In biodiversity management and conservation, the identification and classification of natural vegetation are considered as a major issue. In this paper, natural vegetation and its formations are identified using a Worldview-2 spectral imagery. The classification of the Worldview-2 image and ancillary thematic data was performed by using an Improved Relevance Vector Machine with Mosquito Flying behaviour based swarm intelligence Optimization (IRVM-MFO) algorithm. Here the perceptive strength of the spectral signature and the Local features of spectral bands are considered in each pixel. In addition texture features such as Fourier spectrum and GLCM features are exploited to make the system more robust. In IRVM, the MFO approach used to optimize the kernel functions of parameters to improve the training process. The proposed IRVM-MFO shows improved classification performance in terms of parameters like overall sensitivity, specificity and accuracy compared with simple RVM and SVM methods. The proposed method has results in a high accuracy of 92.3% and the Kappa index varying between 0.92 and 0.78 at vegetation formation levels.

In an automotive electronics applications there are approximately 230 electronic control units ECU’s are used to provide intelligent driving assistance. So, there is an effective multiple objective real time task scheduling techniques are required to provide better solution in this domain. This paper describes novel multi-objective evolutionary algorithmic techniques such as Multi - Objective Genetic Algorithm (MOGA), Non-dominated Sorting Genetic Algorithm (NSGA) and Multi - Objective Messy Genetic Algorithm (MOMGA) for scheduling real time tasks to a multicore processor based ECU. These techniques improve the performance upon earlier reported of an ECU’s by considering multiple objectives such as, low power consumption (P), maximizing core utilization (U) and minimizing deadline missrate (δ). This work also analysis the schedulability of real time tasks by computing the converging value of a series of task parameters such as execution time, release time, workload and arrival time. Finally, we investigated the performance parameters such as power consumption (P), deadline missrate (δ), and core utilization for the given architecture. The evaluation results show that the power consumption is reduced to about 5 - 8%, utilization of the core is increased about 10 % to 40% and deadline missrate is comparatively minimized with other scheduling approaches.

The ECG (Electrocardiogram) signal represents electrical behaviour of heart over time and is measured by placing electrodes on specific locations of limb. These signals are useful for monitoring and diagnosis of heart related issues. ECG signals are often corrupted by artifacts during acquisition and transmission predominantly by high frequency power line interference, electromyography noise and low frequency noise caused by motion of electrodes (baseline changes). Addition of these artifacts changes morphology of the ECG signal which affect accurate analysis and hence need to be reduced for better clinical evaluation. ECG signals also generate massive volume of digital data, so they need to be suitably compressed for efficient transmission and storage. Hence, for efficient compression/approximation, in this paper, the ECG signal taken from MITBIH database is pre-processed using Total Variation Denoising approach and the pre-processed signals are then characterized using Bottom-Up approach. The individual sections are then approximated using Chebyshev polynomials of suitable order. The performance of the approximation technique is measured by computing the Maximum Absolute Error, the Compression Ratio, Root Mean Square Error, Percent Root Mean Square Difference and Percent Root Mean Square Difference Normalized. The results are also compared with other techniques reported in the literature, where significant improvements in all the performance metrics are observed by the proposed method.

In the context of VLSI devices, low-power operation is a critical requirement in CMOS-based architectures. In the present work, an image sensor utilizing pulse-width modulation (PWM) techniques has been designed to operate at a supply voltage below 300 mV and under low signal-to-noise ratio conditions. The proposed CMOS image sensor is modeled for wireless sensing applications, particularly in security-related environments. Compared to previously reported sensor and transducer designs, the proposed architecture demonstrates higher gain, reduced area, and improved throughput. The designed circuit enables CMOS image sensor operation at 0.4 V, delivering an output voltage of approximately 0.38 V with a dynamic range of 54 dB at the pixel level.

With the rapid increase in internet users and customer reviews playing the major role in social media gave rise to sentiment analysis. Pre-processing of input text during sentiment analysis eliminates the incomplete and noisy data. Typically, sentiment is manifested separately and applying a pre-processing model for optimizing the cross-domain sentiment classification is highly required. In this paper, a method called Hidden Markova Continual Progression Cosine Similar (HM-CPCS) is proposed to explore the impact of pre-processing and optimize sentiment analysis. First, a measure of subsequent and antecedent probabilities of tags is made using Hidden Markova POS Tagger for the given input dataset. Subsequent and antecedent probabilities of tags are obtained by measuring the transition probabilities between states (i.e. domains) and observations (i.e. review statements) ensuring feature extraction accuracy. Next, the Continual Progression Stemmer continuously stems the text by adding prefix and suffix to form structured words for the given shortcuts and therefore reduce Error Rate Relative to Truncation (ERRT). Finally a Cosine Similarity function is applied to remove stop word for cross-domain sentiment analysis and classification. The performance evaluation of HM-CPCS method is done with standard benchmark data sets of consumer product and services reviews extracted from Sentiwordnet. The parameters used in evaluation are number of customer review words, execution time, accuracy and error rate. Experimental analysis shows that HM-CPCS method is able to reduce the time to extract the opinions from reviewers by 46% and improve the accuracy by 9% compared to the state-of-the-art works.

The present work was conducted to assess the physiological response of onion plant to GA3 at Sher-e-Bangla Agricultural University, Bangladesh in the open environment under natural sunlight during the period from October 2014 to March 2015. GA3 at levels of 0, 20, 40 and 60 ppm were used with the onion by laid out in a Randomized Complete Block Design with three replications. The factor levels of GA3 which were applied during transplanting by root soaking, and foliar spray at 30 and 60 days after transplanting. GA3 has a great effect on increasing vegetative growth, shoot biomass, bulb biomass and also dry matter accumulation in onion plant compared to control. Insignificant effect by all concentration of GA3 was found in bulb length, fresh root biomass, and dry root biomass. Thus, the use of 60 ppm GA3 was better compared to the other three concentrations and significantly increased the fresh bulb biomass about 42.96 % over control. It is concluded from this study, GA3 @ 60 ppm can be used to bring the improvement of onion production from the economic point of view.