• Journal of Information Processing Systems
• /
• 제16권3호
• /
• pp.541-556
• /
• 2020

Wireless networks have become integral to society as they provide mobility and scalability advantages. However, their disadvantage is that they cannot control the media, which makes them vulnerable to various types of attacks. One example of such attacks is the evil twin access point (AP) attack, in which an authorized AP is impersonated by mimicking its service set identifier (SSID) and media access control (MAC) address. Evil twin APs are a major source of deception in wireless networks, facilitating message forgery and eavesdropping. Hence, it is necessary to detect them rapidly. To this end, numerous methods using clock skew have been proposed for evil twin AP detection. However, clock skew is difficult to calculate precisely because wireless networks are vulnerable to noise. This paper proposes an evil twin AP detection method that uses a multiple-feature-based machine learning classification algorithm. The features used in the proposed method are clock skew, channel, received signal strength, and duration. The results of experiments conducted indicate that the proposed method has an evil twin AP detection accuracy of 100% using the random forest algorithm.

• International Journal of Knowledge Content Development & Technology
• /
• 제11권4호
• /
• pp.35-51
• /
• 2021

This study measured the effects of fake news and propaganda on managing information on COVID-19 among the Nigerian citizenry. This study examined sources of information on COVID-19 available to the people, evaluated reasons behind spreading fake news, examined how fake news has affected the spread of COVID-19 pandemic in Nigeria, established the consequences of fake news on managing COVID-19 pandemic and as well identified ways to contain fake news at a time like this in Nigeria.It is a survey with a sample size of 375 participants selected using simple random technique. Instrument of data gathering was questionnaire widely distributed in the six geo-political zones of Nigeria using Survey monkey. Data was analysed using frequencies, counts and percentages, tables and charts. Findings revealed that people rely more on radio, television, and social media for information on COVID-19. Fake news is spread by people mostly for political reasons and intention to cause panic. In Nigeria, fake news has led to disbelief of the existence of the virus thereby leading to violation of precautionary measures among the citizenry and lack of trust in the government. Concerted effort on the part of the government is required to give public enlightenment on the danger of fake news. Also, directorate of anti-fake news should be established to censor and reprimand sources of fake news. People should always check source of information to confirm its credibility and be weary of sharing unconfirmed information especially on the social media.

• 스마트미디어저널
• /
• 제11권8호
• /
• pp.84-92
• /
• 2022

Precision livestock monitoring promises greater management efficiency for farmers and higher welfare standards for animals. Recent studies on video-based animal activity recognition and tracking have shown promising solutions for understanding animal behavior. To achieve that, surveillance cameras are installed diagonally above the barn in a typical cattle farm setup to monitor animals constantly. Under these circumstances, tracking individuals requires addressing challenges such as occlusion and visual appearance, which are the main reasons for track breakage and increased misidentification of animals. This paper presents a framework for multi-cattle tracking in closed barns with appearance and motion models. To overcome the above challenges, we modify the DeepSORT algorithm to achieve higher tracking accuracy by three contributions. First, we reduce the weight of appearance information. Second, we use an Ensemble Kalman Filter to predict the random motion information of cattle. Third, we propose a supplementary matching algorithm that compares the absolute cattle position in the barn to reassign lost tracks. The main idea of the matching algorithm assumes that the number of cattle is fixed in the barn, so the edge of the barn is where new trajectories are most likely to emerge. Experimental results are performed on our dataset collected on two cattle farms. Our algorithm achieves 70.37%, 77.39%, and 81.74% performance on HOTA, AssA, and IDF1, representing an improvement of 1.53%, 4.17%, and 0.96%, respectively, compared to the original method.

• 스마트미디어저널
• /
• 제12권2호
• /
• pp.36-41
• /
• 2023

지원자 추적 시스템의 등장으로 온라인 채용이 활성화되면서 채용 사기가 심각한 문제로 대두되고 있다. 이 연구는 온라인 채용 환경에서 채용 사기를 탐지할 수 있는 신뢰할 수 있는 모델을 개발하여 비용 손실을 줄이고 개인 사생활 보호를 강화하고자 한다. 이 연구의 주요 기여는 데이터를 탐색적으로 분석하여 얻은 통찰력을 활용하여 어떤 채용 정보가 사기인지, 아니면 합법적인지를 구분할 수 있는 자동화된 방법론을 제공하는데 있다. 캐글에서 제공하는 채용 사기 데이터 집합인 EMSCAD를 사용하여 다양한 단일 분류기 및 앙상블 분류기 기반 머신러닝 모델을 훈련하고 평가하였으며, 그 결과로 앙상블 분류기인 랜덤 포레스트 분류기가 정확도 98.67%, F1 점수 0.81로 가장 좋은 결과를 보이는 것을 알 수 있었다.

• 정보처리학회논문지B
• /
• 제11B권6호
• /
• pp.691-700
• /
• 2004

본 연구는 이동환경에서 연속 미디어 객체에 대한 사용자 요구들에 대하여 효율적으로 자원을 관리하기 위하여, 사용자의 이동성 정보를 반영하는 협력적 프록시 캐슁 정책을 제안한다. 제안된 정책은 담당영역 내에서 사용자의 요구들을 참조함으로서 캐슁하는 기존의 프록시 캐슁정책과는 다르게 인접한 영역의 많은 사용자 요구 정보들을 이용하여 캐슁 객체를 선택함으로써 이동환경에서 발생하는 사용자들의 랜덤 액세스 요구들을 충분히 반영할 수 있도록 한다. 그리고 제안된 캐슁 정책을 위해서 각 프록시에서 발생한 요구 정보의 가중치와 재생량을 기반으로 하는 재배치 기법을 제안한다. 그래서 객체단위와 세그먼트 단위로 재배치 기법을 수행하여 결과를 평가하고 캐슁 정책의 성능을 분석하였다. 그 결과, 이동환경에서 적절한 사용자의 이동성 비율이 협력적 캐슁의 성능에 영향을 미치는 중요한 요인이 된다는 것을 알았다.

• 한국의류산업학회지
• /
• 제15권6호
• /
• pp.971-976
• /
• 2013

This study provides insight into current social media influences and purchasing power of the young generation in that the size of both of these demographic groups will impact the apparel companies and retail market for the predictable future Denim apparel companies are aware of the discretionary spending power of the Y and Z Generations. The characteristics of current teens are so similar to college-age individuals in that they have grown up with digital technology and they prefer to communicate via social networking sites. Retailers have utilized these social media platforms in order to capture the attention of the generations. Traditionally marketing campaigns have differentiated between teens and the college-age population. However, the teens actually have larger spending power and more discretionary income. A survey consisted of 32 questions pertaining to Internet media influences, influence of people, and decision factors on decisionmaking related to purchasing selection. A random sampling of 163 females responded to a set of questionnaires. Teens, like college students desire to make their own decisions when they select and purchase denim jeans. Overall 40% of them wanted to make their own decisions when purchasing their jeans, however, a significant number are influenced by their friend's opinions (34%) and the opinions of family members (15%). However, celebrities (10%) had the least influence on their decisions. Teens, like colleges students make decisions based on the same decision factors: fit (63%), cost (23%), brand (10%) and color (2%). The most important factor in determining preference was "fit".

• 방송공학회논문지
• /
• 제17권3호
• /
• pp.447-458
• /
• 2012

본 논문에서는 키넥트 센서로부터 획득한 관절 정보를 이용하여 손 제스처를 인식하는 방법을 나타낸다. 관절 정보에 대한 관찰열을 표현하기 위한 특징으로 방향 변형에 강인한 다각도 결합 히스토그램 특징을 제안한다. 제안한 특징은 다양한 각도의 양자화 레벨을 갖는 여러 개의 각도 히스토그램들을 결합함으로써, 사람 및 환경에 따라 발생할 수 있는 제스처의 방향 변형에 강인하게 제스처를 표현한다. 또한, 다각도 결합 히스토그램으로 표현된 제스처 관찰열은 랜덤 결정 포레스트 분류기와 잘 겹합되어 높은 성능으로 제스처의 클래스를 인식한다. 키넥트 센서로부터 획득한 정적 및 동적 타입의 손 제스처 데이터셋에서 실험을 진행하였고, 다른 제스처 특징 및 분류기를 갖는 방법과의 인식 성능 비교를 통해 제안하는 방법의 우수함을 입증하였다.

• 방송공학회논문지
• /
• 제14권6호
• /
• pp.703-720
• /
• 2009

본 논문에서는 3D 컨텐츠 서비스에 대한 사용자의 욕구를 만족시킴과 동시에 미래 컴퓨팅 환경에 적합한 새로운 동영상 코딩 방법으로서 실감형 다시점 스케일러블 비디오 코딩 방법을 제안하였다. 미래의 비디오 코딩 방법은 스테레오 스코픽 또는 다시점 비디오를 통하여 삼차원 실감형 입체영상을 사용자로 하여금 느끼게 하는 실감형 서비스를 지원함과 동시에 다양한 통신환경 및 다양한 종류의 단말을 통합적으로 지원하기 위한 'One-source Multi-use'를 달성할 수 있어야 한다. 지금까지 2차원 디스플레이만을 지원하는 동영상 코딩 방법과는 다르게 본 논문에서 제안하는 실감형 다시점 스케일러블 비디오 코딩 방법은 그러한 실감 서비스를 지원할 수 있는 방법이다. 제안된 코딩 방법은 다시점 비디오 코딩 방법과 스케일러블 비디오 코딩 방법의 기능을 통합하는 방향으로 설계되고 구현된 후 성능 평가를 통해 실제 3D 서비스에서의 응용 가능성을 살펴보았다. 성능 평가를 통해 본 논문에서 제안하는 코딩 구조가 코딩 효율을 효율적으로 유지하면서 시점간의 랜덤 액세스 성능을 크게 높여 주는 것을 확인할 수 있었다.

• Imaging Science in Dentistry
• /
• 제53권4호
• /
• pp.291-302
• /
• 2023

Purpose: Early detection of carotid stenosis can reduce cardiovascular risk. In this study, the maximum-carotid intima-media thickness (CIMT), the mean-CIMT, and the presence of plaque were examined in healthy young Thai adults. Additionally, correlations between CIMT and cardiovascular risk factors were assessed. Materials and Methods: Left and right carotid arteries of 302 participants(15-45 years old) were scanned, with CIMT measured at the far walls of the common carotid artery, carotid bulb, and internal carotid artery. Demographics and risk factors were assessed using a questionnaire. Ten random participants were re-scanned after 4 weeks. Results: The study included 123 (40.70%) male and 179 (59.30%) female participants. The max-CIMT, mean-CIMT, and plaque thickness were 0.400±0.100, 0.403±0.095 and 1.520±0.814 mm, respectively. Male participants had significantly higher CIMT values for nearly all locations and age groups. The right-sided CIMT values were higher for all locations. The carotid bulb had the greatest CIMT values(0.437±0.178 mm), followed by the common (0.403±0.095 mm) and internal(0.361±0.099 mm) carotid arteries. Plaque was present in 18 locations (1.00%), affecting 15 participants (4.97%). These plaques were found in the right carotid bulb (n=9; 0.50%), left carotid bulb (n=7; 0.39%), and right internal carotid artery (n=2; 0.11%). Adjusted multivariable regression revealed significant positive associations between CIMT and male, increased age and "other" occupation (P<0.05). Conclusion: Both max-CIMT and mean-CIMT were approximately 0.4 mm. Plaque was observed in 4.97% of patients, with an average thickness of 1.5 mm. The most influential risk factors for increased CIMT were sex, age, and occupation.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.79-88
• /
• 2024

The use of the social media has become part of our daily life activities. The social web channels provide the content generation facility to its users who can share their views, opinions and experiences towards certain topics. The researchers are using the social media content for various research areas. Sentiment analysis, one of the most active research areas in last decade, is the process to extract reviews, opinions and sentiments of people. Sentiment analysis is applied in diverse sub-areas such as subjectivity analysis, polarity detection, and emotion detection. Stance classification has emerged as a new and interesting research area as it aims to determine whether the content writer is in favor, against or neutral towards the target topic or issue. Stance classification is significant as it has many research applications like rumor stance classifications, stance classification towards public forums, claim stance classification, neural attention stance classification, online debate stance classification, dialogic properties stance classification etc. This research study explores different feature sets such as lexical, sentiment-specific, dialog-based which have been extracted using the standard datasets in the relevant area. Supervised learning approaches of generative algorithms such as Naïve Bayes and discriminative machine learning algorithms such as Support Vector Machine, Naïve Bayes, Decision Tree and k-Nearest Neighbor have been applied and then ensemble-based algorithms like Random Forest and AdaBoost have been applied. The empirical based results have been evaluated using the standard performance measures of Accuracy, Precision, Recall, and F-measures.