The largest ICT employer in Hungary, Deutsche Telekom IT Solutions (formerly IT-Services Hungary, ITSH) is a subsidiary of the Deutsche Telekom Group. Established in 2006, the company provides a wide portfolio of IT and telecommunications services with more than 5000 employees. ITSH was awarded with the Best in Educational Cooperation prize by HIPA in 2019, acknowledged as one of the most attractive workplaces by PwC Hungary's independent survey in 2021 and rewarded with the title of the Most Ethical Multinational Company in 2019. The company continuously develops its four sites in Budapest, Debrecen, Pécs and Szeged and is looking for skilled IT professionals to join its team. We seek our new passionate Tech Lead for our existing MLOps platform.

In a promotional video actress Michelle Yeoh walks through a bustling urban landscape at night with a smart phone in her hand as she talks to us about a coming transformation. "Every day Qualcomm is transforming the way we work, live and communicate, pushing the limits of technologies like artificial intelligence," she says. It's a dramatic statement by Qualcomm, as they try to connect the company to artificial intelligence in the mind of the market. "Whether our technology is going into a smartphone or whether it's going into a factory or a robot or a drone flying around Mars, our AI is a horizontal that permeates all of those device categories and applications," said Don McGuire, Qualcomm's chief marketing officer. The technology Qualcomm brings to artificial intelligence is a digital platform, based on Snapdragon computer chips.

Cellular user positioning is a promising service provided by Fifth Generation New Radio (5G NR) networks. Besides, Machine Learning (ML) techniques are foreseen to become an integrated part of 5G NR systems improving radio performance and reducing complexity. In this paper, we investigate ML techniques for positioning using 5G NR fingerprints consisting of uplink channel estimates from the physical layer channel. We show that it is possible to use Sounding Reference Signals (SRS) channel fingerprints to provide sufficient data to infer user position. Furthermore, we show that small fully-connected moderately Deep Neural Networks, even when applied to very sparse SRS data, can achieve successful outdoor user positioning with meter-level accuracy in a commercial 5G environment.

An active reconfigurable intelligent surface (RIS)-aided multi-user downlink communication system is investigated, where non-orthogonal multiple access (NOMA) is employed to improve spectral efficiency, and the active RIS is powered by energy harvesting (EH). The problem of joint control of the RIS's amplification matrix and phase shift matrix is formulated to maximize the communication success ratio with considering the quality of service (QoS) requirements of users, dynamic communication state, and dynamic available energy of RIS. To tackle this non-convex problem, a cascaded deep learning algorithm namely long short-term memory-deep deterministic policy gradient (LSTM-DDPG) is designed. First, an advanced LSTM based algorithm is developed to predict users' dynamic communication state. Then, based on the prediction results, a DDPG based algorithm is proposed to joint control the amplification matrix and phase shift matrix of the RIS. Finally, simulation results verify the accuracy of the prediction of the proposed LSTM algorithm, and demonstrate that the LSTM-DDPG algorithm has a significant advantage over other benchmark algorithms in terms of communication success ratio performance.

IoT networks are increasingly becoming target of sophisticated new cyber-attacks. Anomaly-based detection methods are promising in finding new attacks, but there are certain practical challenges like false-positive alarms, hard to explain, and difficult to scale cost-effectively. The IETF recent standard called Manufacturer Usage Description (MUD) seems promising to limit the attack surface on IoT devices by formally specifying their intended network behavior. In this paper, we use SDN to enforce and monitor the expected behaviors of each IoT device, and train one-class classifier models to detect volumetric attacks. Our specific contributions are fourfold. (1) We develop a multi-level inferencing model to dynamically detect anomalous patterns in network activity of MUD-compliant traffic flows via SDN telemetry, followed by packet inspection of anomalous flows. This provides enhanced fine-grained visibility into distributed and direct attacks, allowing us to precisely isolate volumetric attacks with microflow (5-tuple) resolution. (2) We collect traffic traces (benign and a variety of volumetric attacks) from network behavior of IoT devices in our lab, generate labeled datasets, and make them available to the public. (3) We prototype a full working system (modules are released as open-source), demonstrates its efficacy in detecting volumetric attacks on several consumer IoT devices with high accuracy while maintaining low false positives, and provides insights into cost and performance of our system. (4) We demonstrate how our models scale in environments with a large number of connected IoTs (with datasets collected from a network of IP cameras in our university campus) by considering various training strategies (per device unit versus per device type), and balancing the accuracy of prediction against the cost of models in terms of size and training time.

What's up people, this is Cypherlynk and I have spent 10 hours trying to create a neural network and run it with my GPU, here are all the problems I faced while doing it. So as I told you before I know pytorch and I have been trying to switch from PyTorch to Tensorflow. So I was trying to create a Neural Network for learning just the basics of CNNs, all the math and theory behind it. But as soon as I finished the theory when I started to code it out, I did something really embarrassing, it was a beginner-level mistake but the moment I know what was wrong I was able to fix it. So when I was processing my data I imported 2 datasets from keras (The CIFAR-10 and FASHION MNIST).

Global Navigation Satellite Systems typically perform poorly in urban environments, where the likelihood of line-of-sight conditions between devices and satellites is low. Therefore, alternative location methods are required to achieve good accuracy. We present LocUNet: A convolutional, end-to-end trained neural network (NN) for the localization task, which is able to estimate the position of a user from the received signal strength (RSS) of a small number of Base Stations (BS). Using estimations of pathloss radio maps of the BSs and the RSS measurements of the users to be localized, LocUNet can localize users with state-of-the-art accuracy and enjoys high robustness to inaccuracies in the estimations of radio maps. The proposed method does not require generating RSS fingerprints of each specific area where the localization task is performed and is suitable for real-time applications. Moreover, two novel datasets that allow for numerical evaluations of RSS and ToA methods in realistic urban environments are presented and made publicly available for the research community. By using these datasets, we also provide a fair comparison of state-of-the-art RSS and ToA-based methods in the dense urban scenario and show numerically that LocUNet outperforms all the compared methods. Ron Levie is with the Faculty of Mathematics, Technion - Israel Institute of Technology, 3200003 Haifa, Israel (e-mail: levieron@technion.ac.il). Gitta Kutyniok is with the Department of Mathematics, LMU Munich, 80331 München, Germany, and also with the Department of Physics and Technology, University of Tromsø, 9019 Tromsø, Norway (e-mail: kutyniok@math.lmu.de). Giuseppe Caire is with the Institute of Telecommunication Systems, TU Berlin, 10623 Berlin, Germany (e-mail: caire@tuberlin.de). A short version of this paper was presented in the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2022) in Singapore [1]. The location information of a User Equipment (UE) is essential for many current and envisioned applications that range from emergency 911 services [2], autonomous driving [3], intelligent transportation systems [4], proof of witness presence [5], 5G networks [6], to social networks, asset tracking and advertising [7], just to name a few. In urban environments, Global Navigation Satellite Systems (GNSS) alone may fail to provide a reliable localization estimate due to the lack of line-of-sight conditions between the UE and the GNSS satellites [8]. In addition, the continuous reception and detection of GNSS signals is one of the dominating factors in battery consumption for hand-held devices.

MANET is a collection of mobile nodes that communicate through wireless networks as they move from one point to another. MANET is an infrastructure-less network with a changeable topology; as a result, it is very susceptible to attacks. MANET attack prevention represents a serious difficulty. Malicious network nodes are the source of network-based attacks. In a MANET, attacks can take various forms, and each one alters the network's operation in its unique way. In general, attacks can be separated into two categories: those that target the data traffic on a network and those that target the control traffic. This article explains the many sorts of assaults, their impact on MANET, and the MANET-based defence measures that are currently in place. The suggested SRA that employs blockchain technology (SRABC) protects MANET from attacks and authenticates nodes. The secure routing algorithm (SRA) proposed by blockchain technology safeguards control and data flow against threats. This is achieved by generating a Hash Function for every transaction. We will begin by discussing the security of the MANET. This article's second section explores the role of blockchain in MANET security. In the third section, the SRA is described in connection with blockchain. In the fourth phase, PDR and Throughput are utilised to conduct an SRA review using Blockchain employing PDR and Throughput. The results suggest that the proposed technique enhances MANET security while concurrently decreasing delay. The performance of the proposed technique is analysed and compared to the routing protocols Q-AODV and DSR.

Graph convolutional network (GCN) has been successfully applied to capture global non-consecutive and long-distance semantic information for text classification. However, while GCN-based methods have shown promising results in offline evaluations, they commonly follow a seen-token-seen-document paradigm by constructing a fixed document-token graph and cannot make inferences on new documents. It is a challenge to deploy them in online systems to infer steaming text data. In this work, we present a continual GCN model (ContGCN) to generalize inferences from observed documents to unobserved documents. Concretely, we propose a new all-token-any-document paradigm to dynamically update the document-token graph in every batch during both the training and testing phases of an online system. Moreover, we design an occurrence memory module and a self-supervised contrastive learning objective to update ContGCN in a label-free manner. A 3-month A/B test on Huawei public opinion analysis system shows ContGCN achieves 8.86% performance gain compared with state-of-the-art methods. Offline experiments on five public datasets also show ContGCN can improve inference quality. The source code will be released at https://github.com/Jyonn/ContGCN.

With the advent of high-speed 5G mobile networks, enterprises are more easily positioned than ever with the opportunity to harness the convergence of telecommunications networks and the cloud. As one of the most prominent use cases to date, machine learning (ML) at the edge has allowed enterprises to deploy ML models closer to their end-customers to reduce latency and increase responsiveness of their applications. As an example, smart venue solutions can use near-real-time computer vision for crowd analytics over 5G networks, all while minimizing investment in on-premises hardware networking equipment. Retailers can deliver more frictionless experiences on the go with natural language processing (NLP), real-time recommendation systems, and fraud detection. Even ground and aerial robotics can use ML to unlock safer, more autonomous operations.