Research Outputs
Permanent URI for this communityhttps://hdl.handle.net/20.500.14288/2
Browse
16 results
Search Results
Publication Metadata only A phonetic classification for throat microphone enhancement(IEEE, 2014) N/A; Department of Computer Engineering; Turan, Mehmet Ali Tuğtekin; Erzin, Engin; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 34503In this analysis paper, we investigate the effect of phonetic clustering based on place and manner of articulation for the enhancement of throat-microphone speech through spectral envelope mapping. Place of articulation (PoA) and manner of articulation (MoA) dependent GMM-based spectral envelope mapping schemes have been investigated using the reflection coefficient representation of the linear prediction model. Reflection coefficients are expected to localize mapping performance within the concatenation of lossless tubes model of the vocal tract. In experimental studies, we evaluate spectral mapping performance within clusters of the PoA and MoA using the log-spectral distortion (LSD) and as function of reflection coefficient mapping using the mean-square error distance. Our findings indicate that highest degradations after the spectral mapping occur with stops and liquids of the MoA, and velar and alveolar classes of the PoA. The MoA classification attains higher improvements than the PoA classification.Publication Metadata only Affect burst recognition using multi-modal cues(IEEE Computer Society, 2014) N/A; N/A; Department of Computer Engineering; Department of Computer Engineering; Department of Computer Engineering; Türker, Bekir Berker; Marzban, Shabbir; Erzin, Engin; Yemez, Yücel; Sezgin, Tevfik Metin; PhD Student; Master Student; Faculty Member; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; College of Engineering; N/A; N/A; 34503; 107907; 18632Affect bursts, which are nonverbal expressions of emotions in conversations, play a critical role in analyzing affective states. Although there exist a number of methods on affect burst detection and recognition using only audio information, little effort has been spent for combining cues in a multi-modal setup. We suggest that facial gestures constitute a key component to characterize affect bursts, and hence have potential for more robust affect burst detection and recognition. We take a data-driven approach to characterize affect bursts using Hidden Markov Models (HMM), and employ a multimodal decision fusion scheme that combines cues from audio and facial gestures for classification of affect bursts. We demonstrate the contribution of facial gestures to affect burst recognition by conducting experiments on an audiovisual database which comprise speech and facial motion data belonging to various dyadic conversations.Publication Metadata only Data-driven anomaly detection in autonomous platoon(Institute of Electrical and Electronics Engineers (IEEE), 2018) N/A; Department of Electrical and Electronics Engineering; Department of Computer Engineering; Uçar, Seyhan; Ergen, Sinem Çöleri; Özkasap, Öznur; PhD Student; Faculty Member; Faculty Member; Department of Electrical and Electronics Engineering; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; 7211; 113507Technology brings autonomous vehicles into a reality where vehicles cruise themselves without human input. Vehicular platoon, on the other hand, is a group of autonomous vehicles that are organized into close proximity through wireless communication. In an autonomous platoon, vehicles cooperatively send data to each other to adjust their speed and distance to the leader, the first vehicle in the platoon. However, this cooperative data exchange can lead to security risks. A misbehaving platoon member could alter the data packets which may cause platoon instability. Therefore, identifying the modified packets has become an important requirement. In this paper, we investigate data-driven anomaly detection mechanisms for the autonomous platoon. We propose a novel statistical learning based technique to detect the modified packets and misbehaving vehicles. We demonstrate that the distance change to the leader would be sufficient to detect anomalies and misbehavior.Publication Metadata only Devoloping affordable tangible programming education applications using mobile vision(IEEE, 2021) N/A; Department of Computer Engineering; Sabuncuoğlu, Alpay; Sezgin, Tevfik Metin; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 18632Programming education has become an essential part of the primary and secondary school curriculum. Two main programming environment modalities, web-based visual programming applications and electronic cards, have become popular in curricular activities. Limiting the programming activities around these programming environments restricts education accessibility in socio-economically disadvantaged regions due to the need for an individual computer per student, lack of decent infrastructure, and high electronics prices. Effective, shared use of smartphones and tablets in programming education can provide equal opportunities. in this scenario, students can code simple drawings and animations using their own materials as tangible programming blocks by employing a single shared phone in the classroom as an interpreter. This article explains our development process of a new tangible programming environment which increases the accessibility of education. We discuss effective inclassroom use of image/text processing practices and transfer learning methods on smartphones.Publication Metadata only Dual channel visible light communications for enhanced vehicular connectivity(IEEE Computer Society, 2016) N/A; N/A; Department of Electrical and Electronics Engineering; Department of Computer Engineering; Turan, Buğra; Uçar, Seyhan; Ergen, Sinem Çöleri; Özkasap, Öznur; PhD Student; PhD Student; Faculty Member; Faculty Member; Department of Electrical and Electronics Engineering; Department of Computer Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; N/A; 7211; 113507Visible Light Communication (VLC) has recently been proposed as a low-cost and low-complexity technology for vehicular communications. In this paper, we propose the usage of dual channel VLC with the goal of providing enhanced vehicular connectivity to disseminate safety-critical messages and perform an experimental study to determine the spatial and angular limits of an off-the-shelf automotive Light Emitting Diode (LED) fog light. Single channel VLC refers to the independent transmission of different data packets from each LED fog light, while the dual channel VLC offers the concurrent transmission of the same data packet from both lights. There is a trade-off between increasing the angular limitation and the performance of dual channel VLC, which needs to be experimentally evaluated to identify its efficient usage. We first show the dependency of the received optical power of single channel VLC on the angle and distance, and demonstrate that Lambertian model does not represent the automotive LED fog light radiation pattern accurately. We then demonstrate that dual channel usage increases the angular limitation by up to 10° compared to the single channel VLC. We also show that dual channel improves the packet delivery error rate performance at only short distances due to the photodiode (PD) saturation led by light intensity overlapping at higher distances.Publication Metadata only EdgeKV: distributed key-value store for the network edge(IEEE, 2020) Al Oqily, Ibrahim; Aloqaily, Moayad; N/A; Department of Computer Engineering; Sonbol, Karim; Özkasap, Öznur; Master Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 113507With improvements in computation and storage resources, data access through the network becomes the bottleneck for several cloud applications. Even with high-speed networks, the high latency of the cloud access makes it unfeasible or unfavourable for latency-sensitive applications such as autonomous driving, smart factories, and video streaming. Edge computing provides a solution by utilizing the network edge resources that are closer to the end users. Nevertheless, it is a non-trivial task to design a large-scale edge-capable system that is stable, fault-tolerant, and efficient [1]. In this paper, present the design of EdgeKV: a novel general-purpose distributed key-value store for the network edge. We demonstrate the features of EdgeKV for achieving high efficiency and scalability while providing flexibility, ease of use, and data privacy. We evaluated our prototype on the Grid'5000 framework with multiple realistic Yahoo! Cloud Serving Benchmark (YCSB) workloads. Our initial results show that EdgeKV achieves 72% higher throughput and 47% lower latency on average than centralized cloud storage, for read-dominated workloads.Publication Metadata only Food intake detection using autoencoder-based deep neural networks(Institute of Electrical and Electronics Engineers (IEEE), 2018) N/A; Department of Computer Engineering; Turan, Mehmet Ali Tuğtekin; Erzin, Engin; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 34503Wearable systems have the potential to reduce bias and inaccuracy in current dietary monitoring methods. The analysis of food intake sounds provides important guidance for developing an automated diet monitoring system. Most of the attempts in recent years can be ragarded as impractical due to the need for multiple sensors that specialize in swallowing or chewing detection separately. In this study, we provide a unified system for detecting swallowing and chewing activities with a laryngeal microphone placed on the neck, as well as some daily activities such as speech, coughing or throat clearing. Our proposed system is trained on the dataset containing 10 different food items collected from 8 subjects. The spectrograms, which are extracted from the 276 minute records in total, are fed into a deep autoencoder architecture. In the three-class evaluations (chewing, swallowing and rest), we achieve 71.7% of the F-score and 76.3% of the accuracy. These results provide a promising contribution to an automated food monitoring system that will be developed under everyday conditions.Publication Metadata only IEEE 802.11p and visible light hybrid communication based secure autonomous platoon(IEEE-Inst Electrical Electronics Engineers Inc, 2018) N/A; Department of Electrical and Electronics Engineering; Department of Computer Engineering; Uçar, Seyhan; Ergen, Sinem Çöleri; Özkasap, Öznur; PhD Student; Faculty Member; Faculty Member; Department of Electrical and Electronics Engineering; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; 7211; 113507Autonomous vehicle platoon is an enhancement of autonomous behavior, where vehicles are organized into groups of close proximity through wireless communication. Platoon members mostly communicate with each other via the current dominant vehicular radio frequency (RF) technology, IEEE 802.11p. However, this technology leads security vulnerabilities under various attacks from adversaries. Visible light communication (VLC) has the potential to alleviate these vulnerabilities by exploiting the directivity and impermeability of light. Utilizing only VLC in vehicle platoon, on the other hand, may degrade platoon stability since VLC is sensitive to environmental effects. In this paper, we propose an IEEE 802.11p and VLC-based hybrid security protocol for platoon communication, namely SP-VLC, with the goal of ensuring platoon stability and securing platoon maneuvers under data packet injection, channel overhearing, jamming, and platoon maneuver attacks. We define platoon maneuver attack based on the identification of various scenarios where a fakemaneuver packet is transmitted by amalicious actor. SP-VLC includesmechanisms for the secret key establishment, message authentication, data transmission over both IEEE 802.11p and VLC, jamming detection and reaction to switch to VLC only communication and secure platoon maneuvering based on the joint usage of IEEE 802.11p and VLC. We develop a simulation platform combining realistic vehicle mobility model, realistic VLC and IEEE 802.11p channel models, and vehicle platoon management. We show the functionality of the SP-VLC protocol under all possible security attacks by performing extensive simulations. Ourfindings demonstrate that SP-VLC protocol generates less than 0.1% difference in the speed of and distance between platoon members during security attacks in comparison to 25% and 10% in that of previously proposed IEEE 802.11p and IEEE 802.11p-VLC hybrid protocols, respectively.Publication Metadata only Learning to follow verbal instructions with visual grounding(Institute of Electrical and Electronics Engineers (IEEE), 2019) Department of Electrical and Electronics Engineering; N/A; Department of Computer Engineering; Ünal, Emre; Can, Ozan Arkan; Yemez, Yücel; Other; PhD Student; Faculty Member; Department of Electrical and Electronics Engineering; Department of Computer Engineering; College of Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; N/A; 107907We present a visually grounded deep learning model towards a virtual robot that can follow navigational instructions. Our model is capable of processing raw visual input and natural text instructions. The aim is to develop a model that can learn to follow novel instructions from instruction-perception examples. The proposed model is trained on data collected in a synthetic environment and its architecture allows it to work also with real visual data. We show that our results are on par with the previously proposed methods.Publication Metadata only Multihop-cluster-based IEEE 802.11p and LTE hybrid architecture for VANET safety message dissemination(Institute of Electrical and Electronics Engineers (IEEE), 2016) N/A; N/A; Department of Electrical and Electronics Engineering; Department of Computer Engineering; Uçar, Seyhan; Ergen, Sinem Çöleri; Özkasap, Öznur; PhD Student; Faculty Member; Faculty Member; Department of Electrical and Electronics Engineering; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; N/A; 7211; 113507Several vehicular ad hoc network (VANET) studies have focused on communication methods based on IEEE 802.11p, which forms the standard for wireless access for vehicular environments. In networks employing IEEE 802.11p only, the broadcast storm and disconnected network problems at high and low vehicle densities, respectively, degrade the delay and delivery ratio of safety message dissemination. Recently, as an alternative to the IEEE 802.11p-based VANET, the usage of cellular technologies has been investigated due to their low latency and wide-range communication. However, a pure cellular-based VANET communication is not feasible due to the high cost of communication between the vehicles and the base stations and the high number of handoff occurrences at the base station, considering the high mobility of the vehicles. This paper proposes a hybrid architecture, namely, VMaSC-LTE, combining IEEE 802.11p-based multihop clustering and the fourth-generation (4G) cellular system, i.e., Long-Term Evolution (LTE), with the goal of achieving a high data packet delivery ratio (DPDR) and low delay while keeping the usage of the cellular architecture at a minimum level. In VMaSC-LTE, vehicles are clustered based on a novel approach named Vehicular Multihop algorithm for Stable Clustering (VMaSC). The features of VMaSC are cluster head (CH) selection using the relative mobility metric calculated as the average relative speed with respect to the neighboring vehicles, cluster connection with minimum overhead by introducing a direct connection to the neighbor that is already a head or a member of a cluster instead of connecting to the CH in multiple hops, disseminating cluster member information within periodic hello packets, reactive clustering to maintain the cluster structure without excessive consumption of network resources, and efficient size-and hop-limited cluster merging mechanism based on the exchange of cluster information among CHs. These features decrease the number of CHs while increasing their stability, therefore minimizing the usage of the cellular architecture. From the clustered topology, elected CHs operate as dual-interface nodes with the functionality of the IEEE 802.11p and LTE interface to link the VANET to the LTE network. Using various key metrics of interest, including DPDR, delay, control overhead, and clustering stability, we demonstrate the superior performance of the proposed architecture compared with both previously proposed hybrid architectures and alternative routing mechanisms, including flooding and cluster-based routing via extensive simulations in ns-3 with the vehicle mobility input from the Simulation of Urban Mobility. The proposed architecture also allows achieving higher required reliability of the application quantified by the DPDR at the cost of higher LTE usage measured by the number of CHs in the network.