COPS: A Compact On-device Pipeline for real-time Smishing detection

Smartphones have become indispensable in our daily lives and can do almost everything, from communication to online shopping. However, with the increased usage, cybercrime aimed at mobile devices is rocketing. Smishing attacks, in particular, have observed a significant upsurge in recent years. This problem is further exacerbated by the perpetrator creating new deceptive websites daily, with an average life cycle of under 15 hours. This renders the standard practice of keeping a database of malicious URLs ineffective. To this end, we propose a novel on-device pipeline: COPS that intelligently identifies features of fraudulent messages and URLs to alert the user in real-time. COPS is a lightweight pipeline with a detection module based on the Disentangled Variational Autoencoder of size 3.46MB for smishing and URL phishing detection, and we benchmark it on open datasets. We achieve an accuracy of 98.15% and 99.5%, respectively, for both tasks, with a false negative and false positive rate of a mere 0.037 and 0.015, outperforming previous works with the added advantage of ensuring real-time alerts on resource-constrained devices.

ML-based PBCH symbol detection and equalization for 5G Non-Terrestrial Networks

This paper delves into the application of Machine Learning (ML) techniques in the realm of 5G Non-Terrestrial Networks (5G-NTN), particularly focusing on symbol detection and equalization for the Physical Broadcast Channel (PBCH). As 5G-NTN gains prominence within the 3GPP ecosystem, ML offers significant potential to enhance wireless communication performance. To investigate these possibilities, we present ML-based models trained with both synthetic and real data from a real 5G over-the-satellite testbed. Our analysis includes examining the performance of these models under various Signal-to-Noise Ratio (SNR) scenarios and evaluating their effectiveness in symbol enhancement and channel equalization tasks. The results highlight the ML performance in controlled settings and their adaptability to real-world challenges, shedding light on the potential benefits of the application of ML in 5G-NTN.

WEARS: Wearable Emotion AI with Real-time Sensor data

Emotion prediction is the field of study to understand human emotions. Existing methods focus on modalities like text, audio, facial expressions, etc., which could be private to the user. Emotion can be derived from the subject's psychological data as well. Various approaches that employ combinations of physiological sensors for emotion recognition have been proposed. Yet, not all sensors are simple to use and handy for individuals in their daily lives. Thus, we propose a system to predict user emotion using smartwatch sensors. We design a framework to collect ground truth in real-time utilizing a mix of English and regional language-based videos to invoke emotions in participants and collect the data. Further, we modeled the problem as binary classification due to the limited dataset size and experimented with multiple machine-learning models. We also did an ablation study to understand the impact of features including Heart Rate, Accelerometer, and Gyroscope sensor data on mood. From the experimental results, Multi-Layer Perceptron has shown a maximum accuracy of 93.75 percent for pleasant-unpleasant (high/low valence classification) moods.

Adaptive Timers and Buffer Optimization for Layer-2 Protocols in 5G Non-Terrestrial Networks

Interest in the integration of Terrestrial Networks (TN) and Non-Terrestrial Networks (NTN); primarily satellites; has been rekindled due to the potential of NTN to provide ubiquitous coverage. Especially with the peculiar and flexible physical layer properties of 5G-NR, now direct access to 5G services through satellites could become possible. However, the large Round-Trip Delays (RTD) in NTNs require a re-evaluation of the design of RLC and PDCP layers timers ( and associated buffers), in particular for the regenerative payload satellites which have limited computational resources, and hence need to be optimally utilized. Our aim in this work is to initiate a new line of research for emerging NTNs with limited resources from a higher-layer perspective. To this end, we propose a novel and efficient method for optimally designing the RLC and PDCP layers' buffers and timers without the need for intensive computations. This approach is relevant for low-cost satellites, which have limited computational and energy resources. The simulation results show that the proposed methods can significantly improve the performance in terms of resource utilization and delays.

IRS Assisted MIMO Full Duplex: Rate Analysis and Beamforming Under Imperfect CSI

Intelligent reflecting surfaces (IRS) have emerged as a promising technology to enhance the performance of wireless communication systems. By actively manipulating the wireless propagation environment, IRS enables efficient signal transmission and reception. In recent years, the integration of IRS with full-duplex (FD) communication has garnered significant attention due to its potential to further improve spectral and energy efficiencies. IRS-assisted FD systems combine the benefits of both IRS and FD technologies, providing a powerful solution for the next generation of cellular systems. In this manuscript, we present a novel approach to jointly optimize active and passive beamforming in a multiple-input-multiple-output (MIMO) FD system assisted by an IRS for weighted sum rate (WSR) maximization. Given the inherent difficulty in obtaining perfect channel state information (CSI) in practical scenarios, we consider imperfect CSI and propose a statistically robust beamforming strategy to maximize the ergodic WSR. Additionally, we analyze the achievable WSR for an IRS-assisted MIMO FD system under imperfect CSI by deriving both the lower and upper bounds. To tackle the problem of ergodic WSR maximization, we employ the concept of expected weighted minimum mean squared error (EWMMSE), which exploits the information of the expected error covariance matrices and ensures convergence to a local optimum. We evaluate the effectiveness of our proposed design through extensive simulations. The results demonstrate that our robust approach yields significant performance improvements compared to the simplistic beamforming approach that disregards CSI errors, while also outperforming the robust half-duplex (HD) system considerably

Robust Beamforming for IRS Aided MIMO Full Duplex Systems

In this paper, a novel robust beamforming for an intelligent reflecting surface (IRS) assisted FD system is presented. Since perfect channel state information (CSI) is often challenging to acquire in practice, we consider the case of imperfect CSI and adopt a statistically robust beamforming approach to maximize the ergodic weighted sum rate (WSR). We also analyze the achievable WSR of an IRS-assisted FD with imperfect CSI, for which the lower and the upper bounds are derived. The ergodic WSR maximization problem is tackled based on the expected Weighted Minimum Mean Squared Error (WMMSE), which is guaranteed to converge to a local optimum. The effectiveness of the proposed design is investigated with extensive simulation results. It is shown that our robust design achieves significant performance gain compared to the naive beamforming approaches and considerably outperforms the robust Half-Duplex (HD) system.

SeLiNet: Sentiment enriched Lightweight Network for Emotion Recognition in Images

In this paper, we propose a sentiment-enriched lightweight network SeLiNet and an end-to-end on-device pipeline for contextual emotion recognition in images. SeLiNet model consists of body feature extractor, image aesthetics feature extractor, and learning-based fusion network which jointly estimates discrete emotion and human sentiments tasks. On the EMOTIC dataset, the proposed approach achieves an Average Precision (AP) score of 27.17 in comparison to the baseline AP score of 27.38 while reducing the model size by >85%. In addition, we report an on-device AP score of 26.42 with reduction in model size by >93% when compared to the baseline.

Optimization for truss design using Bayesian optimization

In this work, geometry optimization of mechanical truss using computer-aided finite element analysis is presented. The shape of the truss is a dominant factor in determining the capacity of load it can bear. At a given parameter space, our goal is to find the parameters of a hull that maximize the load-bearing capacity and also don't yield to the induced stress. We rely on finite element analysis, which is a computationally costly design analysis tool for design evaluation. For such expensive to-evaluate functions, we chose Bayesian optimization as our optimization framework which has empirically proven sample efficient than other simulation-based optimization methods. By utilizing Bayesian optimization algorithms, the truss design involves iteratively evaluating a set of candidate truss designs and updating a probabilistic model of the design space based on the results. The model is used to predict the performance of each candidate design, and the next candidate design is selected based on the prediction and an acquisition function that balances exploration and exploitation of the design space. Our result can be used as a baseline for future study on AI-based optimization in expensive engineering domains especially in finite element Analysis.

LEAN: Light and Efficient Audio Classification Network

Over the past few years, audio classification task on large-scale dataset such as AudioSet has been an important research area. Several deeper Convolution-based Neural networks have shown compelling performance notably Vggish, YAMNet, and Pretrained Audio Neural Network (PANN). These models are available as pretrained architecture for transfer learning as well as specific audio task adoption. In this paper, we propose a lightweight on-device deep learning-based model for audio classification, LEAN. LEAN consists of a raw waveform-based temporal feature extractor called as Wave Encoder and logmel-based Pretrained YAMNet. We show that using a combination of trainable wave encoder, Pretrained YAMNet along with cross attention-based temporal realignment, results in competitive performance on downstream audio classification tasks with lesser memory footprints and hence making it suitable for resource constraints devices such as mobile, edge devices, etc . Our proposed system achieves on-device mean average precision(mAP) of .445 with a memory footprint of a mere 4.5MB on the FSD50K dataset which is an improvement of 22% over baseline on-device mAP on same dataset.

Malaria detection using Deep Convolution Neural Network

The latest WHO report showed that the number of malaria cases climbed to 219 million last year, two million higher than last year. The global efforts to fight malaria have hit a plateau and the most significant underlying reason is international funding has declined. Malaria, which is spread to people through the bites of infected female mosquitoes, occurs in 91 countries but about 90% of the cases and deaths are in sub-Saharan Africa. The disease killed 4,35,000 people last year, the majority of them children under five in Africa. AI-backed technology has revolutionized malaria detection in some regions of Africa and the future impact of such work can be revolutionary. The malaria Cell Image Data-set is taken from the official NIH Website NIH data. The aim of the collection of the dataset was to reduce the burden for microscopists in resource-constrained regions and improve diagnostic accuracy using an AI-based algorithm to detect and segment the red blood cells. The goal of this work is to show that the state of the art accuracy can be obtained even by using 2 layer convolution network and show a new baseline in Malaria detection efforts using AI.