S. N. Merchant

Robust Neural-Network-Based Data Association and Multiple Model-Based Tracking of Multiple Point Targets

Data association and model selection are important factors for tracking multiple targets in a dense clutter environment without using a priori information about the target dynamic. We propose a neural-network-based tracking algorithm, incorporating a interacting multiple model and show that it is possible to track both maneuvering and nonmaneuvering targets simultaneously in the presence of dense clutter. Moreover, it can be used for real-time application. The proposed method overcomes the problem of data association by using the method of expectation maximization and Hopfield network to evaluate assignment weights. All validated observations are used to update the target state. In the proposed approach, a probability density function (pdf) of an observed data, given target state and observation association, is treated as a mixture pdf. This allows to combine the likelihood of an observation due to each model, and the association process is defined to incorporate an interacting multiple model, and consequently, it is possible to track any arbitrary trajectory

Routing Protocols for Landslide Prediction using Wireless Sensor Networks

Landslide prediction and early warning system is an important application where sensor networks can be deployed to minimize loss of life and property. Due to the dense deployment of sensors in landslide prone areas, clustering is an efficient approach to reduce redundant communication from co-located sensors. In this paper we propose two distributed clustering and multi-hop routing protocols, CAMP and HBVR, for this problem. While CAMP is a new clustering and routing protocol, HBVR is an enhancement of BVR with HEED. We further enhance CAMP and HBVR with TEEN, a threshold based event driven protocol. TEEN is most suitable protocol for this application since different rock types can have different thresholds for stress values. Simulation results show that CAMP-TEEN gives the best performance with respect to network life time and energy consumption.

Error Concealment Using Digital Watermarking

Images transmitted over unreliable channels are highly prone to errors. This produces severe distortion in the images and are usually repaired using post processing techniques called error concealment techniques. In this paper, the authors propose a new method of error concealment using the principle of digital watermarking. The watermark used in this case is not a separate digital data, but some important information derived from the original image itself. This data can be used for concealing the errors which have occurred during transmission. Obviously the techniques used for retrieving the watermark, which in this case would be used for error concealment, should be blind. Experimental results show the advantage of the proposed scheme for error concealment with loss of blocks of different sizes as well as loss of contiguous blocks. Apart from it, ownership authentication is also achieved

Principal component analysis based backpropagation algorithm for diagnosis of peripheral arterial occlusive diseases

Impedance cardio-vasography (ICVG) serves as a non-invasive screening procedure prior to invasive and expensive angiographic studies. Parameters like Blood Flow Index (BFI) and Differential Pulse Arrival Time (DPAT) at different locations in both lower limbs are computed from impedance measurements on the Impedance Cardiograph. A Backpropagation neural network is developed which uses these parameters for the diagnosis of peripheral vascular diseases such as Leriches syndrome. The target outputs at the various locations are provided to the network with the help of a medical expert. The paper proposes the use of Principal Component Analysis (PCA) based Backpropagation network where the variance in the data is captured in the first seven principal components out of a set of fourteen features. Such a Backpropagation algorithm with three hidden layers provides the least mean squared error for the network parameters. The results demonstrated that the elimination of correlated information in the training data by way of the PCA method improved the networks estimation performance. The cases of arterial Narrowing were predicted accurately with PCA based technique than with the traditional Backpropagation Technique. The diagnostic performance of the neural network to discriminate the diseased cases from normal cases, evaluated using Receiver Operating Characteristic (ROC) analysis show a sensitivity of 95.5% and specificity of 97.36% an improvement over the performance of the conventional Backpropagation algorithm. The proposed approach is a potential tool for diagnosis and prediction for non-experts and clinicians.

FPGA-Based Portable Ultrasound Scanning System with Automatic Kidney Detection

Bedsides diagnosis using portable ultrasound scanning (PUS) offering comfortable diagnosis with various clinical advantages, in general, ultrasound scanners suffer from a poor signal-to-noise ratio, and physicians who operate the device at point-of-care may not be adequately trained to perform high level diagnosis. Such scenarios can be eradicated by incorporating ambient intelligence in PUS. In this paper, we propose an architecture for a PUS system, whose abilities include automated kidney detection in real time. Automated kidney detection is performed by training the Viola–Jones algorithm with a good set of kidney data consisting of diversified shapes and sizes. It is observed that the kidney detection algorithm delivers very good performance in terms of detection accuracy. The proposed PUS with kidney detection algorithm is implemented on a single Xilinx Kintex-7 FPGA, integrated with a Raspberry Pi ARM processor running at 900 MHz.

Replicating the geographical cloud

This paper discusses the current state-of-art and proposes a novel evolution of cloud computing and communications. New attributes, introduced continuously, have additively improved and evolved cloud computing to what it is today. Grid computing, data-centers and High Performance Computing (HPC) are critically reviewed and fall-outs are analyzed to corroborate new solutions. We propound a futuristic paradigm, founded on symbiosis and utility-oriented ideas, and propose a new architecture/framework for systems of the future. The authors have also made an attempt to address the question of what is to transcend cloud computing and current networking paradigms. Several applications are discussed qualitatively and rudimentary approaches are discussed. Principal theoretic feasibility of one of the proposed hypothesis of cloud communications is established. In this proposed scenario we obtain a linear increase in communication capacity, with minimal energy requirement. Unified and distributed communication paradigm Green Symbiotic Cloud Communications.Design postulates for technological systems of future.Virtualization and abstraction are introduced creating a true sense geographical cloud.Architecture allows multiple users to access multiple mediums concomitantly.Linear capacity maximization with minimal power utilization is derived and proved.

Human Mobility Based Stable Clustering for Data Aggregation in Singlehop Cell Phone Based Wireless Sensor Network

Advances in 3G and 4G technology have offered many possibilities for developing novel applications using sensors embedded in hand held devices like cell phones. Mobility of cell phone based wireless sensor network has a critical issue of gathering sensed information in an energy efficient and delay sensitive manner. In this paper we provide a human mobility based stable clustering algorithm for data aggregation in single hop cell phone based sensor network incorporating mobility of cell phone users. We present a human mobility aware weighted clustering algorithm for data aggregation under Truncated Levy Walk (TLW) mobility model. Our approach is to select stable Cluster Heads (CH) to save the energy expenditure of network back bone formation. We have compared our algorithm with WCA [9] of mobile adhoc network and with MRECA [6] algorithm of mobileadhoc sensor network which we consider to be closely related with our work. WCA algorithms mobility parameter is not effectively capturing mobility of human walk. Our Human mobility aware Weighted Cluster based Data Aggregation algorithm (Hm-WCDA) effectively captures human walk characteristics and thereby stabilizes the back bone network. We have evaluated performance of our algorithm primarily with stability related parameters such as number of dominant set (DS) updates, number of reaffiliations and number of cluster heads, which directly effects the energy consumption of the algorithm. The simulation results show that our algorithm is more energy-efficient and reduces the energy consumption by 12.5 percent as compared to MRECA and by 7 percent as compared to WCA for cluster radius of 400m.

Achievable Rates of Underlay-Based Cognitive Radio Operating Under Rate Limitation

A new information-theoretic model is proposed for underlay-based cognitive radio (CR), which imposes rate limitation on the secondary user (SU), whereas the traditional systems impose either interference or transmit power limitations. The channel is modeled as a twin-user interference channel constituted by the primary user (PU) and the SU. The achievable rate of the SU is derived based on the inner bound formulated by Han and Kobayashi, where the PU achieves the maximum attainable rate of the single-user point-to-point link. We show that it is necessary for the SU to allocate its full power for the “public” message that can be decoded both by the SU and by the PU. We also demonstrate that it is optimal for the PU to allocate its full power for the “private” message that can only be decoded by the PU if the level of interference imposed by the PU on the SU is “ergodically strong.” Similarly, it is optimal for the PU to allocate its full power for the public message that can be decoded both by the SU and PU if this interference is “ergodically weak.” These findings suggest that this power allocation is independent of the level of interference imposed by the SU on the PU. Furthermore, the achievable rate is analyzed as a function of the average level of interference. An interesting observation is that if the level of interference imposed by the SU on the PU is “ergodically weak,” the achievable rate becomes a monotonically increasing function of this interference, and it is independent of the level of interference imposed by the PU on the SU. Furthermore, we analyze the realistic imperfect channel estimation scenario and demonstrate that the channel estimation errors will not affect the optimal nature of the SUs power allocation.

Priority based NDS data scheduling algorithm for vehicle to hotspot communication

With increasing popularity of inter-vehicular communication, the need to provide emergency and infotainment services to vehicles in a fair and efficient manner is top priority. These data items can be downloaded or uploaded from a Hotspot which is Roadside Unit. The only difference between a hotspot and a roadside unit is hotspots are kept far apart as compared to roadside units. When many vehicles try to access a hotspot for some services then fair data scheduling is required. In this paper we propose a priority based NDS scheduling algorithm using broadcast transmissions is proposed along with the comparison study with existing algorithms. Simulation results show that the proposed algorithm performs better than other the existing service scheduling algorithms.

A novel multistage decision fusion for cognitive sensor networks using AND and OR rules

We propose a centralized radix-2 multistage decision fusion strategy comprising simple AND and OR rules for cooperative spectrum sensing in cognitive sensor networks. Earlier works on centralized decision fusion show the half-voting and majority rules to be optimum in many spectrum sensing scenarios in terms of minimizing the decision error (or equivalently maximizing the probability of correct decision). We consider a commonly occurring case in spectrum sensing in which the detection probability of a cognitive radio enabled sensor node is greater than its false-alarm probability. For this case, we consider five scenarios and demonstrate that the proposed method either performs better than half-voting and majority rules or exhibits a comparable performance. In this context, we also establish a criterion to make a choice between the AND and OR rules and compute the optimum number of nodes participating in cooperative spectrum sensing for these rules to maximize the correct decision probability.