A very challenging issue in real-world data is that in many domains like medicine, finance, marketing, web, telecommunication, management, etc. the distribution of data among classes is inherently imbalanced. A widely accepted researched issue is that the traditional classifier algorithms assume a balanced distribution among the classes. Data imbalance is evident when the number of instances representing the class of concern is much lesser than other classes. Hence, the classifiers tend to bias towards the well-represented class. This leads to a higher misclassification rate among the lesser represented class. Hence, there is a need of efficient learners to classify imbalanced data. This chapter aims to address the need, challenges, existing methods, and evaluation metrics identified when learning from imbalanced data sets. Future research challenges and directions are highlighted.
Considering the problem of traditional fractal (TF) features being difficult to achieve both high accuracy and fast speed in network traffic cognition, the idea of space-time separation was proposed on the basis of fractal theory. With space-time fractal (SF) features generated by the space-time separation, a new traffic cognition system called the space-time fractal model (SFM) was established. In order to obtain SF, the spatial and temporal sequences were observed, and further constructed to generate vectors by Legendre transformation, which were mapped into dual space. The physical significance of SF lied in capturing the characteristics of traffic bursts at different scales of space and time, while TF were the fusion of SF across spatial and temporal scales. Compared with TF, SF represented network traffic more comprehensively and thus were able to identify traffic more accurately. Moreover, SF were more computationally efficient than TF, enabling SFM to achieve high cognition speed as well as strong cognition accuracy. The experimental results show that the cognition performance of SFM is superior to other methods.
In photonics, the idea of controlling light in a similar way that magnetic fields control electrons has always been attractive. It can be realized by synthesizing pseudomagnetic fields (PMFs) in photonic crystals (PhCs). Previous works mainly focus on the Landau levels and the robust transport of the chiral states. More versatile control over light using complex nonuniform PMFs such as the flexible splitting and routing of light has been elusive, which hinders their application in practical photonic integrated circuits. Here we propose an universal and systematic methodology to design nonuniform PMFs and arbitrarily control the flow of light in silicon PhCs at telecommunication wavelengths. As proofs of concept, a low-loss S-bend and a highly efficient 50:50 power splitter based on PMFs are experimentally demonstrated. A high-speed data transmission experiment is performed on these devices to prove their applicability in real communication systems. The proposed method offers a new paradigm for the exploration of fundamental physics and the development of novel nanophotonic devices.
Pedro Sousa, Cláudio Klautau Mello, Frank B. Morte
et al.
Question-answering tasks in the telecom domain are still reasonably unexplored in the literature, primarily due to the field's rapid changes and evolving standards. This work presents a novel Retrieval-Augmented Generation framework explicitly designed for the telecommunication domain, focusing on datasets composed of 3GPP documents. The framework introduces the use of the Bisecting K-Means clustering technique to organize the embedding vectors by contents, facilitating more efficient information retrieval. By leveraging this clustering technique, the system pre-selects a subset of clusters that are most similar to the user's query, enhancing the relevance of the retrieved information. Aiming for models with lower computational cost for inference, the framework was tested using Small Language Models, demonstrating improved performance with an accuracy of 66.12% on phi-2 and 72.13% on phi-3 fine-tuned models, and reduced training time.
Yurii V. Konov, Dmitrii A. Pykhtin, Rashid G. Bikbaev
et al.
Developing tunable photodetectors that can operate over a wide range of wavelengths and integrating them into integrated circuits is a significant challenge in today's technology. These devices must be miniaturized, inexpensive, and easily manufactured. To address this challenge, we propose the development of a tunable planar hot-electron photodetector based on Tamm plasmon polariton. The tuning of the operational wavelength is achieved by incorporation of a material with a phase transition, Sb2S3, into Tamm plasmon polariton based structure. This allows for tuning of the detection wavelength over a broad range, encompassing all bands of the telecommunications spectrum.
Topological photonics offers transformative potential for robust integrated waveguide devices due to their backscattering-immune properties. However, their integration faces two fundamental challenges: mode symmetry mismatch with conventional waveguides and prohibitive dimensions. We successfully overcome these two critical challenges by introducing a novel valley-ridge gap waveguide based on topological half-supermode engineering. By strategically hybridizing ridge waveguide modes and valley kink states, we create an exotic odd-symmetric supermode enabling robust propagation and ultra-compact operation. The further implementation of a perfect electric conductor boundary halves lateral dimensions while eliminating radiation loss. Crucially, our proposed valley-ridge interface achieves direct transverse electric mode matching with standard waveguides without transition structures, enabling seamless integration. Experimental results demonstrate reflection losses lower than -15 dB in realistic telecommunication scenarios with super-robust signal propagation through sharp bends. This work innovatively conceptualizes topological half-supermodes and pioneers their practical applications for integrated waveguide devices, establishing a completely new waveguide class that uniquely combines robust backscattering immunity with deep subwavelength compactness.
In a telecommunications network, fault alarms generated by network nodes are monitored in a Network Operations Centre (NOC) to ensure network availability and continuous network operations. The monitoring process comprises of tasks such as active alarms analysis, root alarm identification, and resolution of the underlying problem. Each network node potentially can generate alarms of different types, while nodes can be from multiple vendors, a network can have hundreds of nodes thus resulting in an enormous volume of alarms at any time. Since network nodes are inter-connected, a single fault in the network would trigger multiple sequences of alarms across a variety of nodes and from a monitoring point of view, it is a challenging task for a NOC engineer to be aware of relations between the various alarms, when trying to identify, for example, a root alarm on which an action needs to be taken. To effectively identify root alarms, it is essential to learn relation among the alarms for accurate and faster resolution. In this work we propose a novel unsupervised alarm relation learning technique Temporal Optimization (TempOpt) that is practical and overcomes the limitations of an existing class of alarm relational learning method-temporal dependency methods. Experiments have been carried on real-world network datasets, that demonstrate the improved quality of alarm relations learned by TempOpt as compared to temporal dependency method.
As Artificial Intelligence (AI) becomes increasingly embedded in critical digital infrastructure, including telecommunications, its integration introduces new risks that existing regulatory frameworks are ill-prepared to address. This paper conducts a comparative legal study of policy instruments across ten countries, examining how telecom, cybersecurity, data protection, and AI laws approach AI-related risks in infrastructure. The study finds that regulatory responses remain siloed, with minimal coordination across these domains. Most frameworks still prioritize traditional cybersecurity and data protection concerns, offering limited recognition of AI-specific vulnerabilities such as model drift, opaque decision-making, and algorithmic bias. Telecommunications regulations, in particular, exhibit little integration of AI considerations, despite AI systems increasingly supporting critical network operations. The paper identifies a governance gap where oversight remains fragmented and reactive, while AI reshapes the digital infrastructure. It provides a foundation for more coherent and anticipatory regulatory strategies spanning technological and institutional boundaries.
Aiming at the problem that the Web service quality of service (QoS) estimation methods based on the non-negative latent factorization of tensor model (NLFT) depend heavily on non-negative initial random data and specially designed non-negative training schemes, which lead to low compatibility and scalability, an accelerated unconstrained latent factorization of tensor (AULFT) model was proposed.The proposed model consisted of three main parts.The non-negative constraints from decision parameters were transferred to output latent factors and they were connected through the single-element-dependent mapping function.A momentum-incorporated stochastic gradient descent (MSGD) algorithm was used to effectively improve the convergence rate and estimation accuracy of the proposed AULFT model.The detailed algorithm and result analysis of the proposed AULFT model were presented.The empirical study on two dynamic QoS datasets in real industrial applications demonstrates that the proposed AULFT model has higher computational efficiency and estimation accuracy than the state-of-the-art QoS estimation models.
Technological advances and the development of globalization have led to the growth of global and regional media which ultimately encouraged the emergence of K-Pop culture in Indonesia. The purpose of this study was to determine the influence of watching Korean dramas on the imitation behavior of Pekanbaru students. The theory used is the S-O-R (Stimulus, Organism and Response) theory to explain the data and analysis of the stages of students' imitation behavior towards Korean dramas. The research methodology used is a descriptive qualitative method reinforced by interview data sources with references in the form of relevant articles. The research informants used were students of Pekanbaru Telecommunication Middle School, which were determined through purposive sampling techniques. The results of the study showed that based on the analysis of the SOR theory carried out, there were behaviors that were imitated by Pekanbaru Telecommunication Middle School students from the Korean dramas they watched. The habits imitated by Pekanbaru students were related to fashion, including makeup and skin care, eating habits, and language style or terms in Korean.
Quantum and classical telecommunications require efficient sources of light. Semiconductorsources, owing to the high refractive index of the medium, often exploit photonic cavities to enhance the external emission of photons into a well-defined optical mode. Optical Tamm States (OTS), in which light is confined between a distributed Bragg reflector and a thin metal layer have attracted interest as confined Tamm structures are readily manufactureable broadband cavities. Their effficiency is limited however by the absorption inherent in the metal layer. We propose a nanoring Tamm structure in which a nanoscale patterned annular metasurface is exploited to reduce this absorption and thereby enhance emission efficiency. To this end, we present designs for a nanoring Tamm structure optimised for the telecommunications O band, and demonstrate a near doubling of output efficiency (35%) over an analogous solid disc confined Tamm structure (18%). Simulations of designs optimised for different wavelengths are suggestive of annular coupling between the Tamm state and surface plasmons. These designs are applicable to the design of single photon sources, nanoLEDs, and nanolasers for communications.
Luis M. Garcés-Socarrás, Amirhossein Nik, Flor Ortiz
et al.
The Artificial Intelligence Satellite Telecommunications Testbed (AISTT), part of the ESA project SPAICE, is focused on the transformation of the satellite payload by using artificial intelligence (AI) and machine learning (ML) methodologies over available commercial off-the-shelf (COTS) AI-capable chips for onboard processing. The objectives include validating artificial intelligence-driven SATCOM scenarios such as interference detection, spectrum sharing, radio resource management, decoding, and beamforming. The study highlights hardware selection and payload architecture. Preliminary results show that ML models significantly improve signal quality, spectral efficiency, and throughput compared to conventional payload. Moreover, the testbed aims to evaluate the performance and the use of AI-capable COTS chips in onboard SATCOM contexts.
[Purpose] To examine the advancement of nation-wise internet access in the context of policy and regulations that facilitated the transformation of Indian telecommunication. It analyzes government policies on the development of internet infrastructure, technical standards, content, security and digital inclusion. [Methodology/Approach/Design] Review of Indian regulations and Policy measures governing the evolution of internet and telecommunication sector. Study of Telecom Regulatory Authority of India Act,1997 and subordinate legislations. The study of draft Indian Telecommunication Bill, 2022. [Findings] The evolution of the Internet is credited with progressive convergence of the telecommunications, information technology, and broadcast media. This has led to new paradigms of competition, price wars, contesting licensing and tariffs agreements. The paper attempts to illustrate the regulations that govern these evolving paradigms. [Practical Implications] The Indian telecom sector has more than one billion subscribers and makes significant contribution to GDP of the nation. The Indian government has agreed upon a multi-stakeholder’s approach for internet governance in India. The policy reflects a supportive stand on net neutrality and is shaping digital surveillance on the matters of national security. [Originality/Value] This paper is a unique attempt to describe the policy and legislations that govern the fast-growing sectors of internet and telecommunication in India. The restructuring of the regulatory and legal framework for telecommunication sector is being undertaken by the government to protect the consumer and national interest.
Jaspreet Kaur, Satyam Bhatti, Olaoluwa R Popoola
et al.
The pervasive nature of wireless telecommunication has made it the foundation for mainstream technologies like automation, smart vehicles, virtual reality, and unmanned aerial vehicles. As these technologies experience widespread adoption in our daily lives, ensuring the reliable performance of cellular networks in mobile scenarios has become a paramount challenge. Beamforming, an integral component of modern mobile networks, enables spatial selectivity and improves network quality. However, many beamforming techniques are iterative, introducing unwanted latency to the system. In recent times, there has been a growing interest in leveraging mobile users' location information to expedite beamforming processes. This paper explores the concept of contextual beamforming, discussing its advantages, disadvantages and implications. Notably, the study presents an impressive 53% improvement in signal-to-noise ratio (SNR) by implementing the adaptive beamforming (MRT) algorithm compared to scenarios without beamforming. It further elucidates how MRT contributes to contextual beamforming. The importance of localization in implementing contextual beamforming is also examined. Additionally, the paper delves into the use of artificial intelligence schemes, including machine learning and deep learning, in implementing contextual beamforming techniques that leverage user location information. Based on the comprehensive review, the results suggest that the combination of MRT and Zero forcing (ZF) techniques, alongside deep neural networks (DNN) employing Bayesian Optimization (BO), represents the most promising approach for contextual beamforming. Furthermore, the study discusses the future potential of programmable switches, such as Tofino, in enabling location-aware beamforming.
Every year, students around the globe embark upon their higher education journey, making the onboarding of these students a critical task for colleges and universities. Combined with the growth in distance learning and the rapid development in technologies, the onboarding process occurs increasingly in the digital setting. For this reason, the objective of this scoping review was to report and map interventions, which are used in digital onboarding of first-year students in higher education institutions and explore the digital settings that characterized these interventions. The PRISMA-ScR Guidelines and the JBI Manual for Evidence Synthesis guided this investigation, which included researching four databases and screening the resulting titles and abstracts to identify the 17 sources of evidence included in the final analysis. According to our results, digital and virtual onboarding interventions were categorized into four onboarding dimensions: information interventions, socialization interventions, counseling interventions, and self-study interventions. Examples of the purposes and outcomes of these onboarding interventions included the transfer of information and the socialization of incoming students. Of the five onboarding settings that were also identified in the categorization, telecommunication software and virtual environments predominated. An independently developed onboarding tool could combine the identified onboarding settings and dimensions in the future.
Dispersion engineering is essential to the performance of most modern optical systems including fiber-optic devices. Even though the chromatic dispersion of a meter-scale single-mode fiber used for endoscopic applications is negligible, optical lenses located on the fiber end face for optical focusing and imaging suffer from strong chromatic aberration. Here we present the design and nanoprinting of a 3D achromatic diffractive metalens on the end face of a single-mode fiber, capable of performing achromatic and polarization-insensitive focusing across the entire near-infrared telecommunication wavelength band ranging from 1.25 to 1.65 um. This represents the whole single-mode domain of commercially used fibers. The unlocked height degree of freedom in a 3D nanopillar meta-atom largely increases the upper bound of the time-bandwidth product of an achromatic metalens up to 21.34, leading to a wide group delay modulation range spanning from -8 to 14 fs. Furthermore, we demonstrate the use of our compact and flexible achromatic metafiber for fiber-optic confocal imaging, capable of creating in-focus sharp images under broadband light illumination. These results may unleash the full potential of fiber meta-optics for widespread applications including hyperspectral endoscopic imaging, femtosecond laser-assisted treatment, deep tissue imaging, wavelength-multiplexing fiber-optic communications, fiber sensing, and fiber lasers.