| 1. |
- Ma, Tengfei, et al.
(författare)
-
Distinguishing Bipolar Depression from Major Depressive Disorder Using fNIRS and Deep Neural Network
- 2020
-
Ingår i: Progress In Electromagnetics Research. - : The Electromagnetics Academy. - 1070-4698 .- 1559-8985. ; 169, s. 73-86
-
Tidskriftsartikel (refereegranskat)abstract
- A variety of psychological scales are utilized at present as the most important basis for clinical diagnosis of mood disorders. An experienced psychiatrist assesses and diagnoses mood disorders based on clinical symptoms and relevant assessment scores. This symptom based clinical criterion is limited by the psychiatrist's experience. In practice, it is difficult to distinguish the patients with bipolar disorder with depression episode (bipolar depression, BD) from those with major depressive disorder (MDD). The functional near-infrared spectroscopy (fNIRS) technology is commonly used to perceive the emotions of a human. It measures the hemodynamic parameters of the brain, which correlate with cerebral activation. Here, we propose a machine learning classification method based on deep neural network for the brain activations of mood disorders. Large time scale connectivity is determined using an attention long short term memory neural network and short-time feature information are considered using the InceptionTime neural network in this method. Our combined method is referred to as AttentionLSTM-InceptionTime (ALSTMIT). We collected fNIRS data of 36 MDD patients and 48 BD patients who were in the depressed state. All the patients were monitored by fNIRS during conducting the verbal fluency task (VFT). We trained the model with the ALSTMIT network. The algorithm can distinguish the two types of patients effectively: the average accuracy of classification on the test set can reach 96.2% stably. The classification can provide an objective diagnosis tool for clinicians, and this algorithm may be critical for the early detection and precise treatment for the patients with mood disorders.
|
|
| 2. |
- Zhang, Xing, et al.
(författare)
-
Diagnosing NB plasmas on the EAST tokamak with new time-of-flight neutron spectrometer
- 2014
-
Ingår i: Nuclear Fusion. - : IOP Publishing. - 0029-5515 .- 1741-4326. ; 54:10, s. 104008-
-
Tidskriftsartikel (refereegranskat)abstract
- The new neutron spectrometer time-of-flight enhanced diagnostics (TOFED) for the EAST tokamak is presented and its characteristics are described in terms of simulation results, as well as the interface in the torus hall along with new neutral beam (NB) injectors. The use of TOFED for studies of the slowing down of NB-injected deuterons is illustrated. The implications of measuring the neutron emission on a long pulse machine are discussed together with the experimental challenges and diagnostic possibilities approaching those to be encountered in continuous operation.
|
|
| 3. |
- Jaramillo, Fernando, et al.
(författare)
-
Priorities and Interactions of Sustainable Development Goals (SDGs) with Focus on Wetlands
- 2019
-
Ingår i: Water. - : MDPI. - 2073-4441. ; 11:3
-
Tidskriftsartikel (refereegranskat)abstract
- Wetlands are often vital physical and social components of a country’s natural capital, as well as providers of ecosystem services to local and national communities. We performed a network analysis to prioritize Sustainable Development Goal (SDG) targets for sustainable development in iconic wetlands and wetlandscapes around the world. The analysis was based on the information and perceptions on 45 wetlandscapes worldwide by 49 wetland researchers of the Global Wetland Ecohydrological Network (GWEN). We identified three 2030 Agenda targets of high priority across the wetlandscapes needed to achieve sustainable development: Target 6.3—“Improve water quality”; 2.4—“Sustainable food production”; and 12.2—“Sustainable management of resources”. Moreover, we found specific feedback mechanisms and synergies between SDG targets in the context of wetlands. The most consistent reinforcing interactions were the influence of Target 12.2 on 8.4—“Efficient resource consumption”; and that of Target 6.3 on 12.2. The wetlandscapes could be differentiated in four bundles of distinctive priority SDG-targets: “Basic human needs”, “Sustainable tourism”, “Environmental impact in urban wetlands”, and “Improving and conserving environment”. In general, we find that the SDG groups, targets, and interactions stress that maintaining good water quality and a “wise use” of wetlandscapes are vital to attaining sustainable development within these sensitive ecosystems.
|
|
| 4. |
- Kristanl, Matej, et al.
(författare)
-
The Seventh Visual Object Tracking VOT2019 Challenge Results
- 2019
-
Ingår i: 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW). - : IEEE COMPUTER SOC. - 9781728150239 ; , s. 2206-2241
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking challenge VOT2019 is the seventh annual tracker benchmarking activity organized by the VOT initiative. Results of 81 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis as well as the standard VOT methodology for long-term tracking analysis. The VOT2019 challenge was composed of five challenges focusing on different tracking domains: (i) VOT-ST2019 challenge focused on short-term tracking in RGB, (ii) VOT-RT2019 challenge focused on "real-time" short-term tracking in RGB, (iii) VOT-LT2019 focused on long-term tracking namely coping with target disappearance and reappearance. Two new challenges have been introduced: (iv) VOT-RGBT2019 challenge focused on short-term tracking in RGB and thermal imagery and (v) VOT-RGBD2019 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2019, VOT-RT2019 and VOT-LT2019 datasets were refreshed while new datasets were introduced for VOT-RGBT2019 and VOT-RGBD2019. The VOT toolkit has been updated to support both standard short-term, long-term tracking and tracking with multi-channel imagery. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website(1).
|
|
| 5. |
- Zhou, Ping, et al.
(författare)
-
Molecular characterization of transcriptome-wide interactions between highly pathogenic porcine reproductive and respiratory syndrome virus and porcine alveolar macrophages in vivo
- 2011
-
Ingår i: International Journal of Biological Sciences. - 1449-2288. ; 7:7, s. 947-959
-
Tidskriftsartikel (refereegranskat)abstract
- Porcine reproductive and respiratory syndrome virus (PRRSV) infects mainly the porcine alveolar macrophages (PAMs) and causes porcine reproductive and respiratory syndrome (PRRS). Previous studies have analyzed the global gene expression profiles of lung tissue in vivo and PAMs in vitro following infection with PRRSV, however, transcriptome-wide understanding of the interaction between highly pathogenic PRRSV (HP-PRRSV) and PAMs in vivo has not yet been established. In this study, we employed Affymetrix microarrays to investigate the gene expression patterns of PAMs isolated from Tongcheng piglets (a Chinese indigenous breed) after infection with HP-PRRSV. During the infection, Tongcheng piglets exhibited typical clinical signs, e.g. fever, asthma, coughing, anorexia, lethargy and convulsion, but displayed mild regional lung damage at 5 and 7 dpi. Microarray analysis revealed that HP-PRRSV infection has affected PAMs in expression of the important genes involved in cytoskeleton and exocytosis organization, protein degradation and folding, intracellular calcium and zinc homeostasis. Several potential antiviral strategies might be employed in PAMs, including upregulating IFN-induced genes and increasing intracellular zinc ion concentration. And inhibition of the complement system likely attenuated the lung damage during HP-PRRSV infection. Transcriptomic analysis of PAMs in vivo could lead to a better understanding of the HP-PRRSV-host interaction, and to the identification of novel antiviral therapies and genetic components of swine tolerance/susceptibility to HP-PRRS.
|
|
