Wheat (W) and accumulators (A) were planted in plots (arsenic amended soil and without arsenic) designed with ecotoxicological concern for arsenic safe-grains. For the study sixteen plots of ...2 × 2 × 0.5 m (l × b × h) size were prepared. Arsenic (As) in the form of sodium arsenate was applied at 50 mg/kg in plots. Out of these sixteen plots eight plots had arsenic amended soil and rest 8 without any arsenic (C). Accumulator's viz. Pteris vittata (PV), Phragmites australis (PA) and Vetiveria zizanioides (VZ) were planted along with wheat in combination (W + PV, W + PA and W + VZ) in twelve plots (6 AWAs plots and 6 AWC plots). In the rest 4 plots (2 WAs plots and 2 WC plots), only wheat was planted. The study was conducted for two cropping seasons, where accumulators were left in the plots between the cropping seasons except that before 2nd cropping accumulators were properly pruned and extra tillers were removed. The germination % of wheat in WAs in 1st and the 2nd cropping season was found to be 55 and 57%, while in AWAs and AWC plots it was between 86 and 92% (W + VZ, 56 and 73%). The physiological activity was found to be reduced in WAs plots compared to AWAs (except for vetiver combination) and AWC plots in both cropping seasons. The antioxidant activity was enhanced in WAs compared with AWAs. The arsenic concentration in grains of wheat was within the permissible limit set by WHO and GOI in AWAs plots while it exceeded the limit in W + VZ (in 1st cropping) and WAs in both cropings.
Display omitted
•The arsenic in grains of wheat planted with accumulators had reduced arsenic in both cropping.•Germination and yield of wheat with accumulator in arsenic plots was higher compared to wheat planted alone (WAs).•There was increased antioxidant activity of wheat planted in WAs plot.•Proper pruning of accumulator before 2nd cropping was done, reducing the crowding caused by extensive growth of accumulators.•The combination of Pteris and Phragmittes with wheat had reduced arsenic uptake compared to combination of Vetiver.
Field-programmable gate array (FPGA) has become an excellent hardware accelerator solution for convolutional neural networks (CNNs). Meanwhile, optimizing methods, such as model compression, have ...been proposed. As most CNN accelerators focus on dense neural networks, to solve the problem of difficult hardware deployment due to irregular networks, we propose a method for sparse neural networks in our work. The storage and coding format of sparse data obtained by the block pruning method is designed to make it friendly to implement on FPGA. Besides, we also propose an efficient and simple data flow by the planarization of the whole convolution calculation process. The experimental result demonstrates that our implementation can achieve clock frequency of 190 MHz, power consumption of 13.32 W and inferencing speed of 16.37 ms. Compared with some typical Mobilenet implementation schemes, our method has been proven to achieve a better balance between frequency, accuracy, power consumption, and speed.
O sistema de poda do mirtileiro (Vaccinium ashei Read) utilizado no país se fundamenta em estudos realizados em locais com condições edafoclimáticas distintas da nossa realidade. Assim, foram ...avaliadas diferentes intensidades de poda de frutificação em dois genótipos de mirtileiro, e seus efeitos na produção e na qualidade dos frutos. O experimento foi conduzido em pomar comercial, localizado em Pelotas-RS. O delineamento experimental foi o de blocos casualizados completos, em esquema fatorial (2x4), com quatro repetições. Plantas de sete anos de idade, do grupo Rabbiteye, cultivares 'Briteblue' e 'Woodard', foram submetidas às intensidades de poda leve, moderada, drástica e sem poda (testemunha) nos anos de 2010 e 2011, no período de repouso hibernal (primeira quinzena de agosto). Foram avaliadas a produção média por planta, sendo estimada a produtividade por área, peso fresco, diâmetro, teor de sólidos solúveis, pH e acidez titulável dos frutos. De acordo com os resultados, a intensidade de poda tem efeito sobre a antecipação da colheita. Com a decorrência de uma maior intensidade de poda, houve uma tendência de aumento do tamanho dos frutos. Para mirtileiros Briteblue, há decréscimo de produtividade, conforme se aumenta a intensidade de poda. Mirtileiros Briteblue são mais produtivos e apresentam maior matéria fresca de fruto do que Woodard.
Prototype-Based Personalized Pruning Kim, Jangho; Chang, Simyung; Yun, Sungrack ...
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),
2021-June-6
Conference Proceeding
Open access
Nowadays, as edge devices such as smartphones become prevalent, there are increasing demands for personalized services. However, traditional personalization methods are not suitable for edge devices ...because retraining or finetuning is needed with limited personal data. Also, a full model might be too heavy for edge devices with limited resources. Unfortunately, model compression methods which can handle the model complexity issue also require the retraining phase. These multiple training phases generally need huge computational cost during on-device learning which can be a burden to edge devices. In this work, we propose a dynamic personalization method called prototype-based personalized pruning (PPP). PPP considers both ends of personalization and model efficiency. After training a network, PPP can easily prune the network with a prototype representing the characteristics of personal data and it performs well without retraining or finetuning. We verify the usefulness of PPP on a couple of tasks in computer vision and Keyword spotting.
 El objetivo del presente trabajo fue evaluar el efecto de la poda a intervalos de 3 y 6 meses sobre el rendimiento de forraje, la relación hoja:tallo y la densidad de raÃces finas en un banco de ...forraje de especies arbóreas. Se utilizaron 24 parcelas de 10 x 10 m de Leucaena leucocephala (Lam.) de Wit (8 parcelas), Guazuma ulmifolia Lam. (8 parcelas) y la asociación de ambas especies (8 parcelas). La poda a 3 meses incrementó hasta 3 veces el rendimiento de forraje acumulado (P
Numerous reports indicate that learning and memory of conditioned responses are accompanied by genesis of dendritic spines in the hippocampus, although there is a conspicuous lack of information ...regarding spine modifications after behavioral extinction. There is ample evidence that treatments that typically produce amnesia become innocuous when animals are submitted to a procedure of enhanced training. We now report that extinction of inhibitory avoidance (IA), trained with relatively low foot-shock intensities, induces pruning of dendritic spines along the length of the apical dendrites of hippocampal CA1 neurons. When animals are trained with a relatively high foot-shock there is a high resistance to extinction, and pruning in the proximal and medial segments of the apical dendrite are seen, while spine count in the distal dendrite remains normal. These results indicate that pruning is involved in behavioral extinction, while maintenance of spines is a probable mechanism that mediates the protecting effect against amnesic treatments produced by enhanced training.
Extreme Learning Machine (ELM) is a recently proposed machine learning method with successful applications in many domains. The key strengths of ELM are its simple formulation and the reduced number ...of hyper-parameters. Among these hyper-parameters, the number of hidden nodes has significant impact on ELM performance since too few/many hidden nodes may lead to underfitting/overfitting. In this work, we propose a pruning strategy for ELM using the Successive Projections Algorithm (SPA) as an approach to automatically find the number of hidden nodes. SPA was originally proposed for variable selection. In this work, it was adapted in order to be used to prune ELMs. The proposed method was compared to the Optimally Pruned Extreme Learning Machine algorithm (OP-ELM), which is considered as a state of the art method. Real world datasets were used to assess the performance of the proposed method for regression and classification problems. The application of the proposed model resulted in much simpler models with similar performance compared to the OP-ELM. For some classification instances, the performance of the proposed method outperformed the OP-ELM method.
We propose a sender-driven system for adaptive streaming from multiple servers to a single receiver over separate network paths. The servers employ information in receiver feedbacks to estimate the ...available bandwidth on the paths and then compute appropriate transmission schedules for streaming media packets to the receiver based on the bandwidth estimates. An optimization framework is proposed that enables the senders to compute their transmission schedules in a distributed way, and yet to dynamically coordinate them over time such that the resulting video quality at the receiver is maximized. To reduce the computational complexity of the optimization framework an alternative technique based on packet classification is proposed. The substantial reduction in online complexity due to the resulting packet partitioning makes the technique suitable for practical implementations of adaptive and efficient distributed streaming systems. Simulations with Internet network traces demonstrate that the proposed solution adapts effectively to bandwidth variations and packet loss. They show that the proposed streaming framework provides superior performance over a conventional distortion-agnostic scheme that performs proportional packet scheduling on the network paths according to their respective bandwidth values.
Avaliou-se o efeito de épocas de poda verde em dois anos consecutivos visando obter a segunda safra de uva em um mesmo ciclo vegetativo na cv. Niágara Branca (Vitis labrusca L.), cultivada no sistema ...em espaldeira. O experimento foi realizado na Estação Experimental Agronômica da UFRGS, em Eldorado do Sul (RS), nas safras de 2003/2004 e 2004/2005. Os tratamentos constaram de três épocas de poda verde, realizadas imediatamente após a quarta folha acima do último cacho, e dois anos consecutivos de avaliação. Todas as plantas foram submetidas à superação de dormência mediante aplicação de cianamida hidrogenada a 2%. Analisou-se a duração dos estádios fenológicos, o período de maturação, a produção por planta, a massa fresca do cacho, o teor de sólidos solúveis totais e a acidez total titulável. Observou-se que a época de realização da poda verde não afetou a quantidade, nem a qualidade da uva produzida na primeira colheita, apenas atrasando-a em uma semana. A poda verde realizada no início de novembro possibilitou a segunda colheita de uva, realizada entre março e abril, sendo uma alternativa de ampliação do período de oferta do produto no mercado.