Speech emotion analysis using convolutional neural network (CNN) and gamma classifier-based error correcting output codes (ECOC).

Speech emotion analysis is one of the most basic requirements for the evolution of Artificial Intelligence (AI) in the field of human-machine interaction. Accurate emotion recognition in speech can be effective in applications such as online support, lie detection systems and customer feedback analysis. However, the existing techniques for this field have not yet met sufficient development. This paper presents a new method to improve the performance of emotion analysis in speech. The proposed method includes the following steps: pre-processing, feature description, feature extraction, and classification. The initial description of speech features in the proposed method is done by using the combination of spectro-temporal modulation (STM) and entropy features. Also, a Convolutional Neural Network (CNN) is utilized to reduce the dimensions of these features and extract the features of each signal. Finally, the combination of gamma classifier (GC) and Error-Correcting Output Codes (ECOC) is applied to classify features and extract emotions in speech. The performance of the proposed method has been evaluated using two datasets, Berlin and ShEMO. The results show that the proposed method can recognize speech emotions in the Berlin and ShEMO datasets with an average accuracy of 93.33 and 85.73%, respectively, which is at least 6.67% better than compared methods.

N, P, O-codoped biochar from phytoremediation residues: a promising cathode material for Li-S batteries.

Environment and energy are two key issues in today's society. In terms of environmental protection, the treatment of phytoremediation residues has become a key problem to be solved urgently, while for energy storage, it tends to utilize low-cost and high specific energy storage materials (i.e. porous carbon). In this study, the phytoremediation residues is applied to the storage materials with low-cost and high specific capacity. Firstly, the phosphorous acid assisted pyrolysis of oilseed rape stems from phytoremediation is effective in the removal of Zn, Cu, Cd and Cr from the derived biochar. Moreover, the derived biochar from phytoremediation residues shows abundant porous structure and polar groups (-O/-P/-N), and it can deliver 650 mAh g-1with 3.0 mg cm-2sulfur, and keeps 80% capacity after 200 cycles when employing it as a sulfur host for lithium-sulfur (Li-S) batteries. Hence, phosphorous acid assisted pyrolysis and application in Li-S battery is a promising approach for the disposal of phytoremediation residues, which is contributed to the environmental protection as well as energy storage.

Cobalt (0/II) incorporated N-doped porous carbon as effective heterogeneous peroxymonosulfate catalyst for quinclorac degradation.

A cobalt(0/II)-incorporated N-doped porous carbon (Co/NC) catalyst was prepared via one-step thermal decomposition of ethylene-diamine tetra-acetic acid and a Co salt. Fine Co nanoparticles composed of metallic and oxidized Co species were formed and well dispersed in the graphene-like film-type N-doped carbon support. The Co species played a dominant role in peroxymonosulfate (PMS) activation to generate sulfate and hydroxyl radicals. The N-doped porous carbon synergistically affected the catalytic performance by enhancing electronic transfer. The resulting Co/NC was a highly efficient heterogeneous catalyst for PMS activation and enabled considerably enhanced quinclorac (QNC) degradation. Typically, 93% QNC (50 mg L-1) removal was achieved with 0.08 g L-1 Co/NC and 20 mmol L-1 PMS. The QNC degradation kinetic data fitted a pseudo-first-order kinetic model well, with a correlation coefficient (R2) higher than 0.99. Investigation of the reaction mechanism suggested that hydroxyl (HO) and sulfate (SO4-) radicals were the predominant active species in the Co/NCPMS system and QNC degradation mainly involved dehydroxylation and substitution of OH for COOH. This Co/NC catalyst is promising for use in advanced oxidation processes for the removal of persistent organic pollutants.