Search results

The internet has completely merged into contemporary life. People are addicted to using internet services for everyday activities. Consequently, an abundance of information about people and organizations is available online, which encourages the proliferation of cybercrimes. Cybercriminals often use malicious links for large-scale cyberattacks, which are disseminated via email, SMS and social media. Recognizing malicious links online can be exceedingly challenging. The purpose of this paper is to present a strong security system that can detect malicious links in the cyberspace using natural language processing technique.

The researcher recommends a variety of approaches, including blacklisting and rules-based machine/deep learning, for automatically recognizing malicious links. But the approaches generally necessitate the generation of a set of features to generalize the detection process. Most of the features are generated by processing URLs and content of the web page, as well as some external features such as the ranking of the web page and domain name system information. This process of feature extraction and selection typically takes more time and demands a high level of expertise in the domain. Sometimes the generated features may not leverage the full potentials of the data set. In addition, the majority of the currently deployed systems make use of a single classifier for the classification of malicious links. However, prediction accuracy may vary widely depending on the data set and the classifier used.

To address the issue of generating feature sets, the proposed method uses natural language processing techniques (term frequency and inverse document frequency) that vectorize URLs. To build a robust system for the classification of malicious links, the proposed system implements weighted soft voting classifier, an ensemble classifier that combines predictions of base classifiers. The ability or skill of each classifier serves as the base for the weight that is assigned to it.

The proposed method performs better when the optimal weights are assigned. The performance of the proposed method was assessed by using two different data sets (D1 and D2) and compared performance against base machine learning classifiers and previous research results. The outcome accuracy shows that the proposed method is superior to the existing methods, offering 91.4% and 98.8% accuracy for data sets D1 and D2, respectively.

The purpose of this paper is to assess the prevalence and socio-economic determinants of common mental disorders among youth in India.

The study utilizes data from “Youth in India: Situation and Needs 2006-2007”. One-way analysis of variance is used to compare different groups. Poisson regression models are used to test the relationship of household, parental, and individual factors with mental health problems.

An estimated 11-31 million youth suffer from reported mental health problems in India. Results suggest that the household and individual factors like place of residence, wealth quintile, age, education, and occupation are the most important determinants of mental health problems among Indian youth. Parental factors lose their statistical significance once individual factors are controlled.

Little is known about correlates of mental health among youth. Strengthening on-going programmes and creating awareness about mental health issues through various programmes may help improve scenario. The two limitations of the study are: first, data covering all the states would have given a broader and clear picture of the issue; and second, due to cross-sectional nature of the data the study is not able to look into the cause-effect relationship.

There are few studies which have explored mental health problems covering smaller areas in India. This is the first and the largest study conducted on a representative population of Indian youth to determine the correlates of reported mental health problems using General Health Questionnaire-12.

The purpose of this paper is to explore illness beliefs among adults with type 2 diabetes (T2DM), studied in a clinical setting in the Indian context. Diabetes management lies primarily in the hands of the patient, which signifies the need for understanding the various dimensions of individuals’ illness beliefs. While past research from abroad has stressed the need for understanding the patient’s perspective in effective illness management, the lack of studies in the Indian context calls for further research in this area.

Drawing on the Self-Regulation Model (Leventhal et al., 1980), semi-structured interviews were carried out to understand the beliefs about diabetes among individuals diagnosed to have T2DM. In total, 70 individuals with T2DM were included, taking into account the disease duration, urban-rural, age and gender distinctions. The data were analyzed using content analysis method.

The results of the analysis revealed numerous sub-themes related to the perceived consequences of diabetes, control or cure issues, timeline and emotional issues as experienced by the subjects.

Carrying out a triangulated research with the various stakeholders, namely, diabetologists, general practitioners and other support staff like dieticians could add more value to this exploratory study.

There is a dearth of research work that explores the illness beliefs that patients’ hold about diabetes, as discussed in the Indian context. It is expected that the insight provided by the study can help the government bodies, healthcare organizations and practitioners design and develop interventions from a patient-centric view. Additionally, such a patient-centric approach will enable individuals to achieve their treatment goals.