• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3211-3229
• /
• 2022

To solve the problems existing in the process of Weibo disaster rumor recognition, such as lack of corpus, poor text standardization, difficult to learn semantic information, and simple semantic features of disaster rumor text, this paper takes Sina Weibo as the data source, constructs a dataset for Weibo disaster rumor recognition, and proposes a deep learning model BERT_AT_Stacked LSTM for Weibo disaster rumor recognition. First, add adversarial disturbance to the embedding vector of each word to generate adversarial samples to enhance the features of rumor text, and carry out adversarial training to solve the problem that the text features of disaster rumors are relatively single. Second, the BERT part obtains the word-level semantic information of each Weibo text and generates a hidden vector containing sentence-level feature information. Finally, the hidden complex semantic information of poorly-regulated Weibo texts is learned using a Stacked Long Short-Term Memory (Stacked LSTM) structure. The experimental results show that, compared with other comparative models, the model in this paper has more advantages in recognizing disaster rumors on Weibo, with an F1_Socre of 97.48%, and has been tested on an open general domain dataset, with an F1_Score of 94.59%, indicating that the model has better generalization.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.50-56
• /
• 2022

In order to process a vast amount of data, there is demand for a new system with higher processing speed and lower energy consumption. To prevent 'memory wall' in von Neumann architecture, RRAM, which is a neuromorphic device, has been researched. In this paper, we summarize the features of RRAM and propose the device structure for characteristic improvement. RRAM operates as a synapse device using a change of resistance. In general, the resistance characteristics of RRAM are nonlinear and random. As synapse device, linearity and uniformity improvement of RRAM is important to improve learning recognition rate because high linearity and uniformity characteristics can achieve high recognition rate. There are many method, such as TEL, barrier layer, NC, high oxidation properties, to improve linearity and uniformity. We proposed a new device structure of TiN/Al doped TaO_x/AlO_x/Pt that will achieve high recognition rate. Also, with simulation, we prove that the improved properties show a high learning recognition rate.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.4
• /
• pp.289-297
• /
• 2010

In this paper, A method to prevent the external acoustic noise from being misrecognized as the speech recognition object is presented in the speech activity detection process for the speech recognition. Also this paper confirmed besides the acoustic energy to the lip movement image signals. First of all, the successive images are obtained through the image camera for personal computer and the lip movement whether or not is discriminated. The next, the lip movement image signal data is stored in the shared memory and shares with the speech recognition process. In the mean time, the acoustic energy whether or not by the utterance of a speaker is verified by confirming data stored in the shared memory in the speech activity detection process which is the preprocess phase of the speech recognition. Finally, as a experimental result of linking the speech recognition processor and the image processor, it is confirmed to be normal progression to the output of the speech recognition result if face to the image camera and speak. On the other hand, it is confirmed not to the output the result of the speech recognition if does not face to the image camera and speak. Also, the initial feature values under off-line are replaced by them. Similarly, the initial template image captured while off-line is replaced with a template image captured under on-line, so the discrimination of the lip movement image tracking is raised. An image processing test bed was implemented to confirm the lip movement image tracking process visually and to analyze the related parameters on a real-time basis. As a result of linking the speech and image processing system, the interworking rate shows 99.3% in the various illumination environments.

• Laboraroty Animal Research
• /
• v.34 no.4
• /
• pp.239-247
• /
• 2018

Bacopa monnieri is a medicinal plant with a long history of use in Ayurveda, especially in the treatment of poor memory and cognitive deficits. In the present study, we hypothesized that Bacopa monnieri extract (BME) can improve memory via increased cell proliferation and neuroblast differentiation in the dentate gyrus. BME was administered to 7-week-old mice once a day for 4 weeks and a novel object recognition memory test was performed. Thereafter, the mice were euthanized followed by immunohistochemistry analysis for Ki67, doublecortin (DCX), and phosphorylated cAMP response element-binding protein (CREB), and western blot analysis of brain-derived neurotrophic factor (BDNF). BME-treated mice showed moderate increases in the exploration of new objects when compared with that of familiar objects, leading to a significant higher discrimination index compared with vehicle-treated mice. Ki67 and DCX immunohistochemistry showed a facilitation of cell proliferation and neuroblast differentiation following the administration of BME in the dentate gyrus. In addition, administration of BME significantly elevated the BDNF protein expression in the hippocampal dentate gyrus, and increased CREB phosphorylation in the dentate gyrus. These data suggest that BME improves novel object recognition by increasing the cell proliferation and neuroblast differentiation in the dentate gyrus, and this may be closely related to elevated levels of BDNF and CREB phosphorylation in the dentate gyrus.

• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.383-390
• /
• 2020

The present study was conducted to examine the differences and correlations between verbal fluency and story comprehension according to the working memory(WM) capacity, and to find out what WM factors influence the linguistic competence in Alzheimer's disease(AD) and vascular dementia(VaD) groups each consisting of 15 patients. The results of their performance produced firstly significant differences in phonemic fluency, story comprehension, delayed recall and recognition task between the two groups. Further analysis shows that VaD group had significant correlations between the scores of story comprehension and the recognition test scores additionally. These findings suggest that it is possible to differentiate the two groups even by story comprehension tasks and WM. In conclusion, the clinical application of the results is likely to contribute to appropriate treatment plans and effective interventions for elderly with AD and VaD as well as to improve the classification criteria for both types of dementia.

• Journal of Korea Game Society
• /
• v.11 no.6
• /
• pp.103-113
• /
• 2011

In this paper, we propose gesture recognition based 3D Serious Games to prevent dementia. These games are designed to enhance the effect of preventing dementia by helping increase brain usage and physical activities of users by the entire body gesture recognition. The existing cameras used for gesture recognition technology are limited in terms of recognition ratio and operation range. For more stable recognition of the body gestures, we recognized users with a 3D depth camera, obtained joint data of users, and analyzed joint motions to recognize gestures of the body. Game contents were designed to practice memory, reasoning, calculation, and spatial recognition focusing on the atrophy of brain cells as a major cause of dementia. Game results of each user were saved and analyzed to measure how their recognition skills improved.

• The Korean Journal of Physiology and Pharmacology
• /
• v.24 no.1
• /
• pp.27-37
• /
• 2020

Neuroinflammation is an important process underlying a wide variety of neurodegenerative diseases. Carvacrol (CAR) is a phenolic monoterpene commonly used as a food additive due to its antibacterial properties, but it has also been shown to exhibit strong antioxidative, anti-inflammatory, and neuroprotective effects. Here, we sought to investigate the effects of CAR on inflammation in the hippocampus and prefrontal cortex, as well as the molecular mechanisms underlying these effects. In our study, lipopolysaccharide was injected into the lateral ventricle of rats to induce memory impairment and neuroinflammation. Daily administration of CAR (25, 50, and 100 mg/kg) for 21 days improved recognition, discrimination, and memory impairments relative to untreated controls. CAR administration significantly attenuated expression of several inflammatory factors in the brain, including interleukin-1β, tumor necrosis factor-α, and cyclooxygenase-2. In addition, CAR significantly increased expression of brain-derived neurotrophic factor (BDNF) mRNA, and decreased expression of Toll-like receptor 4 (TLR4) mRNA. Taken together, these results show that CAR can improve memory impairment caused by neuroinflammation. This cognitive enhancement is due to the anti-inflammatory effects of CAR medicated by its regulation of BDNF and TLR4. Thus, CAR has significant potential as an inhibitor of memory degeneration in neurodegenerative diseases.

• The Journal of the Korea Contents Association
• /
• v.10 no.6
• /
• pp.80-90
• /
• 2010

In this paper, we introduce some issues to implement an agent system to support service mobility in home network environment, and describe detailed design method in terminal as well as server agent. Specifically, we describe user recognition module, signaling message receiving/parsing module of terminal agent and signaling message receiving/parsing module, multimedia switching module, memory management module of server agent. We define several parameters managed in IP sharing device and design binding table structure to support mobility. And we utilize M/M/1/K queueing theory to obtain relations between memory size, blocking probability and memory utilization. From the obtained results, we show that memory size can be predicted in server agent mounted on IP sharing device.

• The KIPS Transactions:PartA
• /
• v.9A no.2
• /
• pp.147-162
• /
• 2002

Multi-processor system with fast I/O devices improves processing performance and reduces the bottleneck by I/O concentration. In the system, the Performance influenced by shared memory used for exchanging data between processors varies with configuration and utilization. This paper suggests a prediction model for buffer and shared memory optimization under interrupt recognition method using mailbox. Ethernet (IEEE 802.3) packets are used as the input of system and the amount of utilized memory is measured for different network bandwidth and burstiness. Some empirical studies show that the amount of buffer and shared memory varies with packet concentration rate as well as I/O bandwidth. And the studies also show the correlation between two memories.

• Smart Media Journal
• /
• v.8 no.1
• /
• pp.19-26
• /
• 2019

At the opening ceremony of 2018 Winter Olympics in PyeongChang, an unknown cyber-attack occurred. The malicious code used in the attack is based on in-memory malware, which differs from other malicious code in its concealed location and is spreading rapidly to be found in more than 140 banks, telecommunications and government agencies. In-memory malware accounts for more than 15% of all malicious codes, and it does not store its own information in a non-volatile storage device such as a disk but resides in a RAM, a volatile storage device and penetrates into well-known processes (explorer.exe, iexplore.exe, javaw.exe). Such characteristics make it difficult to analyze it. The most recently released in-memory malicious code bypasses the endpoint protection and detection tools and hides from the user recognition. In this paper, we propose a method to efficiently extract the payload by unpacking injection through IDA Pro debugger for Dorkbot and Erger, which are in-memory malicious codes.