Department Publications

Intraoperative PET-laparoscope system has been proposed to locate lymph node metastasis during gastric cancer surgery. The proposed system consists of an external detector array connected to a patient’s surgical bed and a movable detector probe which is inserted into the patient’s stomach along with a laparoscope. In this study a prototype detector for the PET-laparoscope system is presented with a pixelated movable detector probe tracked by an optical tracking system. Detector prototype reconstructed images of a 22 Na source with 3 mm spatial resolution in X (coronal) and Z (longitudinal) directions in a 2 min scan. The use of the pixelated multi-layer movable detector probe improved the spatial resolution of the system.

This research paper presents a novel track based stair-climbing wheelchair design with improved stability and performance. The proposed design has an adaptable arrangement to the staircase especially at the top of the staircase. In the existing wheelchair designs, this particular feature has not been adequately addressed. The proposed design consists of body frame and supporting rubber track arms. Of the two main operations; ascending and descending, the most critical operations is at the top of the staircase, which is smoothly controlled by following the staircase profile. This motion is achieved by properly synchronizing the rubber track arms according to a pre-planned motion profile. As a result, user does not feel sudden motions in position and attitude. Furthermore, the proposed wheelchair is adaptable to any staircase.

Network softwarization enables the novel concept of Local 5G Operator (L5GO) networks, for deploying localized 5G solutions to serve case and location specific communication needs. This paper proposes a L5GO network architecture for delay critical future telehealth services, considering two use cases on augmented reality assisted and robotic aided surgery. The paper compares the latency performance of the proposed L5GO architecture with a traditional legacy network and a network equipped with Multi-access Edge Computing (MEC). The results highlight the unique advantages of utilizing an L5GO to cater the communication needs of delay critical telehealth, compared to a traditional network.

We propose self-supervised deep algorithms to detect anomalies in heterogeneous autonomous systems using frontal camera video and IMU readings. Given that the video and IMU data are not synchronized, each of them are analyzed separately. The vision-based system, which utilizes a conditional GAN, analyzes immediate-past three frames and attempts to predict the next frame. The frame is classified as either an anomalous case or a normal case based on the degree of difference estimated using the prediction error and a threshold. The IMU-based system utilizes two approaches to classify the timestamps; the first being an LSTM autoencoder which reconstructs three consecutive IMU vectors and the second being an LSTM forecaster which is utilized to predict the next vector using the previous three IMU vectors. Based on the reconstruction error, the prediction error, and a threshold, the timestamp is classified as either an anomalous case or a normal case. The composition of algorithms won runners up at the IEEE Signal Processing Cup anomaly detection challenge 2020. In the competition dataset of camera frames consisting of both normal and anomalous cases, we achieve a test accuracy of 94% and an F1-score of 0.95. Furthermore, we achieve an accuracy of 100% on a test set containing normal IMU data, and an F1-score of 0.98 on the test set of abnormal IMU data.

Getting a team of robots to achieve a relatively complex task using manual manipulation through augmented reality (AR) is interesting. However, the true potential of such an approach manifests when the system can learn from humans. We propose a system comprising a team of robots that performs a previously unseen task—a variant, to be specific—by learning from the sequences of actions taken by multiple human beings doing this task in various ways using deep learning (DL). The training inputs can be through actual manipulation of the team of robots using an augmented-reality tablet or through a simulator. Results indicate that the system is able to fulfill the specified variant of the task more than 80% of the time, inaccuracies mainly owing to unrealistic specifications of tasks. This opens up an avenue of training a team of robots, instead of crafting a rule base.

The potential of drone based services is enormous with applications ranging from consumer product delivery to health services. When meeting this demand, one of the major challenges we face is the noise produced by drones, which not only contributes to listener discomfort, but also hinders the device's ability to effectively communicate via audio. Thus, there exists a pressing need for understanding the characteristics of drone related noise, which can then be suppressed using suitable methods. This paper presents a preliminary study on modeling the relationship between input motor current and acoustic noise produced by a drone. An experimental study is conducted indoors for a drone under hovering manoeuvre with a single active motor and propeller. The drone noise was measured by a single on-board microphone. We identify multiple tones or harmonics in the drone noise spectrum that vary proportionally …

A low-complexity codec and a hardware architecture are proposed for achieving real-time compression of four-dimensional (4-D) light field (LF) signals captured from camera/lenslet arrays. The proposed system employs the 4-D extension of the two-dimensional (2-D) 8×8 approximate discrete cosine transform (ADCT) that has recently appeared in the literature. Motivated by the partial separability of the multidimensional spectrum of LFs, the proposed 4-D ADCT is obtained by cascading 2-D inter-view and 2-D intra-view transform stages. Software simulations are provided to confirm the performance of the 4-D ADCT based compression and comparisons are made with respect to 2-D inter-view only and 2-D intra-view only ADCT-based compression. Proposed digital architectures are validated using stepped hardware co-simulation on a Xilinx Virtex-7 VC-707 FPGA platform verifying 597 MHz maximum possible …

The emergence of Industry 4.0 has resulted in a rapid increase in the demand for bandwidth due to the proliferation of the industrial Internet of Things (IIoT). Increased utilization of the network also gives rise to undesirable consequences such as high latency and increased likelihood of data loss through packet drops. Encoding inputs using event-based sampling is a potential solution for decreasing network traffic generated when continuous input variables are sampled. The problem addressed by this article is the fact that currently there is no effective method for comparing different encoders. The resulting contribution is the use of mutual information to compare the input and encoded output in terms of accuracy for the currently most efficient encoders that use either memory based event triggering (MBET) or deadband error modulation (DEM). This allows a practitioner to select a suitable encoder for a given input …

We present a novel low cost time-of-flight (ToF) sensor deck for micro UAVs capable of sparse range measurements for localisation and mapping. In disaster scenarios such as building collapses, the larger UAVs equipped with highfidelity sensors such as lidars, structured light cameras and stereo cameras to perceive the environment with high resolution, may have difficulties when navigating through cluttered confined spaces. Micro UAVs are ideal for providing vital data in the aftermath of a disaster scenario but does not have the payload capacity for such sensors. Miniature low cost ToF sensors can provide range measurements albeit with low range and resolution. The proposed solution includes the design and implementation of a novel sensing deck for a commercially available micro UAV with 13 miniature ToF sensors, a low resolution thermal camera and a method to generate reliable 2D maps of GPS denied areas. The sparse observations obtained from range sensors are combined in a Rao-Blackwellized particle filter to create a reliable map. The ToF sensors are arranged to capture a maximum number of points in the horizontal plane at the flying height despite fluctuations in altitude and orientation. Particle weighting and resampling are only performed in a loop closure or when moving through a known area. Importance weight for the particles are computed by an Iterative Closest Point based method by calculating the error between nearest scan points. The proposed method has been tested in indoor environments and verified as a robust method to generate reliable maps of unknown environments.

We consider the problem of determining Granger causal influences among sources that are indirectly observed through low-dimensional and noisy linear projections. Commonly used methods proceed in a two-stage fashion, by first solving an inverse problem to localize the sources, and then inferring the Granger causal influences from the estimated sources. The inferred Granger causal links thus inherit the various biases that are used in source localization techniques, in the form of spatiotemporal priors designed in favor of spatial localization. In addition, this approach does not account for the structural properties of the underlying functional networks such as sparsity of the links. We address these issues by modeling the source dynamics as sparse vector autoregressive processes and estimate the model parameters directly from the observations, with no recourse to intermediate source localization. We evaluate …

Estimating parameters and properties of various materials without causing damage to the material under test (MUT) is important in many applications. Thus, in this letter, we address MUT's parameter estimation by wireless sensing. Here, the precision of the estimation depends on the accurate estimation of the properties of the reflected signal from the MUT (e.g., number of reflections, their amplitudes, and time delays). For a layered MUT, there are multiple reflections, and due to the limited bandwidth at the receiver, these reflections superimpose with each other. Since the number of reflections coming from the MUT is limited, we utilize sparse signal processing (SSP) to decompose the reflected signal. In SSP, a so called dictionary is required to obtain a sparse representation of the signal. Here, instead of a fixed dictionary, an iterative dictionary-update technique is proposed to improve the estimation of the reflected …

This research paper presents a proof of concept for real-time teleoperation of a robotic arm via internet consisting features such as tactile sense, haptic and visual feedback. According to our system model, a realistic operational experience could be provided to the robotic arm operator when operating the robotic arm to perform tasks in a remote location. Two different algorithms were developed for master and slave ends. Force resistive sensors were used for tactile sensing. Vibrating wearable was designed for haptic feedback. IP camera was used to provide real time visual feedback. The integrated real time robotic control system operates with tactile sensing range of 0.05 N to 0.1 N, overall system response delay of 7.4 ms and accuracy of 99%.

In this paper, a vision-based adaptive traffic light controller is proposed. The proposed controller was successfully deployed and tested as a complete system in a complex roundabout in Colombo city at a highly congested time. There were two main parts to this implementation. The first part was a vision-based traffic monitoring system. In this part, a system was developed so that it monitored lanes in a junction with cameras and extracted a traffic index based on traffic density, vehicle type, and pixel-wise velocity of vehicles by processing the video streams coming from cameras. The traffic signal light controlling part was the second part of the project. This part dealt with estimating a better timing adjustment for the existing system using a mathematical modeling approach while taking the extracted traffic index as input. This system was operated with the existing system with minimum alterations for easy real-world …

In this paper, we propose a novel algorithm based on supervised learning for antenna array extrapolation for the purpose of super resolution DoA estimation. We use multiple signal classification (MUSIC) as a DoA estimation technique to estimate the DoA. In order to reduce the computational burden, existing approaches focus on interpolating the missing elements in a virtual array using a sparse array (or non-uniform linear arrays) or employ antenna selection within the same aperture. In contrast, here we utilize an uniform linear array (ULA) using a low number of antennas (within a small array aperture) to extrapolate another ULA with a higher number of antennas (within a bigger aperture). This approach is not restricted to any specific antenna array configuration, in fact it can be generalized to any array configuration. We propose an algorithm which utilizes the advances of supervised learning (dictionary learning …

A combined approach of low-complexity light field depth filtering and deep learning is proposed for object classification in the presence of partial occlusions. The proposed approach exploits depth information embedded in multi-perspective four-dimensional (4-D) light fields via low-complexity 4-D sparse depth filtering and deep-learning. The proposed 4-D depth filter, designed using numerical optimization techniques by formulating as an ℓ 1 - ℓ ∞ minimization problem, is shown to outperform typical light field refocusing based on 4-D shift-sum averaging filters. Experiments conducted using a light field dataset acquired by a Lytro camera verify 45% and 27% better performance in terms of object classification accuracy compared to the cases when no depth filtering is employed and standard shift-sum refocusing is employed, respectively.

A minimax design for 2-D complex-coefficient FIR filters having asymmetric frequency responses is proposed in this paper. We consider the general form of 2-D FIR filters with low group delay and formulate the minimax design as a semidefinite programming problem. The 2-D linear-phase FIR filters with conjugate-symmetric coefficients are a special case of the proposed design. Example filter designs having near-equiripple magnitude responses are presented to verify the effectiveness of the proposed design method.

The objective of this study is to propose a heuristic model of energy propagation due to an anomaly; electromagnetic (EM) field penetration into a continuously covered conducting enclosure (Faraday shield) from an external radio frequency source, violating the accepted model in the EM field theory. In this study, at an arbitrarily selected frequency, range of 26.965–1,800 MHz, of an external frequency source, an EM field inside the conducting enclosure was observed, contrary to expectations, which was followed by a systematic examination. Although no induced voltage could be expected inside the enclosure according to the classical theory, the experiment revealed a clear induced voltage inside, an attenuated induced voltage of −18.0 to −1.0 dB (for the range of frequencies 26.965–1,800 MHz) was observed. Hence, these results apparently contradict the established notion that an EM field cannot …

The enhanced distributed channel access (EDCA) mechanism enables IEEE 802.11p to accommodate differential quality of service (QoS) levels in vehicle-to-vehicle (V2V) communications, through four access categories (ACs). This paper presents multi-dimensional discrete-time Markov chain (DTMC) based model to study the effect of parallel operation of the ACs on the medium access control (MAC) layer performance of ITS-G5 IEEE 802.11p. The overall model consists of four queue models with their respective traffic generators, which are appropriately linked with the DTMCs modeling the operation of each AC. Closed-form solutions for the steady-state probabilities of the models are obtained, which are then utilized to derive expressions for key performance indicators at the MAC layer. An application for a highway scenario is presented to draw insights on the performance. The results show how the …

Reinforcement learning algorithms have been successfully trained for games like GO, Atari, and Chess in simulated environments. However, in cue sport-based games like Carrom, real world is unpredictable unlike in Chess and GO due to the stochastic nature of the gameplay as well as the effect of external factors such as friction combined with multiple collisions. Hence, solely training in a simulated platform for games like Billiard and Carrom, which need precise execution of a shot, would not be ideal in actual gameplay. This paper presents a real-time vision based efficient robotic system to play Carrom against a proficient human opponent. We demonstrate the challenges of adopting a reinforcement learning algorithm beyond simulations in implementing a strategic gameplay for the robotic system. We currently achieve an overall shot accuracy of 70.6% by combining heuristic and reinforcement learning …

A multi-port spatio-temporal noise-shaping ADC is proposed to process plane waves received by spatially-oversampled antenna arrays. In the proposed multi-port ADC, the desired plane waves are processed with a spatial low-pass frequency response whereas the noise and distortion are shaped with a spatial high-pass frequency response. By employing a first-order Butterworth filter, approximately circular passbands and stopbands are achieved for the signal and the noise transfer functions, respectively. The proposed noise-shaping system is designed in the TSMC 180 nm CMOS process, with ADCs and DACs modeled as noise sources. Circuit simulation results show that the proposed system can achieve a bandwidth of 50 MHz.

Light field saliency detection—important due to utility in many vision tasks—still lack speed and can improve in accuracy. Due to the formulation of the saliency detection problem in light fields as a segmentation task or a “memorizing” tasks, existing approaches consume unnecessarily large amounts of computational resources for (training and) testing leading to execution times is several seconds. We solve this by aggressively reducing the large light-field images to a much smaller three-channel feature map appropriate for saliency detection using an RGB image saliency detector. We achieve this by introducing a novel convolutional neural network based features extraction and encoding module. Our saliency detector takes 0.4 s to process a light field of size 9× 9× 512× 375 in a CPU and is significantly faster than existing systems, with better or comparable accuracy. Our work shows that extracting features from light fields through aggressive size reduction and the attention results in a faster and accurate light-field saliency detector.

The PET-laparoscope system has been proposed to diagnose lymph node metastases intraoperatively in gastric cancer surgeries. The system uses two detector units, a fixed detector array and a movable detector probe to acquire PET images. The detector probe can be inserted into a patient’s stomach through laparoscopic ports. A surgeon can move the detector inside the patient’s body but the movement is limited. In this study the system was evaluated with an abdomen phantom so that the probe movement was realistic. Moreover, performance of an MLEM algorithm was investigated for the PET-laparoscope system. Experiments with the abdomen phantom confirmed that the system performs well when the probe movement is similar to that achievable during a laparoscopic surgery. MLEM algorithm provided better images. Image artifacts were reduced and the spatial resolution in lateral directions were better …