Search

Deinterleaving mixtures of radar pulse sequences is the first and the most vital step for modern electronic reconnaissance systems to intercept and analyze the intentions of non-cooperative radars. Currently, these systems are facing great challenges due to the emerging complexity of radar modulations. This paper proposes a novel method for deinterleaving mixtures of radar pulse sequences based on the time series characteristics of each source (component pulse sequences). Firstly, the mathematical representations are established to describe the structural characteristics of each source. Then, the deinterleaving problem is formulated as a minimization of a maximum-likelihood cost function that can be solved efficiently through a supervised neural machine translation (NMT) network, i.e. to translate each received pulse in the interleaved pulse sequence to the corresponding source label. A sequence-to-sequence NMT model is proposed to capture the structural relationships among the non-adjacent pulses originated from the same source in the mixtures and assign the corresponding label to each pulse. The proposed method does not require the exact knowledge of each component pulse sequence. The experimental results based on the time of arrival sequence of mixed pulse sequences show that the proposed method outperforms the state-of-the-art deinterleaving methods and achieves satisfactory performance under highly non-ideal situations with measuring noise and lost pulse conditions. The proposed method can be directly applied to other fields involving deinterleaving problems and multi-variate input conditions.

Recognition of multi-function radar (MFR) work mode in an input pulse sequence is a fundamental task to interpret the functions and behaviour of an MFR. There are three major challenges that must be addressed: (i) The received radar pulses stream may contain an unknown number of multiple work mode class segments. (ii) The intra-mode and inter-mode knowledge of a modern MFR may be too flexible and complicated to be represented and learned through traditional hand-crafted features and learning models. (iii) The variable duration of each enclosed work mode makes the identification of the transition boundaries of adjacent modes difficult. To address these challenges and implement automatic recognition of MFR work mode sequences at a pulse-level, this study develops a novel processing framework based on a time series representation of MFR work mode sequence and sequence-to-sequence (seq2seq) long short-term memory network. The proposed method can not only automatically recognise multiple complexes modulated work mode classes in a pulse sequence. Still, it can also accurately identify the transition boundaries between each class by labelling the class information for each pulse. The experimental results showed the extended capabilities and improved performance of the proposed method over the state-of-the-art work mode classification methods.

In an ever-increasingly complex electromagnetic environment, multiple low probability of intercept (LPI) radar emitters may transmit their own signals simultaneously on similar bands, resulting in overlapping receiving signals in both time and frequency domain. In this letter, a novel Multi-Instance Multi-Label learning framework based on Deep Convolutional Neural Network (MIML-DCNN) is proposed to automatically recognize the overlapping LPI radar signals,which is trained by single type of signals only. The framework handles signals in an end-to-end manner that is integrated with a well-designed instance generation module, a sophisticated MIML classifier, and an adaptive threshold calibration. Through comprehensive experiments on simulated overlapping signals with four different modulation types, we prove that the proposed framework identifies each individual signal type precisely in the presence of overlapping signals, and is also robust to variation of the signal-to-noise ratio (SNR) and power ratio conditions.

While biochar soil amendment has been widely proposed as a soil organic carbon (SOC) sequestration strategy to mitigate detrimental climate changes in global agriculture, the SOC sequestration was still not clearly understood for the different effects of fresh and aged biochar on SOC mineralization. In the present study of a two‐factorial experiment, topsoil samples from a rice paddy were laboratory‐incubated with and without fresh or aged biochar pyrolyzed of wheat residue and with and without crop residue‐derived dissolved organic matter (CRM) for monitoring soil organic matter decomposition under controlled conditions. The six treatments included soil with no biochar, with fresh biochar and with aged biochar treated with CRM, respectively. For fresh biochar treatment, the topsoil of a same rice paddy was amended with wheat biochar directly from a pyrolysis wheat straw, the soil with aged biochar was collected from the same soil 6 years following a single amendment of same biochar. Total CO2 emission from the soil was monitored over a 64 day time span of laboratory incubation, while microbial biomass carbon and phospholipid fatty acid (PLFA) were determined at the end of incubation period. Without CRM, total organic carbon mineralization was significantly decreased by 38.8% with aged biochar but increased by 28.9% with fresh biochar, compared to no biochar. With CRM, however, the significantly highest net carbon mineralization occurred in the soil without biochar compared to the biochar‐amended soil. Compared to aged biochar, fresh biochar addition significantly increased the total PLFA concentration by 20.3%–33.8% and altered the microbial community structure by increasing 17:1ω8c (Gram‐negative bacteria) and i17:0 (Gram‐positive bacteria) mole percentages and by decreasing the ratio of fungi/bacteria. Furthermore, biochar amendment significantly lowered the metabolic quotient of SOC decomposition, thereby becoming greater with aged biochar than with fresh biochar. The finding here suggests that biochar amendment could improve carbon utilization efficiency by soil microbial community and SOC sequestration potential in paddy soil can be enhanced by the presence of biochar in soil over the long run.

Detecting driver injury patterns is a typical classification problem. Crash data sets are highly skewed where fatalities and severe injuries are often less represented compared to other events. The severity prediction performance of the existing models is poor due to the highly imbalanced samples of different severity levels within a given dataset. This paper proposes a machine learning based analysis framework from a multi-class classification perspective for accurate recognition of the driver injury patterns. The proposed framework includes preprocessing, classification, evaluation and application of a given dataset. This framework is verified based on the three years single-vehicle ROR (run-off-road) crash records collected in Washington State from 2011 to 2013. At first, thirteen most important safety-related variables are recognized through random forests. Then, the four driver's injury severity levels viz., fatal/serious injury, evident injury, possible injury, and no injury are predicted by integrating the decomposed binary neural network models to achieve better performance. Finally, a sensitivity analysis is carried out to interpret variables' impacts on the decomposed injury severity levels. The study shows that lack of restraint, female drivers, truck usage, driver impairment, driver distraction, vehicle overturn (rollover), dawn/dusk, and overtaking are the leading factors contributing to the driver fatalities or severe injuries in a single-vehicle ROR crash. Most of the findings are consistent with the previous studies. The experimental results validate the effectiveness of the proposed framework which can be further applied for pattern recognition in traffic safety research.

Understanding the temporal inequality in precipitation is of great importance for water resource management, environmental risk management, and ecological conservation. This study investigated the spatial patterns and trends of the daily precipitation concentration over the Yarlung Tsangpo River Basin using the concentration index (CI) and the Lorentz asymmetric coefficient (LAC). A Mann–Kendall test and Hurst’s rescaled range analysis were used to detect the change in CI trends. The CI ranged from 0.58 to 0.65, suggesting that a quarter of the rainiest days contributed approximately 69–78% of the total precipitation. The LAC analysis indicated that the nonuniform distribution of precipitation was mainly attributed to a large proportion of days with light rainfall. Compared with that of the central region, the daily precipitation in the western and eastern regions was more irregular. At a seasonal scale, the dry season had a less homogeneous spatial distribution of CI compared to that of the wet season. Most areas exhibited no significant trends in CI from 1970 to 2017. A quarter of the stations presented a significant downward trend in CI, which were primarily found in the central and northern regions. In addition, the future trends of CI in most areas mostly agree with those of the current state; however, the majority of stations exhibited an uneven precipitation distribution in the dry season.

Facing the complex electromagnetic environment, the fast and precise recognition of the type of jamming singals plays an indispensable role for rader to achieve effective electonic counter-counermeasures (ECCM). The implementation of pull-off jamming can be considered as a gradually separation of the true and false targets in the tracking gate of the radar. Thus the pull-off jamming signals can be recognized through a Long Short Term Memory (LSTM) network based on automatic features extraction and sequence dependency learning. This paper considers the signal sequences in the tracking gate as the input of the exploited LSTM model. Owing to the dependencies between signal at each frames, our method is capable of recognizing pull-off jamming at the early stage of jamming. Experimental results show that the proposed method can recognize the pull-off jamming quickly and accurately and has excellent generalization performance. Therefore, ECCM for radar against the pull-off jamming became more effective.

The modern battlefield is getting more complicated due to the increasing number of different radiation sources as well as their fierce contention (interference) and confrontations (jamming) in the frequency spectrum. A radar, or a communication system usually has to struggle with multiple overlapped signals injected into its receiver to ensure desired system performance. Thus, the requirement for recognition of the modulation type of each constituent signal in a compound signal has emerged as a multiuser automatic modulation classification (mAMC) task in a signal processing field. This paper proposes a deep multi-label based mAMC framework (MLAMC) for compound signals which includes three serial steps, the time-frequency representation image (TFRI) extraction for signal preprocessing, multi-label convolutional neural network (MLCNN) construction for multi-label classification, and multi-decision thresholds optimization for output label decision. By applying the proposed MLAMC method on the compound radar jamming signals as a case study, the effectiveness and superiority of our proposed method are validated in four aspects of a smaller model size, better total performance, good extensibility for unseen signal combinations, and fine-grained analysis for recognition results.

Twenty-five climate indices based on daily maximum and minimum temperature and precipitation at 15 meteorological stations were examined to investigate changes in temperature and precipitation extremes over the Yarlung Tsangpo River Basin (1970&ndash, 2017). The trend-free prewhitening (TFPW) Mann&ndash, Kendall test and Pettitt&rsquo, s test were used to identify trends and abrupt changes in the time series, respectively. The results showed widespread significant changes in extreme temperature indices associated with warming, most of which experienced abrupt changes in the 1990s. Increases in daily minimum and maximum temperature were detected, and the magnitude of daily minimum temperature change was greater than that of the daily maximum temperature, revealing an obvious decrease in the diurnal temperature range. Warm days and nights became more frequent, whereas fewer cold days and nights occurred. The frequency of frost and icing days decreased, while summer days and growing season length increased. Moreover, cold spell length shortened, whereas warm spell length increased. Additionally, changes in the precipitation extreme indices exhibited much less spatial coherence than the temperature indices. Spatially, mixed patterns of stations with positive and negative trends were found, and few trends in the precipitation extreme indices at individual stations were statistically significant. Generally, precipitation extreme indices showed a tendency toward wetter conditions, and the contribution of extreme precipitation to total precipitation has increased. However, no significant regional trends and abrupt changes were detected in total precipitation or in the frequency and duration of precipitation extremes.

LFM is a typical non-stationary signal and had long been widely used in modern radar and communication system. A new algorithm based on STFT transformation is presented in order to attain fast and accurate estimation of LFM modulation parameters under low SNR. Long window length was employed in STFT to enhance LFM signal, and then shift frequency and accumulate energy based on STFT result to measure FM rate coarsely. Finally, appropriate short window length and search step were employed to search FM rate finely in order to estimate parameter accurately. The proposed method not only reduce the computation but also improve precision of estimating and it is easy to implement.