Publikasjoner

Screening chemicals in commerce in the Nordic countries using multimedia fate and bioaccumulation models. NILU PP

Krogseth, I.; Breivik, K.; Arnot, J.; Wania, F.

Screening chemicals for POP-like long range transport behavior

Breivik, Knut; McLachlan, Michael S.; Frank, Wania

Screening av miljøgifter

Rostkowski, Pawel Marian

Screening 2004 - uppföljningsprojekt. Analys av oktaklorstyren, flyktiga metylsiloxaner, vissa fenoler och endosulfan. IVL Rapport, B1745

Kaj, L.; Ekheden, Y.; Dusan, B.; Hansson, K.; Cousins, A.P.; Remberger, M.; Brorström-Lundén, E.; Schlabach, M.

Schools taking part in a research project investigating dioxins in fish. From pole to pole

Heimstad, E.S.; Grønstøl, G.; Hetland, K.T.; Alarcon, J.M.; Rylander, C.; Mariussen, E.

Schadstoff-Ferntransport in die Arktis.

Kallenborn, R.; Herzke, D.

Scenarios for EU-27 heavy metals and POPs emissions to air, water and soil until 2050. NILU PP

Sundseth, K.; Panasiuk, D.; Pacyna, J.M.; Pacyna, E.G.; Glodek, A.

Scenario, planning and information dissemination system for hazardous air emissions. NILU F

Endregard, G.

Scenario calculations of mercury exposure from fish and overview of species with high mercury concentrations. Opinion of the Panel on Contaminants of the Norwegian Scientific Committee for Food and Environment

Amlund, Heidi; Rakkestad, Kirsten Eline; Ruus, Anders; Starrfelt, Jostein; Beyer, Jonny; Brantsæter, Anne Lise; Bremer, Sara; Eriksen, Gunnar Sundstøl; Mariussen, Espen; Samdal, Ingunn Anita; Thomsen, Cathrine; Knutsen, Helle Katrine

Norwegian Scientific Committee for Food and Environment (VKM)

SCCS scientific opinion on Butylated hydroxytoluene (BHT) - SCCS/1636/21

Granum, Berit; Bernauer, Ulrike; Bodin, Laurent; Chaudhry, Qasim; Coenraads, Pieter Jan; Dusinska, Maria; Ezendam, Janine; Gaffet, Eric; Galli, Corrado Lodovico; Panteri, Eirini; Rogiers, Vera; Rousselle, Christophe; Stepnik, Maciej; Vanhaecke, Tamara; Wijnhoven, Susan; Koutsodimou, Aglaia; Uter, Wolfgang; von Goetz, Natalie

Elsevier

Scaling the measurements of the Poleno bioaerosolmonitor to those of the Hirst-type sampler

Lieberherr, Gian-Duri; Crouzy, Benoit; Marsteen, Leif; Bäcklund, Are; Ramfjord, Hallvard; Horender, Stefan; Vasilatou, Konstantina

Sb-PiPLU: A Novel Parametric Activation Function for Deep Learning

Mondal, Ayan; Shrivastava, Vimal K.; Chatterjee, Ayan; Ramachandra, Raghavendra

The choice of activation function—particularly non-linear ones—plays a vital role in enhancing the classification performance of deep neural networks. In recent years, a variety of non-linear activation functions have been proposed. However, many of these suffer from drawbacks that limit the effectiveness of deep learning models. Common issues include the dying neuron problem, bias shift, gradient explosion, and vanishing gradients. To address these challenges, we introduce a new activation function: Softsign-based Piecewise Parametric Linear Unit (Sb-PiPLU). This function offers improved non-linear approximation capabilities for neural networks. Its piecewise, parametric design allows for greater adaptability and flexibility, which in turn enhances overall model performance. We evaluated Sb-PiPLU through a series of image classification experiments across various Convolutional Neural Network (CNN) architectures. Additionally, we assessed its memory usage and computational cost, demonstrating that Sb-PiPLU is both stable and efficient in practical applications. Our experimental results show that Sb-PiPLU consistently outperforms conventional activation functions in both classification accuracy and computational efficiency. It achieved higher accuracy on multiple benchmark datasets, including CIFAR-10, CINIC-10, MWD, Brain Tumor, and SVHN, surpassing widely-used functions such as ReLU and Tanh. Due to its flexibility and robustness, Sb-PiPLU is particularly well-suited for complex image classification tasks.

IEEE (Institute of Electrical and Electronics Engineers)