed approach outperforms existing deep learning alternatives while providing a more straightforward detection method that can be effectively applied to raw unprocessed retinal images.