199,470 research outputs found
Bayesian analysis of change point problem in autoregressive model: a mixture model approach
No full textThis paper is a generalization of earlier studies by Venkatesan and Arumugam (2007) who considered the changes in the parameters of an autoregressive (AR) time series model in order to make Bayesian inference for the shift points and other parameters of a changing AR model. In this paper, the problem of gradual changes in the parameters of an AR model of pth order, through Bayesian mixture approach is considered. This model incorporates the beginning and end points of the interval of switch. Further, the Bayes estimates of the parameters are illustrated with the data generated from known model
Pseudobinomiality of the Sticky Random Walk
No full textRandom walks on expanders are a central and versatile tool in pseudorandomness. If an arbitrary half of the vertices of an expander graph are marked, known Chernoff bounds for expander walks imply that the number M of marked vertices visited in a long n-step random walk strongly concentrates around the expected n/2 value. Surprisingly, it was recently shown that the parity of M also has exponentially small bias.
Is there a common unification of these results? What other statistics about M resemble the binomial distribution (the Hamming weight of a random n-bit string)? To gain insight into such questions, we analyze a simpler model called the sticky random walk. This model is a natural stepping stone towards understanding expander random walks, and we also show that it is a necessary step. The sticky random walk starts with a random bit and then each subsequent bit independently equals the previous bit with probability (1+λ)/2. Here λ is the proxy for the expander’s (second largest) eigenvalue.
Using Krawtchouk expansion of functions, we derive several probabilistic results about the sticky random walk. We show an asymptotically tight Θ(λ) bound on the total variation distance between the (Hamming weight of the) sticky walk and the binomial distribution. We prove that the correlation between the majority and parity bit of the sticky walk is bounded by O(n^{-1/4}). This lends hope to unifying Chernoff bounds and parity concentration, as well as establishing other interesting statistical properties, of expander random walks
Mr. T. M Venkatesan
No full textPresently working as a mentor for 5S, TPM, lean Energy Conservation and six sigma training, Implementation and projects for mfg and service industry. He teaches change Business Management through 5S, LEAN, TPM,Energy Conservation and Six Sigma. He works extensively with several clients. Some of them are Premier Explosives Ltd- Hyderabad, RAK Ceramics Ltd- Samalkot, JNTU- Hyderabad, Rani pettai Engg Collg- Vellore (TamilNadu), BHEL- Hyderabad, Aurobindo Pharma Hyd Ltd, Dr.Reddy Laboratory Ltd – Hyd ,Sonali Castings (P) Ltd –Hyd, Fine Alloy Castings Ltd, Kamal Foot wear – Vijayawada, CII – Hyderabad, Vijayawada, Vizag & Kakinada, Hi-Tech institute of Pharma sciences – Hyd, GMR Airport – Shamshabad, APITCO – Hyd, Roots Industries India Ltd – TamilNadu, Sweet Magic – Vijayawada, Garapati/ Ramcor – Vijayawada, Vilan Garments (P) Ltd – Vijayawada, Ramcor Marketing (P) Ltd. etc.
Mr. T.M.Venkatesan enjoys balancing out a very busy professional life with strong community links through involvement in not-for-profit organizations that can use his skills and enthusiasm. His interests include literature, movies, music, theatre, intricacies of business/financial world. Certified Energy Auditor- Bureau of Energy Efficiency, under Ministry of Power, Govt.of India. Chartered Engineer in Mechanical Engineering. Total Manufacturing Industry experience in Auto Parts 48yrs. From TVS for 12years (A Deming Award Company )and Own Industry for 22yrs.(auto parts to multinationals) Trained in TOC by Dr Goldratt the author of the book The Goal Best Entrepreneur Award from HMA.(Hyderabad Management Association) Best Entrepreneur Award from Govt. of Andhra Pradesh. Exporter from 1991 to Singapore, Indonesia and Srilanka. Visited U.S., Germany, Italy, France, Singapore, Malaysia, Thailand, Indonesia and Srilanka (9 countries). Represented Govt. of Andhra Pradesh in LASVEGAS (U.S) and Govt. of India in Jakarta (Indonesia). Past President of Rotary club Hyderabad - Mega City. BLACK BELT IN SIX SIGMA and Practicing MASTER BLACK BELT and Trained in Lean Sigma by BMG(Longmont. Co., USA)..Trained more than 3000 participants in Manufacturing &Service Industries.
T. M. Venkatesan is currently doing his PhD (Kaizen) (Operations Management-Quality) at VIT Business School, VIT University, and Vellore India. Prior to this he did his M.S (Research) studies at the same Business School and upon obtaining Distinction in M.S he got upgraded to PhD Program. Earlier he was graduated as Mechanical Engineer from Institution of Engineers (India) in the year 1975. He has a total of 50 years industry exposure both in Manufacturing &Training He is a Certified Energy Auditor (Govt. Of India) Certified Quality Examiner with RBNQA (2014) and a Certified Master Trainer for ZED Rating (Quality Council of India), BB in six sigma from Benchmark Six Sigma
He has presented research papers at IIT Kharagpur, IIM Indore, IIM, Trichy. Received Golden Paper Award for his paper @Pondicherry University in 2018, and two research papers on KAIZEN, submitted in Scopus indexed Journal has been accepted for Publicationhttps://www.interscience.in/mentors/1059/thumbnail.jp
Metrocoris sikkimensis Basu & Chandra & Venkatesan 2018, sp. nov.
No full textMetrocoris sikkimensis sp. nov. Type material examined: HOLOTYPE, apterous male (in 75% ethyl alcohol): INDIA, Sikkim, West Sikkim District, hill stream, Kaleg Khola, Pelling road, 27.2956°N, 88.2226°E, alt. 1841 m, 10 May 2016, coll: S. Basu. PARATYPES (in 75% ethyl alcohol):10 apterous males,10 apterous females: same data as holotype; 15 apterous males, 12 apterous females, West Sikkim District, Reshikhola River, Rinchenpong, 27.2441°N, 88.8735°E, alt. 1618 m, 9 May 2016, coll: S. Basu. 8 apterous males, 17 apterous females, INDIA: Arunachal Pradesh, West Kameng District, Rupa river, near Rupa village, Bomdila, 27.20390°N, 92.39420°E, 4804ft, 9 October, 2017, coll: S. Basu; 4 apterous males, 4 apterous females, West Kameng District, Dublekha River, Jigaon, near Rupa village, Bomdila, 27.20840°N, 92.39965°E, 4780 ft, 9 October, 2017, coll: S. Basu; 5 males, 5 females, West Kameng District, Kameng River, Nagmandir, 27.28440°N, 92.82830°E, 1495 ft, 5 October, 2017, coll: S. Basu. Description. Apterous male (Figs. 2, 4–6, 7, 9, 10, 13–17). Size: Body length 5.37, body width across mesoacetabula 2.50. Colour: Dorsally black with bright yellowish orange markings. Interocular mark on posterior margin of head distinct, yellowish (Figs. 2, 5). Eyes black. Antenna black with yellow basally. Rostrum black with yellowish laterally. Pronotum with a pair of flattened ‘u’ shaped yellowish orange markings (Figs. 2, 5). Meso- and Metanota each with a pair of yellow markings (Figs. 2, 5). Pro-, meso-and metapleura with a longitudinal yellow stripe, discontinuous near posterior margin of pronotum. Mesosternum without yellow markings. Meso- and metacetabula each with a dorsal yellow mark. Fore, mid and hind coxae and trochanters yellow. Fore femur (Fig. 7) black, yellowish basally, dorsally and ventrally. Mid and hind femora, tibiae and tarsi black. Abdominal terga I–VII and proctiger black, tergum VIII black with yellow margins (Fig. 9). Abdominal laterotergites black, except yellow posterolateral angles of last segment. Venter black, except sterna VII–IX yellowish brown (Fig. 10). Structural characteristics: Head length 0.77, width excluding eyes 0.95, narrower than pronotum. Eyes 2.2 times longer than broad, length 0.62, width 0.28. Minimum interocular width 0.63. Length of antennal segments I– IV= 2.34, 0.73, 0.79, 0.63, first segment longer than combined length of segments II–IV, without spines or bristles. Rostrum reaching to mesothorax, length 1.26. Pronotum 2.8 times wider than long, length 0.47, width 1.35, slightly bulbous. Combined length and maximum width of meso- and metanota 2.26 and 1.77 respectively. Fore femur (Fig. 7) slender, fringed with short setae, slightly constricted apically and with one or two thin small setae basally, ratio of length/width 7.51 (2.33/0.31). Fore tibia and tarsus without modification, but covered with short setae. Pretarsal claws distinct, curved and sharp. Mid and hind trochanters lacking modifications. Abdominal terga densely covered by setae, combined length 2.03, maximum width at tergum V 1.48. Abdominal sterna II–VI with golden pubescence, sterna VII–VIII long, distinctly clothed with long dense golden setae (Fig. 10). For measurements of leg segments see Table 1. Genitalia: Abdominal sternum VIII (Figs. 10, 13) short with median inverted U-shaped excavation, blunt at apex, anterior margin emarginated at middle, length 0.79, width 0.65, covered by golden setae, density increasing laterally. Pygophore (Fig. 14) elongated, broadened medially, heavily setiferous, posterior margin almost straight. Proctiger (Fig. 15) elongated, with maximum width near middle, parts of lateral margins anterior and posterior to the protrusion are concave, laterally slightly protruded near middle, apex rounded, clothed with dense setae. Parameres (Figs. 13, 17) symmetrical, projecting laterally from genital segments, curved apically, without setae, apex slightly pointed; in few individuals, parameres not visible from above. Endosomal sclerites (Fig. 16) well developed; dorsal sclerite long, entirely covering the endosomal sheath and extended apically; lateral sclerite almost straight, relatively long; ventral sclerite long. Apterous female (Figs. 3, 8, 11, 12). Size: Body length ranges from 5.10–5.39 (n=48), maximum width across mesoacetabula ranges from 2.56–2.62 (n= 48). Colour: Colour pattern similar to that of male, except yellowish marks much wider and more prominent. Structural characteristics: Head length 0.74, width (without eyes) 0.89. Length of antennal segments I–IV: 2.18, 0.79, 0.77, 0.69. Eye length 0.64, width 0.37. Minimum interocular width 0.70.Length of rostrum 1.26. Pronotum wider than long, length 0.46, width 1.51. Combined length of meso- and metanota 2.26, maximum width 2.35. Fore femur (Fig. 8) length/width ratio 8.4 (2.45/0.29), without modifications; pretarsi with sharp curved claws. Hind trochanter apically with fringe of setae. Abdominal sterna length 1.36, maximum widths 1.59 at sternum V. For measurements of leg segments see Table 2. Abdominal sternum VII (Fig. 12) more or less oval, constricted laterally, with small lobe, covered by short golden pubescence, length 0.65, width 1.09, posterior margin straight. Macropterous forms: Unknown. Etymology. The specific epithet ‘sikkimensis’ derives from its place of origin, the northeastern state of Sikkim. Discussion. The newly described species belongs to the compar group and can be easily distinguished from congeners by the entirely black venter lacking yellow markings on the meso- and metasterna (Fig. 4); the distinctive shape of male paramere (Fig. 17), which is almost straight in the middle with the apex slightly pointed and without projections; the structure of male endosomal sclerites (Fig. 16) and the male proctiger (Fig. 15); and by the female terminalia, which are ventrally more or less oval, with a small lobe and covered by golden pubescence (Fig. 12). Recently, Basu et al. (2016) reported a total of 20 species of Metrocoris from India, with a key to all known Indian species. Hence, Metrocoris sikkimensis sp. nov. is the 21 st species described from the country. Within the Metrocoris compar group, M. sikkimensis sp. nov. is closely related to M. hirtus Chen & Nieser, 1993 from China, but differs from the latter as follows. In M. hirtus, surface of the male paramere has a small projection pointing forward and the apex is blunt, whereas in M. sikkimensis sp. nov. the paramere is slightly curved apically and the apex is more or less pointed, without projections or setae. Furthermore, the male pygphore is subovate in M. hirtus, but in M. sikkimensis it is elongated and heavily setiferous and the posterior margin of male pygophore almost straight. Additionally, the male forefemur is slightly constricted apically and has one or two thin short setae basally at the ventral surface in M. sikkimensis, whereas there is no apical constriction or thin basal setae in M. hirtus. Metrocoris sikkimensis is also similar to M. nepalensis, but can be separated from the latter by the following characteristics: In M. nepalensis, the male paramere bears a small projection pointing dorsally, and by the endosoma with a small accessory apical sclerite, indistinct lateral sclerite, and long ventral sclerite. In contrast, M. sikkimensis does not have a projection on the male paramere, an accessory apical endosomal scleriteis absent, the lateral sclerite is distinct and extends upto the proximal portion of the dorsal sclerite, and the ventral sclerite is long, slender and extends forward.Published as part of Basu, Srimoyee, Chandra, Kailash & Venkatesan, Thiruvengadam, 2018, Metrocoris sikkimensis sp. nov. (Hemiptera: Heteroptera: Gerridae) from northeastern India, with a key to species of the compar group occurring in India, pp. 369-374 in Zootaxa 4471 (2) on pages 370-374, DOI: 10.11646/zootaxa.4471.2.9, http://zenodo.org/record/143978
BAYESIAN INFERENCE TO MULTIPLE CHANGES IN THE VARIANCE OF AR(p) TIME SERIES MODEL
No full textThe problem of a change in the mean of a sequence of random variables at an unknown
time point has been addressed extensively in the literature. But, the problem of a change in the
variance at an unknown time point has, however, been covered less widely. This paper analyses a
sequence of autoregressive, AR(p), time series model in which the variance may be subjected to
multiple changes at an unknown time points. Posterior distributions are found both for the
unknown points of time at which the changes occurred and for the parameters of the model. A
numerical example is also discussed
New family of time series models and its bayesian analysis
No full textA new family of time series models, called the Full Range Autoregressive model, is introduced which avoids the difficult problem of order determination in time series analysis. Some of the basic statistical properties of the new model are studied. Further, the paper describes the Bayesian inference and forecasting as applied to the Full Range Autoregressive model. The Canadian lynx data is used to compare the efficiency of the predictive power of the new model with those of
some of the existing models in the time series literature
A Bayesian Analysis of Multiple Changes in the Variance of First-Order Autoregressive Time Series Models
No full textThe problem of a change in the mean of a sequence of random variables at an unknown time point has been addressed extensively in the literature. But, the problem of a change in the variance at an unknown time point has, however, been covered less widely. Hsu examines the problem of testing whether there has been a change in the variance at an unknown time point using sampling theory, and applies to stock return data and also give a Bayesian treatment of a similar problem.
This paper analyses a sequence of first order autoregressive time series model in which the variance may have subjected to multiple changes at an unknown time points. Posterior distributions are found both for the unknown points of time at which the changes occurred and for the parameters of the model. A numerical example is discussed
A bayesian analysis of multiple changes in the variance of first - order autoregressive time series models
No full textThe problem of a change in the mean of a sequence of random variables at an unknown time point has been addressed extensively in the literature. But, the problem of a change in the variance at an unknown time point has, however, been covered less widely. This paper analyses a sequence of first order autoregressive time series model in which the variance may have subjected to multiple changes at an unknown time points. Posterior distributions are found both for the unknown points of time at which the changes occurred and for the parameters of the model. A numerical example is illustrated
Advancing WSN physical security adopting TPM-based architectures
No full textCyber Physical Systems typically operate unattended in hostile outdoor environments. A lot of effort has has been made to protect the communication between sensing nodes and the processing infrastructure. However, with regards to physical protection of a node, assessing the integrity of its hardware/software is a challenging issue. In this paper, we propose and evaluate a node architecture which makes use of Trusted Platform Module (TPM) to perform cryptographic operations in a trustworthy manner. TPM builds a chain of trust which enforces a trustability relationship among the node's components. In such context, the node will function only if all the hardware and software configurations have been verified by means of cryptographic operations. Moreover, using tamper resistant hardware we will ensure that the cryptographic keys do not leave a secure perimeter
Dr. Duane M. Jackson, Morehouse College, July 2011
No full textThis video is a conversation with Dr. Duane M. Jackson. Dr. Jackson talks about his paper, "Recall and the Serial Position Effect: The Role of Primacy and Recency on Accounting Students' Performance." Jackie Daniel, AUC Woodruff Library, is the interviewer
- …
