Understanding human behavior and monitoring mental health are essential to maintaining the community and society's safety. As there has been an increase in mental health problems during the COVID-19 pandemic due to uncontrolled mental health, early detection of mental issues is crucial. Nowa-days, the usage of Intelligent Virtual Personal Assistants (IVA) has increased worldwide. Individuals use their voices to control these devices to fulfill requests and acquire different services. This paper proposes a novel deep learning model based on the gated recurrent neural network and convolution neural network to understand human emotion from speech to improve their IVA services and monitor their mental health.

This study explores how integrating Artificial General Intelligence (AGI) with Artificial Immune Systems (AIS) could significantly enhance the efficiency of Security Operations Centers (SOCs). By employing a hypothetical case study and mathematical models, the research compares AGI-driven AIS with traditional AI-driven AIS across key SOC metrics, including True Positives, Benign Positives, False Positives, and False Negatives. The analysis reveals that AGI-driven AIS offers substantial improvements in detection accuracy and operational efficiency while reducing costs. These findings highlight the transformative potential of AGI in bolstering cybersecurity defenses. The research emphasizes the importance of AGI for SOCs, presenting it as a critical advancement over current AI technologies. This is particularly relevant for government regulators, original equipment manufacturers (OEMs), cybersecurity professionals, and investors. The study provides compelling evidence that AGI can drive more effective and efficient SOC operations, encouraging stakeholders to consider investing in and adopting these advanced AI technologies. In a landscape where cybersecurity threats are becoming increasingly sophisticated, the integration of AGI with AIS represents a promising frontier. This research underscores the potential for AGI to not only enhance detection and response capabilities but also to streamline operations and optimize resource allocation within SOCs. The findings suggest that AGI could play a pivotal role in the future of cybersecurity, making it an essential consideration for those looking to stay ahead in the ongoing battle against cyber threats.

ALPR systems have been rapidly spreading in the US. However, little is known about their effectiveness. Results of an interrupted time series model suggest that ALPR systems significantly increased follow-up arrests in the Cincinnati Police Department (CPD) compared with traditional policing approaches. Human resources cost analysis of the study showed that ALPR technology carried out more follow-up arrests by using fewer police officers compared with traditional policing. Finally, cost-effective analysis revealed that ALPR technology is cost-effective and amortises itself within less than one week for property crimes, and less than a month for violent crimes.

The research on predictors of successful terrorism incidents is scarce and warrants more scholarly attention to minimize the number of successful terrorist attacks. This study examined whether suicide attack, region, weapon type, attack type, target/victim type, and type of terrorist organization are predictors of successful terrorism incidents. The data contained global terrorism incidents that occurred between 1970 and 2019 and were obtained from the Global Terrorism Database (N = 154,289). The results of multivariate analyses obtained from the binary logistic regression test showed that successful terrorism is less likely to occur in North America but, when such attacks do occur, they are more likely to involve facility/infrastructure as the attack type and a firearm as the weapon type; target private citizens and property; and be committed by religious terrorist organizations. The findings of the study and its policy implications are discussed.