Intelligent Agents Research Articles

Adaptive urban traffic signal control based on enhanced deep reinforcement learning

One of the focal points in the field of intelligent transportation is the intelligent control of traffic signals (TS), aimed at enhancing the efficiency of urban road networks through specific algorithms. Deep Reinforcement Learning (DRL) algorithms have become mainstream, yet they suffer from inefficient training sample selection, leading to slow convergence. Additionally, enhancing model robustness is crucial for adapting to diverse traffic conditions. Hence, this paper proposes an enhanced method for traffic signal control (TSC) based on DRL. This approach utilizes dueling network and double q-learning to alleviate the overestimation issue of DRL. Additionally, it introduces a priority sampling mechanism to enhance the utilization efficiency of samples in memory. Moreover, noise parameters are integrated into the neural network model during training to bolster its robustness. By representing high-dimensional real-time traffic information as matrices, and employing a phase-cycled action space to guide the decision-making of intelligent agents. Additionally, utilizing a reward function that closely mirrors real-world scenarios to guide model training. Experimental results demonstrate faster convergence and optimal performance in metrics such as queue length and waiting time. Testing experiments further validate the method's robustness across different traffic flow scenarios.

Multi-IRSs enhanced UAV secure semantic communication system

This paper delves into a unmanned aerial vehicle (UAV) semantic communication system featuring multiple intelligent reflecting surfaces (IRSs). The UAV transmits semantic symbols to users in the presence of eavesdropping, and thus has inevitable security problems. In order to measure secure communication performance in semantic communication, the security semantic transmission rate (SSR) based on the semantic similarity is employed. An optimization problem is formulated to enhance the average SSR by optimizing UAV trajectory, IRS reflecting coefficients, number of semantic symbols, and transmission power, while satisfying position, speed, anti-collision, and power constraints. Due to the highly dynamic nature of the environment and the difficulties in solving complex modeling problems, a novel approach based on hybrid soft actor–critic (H-SAC) deep reinforcement learning (DRL) is proposed to address this non-convex optimization problem. The algorithm addresses the challenge of dynamic environments in UAV scenarios by seamlessly accommodating both discrete and continuous action spaces such as the trajectory and the IRS reflecting coefficient within the network. This enables effective processing of actions taken by intelligent agents, ensuring adaptability to the diverse requirements of the environment without the need for separate handling mechanisms. Simulation results show that the proposed intelligent algorithm exhibits excellent convergence and achieves a well-balanced pairing of appropriate IRSs and selection of flight paths, significantly improving the average SSR of the system. Specifically, our proposed scheme enhances the secure semantic transfer rate by more than fifty percent compared to when the number of semantic symbols is fixed at two.

The application of special operations forces combat tactics

Special Operations Forces (SOF) are pivotal assets in contemporary military endeavors, undertaking missions demanding precision, stealth, and adaptability. This article scrutinizes the critical imperative of refining combat tactics for SOF units. It delineates multifaceted strategies for tactical enhancement, including rigorous training regimes and immersive simulation exercises. Moreover, it emphasizes the integration of cutting-edge technologies, such as advanced weaponry, surveillance systems, unmanned aerial vehicles (UAVs), and cyber capabilities, to augment situational awareness and mission efficacy. Effective collaboration and information sharing among diverse military branches and intelligence agencies are underscored as indispensable for maximizing operational impact. By perpetually evolving their tactics, SOF units can adeptly navigate the intricate dynamics of modern warfare, effectively countering emerging threats and ensuring mission success in today's ever-evolving security milieu. The article explores the importance of enhancing the application of combat tactics for Special Operations Forces (SOF) in modern military operations. It discusses various strategies for tactical improvement, including training and simulation, integration of technology, collaboration, and information sharing among different branches of the military and intelligence agencies. By continuously refining and innovating their tactics, SOF units can stay ahead of emerging threats and achieve mission success with greater efficiency and precision in today's dynamic security landscape.

Educational Coaching through an intelligent agent based on the three knowledges of education in a Teaching Environment and the virtual learning

Educational Coaching through an intelligent agent based on the three knowledges of education in a Teaching Environment and the virtual learning

The Triumph of HUMINT: The GDR Foreign Intelligence Services’ Collection of Defense Intelligence, 1951–1989

During the Cold War, the German Democratic Republic (GDR)’s foreign intelligence agencies collected much defense intelligence from human sources in West Germany. By the mid-1960s, the two services had created agent networks in their principal targets in West Germany’s government, armed forces, industry and universities. For the next 25 years, these agent networks supplied a wealth of varied and valuable military intelligence and scientific and technological intelligence. At their heart was a small number of outstanding human sources. The GDR’s intelligence agencies significantly strengthened the Soviet Bloc’s intelligence collection. The intelligence they obtained was more valuable to the Warsaw Pact than the GDR’s armed forces and would have been of great benefit to the Pact if war had broken out. Their success ran counter to the trend of military intelligence collection at that time, which was to rely increasingly heavily on technical collection.

Nanostructured cruciform phototheranostic agents for efficient multimodal imaging-guided type I photodynamic/photothermal synergistic therapy

One-component multimodel imaging-guided synergistic platform provides an attracting strategy for the precise cancer therapy. However, the construction of single molecules integrating near-infrared (NIR) II emission, multimodel-imaging and multiple therapeutic modalities still remains a great challenge. In this study, a series of organic phototheranostic agents (named PMY, MePMY and TPMY) based on a cross-shaped D-π-A framework were designed and synthesized, and their corresponding nanoparticles (NPs) were facilely fabricated by encapsulating them with an amphiphilic polymer. The twisted structure and lower band gaps of these compounds extended their emissions deep into the NIR-II region, and the narrow singlet-triplet energy gaps endowed them with highly efficient intersystem crossing from S1 to T1 state. Specifically, TPMY NPs exhibit NIR-II emission at 1022 nm, efficient generation of type I reactive oxygen species, and high photothermal conversion efficiency (37.8 %), as well as good photostability and biocompatibility. In vitro and in vivo experiments further revealed the excellent photoacoustic and photothermal imaging ability and superior tumoricidal activity of TPMY NPs, in which the tumor growth was effectively inhibited or even completely eradicated upon single administration and once light irradiation. This study thus provides a new insight into the design and development of intelligent phototheranostic agents for multimodel imaging-guided synergistic therapy which has potential in future practical applications.

The role of AI agents in fostering inclusivity for HEIs’ students with special needs against backdrops of the accreditation trend

PurposeThis paper aims to study the role of artificial intelligence (AI) agents in creating a climate of inclusion for people with special needs in the higher education sector (HES).Design/methodology/approachA qualitative methodology is used in this research that is mainly based on semistructured interviews conducted with the top ten universities in Lebanon with deans, information technology managers, professors and administrative officers.FindingsThis paper highlights findings related to the current status of the higher education institutions (HEIs) in Lebanon vis-à-vis their accreditation and quality assurance processes in accommodating and creating a climate of inclusion for people with special needs. The results show the important role of AI agents in aiding HEI in creating such a climate of inclusion for people with special needs.Originality/valueThe study sheds light on existing gaps in the literature related to creating a climate of inclusion for people with special needs in HEI. Additionally, there is yet a lack of research that focuses on the role of AI technology in general and AI agents in particular in fostering a climate of inclusion for people with special needs within the HES.

Effect of AI counsellor’s nonverbal immediacy behaviour on user satisfaction: serial mediation of positive expectancy violation and rapport

ABSTRACT The aim of this study is to verify the causal relationship between the nonverbal immediacy behaviour (NIB) of an artificial intelligence (AI) agent for mental health counselling and user satisfaction through an experiment. We explored whether the anthropomorphism of the AI agent moderated the effect of the AI agent. A 2 (NIB: absent vs. present) × 2 (anthropomorphism: low vs. high) between-subjects experiment was conducted. The participants answered questionnaires after having a conversation about their daily stress with an AI counsellor, which was implemented according to the experimental conditions in the metaverse counselling room. The results showed that the NIB of the AI agent had a positive effect on user satisfaction, which was serially mediated by positive expectancy violations and rapport. However, anthropomorphism was not found to moderate the effects of NIB on user satisfaction. This study contributed to theoretical elaboration by providing empirical evidence that the effect of NIB is significant in AI counselling and by revealing that this effect occurs through a serial mediation path of positive expectation violation and rapport.

AI Chatbots: Elevating Customer Interactions Amidst Challenges

In the current era of rapid technological advancement, businesses must stay abreast of current trends to maintain competitive edge and ensure continued success. Prioritizing customer experience is paramount wherein showcasing a deep commitment to customer-oriented style is the differentiator. The modern marketing technologies give rise to intelligent conversational agents that has revolutionized customer engagement. As technology continues to shape the global business landscape, this study assessed the customer experience through their extent of interaction and challenges encountered in using artificial intelligence (AI) chatbots.Descriptive-quantitative research method was employed using validated survey questionnaire distributed to 258 locals from targeted respondents in the barangays of Las Pinas City who have experiences in interacting with AI-chatbots. The respondents were clustered to smaller groups who are knowledgeable about the topic, experienced using AI Chatbots by top e-commerce shops and are willing to participate. While AI chatbots have the potential to improve customer experience, their limitations and challenges must be addressed to ensure more effective and satisfying customer transactions.

Human–AI communication in initial encounters: How AI agency affects trust, liking, and chat quality evaluation

Artificial intelligence (AI) agency plays an important role in shaping humans’ perceptions and evaluations of AI. This study seeks to conceptually differentiate AI agency from human agency and examine how AI’s agency manifested on source and language dimensions may be associated with humans’ perceptions of AI. A 2 (AI’s source autonomy: autonomous vs human-assisted) × 2 (AI’s language subjectivity: subjective vs objective) × 2 (topics: traveling vs reading) factorial design was adopted ( N = 376). The results showed autonomous AI was rated as more trustworthy, and AI using subjective language was rated as more trustworthy and likable. Autonomous AI using subjective language was rated as the most trustworthy, likable, and of the best quality. Participants’ AI literacy moderated the interaction effect of source autonomy and language subjectivity on human trust and chat quality evaluation. Results were discussed in terms of human–AI communication theories and the design and development of AI chatbots.

Healthcare security in cloud‐based wireless sensor networks: Botnet attack detection via autoencoder‐aided goal‐based artificial intelligent agent

SummaryThis paper presents a new method in the field of healthcare security that specifically targets cloud‐based wireless sensor networks (WSNs). The suggested method integrates a goal‐based artificial intelligent agent (GAIA) with an autoencoder (AE) architecture, yielding an autoencoder‐based agent (AE‐A). The main goal of this integrated system is to improve the efficiency of identifying botnet assaults, with a specific emphasis on the evolving security threats related to cloud computing. Our concept is around creating a meticulously calibrated, goal‐driven AI agent tailored explicitly for healthcare applications. The agent meticulously analyses network data and proficiently integrates autoencoder‐enhanced anomaly detection techniques to uncover intricate patterns indicative of botnet activities. The adaptability of the goal‐based AI agent is improved by ongoing real‐time learning, guaranteeing that its responses are in line with the primary goal of neutralizing threats. The autoencoder serves a vital role in the system by functioning as a tool for extracting features. This approach enables the AI Agent to navigate complex information and derive significant insights efficiently. Cloud computing resources greatly enhance the functionalities of a system, enabling scalability, real‐time analysis, and improved responsiveness. Utilizing goal‐driven AI and autoencoder together proves to be a successful strategy in safeguarding healthcare‐oriented WSNs against botnet attacks. This technique takes a proactive stance in ensuring the security of sensitive medical data. The suggested model is evaluated against various models, including the bidirectional long short‐term memory (BLSTM) method, the hybrid BLSTM with recurrent neural network (BLSTM‐RNN) algorithm, and the Random Forest algorithm. The models are evaluated using metrics such as Matthews correlation coefficient (MCC), prediction rate, accuracy, recall, precision, and F1 score analysis. The investigation demonstrates that the suggested model achieved the most significant values of 93% MCC, 94% prediction rate, 91% accuracy, 98% recall, 98% precision, and 98% F1 score, respectively when compared to the existing models.

British surveillance of postwar Soviet radio jamming: US–UK intelligence relations and interference detection at BBC Tatsfield, 1948-1949

ABSTRACT Following World War II, the BBC, better known for radio programme broadcasts, continued its long-standing work of radio spectrum surveillance at the specialized receiving and measurement facility located at Tatsfield. Both before and after Soviet jamming of US and British Russian-language broadcasts escalated in April 1949, Tatsfield catalogued the technical characteristics of jamming signals. BBC engineers, experienced in interpreting types and sources of radio interference, issued fortnightly summaries with interpretations of these technical observations. US intelligence agencies knew of Tatsfield’s findings, but differing perspectives in Washington and London resulted in divergent responses to the technical intelligence data. With rising tensions in wider Anglo-American intelligence relations, fueled by the Soviet weapons program and security breaches, such differences presaged separate approaches to Soviet communications threats. US agencies received greatly increased funding, while the BBC’s budget struggles persisted. Even so, interference detection was a high-water mark in Britain’s early Cold War intelligence work.

Australian Anti-encryption Legislation and Its Impacts on Security and Privacy

Telecommunications and Other Legislation Amendment (Assistance and Access) Act 2018 gives relevant authorities (e.g. law enforcement, national security agencies and intelligence agencies) significant new powers regarding access to encrypted communications data, and hence extensive public attention have been attracted and opinions expressed concerning general security and privacy of users. This essay will first briefly introduce the key contents of the Assistance and Access Act 2018, then discuss how it will affect security and privacy of users respectively by considering both supporting and opposing arguments, and then further the discussion into a global environment by examining the history of a variety of efforts on similar powers. It concludes that though the Assistance and Access Act 2018 has sophisticated oversight mechanism and takes into consideration the most concerned systemic weaknesses security issue, its definition and guidance are vague and is likely not practical to achieve what the Act is designed for in practice. The potential overreach of the Act not only will impose great threats to system security as a whole, but also will breach the principle of privacy.

Large-Language-Model-Based AI Agent for Organic Semiconductor Device Research.

Large language models (LLMs) have attracted widespread attention recently, however, their application in specialized scientific fields still requires deep adaptation. Here, an artificial intelligence (AI) agent for organic field-effect transistors (OFETs) is designed by integrating the generative pre-trained transformer 4 (GPT-4)model with well-trained machine learning (ML) algorithms. It can efficiently extract the experimental parameters of OFETs from scientific literature and reshape them into a structured database, achieving precision and recall rates both exceeding 92%. Combined with well-trained ML models, this AI agent can further provide targeted guidance and suggestions for device design. With prompt engineering and human-in-loop strategies, the agent extracts sufficient information of 709 OFETs from 277 research articles across different publishers and gathers them into a standardized database containing more than 10000 device parameters. Using this database, a ML model based on Extreme Gradient Boosting is trained for device performance judgment. Combined with the interpretation of the high-precision model, the agent has provided a feasible optimization scheme that has tripled the charge transport properties of 2,6-diphenyldithieno[3,2-b:2',3'-d]thiophene OFETs. This work is an effective practice of LLMs in the field of organic optoelectronic devices and expands the research paradigm of organic optoelectronic materials and devices.

Pentingnya Badan Intelijen Pertahanan dalam Non-Combat Military Mission: Instrumen Perhatian Khusus untuk Peningkatan Kapasitas dan Kapabilitas Pertahanan

This research will focus on the importance of Defense Intelligence Agencies in Non-Combat Military Missions. This research method will use a qualitative approach with case studies to explore the importance of the Defense Intelligence Agency in Non-Combat Military Missions. The data will be collected through in-depth interviews with defense experts, intelligence analysts, and military personnel involved in non-combat missions, as well as through analysis of related documents and official reports. As a result, Military Intelligence has a vital role to play in defense policymaking by providing information to anticipate and confront potential threats, enabling comprehensive threat assessment, and supporting defense diplomacy with accurate intelligence. The establishment of the Defense Intelligence Agency under the Secretary of Defense was proposed because it could coordinate intelligence with military operations, speed up decision-making, and support non-combat missions with strategic intelligence. The agency also strengthens Indonesia's defense diplomacy by providing information for strategic planning and supporting collaboration with the local defense industry, which contributes to enhanced national defense capabilities and economic growth. To be effective, the intelligence function of the Defense Intelligence Agency must synergize with the existing intelligence community, to support Indonesia's mission to become an Asian Tiger.

Fully distributed multi-agent processing strategy applied to vehicular networks

This work explores distributed processing techniques, together with recent advances in multi-agent reinforcement learning (MARL) to implement a fully decentralized reward and decision-making scheme to efficiently allocate resources (spectrum and power). The method targets processes with strong dynamics and stringent requirements such as cellular vehicle-to-everything networks (C-V2X). In our approach, the C-V2X is seen as a strongly connected network of intelligent agents which adopt a distributed reward scheme in a cooperative and decentralized manner, taking into consideration their channel conditions and selected actions in order to achieve their goals cooperatively. The simulation results demonstrate the effectiveness of the developed algorithm, named Distributed Multi-Agent Reinforcement Learning (DMARL), achieving performances very close to that of a centralized reward design, with the advantage of not having the limitations and vulnerabilities inherent to a fully or partially centralized solution.

Tracing Shifting Host Country Problematization(s) of Transnational Repression: The Evolution of Swedish Efforts to Counter “Refugee Espionage”

ABSTRACT Not least since the brutal killing of Saudi journalist and regime-critic Jamal Khashoggi in the Saudi embassy in Istanbul in late 2018 has the question of transnational repression emerged on the agendas of human rights activists, policy makers, and scholars of migration and authoritarianism. Such practices are commonly conceptualized as a dyadic interaction between repressor and repressed. However, on closer inspection, the dyad is, in fact, a triad. Relatively few studies account for or explore the context in which such acts of transnational repression occur: the countries of residence in which targets and victims reside. Taking inspiration from the problematization framework, this article deepens our understanding of the complex and multifaceted ways in which Sweden, a country often lauded for its comprehensive approach and response to transnational repression, has constructed “refugee espionage” as a challenge not only for law enforcement and intelligence agencies but also, Swedish bilateral relations and sovereignty. Through an in-depth analysis of 21 annual reports published by the Swedish Security Service (SÄPO), the article shows how the conceptualization and problematization of the issue has – often in response to particular incidents – become both broader and wider over time.

Development of a neural network model of an intelligent monitoring agent based on a recurrent neural network with a long chain of short-term memory elements

The article continues to review the approach to designing the architecture of a distributed information monitoring system and quality management of communication services provided by the infrastructures of the Internet of Things and the industrial Internet of Things, based on solutions that support machine-to-machine and human-machine interaction. The development of a neural network model of an intelligent monitoring agent based on a recurrent neural network with a long chain of short-term memory elements is proposed. The matrix structure of the LSTM network memory cell is proposed, which takes into account the spatio-temporal correlation of load parameters associated with the time lag of its propagation and is a matrix of connectivity of LSTM network hyperparameters and accumulated values of load parameters of monitoring nodes in the vicinity of a controlled monitoring node, taking into account the characteristics of the time series of propagation of load in stationarity moments.

Termination of Employment Relationship in Uniformed Services in Connection with their Reorganisation or Dissolution–Constitutional Issues

Abstract This article addresses the legal issues arising from the transformation of internal security bodies within the structure of public administration, specifically focusing on how such events impact the service relationship of officers employed in those structures (the so-called ‘uniformed services’). The analysis covers regulations governing the service relationships of officers in the State Protection Office, Government Protection Bureau, and Customs Services in connection with the dissolution of these institutions and the establishment of the Internal Security Agency, the Intelligence Agency, the State Protection Service, and the Customs and Fiscal Service. Theoretical and legal models are identified, and substantive legal provisions are presented to assess their compliance with the relevant provisions of the Constitution of the Republic of Poland.

Channel utilization of media access control protocols for underwater acoustic networks with propagation delay and mobilitya).

This paper investigates the impact of mobility on underwater acoustic communication networks in which the propagation delay is comparable to or larger than the packet duration. An underwater acoustic wireless network, consisting of static and mobile nodes, is studied for its link-layer channel utilization. Synchronous and asynchronous media access control (MAC) protocols are employed with ALOHA, TDMA (time-division multiple access), and artificial intelligence (AI) agent nodes. The simulation results of a multi-node network show that the asynchronous MAC protocols achieve up to 6.66× higher channel utilization than synchronous protocols by allowing time slots to be shorter than the maximum propagation delay among nodes and permitting asynchronous transmission time. The high mobility of a few mobile nodes also favors asynchronous protocols and increases the overall channel utilization. However, node mobility causes more difficulties for the AI node to learn the environment, which may be ineffective to achieve higher gains in channel utilization.