Search

Parkinson's disease (PD) is a progressive neurodegenerative disorder that impacts motor functions and speech characteristics This study focuses on differentiating individuals with Parkinson's disease from healthy controls through the extraction and classification of speech features. Patients were further divided into 2 groups. Med On represents the patient with medication, while Med Off represents the patient without medication. The dataset consisted of patients and healthy individuals who read a predefined text using the H1N Zoom microphone in a suitable recording environment at F{\i}rat University Neurology Department. Speech recordings from PD patients and healthy controls were analyzed, and 19 key features were extracted, including jitter, luminance, zero-crossing rate (ZCR), root mean square (RMS) energy, entropy, skewness, and kurtosis.These features were visualized in graphs and statistically evaluated to identify distinctive patterns in PD patients. Using MATLAB's Classification Learner toolbox, several machine learning classification algorithm models were applied to classify groups and significant accuracy rates were achieved. The accuracy of our 3-layer artificial neural network architecture was also compared with classical machine learning algorithms. This study highlights the potential of noninvasive voice analysis combined with machine learning for early detection and monitoring of PD patients. Future research can improve diagnostic accuracy by optimizing feature selection and exploring advanced classification techniques., Comment: Presented at the 13th International Marmara Science Congress (IMASCON 2024)

Artificial intelligence (AI) is expected to significantly enhance radio resource management (RRM) in sixth-generation (6G) networks. However, the lack of explainability in complex deep learning (DL) models poses a challenge for practical implementation. This paper proposes a novel explainable AI (XAI)- based framework for feature selection and model complexity reduction in a model-agnostic manner. Applied to a multi-agent deep reinforcement learning (MADRL) setting, our approach addresses the joint sub-band assignment and power allocation problem in cellular vehicle-to-everything (V2X) communications. We propose a novel two-stage systematic explainability framework leveraging feature relevance-oriented XAI to simplify the DRL agents. While the former stage generates a state feature importance ranking of the trained models using Shapley additive explanations (SHAP)-based importance scores, the latter stage exploits these importance-based rankings to simplify the state space of the agents by removing the least important features from the model input. Simulation results demonstrate that the XAI-assisted methodology achieves 97% of the original MADRL sum-rate performance while reducing optimal state features by 28%, average training time by 11%, and trainable weight parameters by 46% in a network with eight vehicular pairs.

Integrated sensing and communication (ISAC) has emerged as a transformative paradigm, enabling situationally aware and perceptive next-generation wireless networks through the co-design of shared network resources. With the adoption of millimeter-wave (mmWave) and terahertz (THz) frequency bands, ultra-massive MIMO (UM-MIMO) systems and holographic surfaces unlock the potential of near-field (NF) propagation, characterized by spherical wavefronts that facilitate beam manipulation in both angular and range domains. This paper presents a unified approach to near-field beam-training and sensing, introducing a dual-purpose codebook design that employs discrete Fourier transform (DFT)-based codebooks for coarse estimation of sensing parameters and polar codebooks for parameter refinement. Leveraging these range and angle estimates, a customized low-complexity space-time adaptive processing (STAP) technique is proposed for NF-ISAC to detect slow-moving targets and efficiently mitigate clutter. The interplay between codebooks and NF-STAP framework offers three key advantages: reduced communication beam training overhead, improved estimation accuracy, and minimal STAP computational complexity. Simulation results show that the proposed framework can reduce STAP complexity by three orders of magnitude, validating efficacy, and highlighting the potential of the proposed approach to seamlessly integrate NF communication and sensing functionalities in future wireless networks.

The design and performance analysis of relay lenses that provide high-performance image transmission for target acquisition and tracking in military optical systems. Relay lenses are critical components for clear and lossless image transmission over long distances. In this study, the optical performance of a relay lens system designed and optimized using ZEMAX software is investigated in detail. The analysis focuses on important optical properties such as modulation transfer function (MTF), spot diagrams, Seidel diagram, field curvature and distortion. The results show that the lens has significant potential in military applications for target detection and tracking with high resolution and low aberration.

Citations are essential building blocks in scientific writing. The scientific community is longing for support in their generation. Citation generation involves two complementary subtasks: Determining the citation worthiness of a context and, if it's worth it, proposing the best candidate papers for the citation placeholder. The latter subtask is called local citation recommendation (LCR). This paper proposes CiteBART, a custom BART pre-training based on citation token masking to generate citations to achieve LCR. In the base scheme, we mask the citation token in the local citation context to make the citation prediction. In the global one, we concatenate the citing paper's title and abstract to the local citation context to learn to reconstruct the citation token. CiteBART outperforms state-of-the-art approaches on the citation recommendation benchmarks except for the smallest FullTextPeerRead dataset. The effect is significant in the larger benchmarks, e.g., Refseer and ArXiv. We present a qualitative analysis and an ablation study to provide insights into the workings of CiteBART. Our analyses confirm that its generative nature brings about a zero-shot capability., Comment: 15 pages, 2 figures, 7 tables

Language model approaches have recently been integrated into binary analysis tasks, such as function similarity detection and function signature recovery. These models typically employ a two-stage training process: pre-training via Masked Language Modeling (MLM) on machine code and fine-tuning for specific tasks. While MLM helps to understand binary code structures, it ignores essential code characteristics, including control and data flow, which negatively affect model generalization. Recent work leverages domain-specific features (e.g., control flow graphs and dynamic execution traces) in transformer-based approaches to improve binary code semantic understanding. However, this approach involves complex feature engineering, a cumbersome and time-consuming process that can introduce predictive uncertainty when dealing with stripped or obfuscated code, leading to a performance drop. In this paper, we introduce ProTST, a novel transformer-based methodology for binary code embedding. ProTST employs a hierarchical training process based on a unique tree-like structure, where knowledge progressively flows from fundamental tasks at the root to more specialized tasks at the leaves. This progressive teacher-student paradigm allows the model to build upon previously learned knowledge, resulting in high-quality embeddings that can be effectively leveraged for diverse downstream binary analysis tasks. The effectiveness of ProTST is evaluated in seven binary analysis tasks, and the results show that ProTST yields an average validation score (F1, MRR, and Recall@1) improvement of 14.8% compared to traditional two-stage training and an average validation score of 10.7% compared to multimodal two-stage frameworks.

The transition to 6G networks promises unprecedented advancements in wireless communication, with increased data rates, ultra-low latency, and enhanced capacity. However, the complexity of managing and optimizing these next-generation networks presents significant challenges. The advent of large language models (LLMs) has revolutionized various domains by leveraging their sophisticated natural language understanding capabilities. However, the practical application of LLMs in wireless network orchestration and management remains largely unexplored. Existing literature predominantly offers visionary perspectives without concrete implementations, leaving a significant gap in the field. To address this gap, this paper presents NETORCHLLM, a wireless NETwork ORCHestrator LLM framework that uses LLMs to seamlessly orchestrate diverse wireless-specific models from wireless communication communities using their language understanding and generation capabilities. A comprehensive framework is introduced, demonstrating the practical viability of our approach and showcasing how LLMs can be effectively harnessed to optimize dense network operations, manage dynamic environments, and improve overall network performance. NETORCHLLM bridges the theoretical aspirations of prior research with practical, actionable solutions, paving the way for future advancements in integrating generative AI technologies within the wireless communications sector.

Detecting Beyond Standard Model (BSM) signals in high-energy particle collisions presents significant challenges due to complex data and the need to differentiate rare signal events from Standard Model (SM) backgrounds. This study investigates the efficacy of deep learning models, specifically Deep Neural Networks (DNNs) and Graph Neural Networks (GNNs), in classifying particle collision events as either BSM signal or background. The research utilized a dataset comprising 214,000 SM background and 10,755 BSM events. To address class imbalance, an undersampling method was employed, resulting in balanced classes. Three models were developed and compared: a DNN and two GNN variants with different graph construction methods. All models demonstrated high performance, achieving Area Under the Receiver Operating Characteristic curve (AUC) values exceeding $94\%$. While the DNN model slightly outperformed GNNs across various metrics, both GNN approaches showed comparable results despite different graph structures. The GNNs' ability to explicitly capture inter-particle relationships within events highlights their potential for BSM signal detection., Comment: Accepted for publication in APPB

Introduction: Circadian rhythm disruption has garnered significant attention for its adverse effects on human health, particularly in reproductive medicine and fetal well-being. Assessing pregnancy health often relies on diagnostic markers such as the labyrinth zone (LZ) proportion within the placenta. This study aimed to investigate the impact of disrupted circadian rhythms on placental health and fetal development using animal models. Methods and Results: Employing unstained photo-acoustic microscopy (PAM) and hematoxylin and eosin (HE)-stained images, we found them mutually reinforcing. Our images revealed the role of MCRD on the LZ and fetus weight: a decrease in LZ area from 5.01-HE(4.25-PAM) mm2 to 3.58-HE (2.62-PAM) mm2 on day 16 and 6.48-HE(5.16-PAM) mm2 to 4.61-HE (3.03-PAM) mm2 on day 18, resulting in 0.71 times lower fetus weights. We have discriminated a decrease in the mean LZ to placenta area ratio from 64% to 47% on day 18 in mice with disrupted circadian rhythms with PAM. Discussion: The study highlights the negative influence of circadian rhythm disruption on placental development and fetal well-being. Reduced LZ area and fetal weights in the MCRD group suggest compromised placental function under disrupted circadian rhythms. PAM imaging proved to be an efficient technique for assessing placental development, offering advantages over traditional staining methods. These findings contribute to understanding the mechanisms underlying circadian disruption's effects on reproductive health and fetal development, emphasizing the importance of maintaining normal circadian rhythms for optimal pregnancy outcomes. Further research is needed to explore interventions to mitigate these effects and improve pregnancy outcomes., Comment: 9 pages, 3 figures

Integrated sensing and communications (ISAC) has emerged as a means to efficiently utilize spectrum and thereby save cost and power. At the higher end of the spectrum, ISAC systems operate at wideband using large antenna arrays to meet the stringent demands for high-resolution sensing and enhanced communications capacity. On the other hand, the overall design should satisfy energy-efficiency and hardware constraints such as operating on low resolution components for a practical scenario. Therefore, this paper presents the design of Hybrid ANalog and Digital BeAmformers with Low resoLution (HANDBALL) digital-to-analog converters (DACs). We introduce a greedy-search-based approach to design the analog beamformers for multi-user multi-target ISAC scenario. Then, the quantization distortion is taken into account in order to design the baseband beamformer with low resolution DACs. We evaluated performance of the proposed HANDBALL technique in terms of both spectral efficiency and sensing beampattern, providing a satisfactory sensing and communication performance for both one-bit and few-bit designs., Comment: Accepted Paper in IEEE Wireless Communications Letters

Large-scale cell microscopy screens are used in drug discovery and molecular biology research to study the effects of millions of chemical and genetic perturbations on cells. To use these images in downstream analysis, we need models that can map each image into a feature space that represents diverse biological phenotypes consistently, in the sense that perturbations with similar biological effects have similar representations. In this work, we present the largest foundation model for cell microscopy data to date, a new 1.9 billion-parameter ViT-G/8 MAE trained on over 8 billion microscopy image crops. Compared to a previous published ViT-L/8 MAE, our new model achieves a 60% improvement in linear separability of genetic perturbations and obtains the best overall performance on whole-genome biological relationship recall and replicate consistency benchmarks. Beyond scaling, we developed two key methods that improve performance: (1) training on a curated and diverse dataset; and, (2) using biologically motivated linear probing tasks to search across each transformer block for the best candidate representation of whole-genome screens. We find that many self-supervised vision transformers, pretrained on either natural or microscopy images, yield significantly more biologically meaningful representations of microscopy images in their intermediate blocks than in their typically used final blocks. More broadly, our approach and results provide insights toward a general strategy for successfully building foundation models for large-scale biological data., Comment: NeurIPS 2024 Foundation Models for Science Workshop (38th Conference on Neural Information Processing Systems). 18 pages, 7 figures

In 2021, Dan Reznik made a YouTube video demonstrating that power circles of Poncelet triangles have an invariant total area. He made a simulation based on this observation and put forward a few conjectures. One of these conjectures suggests that the sum of the areas of three circles, each centered at the midpoint of a side of the Poncelet triangle and passing through the opposite vertex, remains constant. In this paper, we provide a proof of Reznik's conjecture and present a formula for calculating the total sum. Additionally, we demonstrate the algebraic structures formed by various sets of products and the geometric properties of polygons and ellipses created by these products., Comment: 13 pages. This article was written as part of the Polymath Jr. program in the summer of 2022

Large language models (LLMs) hold significant promise in advancing network management and orchestration in 6G and beyond networks. However, existing LLMs are limited in domain-specific knowledge and their ability to handle multi-modal sensory data, which is critical for real-time situational awareness in dynamic wireless environments. This paper addresses this gap by introducing ENWAR, an ENvironment-aWARe retrieval augmented generation-empowered multi-modal LLM framework. ENWAR seamlessly integrates multi-modal sensory inputs to perceive, interpret, and cognitively process complex wireless environments to provide human-interpretable situational awareness. ENWAR is evaluated on the GPS, LiDAR, and camera modality combinations of DeepSense6G dataset with state-of-the-art LLMs such as Mistral-7b/8x7b and LLaMa3.1-8/70/405b. Compared to general and often superficial environmental descriptions of these vanilla LLMs, ENWAR delivers richer spatial analysis, accurately identifies positions, analyzes obstacles, and assesses line-of-sight between vehicles. Results show that ENWAR achieves key performance indicators of up to 70% relevancy, 55% context recall, 80% correctness, and 86% faithfulness, demonstrating its efficacy in multi-modal perception and interpretation.

There is a growing interest in integrating Large Language Models (LLMs) with autonomous driving (AD) systems. However, AD systems are vulnerable to attacks against their object detection and tracking (ODT) functions. Unfortunately, our evaluation of four recent LLM agents against ODT attacks shows that the attacks are 63.26% successful in causing them to crash or violate traffic rules due to (1) misleading memory modules that provide past experiences for decision making, (2) limitations of prompts in identifying inconsistencies, and (3) reliance on ground truth perception data. In this paper, we introduce Hudson, a driving reasoning agent that extends prior LLM-based driving systems to enable safer decision making during perception attacks while maintaining effectiveness under benign conditions. Hudson achieves this by first instrumenting the AD software to collect real-time perception results and contextual information from the driving scene. This data is then formalized into a domain-specific language (DSL). To guide the LLM in detecting and making safe control decisions during ODT attacks, Hudson translates the DSL into natural language, along with a list of custom attack detection instructions. Following query execution, Hudson analyzes the LLM's control decision to understand its causal reasoning process. We evaluate the effectiveness of Hudson using a proprietary LLM (GPT-4) and two open-source LLMs (Llama and Gemma) in various adversarial driving scenarios. GPT-4, Llama, and Gemma achieve, on average, an attack detection accuracy of 83. 3%, 63. 6%, and 73. 6%. Consequently, they make safe control decisions in 86.4%, 73.9%, and 80% of the attacks. Our results, following the growing interest in integrating LLMs into AD systems, highlight the strengths of LLMs and their potential to detect and mitigate ODT attacks.

High-level robot skills represent an increasingly popular paradigm in robot programming. However, configuring the skills' parameters for a specific task remains a manual and time-consuming endeavor. Existing approaches for learning or optimizing these parameters often require numerous real-world executions or do not work in dynamic environments. To address these challenges, we propose MuTT, a novel encoder-decoder transformer architecture designed to predict environment-aware executions of robot skills by integrating vision, trajectory, and robot skill parameters. Notably, we pioneer the fusion of vision and trajectory, introducing a novel trajectory projection. Furthermore, we illustrate MuTT's efficacy as a predictor when combined with a model-based robot skill optimizer. This approach facilitates the optimization of robot skill parameters for the current environment, without the need for real-world executions during optimization. Designed for compatibility with any representation of robot skills, MuTT demonstrates its versatility across three comprehensive experiments, showcasing superior performance across two different skill representations.

We numerically investigate the existence and stability dynamics of self-steepening optical solitons in a periodic PT-symmetric potential. We show that self-steepening solitons of the modified nonlinear Schr\"odinger (MNLS) equation undergo a position shift and amplitude increase during their evolution in the MNLS equation. The stabilization of solitons by an external potential is a challenging issue. This study demonstrates that the suppression of both the amplitude increase and the position shift of self-steepening solitons can be achieved by adding a periodic PT-symmetric potential to the MNLS equation.

This work introduces Variational Diffusion Distillation (VDD), a novel method that distills denoising diffusion policies into Mixtures of Experts (MoE) through variational inference. Diffusion Models are the current state-of-the-art in generative modeling due to their exceptional ability to accurately learn and represent complex, multi-modal distributions. This ability allows Diffusion Models to replicate the inherent diversity in human behavior, making them the preferred models in behavior learning such as Learning from Human Demonstrations (LfD). However, diffusion models come with some drawbacks, including the intractability of likelihoods and long inference times due to their iterative sampling process. The inference times, in particular, pose a significant challenge to real-time applications such as robot control. In contrast, MoEs effectively address the aforementioned issues while retaining the ability to represent complex distributions but are notoriously difficult to train. VDD is the first method that distills pre-trained diffusion models into MoE models, and hence, combines the expressiveness of Diffusion Models with the benefits of Mixture Models. Specifically, VDD leverages a decompositional upper bound of the variational objective that allows the training of each expert separately, resulting in a robust optimization scheme for MoEs. VDD demonstrates across nine complex behavior learning tasks, that it is able to: i) accurately distill complex distributions learned by the diffusion model, ii) outperform existing state-of-the-art distillation methods, and iii) surpass conventional methods for training MoE., Comment: Accepted by the 38th Annual Conference on Neural Information Processing Systems

This work presents Mamba Imitation Learning (MaIL), a novel imitation learning (IL) architecture that provides an alternative to state-of-the-art (SoTA) Transformer-based policies. MaIL leverages Mamba, a state-space model designed to selectively focus on key features of the data. While Transformers are highly effective in data-rich environments due to their dense attention mechanisms, they can struggle with smaller datasets, often leading to overfitting or suboptimal representation learning. In contrast, Mamba's architecture enhances representation learning efficiency by focusing on key features and reducing model complexity. This approach mitigates overfitting and enhances generalization, even when working with limited data. Extensive evaluations on the LIBERO benchmark demonstrate that MaIL consistently outperforms Transformers on all LIBERO tasks with limited data and matches their performance when the full dataset is available. Additionally, MaIL's effectiveness is validated through its superior performance in three real robot experiments. Our code is available at https://github.com/ALRhub/MaIL.

Integrated sensing and communications (ISAC) has emerged as a means to efficiently utilize spectrum and thereby save cost and power. At the higher end of the spectrum, ISAC systems operate at wideband using large antenna arrays to meet the stringent demands for high-resolution sensing and enhanced communications capacity. However, the wideband implementation entails beam-squint, that is, deviations in the generated beam directions because of the narrowband assumption in the analog components. This causes significant degradation in the communications capacity, target detection, and parameter estimation. This article presents the design challenges caused by beam-squint and its mitigation in ISAC systems. In this context, we also discuss several ISAC design perspectives including far-/near-field beamforming, channel/direction estimation, sparse array design, and index modulation. There are also several research opportunities in waveform design, beam training, and array processing to adequately address beam-squint in ISAC., Comment: Accepted Paper in IEEE Communications Magazine